Spaces:
Paused
Paused
Commit
•
9189e38
1
Parent(s):
5652946
first
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitignore +4 -0
- README.md +57 -12
- add_mappings_to_embeddings.py +55 -0
- algo.py +195 -0
- app.py +42 -0
- ask_gpt.py +49 -0
- audits/1718289794.csv +591 -0
- audits/1718291402.csv +24 -0
- audits/1718300113.csv +16 -0
- audits/1718300232.csv +192 -0
- audits/1718300482.csv +42 -0
- audits/1718300736.csv +5 -0
- audits/1718300752.csv +11 -0
- audits/1718301576.csv +8 -0
- audits/1718362114.csv +1228 -0
- category_mapper.py +75 -0
- chatgpt_audit.py +145 -0
- db/db_utils.py +64 -0
- dictionary/additions.csv +32 -0
- dictionary/dictionary.csv +0 -0
- dictionary/final_corrected_wweia_food_category_complete - final_corrected_wweia_food_category_complete.csv +172 -0
- env +1 -0
- flagged/log.csv +2 -0
- food_nonfood.py +46 -0
- multi-item-experiments/classification_results2.csv +9 -0
- multi-item-experiments/multifood2.py +139 -0
- multi-item-experiments/multifood_viz.py +149 -0
- multi_food_item_detector.py +38 -0
- old_experiments/bert.py +84 -0
- old_experiments/bert2.py +0 -0
- old_experiments/experiment2.py +139 -0
- old_experiments/llama3-gpu-compare.py +92 -0
- old_experiments/llama3-gpu-compare2.py +80 -0
- old_experiments/llama3-gpu-instructions.py +92 -0
- old_experiments/llama3-gpu.py +122 -0
- old_experiments/llama3-gpu2.py +56 -0
- old_experiments/llama3-simple.py +171 -0
- old_experiments/llama3.py +79 -0
- old_experiments/mistral.py +31 -0
- old_experiments/mistral2.py +13 -0
- old_experiments/qa.py +23 -0
- old_experiments/roberta.py +79 -0
- old_experiments/run.py +57 -0
- old_experiments/run2.py +62 -0
- old_experiments/sbert.py +60 -0
- old_experiments/sbert2.py +80 -0
- old_experiments/sbert3.py +82 -0
- old_experiments/t5.py +62 -0
- playground.py +108 -0
- preseed.py +69 -0
.gitignore
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
.DS_Store
|
2 |
+
*.pkl
|
3 |
+
*.pyc
|
4 |
+
.env
|
README.md
CHANGED
@@ -1,12 +1,57 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Brightly AI
|
2 |
+
|
3 |
+
AI Algorithms to classify words provided by food rescue organizations into a predefined dictionary given by the USDA.
|
4 |
+
|
5 |
+
brightly-python2 (3.9.6)
|
6 |
+
|
7 |
+
## Overview
|
8 |
+
|
9 |
+
This script processes a list of input words, classifies them as food or non-food items, and finds the most similar words from a predefined dictionary. It uses various techniques, including fast and slow similarity searches, GPT-3 queries, and a custom pluralizer.
|
10 |
+
|
11 |
+
### How It Works
|
12 |
+
|
13 |
+
1. Initialization:
|
14 |
+
|
15 |
+
- Database Connection: Connects to a database to store and retrieve word mappings.
|
16 |
+
- Similarity Models: Initializes models to quickly and accurately find similar words.
|
17 |
+
- Pluralizer: Handles singular and plural forms of words.
|
18 |
+
|
19 |
+
2. Processing Input Words:
|
20 |
+
|
21 |
+
- Reading Input: The script reads input words, either from a file or a predefined list.
|
22 |
+
- Handling Multiple Items: If an input contains multiple items (separated by commas or slashes), it splits them and processes each item separately.
|
23 |
+
|
24 |
+
3. Mapping Words:
|
25 |
+
|
26 |
+
- Fast Similarity Search: Quickly finds the most similar word from the dictionary.
|
27 |
+
- Slow Similarity Search: If the fast search is inconclusive, it performs a more thorough search.
|
28 |
+
- Reverse Mapping: Attempts to find similar words by reversing the input word order.
|
29 |
+
- GPT-3 Query: If all else fails, queries GPT-3 for recommendations.
|
30 |
+
|
31 |
+
4. Classifying as Food or Non-Food:
|
32 |
+
|
33 |
+
- Classification: Determines if the word is a food item.
|
34 |
+
- Confidence Score: Assigns a score based on the confidence of the classification.
|
35 |
+
|
36 |
+
5. Storing Results:
|
37 |
+
|
38 |
+
- Database Storage: Stores the results in the database for future reference.
|
39 |
+
- CSV Export: Saves the final results to a CSV file for easy access.
|
40 |
+
|
41 |
+
# TODO
|
42 |
+
|
43 |
+
[ ] Add requirements.txt file
|
44 |
+
[ ] Add instructions re: each file in repo
|
45 |
+
|
46 |
+
## Files and their purpose
|
47 |
+
|
48 |
+
Here's a markdown table of the filename, and a brief description of what it does.
|
49 |
+
|
50 |
+
| Filename | Description |
|
51 |
+
| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
52 |
+
| run.py | The main file to run the program. You pass it an array of words, and it'll process each word, store the results to a CSV file in the results folder, and stores any new mappings in the sqlite database |
|
53 |
+
| algo_fast.py | Uses a fast version of our LLM to encode word embeddings, and use cosine similarity to determine if they are similar. |
|
54 |
+
| algo_slow.py | A similar version of the algorithm, however, it has more a larger amount of embeddings from the dictionary. |
|
55 |
+
| multi_food_item_detector.py | Determines if the given string of text is multiple food items, or a single food item. |
|
56 |
+
| update_pickle.py | Updates the dictionary pickle file with any new words that have been added to the dictionary/additions.csv file. |
|
57 |
+
| add_mappings_to_embeddings.py | This takes all the reviewed mappings in the mappings database, and adds them to the embeddings file. |
|
add_mappings_to_embeddings.py
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pickle
|
2 |
+
import os
|
3 |
+
from similarity_fast import SimilarityFast
|
4 |
+
import pandas as pd
|
5 |
+
from utils import generate_embedding
|
6 |
+
from db.db_utils import get_connection
|
7 |
+
|
8 |
+
|
9 |
+
def load_pickle(file_path):
|
10 |
+
if os.path.exists(file_path):
|
11 |
+
with open(file_path, 'rb') as f:
|
12 |
+
data = pickle.load(f)
|
13 |
+
return data
|
14 |
+
else:
|
15 |
+
raise FileNotFoundError(f"No pickle file found at {file_path}")
|
16 |
+
|
17 |
+
def save_pickle(data, file_path):
|
18 |
+
with open(file_path, 'wb') as f:
|
19 |
+
pickle.dump(data, f)
|
20 |
+
|
21 |
+
def update_data(data, new_data):
|
22 |
+
data.update(new_data)
|
23 |
+
return data
|
24 |
+
|
25 |
+
pickle_file_paths = ['./embeddings/fast/sentence-transformers-all-mpnet-base-v2.pkl', './embeddings/slow/sentence-transformers-all-mpnet-base-v2.pkl']
|
26 |
+
|
27 |
+
db_conn = get_connection()
|
28 |
+
db_cursor = db_conn.cursor()
|
29 |
+
|
30 |
+
# select all mappings that have not been reviewed
|
31 |
+
db_cursor.execute("SELECT input_word, dictionary_word FROM mappings WHERE reviewed = 1")
|
32 |
+
results = db_cursor.fetchall()
|
33 |
+
|
34 |
+
|
35 |
+
for pickle_file_path in pickle_file_paths:
|
36 |
+
new_entries = {}
|
37 |
+
data = load_pickle(pickle_file_path)
|
38 |
+
|
39 |
+
algo_fast = SimilarityFast(None)
|
40 |
+
|
41 |
+
for row in results:
|
42 |
+
input_word = row[0]
|
43 |
+
dictionary_word = row[1]
|
44 |
+
new_entries[input_word] = {
|
45 |
+
'v': generate_embedding(algo_fast.model, input_word),
|
46 |
+
'd': dictionary_word
|
47 |
+
}
|
48 |
+
|
49 |
+
updated_data = update_data(data, new_entries)
|
50 |
+
print("Updated Data")
|
51 |
+
|
52 |
+
# Save the updated data back to the pickle file
|
53 |
+
print("Saving data to pickle file...")
|
54 |
+
save_pickle(updated_data, pickle_file_path)
|
55 |
+
print(f"Data saved to {pickle_file_path}")
|
algo.py
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import time
|
2 |
+
from tqdm import tqdm
|
3 |
+
import pandas as pd
|
4 |
+
from pluralizer import Pluralizer
|
5 |
+
from similarity_fast import SimilarityFast
|
6 |
+
from similarity_slow import SimilaritySlow
|
7 |
+
from food_nonfood import classify_as_food_nonfood, pessimistic_food_nonfood_score
|
8 |
+
from utils import clean_word
|
9 |
+
from db.db_utils import store_mapping_to_db, get_mapping_from_db
|
10 |
+
from ask_gpt import query_gpt
|
11 |
+
from multi_food_item_detector import extract_food_phrases
|
12 |
+
|
13 |
+
similarity_threshold = 0.75
|
14 |
+
|
15 |
+
|
16 |
+
class Algo:
|
17 |
+
def __init__(self, db_conn, enable_csv=False):
|
18 |
+
self.db_conn = db_conn
|
19 |
+
self.enable_csv = enable_csv
|
20 |
+
self.db_cursor = db_conn.cursor()
|
21 |
+
self.similarity_fast = SimilarityFast(self.db_cursor)
|
22 |
+
# self.similarity_slow = SimilaritySlow(self.db_cursor, self.db_conn)
|
23 |
+
self.pluralizer = Pluralizer()
|
24 |
+
|
25 |
+
def save_to_csv(self, results):
|
26 |
+
if not self.enable_csv:
|
27 |
+
return
|
28 |
+
output_file_path = f'./results/{int(time.time())}.csv'
|
29 |
+
df_results = pd.DataFrame(results, columns=[
|
30 |
+
'input_word', 'cleaned_word', 'matching_word',
|
31 |
+
'dictionary_word', 'similarity_score', 'confidence_score',
|
32 |
+
'similar_words', 'is_food', 'food_nonfood_score'
|
33 |
+
])
|
34 |
+
df_results.to_csv(output_file_path, index=False)
|
35 |
+
|
36 |
+
def perform_mapping(self, input_word, attempts=0):
|
37 |
+
mapping = self.similarity_fast.find_most_similar_word(input_word)
|
38 |
+
|
39 |
+
# skip slow mapping for now
|
40 |
+
# if mapping['similarity_score'] < similarity_threshold:
|
41 |
+
# print("Attempting slow mapping")
|
42 |
+
# slow_mapping = self.similarity_slow.find_most_similar_word(input_word)
|
43 |
+
# print(f" - Slow: {slow_mapping}")
|
44 |
+
# if slow_mapping['similarity_score'] > mapping['similarity_score']:
|
45 |
+
# mapping = slow_mapping
|
46 |
+
|
47 |
+
if mapping['similarity_score'] < similarity_threshold and len(input_word.split(' ')) > 1:
|
48 |
+
print(" - Attempting reverse mapping")
|
49 |
+
reversed_input_word = ' '.join(input_word.split(' ')[::-1])
|
50 |
+
reversed_mapping = self.similarity_fast.find_most_similar_word(reversed_input_word)
|
51 |
+
if reversed_mapping['similarity_score'] > mapping['similarity_score']:
|
52 |
+
reversed_mapping.update(
|
53 |
+
{
|
54 |
+
'input_word': input_word,
|
55 |
+
'cleaned_word': mapping['cleaned_word']
|
56 |
+
}
|
57 |
+
)
|
58 |
+
mapping = reversed_mapping
|
59 |
+
|
60 |
+
|
61 |
+
# check if the cleaned_word is a substring of the matching_word
|
62 |
+
is_substring = mapping['cleaned_word'] in mapping['matching_word']
|
63 |
+
|
64 |
+
if mapping['similarity_score'] < similarity_threshold and not is_substring:
|
65 |
+
print(" - Attempting GPT mapping")
|
66 |
+
try:
|
67 |
+
gpt_recommended_word = query_gpt(input_word)
|
68 |
+
if gpt_recommended_word:
|
69 |
+
|
70 |
+
if gpt_recommended_word == 'Non-Food Item':
|
71 |
+
mapping.update(
|
72 |
+
{
|
73 |
+
'similarity_score': 1.0,
|
74 |
+
'confidence_score': 1.0,
|
75 |
+
'is_food': False,
|
76 |
+
'food_nonfood_score': 1.0
|
77 |
+
}
|
78 |
+
)
|
79 |
+
return mapping
|
80 |
+
elif gpt_recommended_word == 'Mixed Food Items':
|
81 |
+
mapping.update(
|
82 |
+
{
|
83 |
+
'matching_word': 'Mixed Food Items',
|
84 |
+
'dictionary_word': 'Mixed Food Items', 'similarity_score': 1.0,
|
85 |
+
'confidence_score': 1.0
|
86 |
+
}
|
87 |
+
)
|
88 |
+
return mapping
|
89 |
+
else:
|
90 |
+
gpt_mapping = self.similarity_fast.find_most_similar_word(gpt_recommended_word)
|
91 |
+
if gpt_mapping['similarity_score'] > mapping['similarity_score']:
|
92 |
+
gpt_mapping.update(
|
93 |
+
{
|
94 |
+
'input_word': input_word,
|
95 |
+
'cleaned_word': mapping['cleaned_word']
|
96 |
+
}
|
97 |
+
)
|
98 |
+
mapping = gpt_mapping
|
99 |
+
except Exception as e:
|
100 |
+
print(f" - Error querying GPT: {e}")
|
101 |
+
|
102 |
+
return mapping
|
103 |
+
|
104 |
+
def handle_multi_item(self, input_word):
|
105 |
+
# The input word has a comma or a slash in it
|
106 |
+
# If it has more commas, its comma-delimited
|
107 |
+
# If it has more slashes, its slash-delimited
|
108 |
+
# If it has equal number of commas and slashes, we'll go with slashes
|
109 |
+
|
110 |
+
input_word_parts = extract_food_phrases(input_word)
|
111 |
+
|
112 |
+
mappings = []
|
113 |
+
for part in input_word_parts:
|
114 |
+
mapping = self.handle_single_item(part)
|
115 |
+
mappings.append(mapping)
|
116 |
+
|
117 |
+
# TODO categorize the whole mapping list as homogenous, heterogenous, or non-food item
|
118 |
+
return None
|
119 |
+
|
120 |
+
def handle_single_item(self, input_word):
|
121 |
+
input_word_clean = clean_word(input_word)
|
122 |
+
|
123 |
+
# try the singular form of the word
|
124 |
+
singular = self.pluralizer.pluralize(input_word_clean, 1)
|
125 |
+
mapping = get_mapping_from_db(self.db_cursor, singular)
|
126 |
+
if mapping:
|
127 |
+
print(f" - Found mapping in db: {mapping}")
|
128 |
+
return mapping
|
129 |
+
|
130 |
+
# try the plural form of the word
|
131 |
+
plural = self.pluralizer.pluralize(input_word_clean, 2)
|
132 |
+
mapping = get_mapping_from_db(self.db_cursor, plural)
|
133 |
+
if mapping:
|
134 |
+
print(f" - Found mapping in db: {mapping}")
|
135 |
+
return mapping
|
136 |
+
|
137 |
+
|
138 |
+
food_nonfood = classify_as_food_nonfood(input_word)
|
139 |
+
|
140 |
+
# if we're very confident that the word is non-food, let's not even classify it
|
141 |
+
if food_nonfood[1] > 0.9 and food_nonfood[0] == False:
|
142 |
+
mapping = {
|
143 |
+
'input_word': input_word,
|
144 |
+
'cleaned_word': input_word_clean,
|
145 |
+
'matching_word': 'Non-Food Item',
|
146 |
+
'dictionary_word': 'Non-Food Item',
|
147 |
+
'similarity_score': None,
|
148 |
+
'confidence_score': None,
|
149 |
+
'similar_words': None,
|
150 |
+
'is_food': False,
|
151 |
+
'food_nonfood_score': food_nonfood[1]
|
152 |
+
}
|
153 |
+
store_mapping_to_db(self.db_cursor, self.db_conn, mapping)
|
154 |
+
return mapping
|
155 |
+
|
156 |
+
mapping = self.perform_mapping(input_word)
|
157 |
+
|
158 |
+
food_nonfood_pessimistic = pessimistic_food_nonfood_score(food_nonfood, mapping['similarity_score'])
|
159 |
+
mapping.update({
|
160 |
+
'is_food': food_nonfood_pessimistic[0],
|
161 |
+
'food_nonfood_score': food_nonfood_pessimistic[1]
|
162 |
+
})
|
163 |
+
|
164 |
+
print(f" - Storing new mapping to db: {mapping}")
|
165 |
+
store_mapping_to_db(self.db_cursor, self.db_conn, mapping)
|
166 |
+
return mapping
|
167 |
+
|
168 |
+
def match_words(self, input_words, stream_results=False):
|
169 |
+
results = []
|
170 |
+
for input_word in tqdm(input_words, desc="Processing input words"):
|
171 |
+
if not isinstance(input_word, str) or pd.isna(input_word) or input_word == "" or input_word.lower() == "nan":
|
172 |
+
continue
|
173 |
+
|
174 |
+
print()
|
175 |
+
print(f"Processing: {input_word}")
|
176 |
+
|
177 |
+
if "&" in input_word or "and" in input_word:
|
178 |
+
print(" - Skipping multi-item word")
|
179 |
+
continue
|
180 |
+
|
181 |
+
# if the word has a "," or "/" in it, let's skip it for now
|
182 |
+
if ',' in input_word or '/' in input_word:
|
183 |
+
mapping = self.handle_multi_item(input_word)
|
184 |
+
else:
|
185 |
+
mapping = self.handle_single_item(input_word)
|
186 |
+
|
187 |
+
if mapping:
|
188 |
+
results.append(mapping)
|
189 |
+
|
190 |
+
if stream_results:
|
191 |
+
return mapping
|
192 |
+
|
193 |
+
self.save_to_csv(results)
|
194 |
+
|
195 |
+
return results
|
app.py
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pandas as pd
|
3 |
+
from algo import Algo
|
4 |
+
from db.db_utils import get_connection
|
5 |
+
|
6 |
+
db_conn = get_connection()
|
7 |
+
algo = Algo(db_conn)
|
8 |
+
|
9 |
+
# Function to process the input
|
10 |
+
def process_input(input_text, csv_file):
|
11 |
+
if csv_file is not None:
|
12 |
+
# Read the uploaded CSV file
|
13 |
+
df = pd.read_csv(csv_file.name)
|
14 |
+
# Check if 'description' column exists
|
15 |
+
if 'description' in df.columns:
|
16 |
+
descriptions = df['description'].tolist()
|
17 |
+
results = algo.match_words(descriptions)
|
18 |
+
else:
|
19 |
+
return pd.DataFrame({"Error": ["CSV file must have a 'description' column"]})
|
20 |
+
else:
|
21 |
+
# Process the single input text
|
22 |
+
results = algo.match_words([input_text])
|
23 |
+
|
24 |
+
df = pd.DataFrame(results, columns=["input_word", "cleaned_word", 'matching_word', 'dictionary_word', 'similarity_score', 'confidence_score', 'similar_words', 'is_food', 'food_nonfood_score'])
|
25 |
+
# Filter to only required columns
|
26 |
+
df_filtered = df[["input_word", "dictionary_word", "similarity_score", "is_food", "food_nonfood_score"]]
|
27 |
+
return df_filtered
|
28 |
+
|
29 |
+
# Gradio interface
|
30 |
+
with gr.Blocks() as demo:
|
31 |
+
with gr.Column():
|
32 |
+
with gr.Row():
|
33 |
+
input_text = gr.Textbox(label="Enter a food item", placeholder="e.g. apple")
|
34 |
+
csv_input = gr.File(label="Upload a CSV file (optional)")
|
35 |
+
submit_button = gr.Button("Submit")
|
36 |
+
output_table = gr.DataFrame(label="Processed Results")
|
37 |
+
|
38 |
+
input_text.submit(fn=process_input, inputs=[input_text, csv_input], outputs=output_table)
|
39 |
+
submit_button.click(fn=process_input, inputs=[input_text, csv_input], outputs=output_table)
|
40 |
+
|
41 |
+
demo.launch()
|
42 |
+
db_conn.close()
|
ask_gpt.py
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import csv
|
3 |
+
import json
|
4 |
+
import pandas as pd
|
5 |
+
from openai import OpenAI
|
6 |
+
from dotenv import load_dotenv
|
7 |
+
|
8 |
+
|
9 |
+
load_dotenv()
|
10 |
+
|
11 |
+
api_key = os.getenv("OPENAI_API_KEY")
|
12 |
+
client = OpenAI(api_key=api_key)
|
13 |
+
|
14 |
+
|
15 |
+
def query_gpt(food_item):
|
16 |
+
prompt = (
|
17 |
+
f"I have a particular food item and I can't find it in the USDA database. Can you suggest the most similar food item that would likely be in the USDA food database?\n\n"
|
18 |
+
f"Try to be as similar as possible to the food item, such that if the word is Leek, tell me 'Leeks, raw' and not 'Onion'.\n\n"
|
19 |
+
f"Make sure you're accurate about whether it is cooked, prepared, etc or not.\n\n"
|
20 |
+
f"But if its an obscure food, you can come up with a extremely similar food item that is similar in DMC.\n\n"
|
21 |
+
f"If it's not a food item, return 'Non-Food Item'.\n\n"
|
22 |
+
f"If it's a generic term like 'Mixture of foods', just say: 'Mixed Food Items'.\n\n"
|
23 |
+
f"You should respond in json format with an object that has the key `guess`, and the value is the most similar food item.\n\n"
|
24 |
+
f"The food item is: \"{food_item}\""
|
25 |
+
)
|
26 |
+
|
27 |
+
completion = client.chat.completions.create(
|
28 |
+
messages=[
|
29 |
+
{"role": "system", "content": "You are a helpful assistant."},
|
30 |
+
{"role": "user", "content": prompt}
|
31 |
+
],
|
32 |
+
model="gpt-3.5-turbo-1106",
|
33 |
+
response_format={"type": "json_object"},
|
34 |
+
)
|
35 |
+
response = completion.choices[0].message.content
|
36 |
+
parsed = parse_response(response)
|
37 |
+
print(f"Q: '{food_item}'")
|
38 |
+
print(f"A: '{parsed}'")
|
39 |
+
print()
|
40 |
+
return parsed
|
41 |
+
|
42 |
+
# Define the function to parse the GPT response
|
43 |
+
def parse_response(response):
|
44 |
+
try:
|
45 |
+
result = json.loads(response)
|
46 |
+
return result['guess']
|
47 |
+
except (json.JSONDecodeError, KeyError) as e:
|
48 |
+
print(f"Error parsing response: {response} - {e}")
|
49 |
+
return None
|
audits/1718289794.csv
ADDED
@@ -0,0 +1,591 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input_word,original_dictionary_word,new_dictionary_word
|
2 |
+
Pepper - Bell Pepper,"Pepper, raw, NFS","Pepper, raw, NFS"
|
3 |
+
Bean - Green Bean,"Green beans, raw","Green beans, raw"
|
4 |
+
Eggplant,"Eggplant, raw","Eggplant, raw"
|
5 |
+
Onion - Brown Onion,"Onions, yellow, raw","Onions, yellow, raw"
|
6 |
+
Potato ,"Potato, NFS","Potato, NFS"
|
7 |
+
Squash - Kabocha Squash,"Summer squash, green, raw","Squash, butternut, raw"
|
8 |
+
Banana,"Banana, raw","Banana, raw"
|
9 |
+
Brussel Sprout,"Brussels sprouts, raw","Brussels sprouts, raw"
|
10 |
+
Cauliflower,"Cauliflower, raw","Cauliflower, raw"
|
11 |
+
Corn - White Corn,"Corn, sweet, white, raw","Corn, sweet, white, raw"
|
12 |
+
Cucumber,"Cucumber, raw","Cucumber, raw"
|
13 |
+
Lime,"Lime, raw","Lime, raw"
|
14 |
+
Mango,"Mango, raw","Mango, raw"
|
15 |
+
nan,"Nance, frozen, unsweetened","Nance, frozen, unsweetened"
|
16 |
+
Pepper - Jalapeno Pepper,"Peppers, jalapeno, raw","Peppers, jalapeno, raw"
|
17 |
+
Squash - Butternut Squash,"Squash, butternut, raw","Squash, butternut, raw"
|
18 |
+
Tomato - Cherry Tomato,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
19 |
+
Melon - Cantaloupe,"Melons, cantaloupe, raw","Melons, cantaloupe, raw"
|
20 |
+
Pineapple,"Pineapple, raw","Pineapple, raw"
|
21 |
+
Tomato - Roma Tomato,"Tomato, roma","Tomato, roma"
|
22 |
+
Lettuce - Iceberg Lettuce,"Lettuce, iceberg, raw","Lettuce, iceberg, raw"
|
23 |
+
Orange ,"Orange, raw","Orange, raw"
|
24 |
+
Pepper - Pasilla Pepper,"Pepper, hot chili, raw","Pepper, hot chili, raw"
|
25 |
+
Onion - Green Onion,"Onions, green, raw","Onions, green, raw"
|
26 |
+
Broccoli,"Broccoli, raw","Broccoli, raw"
|
27 |
+
Cabbage -Cabbage salad,"Cabbage salad, NFS","Cabbage salad, NFS"
|
28 |
+
Pepper - Serrano Pepper,"Peppers, serrano, raw","Peppers, serrano, raw"
|
29 |
+
Radish,"Radish, raw","Radish, raw"
|
30 |
+
Squash - Mexican Squash,"Squash, Indian, raw (Navajo)","Squash, Indian, raw (Navajo)"
|
31 |
+
Parsley,"Parsley, raw","Parsley, raw"
|
32 |
+
Tejocote - Tejocote,"Taro, tahitian, raw",Tejocote - Tejocote
|
33 |
+
Persimmon,"Persimmon, raw","Persimmon, raw"
|
34 |
+
Cabbage - Napa Cabbage,"Cabbage, napa, cooked","Cabbage, napa, cooked"
|
35 |
+
Squash - Italian Squash,"Squash, winter, spaghetti, raw","Squash, winter, spaghetti, raw"
|
36 |
+
Chayote,"Chayote, fruit, raw","Chayote, fruit, raw"
|
37 |
+
Carrot,"Carrots, raw","Carrots, raw"
|
38 |
+
Chard,"Chard, raw","Chard, raw"
|
39 |
+
Cucumber - English/Hot hauce,"Cucumber, raw","Cucumber, raw"
|
40 |
+
Orange - Mandarin Orange,"Tangerines, (mandarin oranges), raw","Tangerines, (mandarin oranges), raw"
|
41 |
+
Grapefruit,"Grapefruit, raw","Grapefruit, raw"
|
42 |
+
Lettuce - Iceberg Lettuce (35lbs,"Lettuce, iceberg, raw","Lettuce, iceberg, raw"
|
43 |
+
Bean Green Bean,"Green beans, raw","Green beans, raw"
|
44 |
+
Bok Choy,"Cabbage, bok choy, raw","Cabbage, bok choy, raw"
|
45 |
+
Pear Asian,"Pear, Asian, raw","Pear, Asian, raw"
|
46 |
+
Celery,"celery, raw","celery, raw"
|
47 |
+
Green Mango,"Mango, raw","Mango, raw"
|
48 |
+
Young Coconut,"Coconut, fresh","Coconut, fresh"
|
49 |
+
Papaya,"Papaya, raw","Papaya, raw"
|
50 |
+
Cactus - Cactus Pear (40 lb),"Cactus, raw","Cactus, raw"
|
51 |
+
Coconut,"Coconut, fresh","Coconut, fresh"
|
52 |
+
Tangerine,"Tangerine, raw","Tangerine, raw"
|
53 |
+
Asparagus,"Asparagus, raw","Asparagus, raw"
|
54 |
+
Mustard,Mustard,Mustard
|
55 |
+
Tomatillo,"Tomatillos, raw","Tomatillos, raw"
|
56 |
+
Squash - Acorn Squash,"Squash, acorn, raw","Squash, acorn, raw"
|
57 |
+
Cucumber - Persian Cucumber,"Cucumber, raw","Cucumber, raw"
|
58 |
+
Onion-Mexican Green Onion,"Onions, green, raw","Onions, green, raw"
|
59 |
+
Jackfruit,"Jackfruit, raw","Jackfruit, raw"
|
60 |
+
Lettuce - Green Leaf Lettuce,"Lettuce, leaf, green, raw","Lettuce, leaf, green, raw"
|
61 |
+
Pepper ,"Pepper, raw, NFS","Pepper, raw, NFS"
|
62 |
+
Spinach,"Spinach, raw","Spinach, raw"
|
63 |
+
Tomato - Beefsteak Tomato,"Tomato, roma","Tomato, roma"
|
64 |
+
Apple ,"Apple, raw","Apple, raw"
|
65 |
+
Mixed Produce Pallet (Set Weight),"Vegetables, mixed, frozen, unprepared","Vegetables, mixed, frozen, unprepared"
|
66 |
+
Pepper - Anaheim Pepper,"Pepper, raw, NFS","Pepper, raw, NFS"
|
67 |
+
Cabbage - Green Cabbage,"cabbage, green, raw","cabbage, green, raw"
|
68 |
+
spring mix,"Wheat, hard red spring","Wheat, hard red spring"
|
69 |
+
Avocado,"Avocado, raw","Avocado, raw"
|
70 |
+
Tomato - Grape Tomato,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
71 |
+
Plum,"Plum, raw","Plum, raw"
|
72 |
+
Mixed Greens - Salad,"Mixed salad greens, raw","Mixed salad greens, raw"
|
73 |
+
Radicchio,"Radicchio, raw","Radicchio, raw"
|
74 |
+
Cactus,"Cactus, raw","Cactus, raw"
|
75 |
+
Jicama,"Jicama, raw","Jicama, raw"
|
76 |
+
Yam,"Yam, raw","Yam, raw"
|
77 |
+
Grape - Green Grape,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
78 |
+
Lettuce - Romaine Lettuce,"Romaine lettuce, raw","Romaine lettuce, raw"
|
79 |
+
Yucca,"Snacks, yucca (cassava) chips, salted","Snacks, yucca (cassava) chips, salted"
|
80 |
+
Pepper - Red Fresno Pepper,"Pepper, sweet, red, raw","Pepper, sweet, red, raw"
|
81 |
+
Melon - Korean,"Melon, banana (Navajo)","Melon, banana (Navajo)"
|
82 |
+
Mushroom ,"Mushrooms, raw","Mushrooms, raw"
|
83 |
+
Tomato - Heirloom Tomato,"Tomatoes, canned, red, ripe, diced","Tomatoes, canned, red, ripe, diced"
|
84 |
+
Kohlrabi,"Kohlrabi, raw","Kohlrabi, raw"
|
85 |
+
Lemon,"Lemon, raw","Lemon, raw"
|
86 |
+
Pepper - Mini Sweet Pepper,"peppers, bell, yellow, raw, mini ","peppers, bell, yellow, raw, mini"
|
87 |
+
Bean Romano Bean,"Pinto beans, NFS","Pinto beans, NFS"
|
88 |
+
Banana - Burro Banana,"Banana, raw","Banana, raw"
|
89 |
+
Kiwi ( 10 Lbs),"Kiwi fruit, raw","Kiwi fruit, raw"
|
90 |
+
Melon - Honeydew,"Honeydew melon, raw","Honeydew melon, raw"
|
91 |
+
Radish - Daikon Radish,"Daikon radish, cooked","Daikon radish, cooked"
|
92 |
+
Pear,"Pear, raw","Pear, raw"
|
93 |
+
Nectarine,"Nectarine, raw","Nectarine, raw"
|
94 |
+
Potato - Red Potato,"Potatoes, red, without skin, raw","Potatoes, red, without skin, raw"
|
95 |
+
Pepper Shishito,"Pepper, raw, NFS","Pepper, raw, NFS"
|
96 |
+
Leek,"Leek, cooked","Leek, cooked"
|
97 |
+
Apricot,"Apricot, raw","Apricot, raw"
|
98 |
+
Aloe vera,Aloe vera juice drink,Aloe vera juice drink
|
99 |
+
Squash - Yellow Squash,"Summer squash, yellow, raw","Summer squash, yellow, raw"
|
100 |
+
Celery - Celery Heart,"celery, raw","celery, raw"
|
101 |
+
Guava (13 lbs),"Guava, raw","Guava, raw"
|
102 |
+
Pepper - Shishito Pepper,"Pepper, raw, NFS","Pepper, raw, NFS"
|
103 |
+
Squash mix italian/yellow (30 lbs ),"Summer squash, yellow, raw","Summer squash, yellow, raw"
|
104 |
+
Banana - Plantain,"Plantains, yellow, raw","Plantains, yellow, raw"
|
105 |
+
Cherry,"Cobbler, cherry","Cobbler, cherry"
|
106 |
+
Grape - Red Grape,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
107 |
+
Pepper - Yellow Pepper,"Peppers, sweet, yellow, raw","Peppers, sweet, yellow, raw"
|
108 |
+
Pepper - Habanero Pepper,"Peppers, jalapeno, raw","Peppers, jalapeno, raw"
|
109 |
+
Lettuce Green Leaf,"Lettuce, leaf, green, raw","Lettuce, leaf, green, raw"
|
110 |
+
Pea - Snow Pea,"Blackeyed peas, from frozen","Blackeyed peas, from frozen"
|
111 |
+
Corn - Yellow Corn,"Corn, sweet, yellow, raw","Corn, sweet, yellow, raw"
|
112 |
+
Dandelion,"Dandelion greens, raw","Dandelion greens, raw"
|
113 |
+
Pear - Asian Pear,"Pear, Asian, raw","Pear, Asian, raw"
|
114 |
+
Turnip,"Turnip, raw","Turnip, raw"
|
115 |
+
Onion - White Onion,"Onions, white, raw","Onions, white, raw"
|
116 |
+
Bean bag,"Yardlong bean, raw","Yardlong bean, raw"
|
117 |
+
Cilantro,"Cilantro, raw","Cilantro, raw"
|
118 |
+
Cucumber - Pickling Cucumber,"Cucumber, cooked","Cucumber, pickling"
|
119 |
+
Mushroom - White Mushroom (6 pounds),"Mushrooms, white, raw","Mushrooms, white, raw"
|
120 |
+
Squash de Castilla (bin ),"Squash, summer, souffle","Squash, winter, spaghetti, raw"
|
121 |
+
Apple Other,"Apple, raw","Apple, raw"
|
122 |
+
Mushroom - Portabella Mushroom,"Mushroom, portabella","Mushroom, portabella"
|
123 |
+
Arugula (5lbs),"Arugula, raw","Arugula, raw"
|
124 |
+
Basil,"Basil, raw","Basil, raw"
|
125 |
+
Lettuce - Red Leaf Lettuce,"Lettuce, leaf, red, raw","Lettuce, leaf, red, raw"
|
126 |
+
Fennel,"Fennel, bulb, raw","Fennel, bulb, raw"
|
127 |
+
Carrot - Baby Carrot,"Carrots, baby, raw","Carrots, baby, raw"
|
128 |
+
Collard Greens,"Chicory greens, raw",Collard greens
|
129 |
+
Artichoke,"Artichoke, raw","Artichoke, raw"
|
130 |
+
Squash - Spaghetti Squash,"Squash, winter, spaghetti, raw","Squash, winter, spaghetti, cooked"
|
131 |
+
Beet - Red Beet,"Beets, raw","Beets, raw"
|
132 |
+
Ginger,"Tea, ginger","Ginger root, raw"
|
133 |
+
Berry - Raspberry,"Raspberries, raw","Raspberries, raw"
|
134 |
+
Lettuce - Mixed Lettuce,"Lettuce, cooked","Lettuce, raw"
|
135 |
+
Cucumber - English/Hothouse Cucumber,"Cucumber, raw","Cucumber, raw"
|
136 |
+
Melon - Bittermelon,"Bitter melon, cooked","Bitter melon, cooked"
|
137 |
+
Dragon Fruit,Dragon fruit,Dragon fruit
|
138 |
+
Lettuce ,"Lettuce, raw","Lettuce, raw"
|
139 |
+
Banana - Thai Banana,"Banana, raw","Banana, raw"
|
140 |
+
French Beans,"Beans, NFS","Green beans, raw"
|
141 |
+
Cane,"Syrup, Cane","Syrup, Cane"
|
142 |
+
Pea - Snap Pea,Pea salad,Pea salad
|
143 |
+
Bean - Garbanzo Bean (45Lbs),"Bean sprouts, raw","Chickpeas, (garbanzo beans, bengal gram), dry"
|
144 |
+
Squash ,"Winter squash, raw","Winter squash, raw"
|
145 |
+
Sugar Cane,Sugar cane beverage,Sugar cane beverage
|
146 |
+
Lettuce Butter Lettuce,"Lettuce, raw","Lettuce, raw"
|
147 |
+
Kale,"Kale, raw","Kale, raw"
|
148 |
+
Pear - Bartlett Pear,"Pears, raw, bartlett","Pears, raw, bartlett"
|
149 |
+
Long Beans,"Yardlong bean, raw","Yardlong bean, raw"
|
150 |
+
Orange - Blood Orange,"Orange, raw","Orange, raw"
|
151 |
+
Random Foods,Assorted Foods,Assorted Foods
|
152 |
+
Assorted Food Items,Assorted Edible Items,Assorted Edible Items
|
153 |
+
Mixed produce,Mixed Produce,Mixed Produce
|
154 |
+
Malanga - Malanga,"Taro, cooked","Taro, cooked"
|
155 |
+
Sing Qua,"Gourd, white-flowered (calabash), raw","Gourd, white-flowered (calabash), raw"
|
156 |
+
Garlic,"Garlic, raw","Garlic, raw"
|
157 |
+
pea sugar snap pea (30 lbs ),"Peas, edible-podded, raw","Peas, edible-podded, raw"
|
158 |
+
Pepper Red Fresno (10 lbs ),"Peppers, sweet, red, raw","Peppers, sweet, red, raw"
|
159 |
+
Chard - Rainbow Chard,"Chard, swiss, raw","Chard, swiss, raw"
|
160 |
+
Bean - Fava Bean (28 lbs),"Beans, fava, in pod, raw","Beans, fava, in pod, raw"
|
161 |
+
Taro,"Taro, raw","Taro, raw"
|
162 |
+
Dill,"Pickles, dill","Pickles, dill"
|
163 |
+
Onion Green onion iceless,"Onions, spring or scallions (includes tops and bulb), raw","Onions, spring or scallions (includes tops and bulb), raw"
|
164 |
+
Carrot Baby,"Carrots, baby, raw","Carrots, baby, raw"
|
165 |
+
Mint,"Candy, mint","Herbs, fresh, spearmint"
|
166 |
+
Pepper Jalapeno (10 Lbs ),"Jalapenos, NFS","Jalapenos, NFS"
|
167 |
+
Onion ,"Onions, raw","Onions, raw"
|
168 |
+
Squash - Butternut,"Squash, butternut, raw","Squash, butternut, raw"
|
169 |
+
Onion - Red Onion,"Onions, red, raw","Onions, red, raw"
|
170 |
+
Squash - Pumpkin,"Pumpkin, raw","Pumpkin, raw"
|
171 |
+
Nira Green,"Spinach, raw","Spinach, raw"
|
172 |
+
Peach,"Peach, raw","Peach, raw"
|
173 |
+
Mango Ataulfo,"Mango, raw","Mango, raw"
|
174 |
+
Pomegranate,"Pomegranate, raw","Pomegranate, raw"
|
175 |
+
Onion Shallot,"Shallots, raw","Shallots, raw"
|
176 |
+
Garlic peel,"Garlic, raw","Garlic, raw"
|
177 |
+
Tomato Tomato,"Tomatoes, red, ripe, raw, year round average","Tomatoes, red, ripe, raw, year round average"
|
178 |
+
Escarole,"Lettuce, cos or romaine, raw","Lettuce, cos or romaine, raw"
|
179 |
+
Pea - english (5 Lbs ),"Peas, green, raw","Peas, green, raw"
|
180 |
+
Berry ,"Berries, NFS","Berries, NFS"
|
181 |
+
Mixed Greens,"Mixed salad greens, raw","Mixed salad greens, raw"
|
182 |
+
Cucumber persian,"Cucumber, peeled, raw","Cucumber, peeled, raw"
|
183 |
+
quince,"Quinces, raw","Quinces, raw"
|
184 |
+
Pepper - Chile Pepper,"Pepper, hot chili, raw","Pepper, hot chili, raw"
|
185 |
+
Turmeric,"Spices, turmeric, ground","Spices, turmeric, ground"
|
186 |
+
Grape ,"Grapes, raw","Grapes, raw"
|
187 |
+
Pomegranate (6 lbs,"Pomegranate, raw","Pomegranate, raw"
|
188 |
+
Okra,"Okra, raw","Okra, raw"
|
189 |
+
Pea-English Pea,"Peas, green, raw","Peas, green, raw"
|
190 |
+
Parsnip,"Parsnips, raw","Parsnips, raw"
|
191 |
+
Potato - Russet Potato,"Potatoes, russet, without skin, raw","Potatoes, russet, without skin, raw"
|
192 |
+
Mamey,"Sapote, mamey, raw","Sapote, mamey, raw"
|
193 |
+
India CHili,"Spices, chili powder","Spices, chili powder"
|
194 |
+
Cactus peel (40lbs ),"Lemon peel, raw","Cactus, raw"
|
195 |
+
Mixed Greens Salad,"Mixed salad greens, raw","Mixed salad greens, raw"
|
196 |
+
Bean - Sprouts,"Bean sprouts, raw","Bean sprouts, raw"
|
197 |
+
Tomato On The Vine,"Tomatoes, red, ripe, raw, year round average","Tomatoes, red, ripe, raw, year round average"
|
198 |
+
Pomelo,"Grapefruit, raw, white, California",Pomelo
|
199 |
+
Organic Onion - Brown Onion,"Onions, raw","Onions, raw"
|
200 |
+
Potatos - Baby Potatos (Bin 2K),"Potato, NFS","Potato, NFS"
|
201 |
+
Lettuce - frisee,"Lettuce, cos or romaine, raw","Lettuce, cos or romaine, raw"
|
202 |
+
Orange Mandarine (10 Lbs ),"Tangerines, (mandarin oranges), raw","Tangerines, (mandarin oranges), raw"
|
203 |
+
Lime - Key Lime,"Lime juice, raw","Lime juice, raw"
|
204 |
+
Oregano,"Spices, oregano, dried","Spices, oregano, dried"
|
205 |
+
Orange - Minneola Orange,"Orange, raw","Orange, raw"
|
206 |
+
Squash - Squash Blossom,"Squash, summer, all varieties, raw","Squash, summer, all varieties, raw"
|
207 |
+
Onion - Shallot,"Shallots, raw","Shallots, raw"
|
208 |
+
Milk (36 lbs),"Milk, NFS","Milk, NFS"
|
209 |
+
Pepper - Mix,"Peppers, sweet, red, raw","Peppers, sweet, red, raw"
|
210 |
+
Cabbage - Red Cabbage,"cabbage, red, raw",red cabbage
|
211 |
+
Watermelon Radish,"Radish, raw","Radish, raw"
|
212 |
+
Beet - Yellow Beet,"Beet greens, raw","Beet greens, raw"
|
213 |
+
Lemongrass,"Lemon grass (citronella), raw","Lemon grass (citronella), raw"
|
214 |
+
Mixed Fruit,Mixed Fruits and Vegetables,Mixed Fruits and Vegetables
|
215 |
+
Malanga,"Taro, raw","Taro, raw"
|
216 |
+
Bean ,"Beans, NFS","Beans, NFS"
|
217 |
+
beet Warter melon beet,"Beets, cooked, boiled, drained","Beets, cooked, boiled, drained"
|
218 |
+
Water Pallet Set Weight,"Beverages, carbonated, cola, regular","Beverages, carbonated, cola, regular"
|
219 |
+
Gooseberry tomatillo (5lbs),"Tomatillos, raw","Tomatillos, raw"
|
220 |
+
Onion Brown Onion,"Onions, raw","Onions, raw"
|
221 |
+
Date (11 lbs ),Date,Date
|
222 |
+
juice,"Fruit juice, NFS","Fruit juice, NFS"
|
223 |
+
Orchids Flower,Mixed Edibles,Mixed Edibles
|
224 |
+
onion chives (10 lbs ),"Chives, raw","Chives, raw"
|
225 |
+
Rosemary,"Rosemary, fresh","Rosemary, fresh"
|
226 |
+
Pepper - Banana Pepper,"Pepper, banana, raw","Pepper, banana, raw"
|
227 |
+
Cauliflower - Cauliflower,"Cauliflower, raw","Cauliflower, raw"
|
228 |
+
Starfruit,"Starfruit, raw","Starfruit, raw"
|
229 |
+
Passion Fruit,"Passion fruit, raw","Passion fruit, raw"
|
230 |
+
Tung Qwa (Bin ),"MORI-NU, Tofu, silken, lite extra firm","MORI-NU, Tofu, silken, lite extra firm"
|
231 |
+
almond,Almond chicken,Almonds
|
232 |
+
Garlic - Peeled Garlic,"Garlic, raw","Garlic, raw"
|
233 |
+
Squash - Baby Summer Squash,"Summer squash, green, raw","Summer squash, green, raw"
|
234 |
+
Cactus Pitaya,Dragon fruit,Dragon fruit
|
235 |
+
Rutabaga,"Rutabaga, raw","Rutabaga, raw"
|
236 |
+
Endive,"Endive, raw","Endive, raw"
|
237 |
+
Squash - Baby Italian Squash,"Summer squash, yellow, raw","Summer squash, yellow, raw"
|
238 |
+
Melon - Hami Melon,"Melons, cantaloupe, raw","Melons, cantaloupe, raw"
|
239 |
+
Peach - White Peach,"Peach, raw","Peach, raw"
|
240 |
+
carrots bag (5 lbs ),"Carrots, raw","Carrots, raw"
|
241 |
+
Rambutan,Lychee,Lychee
|
242 |
+
Lyches,Lychee,Lychee
|
243 |
+
Almond - Fresh Almond,"Almonds, unsalted","Almonds, unsalted"
|
244 |
+
Bean green beann,"Beans, snap, green, canned, regular pack, drained solids","Beans, snap, green, canned, regular pack, drained solids"
|
245 |
+
verdolaga,"Purslane, raw","Purslane, raw"
|
246 |
+
Banana leaf,"Banana, raw","Banana, raw"
|
247 |
+
Melon ,"Melons, cantaloupe, raw","Melons, cantaloupe, raw"
|
248 |
+
RIce,"Rice, white, long-grain, regular, raw, enriched","Rice, white, long-grain, regular, raw, enriched"
|
249 |
+
Oil Vegetable,"Vegetable oil, NFS","Vegetable oil, NFS"
|
250 |
+
Carrot Bin,"Carrots, raw","Carrots, raw"
|
251 |
+
Lemon meyers,"Lemons, raw, without peel","Lemons, raw, without peel"
|
252 |
+
Baby Corn (10 lbs ),"Corn, sweet, white, canned, whole kernel, regular pack, solids and liquids","Corn, sweet, white, canned, whole kernel, regular pack, solids and liquids"
|
253 |
+
Tomato ,"Tomatoes, raw","Tomatoes, raw"
|
254 |
+
Flour white,"FLOUR, RICE, WHITE",FLOUR
|
255 |
+
Sugar,"Sugar, NFS","Sugar, NFS"
|
256 |
+
Cake Mix,"Cake, yellow, light, dry mix","Cake, yellow, light, dry mix"
|
257 |
+
Jackfruit - Bin 1.5K,"Jackfruit, raw","Jackfruit, raw"
|
258 |
+
Soup Cream,"Soup, cream of chicken, canned, condensed","Soup, cream of chicken, canned, condensed"
|
259 |
+
Cabbage - Savoy Cabbage,"Cabbage, savoy, raw","Cabbage, savoy, raw"
|
260 |
+
Corn ,"Corn, raw","Corn, raw"
|
261 |
+
Basil - Thai Basil,"Basil, fresh","Basil, fresh"
|
262 |
+
Tofu,"Tofu, raw, regular, prepared with calcium sulfate","Tofu, raw, regular, prepared with calcium sulfate"
|
263 |
+
Peanut ( 40 lbs),"peanuts, raw","peanuts, raw"
|
264 |
+
Pepper serrano Pepper (10 Lbs ),"Peppers, serrano, raw","Peppers, serrano, raw"
|
265 |
+
Nectarine - White Nectarine,"Nectarine, raw","Nectarine, raw"
|
266 |
+
melon cantaloupe,"Melons, cantaloupe, raw","Melons, cantaloupe, raw"
|
267 |
+
Apple - Granny Smith Apple,"APPLES, GRANNY SMITH","APPLES, GRANNY SMITH"
|
268 |
+
Sumer Squash,"Bread, zucchini","Zucchini, pickled"
|
269 |
+
Miscellaneous Mix,"Nuts, mixed nuts, oil roasted, with peanuts, lightly salted","Nuts, mixed nuts, oil roasted, with peanuts, lightly salted"
|
270 |
+
Pepper- manzano,"Peppers, sweet, red, raw","Peppers, sweet, red, raw"
|
271 |
+
Miscellaneous Mix,"Mixed nuts, NFS","Mixed nuts, NFS"
|
272 |
+
Fig,"Fig, raw","Fig, raw"
|
273 |
+
Celery - Celery Root,"celery, raw","celery, raw"
|
274 |
+
Berry Red Currants (5lbs),"Currants, red and white, raw","Currants, red and white, raw"
|
275 |
+
Nance Fruit,"Nance, frozen, unsweetened","Nance, frozen, unsweetened"
|
276 |
+
Lemon - Meyer Lemon (28 lbs ),"Lemon peel, raw","Lemon peel, raw"
|
277 |
+
olive,Olive oil,Olive oil
|
278 |
+
Lettuce - Watercress,"Lettuce, butterhead (includes boston and bibb types), raw","Lettuce, butterhead (includes boston and bibb types), raw"
|
279 |
+
Potato - Sweet Potato,"Sweet potato, NFS","Sweet potato, NFS"
|
280 |
+
Sun Choke,"Jerusalem-artichokes, raw","Jerusalem-artichokes, raw"
|
281 |
+
Melon Korean (40Lbs),"Melons, cantaloupe, raw","Melons, cantaloupe, raw"
|
282 |
+
Pepper Mansano Pepper (10 Lbs ),"Peppers, sweet, red, raw","Peppers, sweet, red, raw"
|
283 |
+
Pineaple,"Pineapple, raw","Pineapple, raw"
|
284 |
+
Berry blue berry (9Lbs ),"Blueberries, raw","Blueberries, raw"
|
285 |
+
Berry - Cranberry,"Cranberries, raw","Cranberries, raw"
|
286 |
+
Tamarindo,Tamarind,Tamarind
|
287 |
+
Pea Englis,"Peas, green, raw","Peas, green, raw"
|
288 |
+
Beet - Candy Beet,"Beets, raw","Beets, raw"
|
289 |
+
Broccoli Florets,"Broccoli, raw","Broccoli, raw"
|
290 |
+
Cheznuts,Chestnuts,Chestnuts
|
291 |
+
Garlic - Garlic,"Garlic, raw","Garlic, raw"
|
292 |
+
banana blossom,"Bananas, raw","Bananas, raw"
|
293 |
+
Corn Corn ( BIN ),"Corn, raw","Corn, raw"
|
294 |
+
Potatos -,"Potatoes, flesh and skin, raw","Potatoes, flesh and skin, raw"
|
295 |
+
Collar Green,"Mustard greens, cooked, boiled, drained, without salt","Collards, cooked, boiled, drained, without salt"
|
296 |
+
lettuce romaine Bin,"Lettuce, cos or romaine, raw","Lettuce, cos or romaine, raw"
|
297 |
+
Mango Manila,"Mango, raw","Mango, raw"
|
298 |
+
Miscellaneous,Miscellaneous,Miscellaneous
|
299 |
+
Squash - Butternut Squash,"Squash, butternut, raw","Squash, butternut, raw"
|
300 |
+
Cactus - Xoconostle,"Prickly pears, raw","Prickly pears, raw"
|
301 |
+
Broccoli - Romanesco Broccoli,"Broccoli, cooked, boiled, drained, with salt","Broccoli, cooked, boiled, drained, with salt"
|
302 |
+
sherly hon,"MUSHROOMS, SHIITAKE","MUSHROOMS, SHIITAKE"
|
303 |
+
Yam BIN,"Yam, raw","Yam, raw"
|
304 |
+
Cabbage - Green (BIN ),"cabbage, green, raw","cabbage, green, raw"
|
305 |
+
Celery - Celery,"celery, raw","celery, raw"
|
306 |
+
Banana - Apple Banana,"Banana, raw","Banana, raw"
|
307 |
+
melon honeydew (bin ),"Honeydew melon, raw","Honeydew melon, raw"
|
308 |
+
Broccoli - Rapini,"Broccoli, raw","Broccoli, raw"
|
309 |
+
Pitaya ( 4 lbs),Dragon fruit,Dragon fruit
|
310 |
+
Mushroom - Other ( 3 bls),"Mushrooms, white, raw","Mushrooms, white, raw"
|
311 |
+
Tomato Medley Mix (12x1),"Tomatoes, red, ripe, raw, year round average","Tomatoes, red, ripe, raw, year round average"
|
312 |
+
Chirimoya,"Cherimoya, raw","Cherimoya, raw"
|
313 |
+
Savory Herbs,"Spices, parsley, dried","Spices, parsley, dried"
|
314 |
+
Berry - Mix Berry,"Blackberries, frozen, unsweetened","Blackberries, frozen, unsweetened"
|
315 |
+
Sage,"Rosemary, fresh","Sage, ground"
|
316 |
+
Cauliflower - Purple Cauliflower,"Cauliflower, green, raw","Cauliflower, purple, raw"
|
317 |
+
Thyme (10 lbs ),"Thyme, fresh","Thyme, fresh"
|
318 |
+
Longan,"Longans, raw","Longans, raw"
|
319 |
+
CORN Other,"Corn, sweet, white, raw","Corn, sweet, white, raw"
|
320 |
+
Clementines,"Clementines, raw","Clementines, raw"
|
321 |
+
Tomato Medley Mixed (12x2Lb),"Tomatoes, red, ripe, raw, year round average","Tomatoes, red, ripe, raw, year round average"
|
322 |
+
Winter Squash BIN ( 700 Lbs),"Winter squash, raw","Winter squash, raw"
|
323 |
+
Cabbage,"Cabbage, raw","Cabbage, raw"
|
324 |
+
Jujube,"Jujube, raw","Jujube, raw"
|
325 |
+
Broccoli Florets,"Broccoli, raw","Broccoli, raw"
|
326 |
+
Potato - Yukon Potato,"Potatoes, white, flesh and skin, raw","Potatoes, white, flesh and skin, raw"
|
327 |
+
Flowers (350lbs),"Pumpkin flowers, raw","Pumpkin flowers, raw"
|
328 |
+
Persimmon -Fuyu,"Persimmons, japanese, raw","Persimmons, japanese, raw"
|
329 |
+
Potatos,"Potato, NFS","Potato, NFS"
|
330 |
+
Mixed Greens Salad,"Mixed salad greens, raw","Mixed salad greens, raw"
|
331 |
+
Apple Other,"Apples, raw, without skin","Apples, raw, without skin"
|
332 |
+
Pea (3 lbs),"Peas, edible-podded, frozen, unprepared","Peas, edible-podded, frozen, unprepared"
|
333 |
+
Persimmons (3 Lbs),"Persimmon, raw","Persimmon, raw"
|
334 |
+
Pepper shishito 20lbs,"Peppers, sweet, green, raw","Peppers, sweet, green, raw"
|
335 |
+
cardone,"Artichokes, (globe or french), cooked, boiled, drained, with salt","Artichokes, (globe or french), cooked, boiled, drained, with salt"
|
336 |
+
Melon other,"Melons, honeydew, raw","Melons, honeydew, raw"
|
337 |
+
Organic Lettuce - Romaine Lettuce,"Lettuce, cos or romaine, raw","Lettuce, cos or romaine, raw"
|
338 |
+
Horseradish Roots,Horseradish,Horseradish
|
339 |
+
USDA BOX Daylight food,"Broccoli, frozen, spears, unprepared (Includes foods for USDA's Food Distribution Program)","Broccoli, frozen, spears, unprepared (Includes foods for USDA's Food Distribution Program)"
|
340 |
+
Carrot - Peeled Carrot,"carrots, baby, raw, peeled","carrots, baby, raw, peeled"
|
341 |
+
Sprout-Alfalfa,"Alfalfa sprouts, raw","Alfalfa sprouts, raw"
|
342 |
+
Nansui Pear,"Pear, Asian, raw","Pear, Asian, raw"
|
343 |
+
Pepper Jalape�o ( bin ),"Peppers, jalapeno, raw","Peppers, jalapeno, raw"
|
344 |
+
Coffee Cream,"Coffee creamer, NFS","Coffee creamer, NFS"
|
345 |
+
Eggplant - (bin 750 Lbs ),"Eggplant, raw","Eggplant, raw"
|
346 |
+
Mushroo Criminy,"mushrooms, crimini","mushrooms, crimini"
|
347 |
+
Basil - Lemon Basil,"Basil, raw","Basil, raw"
|
348 |
+
Greens,"Lettuce, cos or romaine, raw","Lettuce, cos or romaine, raw"
|
349 |
+
Tomatoes,"Tomatoes, raw","Tomatoes, raw"
|
350 |
+
Other Non-Food Item,Non-Food Item,Non-Food Item
|
351 |
+
Carrots,"Carrots, raw","Carrots, raw"
|
352 |
+
Berries,"Berries, NFS","Berries, NFS"
|
353 |
+
Peppers (Capsicums),"Pepper, raw, NFS","Pepper, raw, NFS"
|
354 |
+
Avocados,"Avocado, raw","Avocado, raw"
|
355 |
+
Brussels Sprouts,"Brussels sprouts, raw","Brussels sprouts, raw"
|
356 |
+
Bananas,"Bananas, raw","Bananas, raw"
|
357 |
+
Other Non-Perishable,"Tomatoes, canned","Tomatoes, canned"
|
358 |
+
Beans,"Beans, NFS","Beans, NFS"
|
359 |
+
Leeks,"Leek, cooked","Leek, cooked"
|
360 |
+
Onions,"Onions, raw","Onions, raw"
|
361 |
+
Dairy,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
362 |
+
Other Vegetables,"Classic mixed vegetables, canned, cooked with oil",Mixed Vegetables
|
363 |
+
Mushrooms,"Mushrooms, raw","Mushrooms, raw"
|
364 |
+
Green Beans,"Green beans, raw","Green beans, raw"
|
365 |
+
Grapes,"Grapes, raw","Grapes, raw"
|
366 |
+
Bakery Item,"Bread, white, made from home recipe or purchased at a bakery","Bread, white, made from home recipe or purchased at a bakery"
|
367 |
+
Sweet Potato/Yam/Kumara,"Sweet potato, NFS","Sweet potato, NFS"
|
368 |
+
Other Food Items,Assorted Foods,Assorted Foods
|
369 |
+
Frozen,"Frozen dinner, NFS","Frozen dinner, NFS"
|
370 |
+
TBD,Non-Food Item,Non-Food Item
|
371 |
+
Oranges,"Oranges, raw, Florida","Oranges, raw, Florida"
|
372 |
+
Limes,"Limes, raw","Limes, raw"
|
373 |
+
Lemons,"Lemon, raw","Lemon, raw"
|
374 |
+
Pears,"Pears, raw","Pears, raw"
|
375 |
+
Beverages,Beer,Beverages
|
376 |
+
Tangerines/Mandarins,"Tangerines, (mandarin oranges), raw","Tangerines, (mandarin oranges), raw"
|
377 |
+
Apples,"APPLES, RED DELICIOUS","APPLES, RED DELICIOUS"
|
378 |
+
Peaches,"Peach, raw","Peach, raw"
|
379 |
+
Plums,"Plums, raw","Plums, raw"
|
380 |
+
Papaya/Pawpaw,"Papaya, raw","Papaya, raw"
|
381 |
+
Bin - not rented by FLP,Non-Food Item,Non-Food Item
|
382 |
+
Bins Palogix-34,Non-Food Item,Non-Food Item
|
383 |
+
Bins Palogix-330,Non-Food Item,Non-Food Item
|
384 |
+
Pumpkin,"Pumpkin, raw","Pumpkin, raw"
|
385 |
+
Bean Sprouts,"Bean sprouts, raw","Bean sprouts, raw"
|
386 |
+
Bread,"Bread, wheat","Bread, wheat"
|
387 |
+
roma tomatoes,"TOMATOES, ROMA","TOMATOES, ROMA"
|
388 |
+
tomate,"Tomatoes, red, ripe, raw, year round average","Tomatoes, red, ripe, raw, year round average"
|
389 |
+
mixed load,Mixed Food Items,Mixed Food Items
|
390 |
+
variety of snack items pretzels chips popcorn pork rinds etc. all in family size servings,Mixed Food Items,Mixed Food Items
|
391 |
+
cantaloupes,"Cantaloupe, raw","Cantaloupe, raw"
|
392 |
+
mixed vegetables,Mixed Vegetables,Mixed Vegetables
|
393 |
+
bell peppers,"peppers, bell, red, raw",bell peppers
|
394 |
+
cantalopues honeydews watermelons,"Melons, cantaloupe, raw","Melons, cantaloupe, raw"
|
395 |
+
yellow squash,"Summer squash, yellow, raw","Summer squash, yellow, raw"
|
396 |
+
tomatoes grape type,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
397 |
+
mixed prouce,Mixed Vegetables,Mixed Vegetables
|
398 |
+
cilantro chicken,"Cilantro, raw","Cilantro, raw"
|
399 |
+
vegan mayo,Vegan mayonnaise,Vegan mayonnaise
|
400 |
+
salad greens,"Mixed salad greens, raw","Mixed salad greens, raw"
|
401 |
+
watermelon,"Watermelon, raw","Watermelon, raw"
|
402 |
+
lettuce romaine,"Romaine lettuce, raw","Romaine lettuce, raw"
|
403 |
+
peppers bell type,"Peppers, sweet, green, raw","Peppers, sweet, green, raw"
|
404 |
+
package salads,"Salad dressing, mayonnaise, regular","Salad dressing, ranch dressing, regular"
|
405 |
+
packaged salads,"Salad dressing, russian dressing, low calorie","Salad dressing, russian dressing, low calorie"
|
406 |
+
italian squash,"Squash, summer, all varieties, raw","Squash, zucchini, baby, raw"
|
407 |
+
Dry Food,Mixed Food Items,"Cereals, WHEATENA, dry"
|
408 |
+
cantaloups,"Cantaloupe, raw","Cantaloupe, raw"
|
409 |
+
beets,"Beets, raw","Beets, raw"
|
410 |
+
chipotle barbacoa meat,"Beef, variety meats and by-products, tongue, raw","Beef, variety meats and by-products, tongue, raw"
|
411 |
+
lettuce iceberg lettuce romaine greens misc melons tomatoes strawberries broccoli cauliflower kale greens bok choy cucumbers long beans asparagus,Mixed Food Items,Mixed Salad Greens
|
412 |
+
greens beets,"Beet greens, raw","Beet greens, raw"
|
413 |
+
tomatoes grape type tomatoes,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
414 |
+
lettuce iceberg,"Lettuce, iceberg, raw","Lettuce, iceberg, raw"
|
415 |
+
celery lettuce iceberg,"Lettuce, iceberg, raw","Lettuce, iceberg, raw"
|
416 |
+
limes potatoes orange juice cartons suja juice orange juice bottles,Mixed Food Items,Mixed Food Items
|
417 |
+
tomatoes cherry tomatoes grape type,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
418 |
+
broccoli lettuce romaine spinach carrots cabbage mixed produce assorted produce mixed greens,"Lettuce, romaine, green, raw","Lettuce, romaine, green, raw"
|
419 |
+
tomatoes cherry,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
420 |
+
classic gravy mushroom gravy,"Gravy, mushroom, canned","Gravy, mushroom, canned"
|
421 |
+
lettuce green leaf,"Lettuce, leaf, green, raw","Lettuce, leaf, green, raw"
|
422 |
+
Grape Tomatoes Tomatoes,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
423 |
+
cherry tomato roma tomato cherry tomato banana sugar snap peas iceberg lettuce brown onion dragon fruit plum melon cauliflower,Mixed Food Items,Mixed Food Items
|
424 |
+
parsley squash tomato (roma) tomato (grape) onion (green onion) melon (hami) mango spinach bok choy,Mixed Food Items,Mixed Food Items
|
425 |
+
tomatoes cherry tomatoes grape type tomatoes tomatoes plum type,"Tomatoes, grape, raw","Tomatoes, grape, raw"
|
426 |
+
tomatoes peppers,"peppers, bell, red, raw","peppers, bell, red, raw"
|
427 |
+
tomatoes mixed produce,"Vegetables, mixed, canned, drained solids","Vegetables, mixed, canned, drained solids"
|
428 |
+
sushi (fish rice cucumber),"Sushi, NFS","Sushi, NFS"
|
429 |
+
frozen turkeys,"Turkey and gravy, frozen","Turkey and gravy, frozen"
|
430 |
+
fozen turkeys,frozen turkey and gravy,frozen turkey and gravy
|
431 |
+
blueberries,"Blueberries, raw","Blueberries, raw"
|
432 |
+
Berry - Strawberry,"Strawberries, raw","Strawberries, raw"
|
433 |
+
Berry - Blackberry,"Blackberries, raw","Blackberries, raw"
|
434 |
+
strawberries,"Strawberries, raw","Strawberries, raw"
|
435 |
+
raw pineapples,"Pineapple, dried","Pineapple, dried"
|
436 |
+
bananas sliced thin,"Bananas, raw","Bananas, raw"
|
437 |
+
chocolate,Chocolate candy,Chocolate candy
|
438 |
+
Canadian Bacon,"Canadian bacon, cooked","Canadian bacon, cooked"
|
439 |
+
Misc Grocery,Assorted Groceries,Assorted Groceries
|
440 |
+
Gatorade,Sports drink (Gatorade G),Sports drink (Gatorade G)
|
441 |
+
Chips,"Potato chips, NFS","Potato chips, NFS"
|
442 |
+
Candy,"Candy, NFS","Candy, NFS"
|
443 |
+
Vegetables,Assorted Vegetables,Assorted Vegetables
|
444 |
+
Fruit,"Fruit, NFS","Fruit, NFS"
|
445 |
+
Water,"Water, NFS","Water, NFS"
|
446 |
+
Bread & Pastries,"Bread, cheese","Bread, cheese"
|
447 |
+
Misc Meat,Mixed Food Items,Mixed Food Items
|
448 |
+
DR Food boxes,Various Groceries,Various Groceries
|
449 |
+
Ramen Noodles,"Noodles, chow mein","Noodles, chow mein"
|
450 |
+
Plant Based Jerky,"Snacks, beef jerky, chopped and formed","Snacks, beef jerky, chopped and formed"
|
451 |
+
Home,"Potato, home fries, NFS",Non-Food Item
|
452 |
+
Hygiene Kits,Miscellaneous Items,Non-Food Item
|
453 |
+
Misc. groceries,Assorted Groceries,Assorted Groceries
|
454 |
+
Soda,"Ice cream soda, chocolate","Soft drink, cola"
|
455 |
+
Coffee - Cold Brew,"Iced Coffee, brewed","Iced Coffee, brewed"
|
456 |
+
Dog and Cat Food,"Hot dog, meat and poultry","Hot dog, meat and poultry"
|
457 |
+
Grocery Items,Assorted Groceries,Assorted Groceries
|
458 |
+
Grocery,Mixed Food Items,Non-Food Item
|
459 |
+
Misc Load,Energy drink (No Fear Motherload),Energy drink (No Fear Motherload)
|
460 |
+
Misc Produce,Mixed Food Items,Mixed Food Items
|
461 |
+
Chocolate Pretzels,"Pretzels, NFS","Pretzels, NFS"
|
462 |
+
Pizza,"Pizza, cheese, from restaurant or fast food, NS as to type of crust","Pizza, cheese, from restaurant or fast food, NS as to type of crust"
|
463 |
+
Prepared Meals,Mixed Food Items,Mixed Food Items
|
464 |
+
DR Misc Groceries,Various Groceries,Various Groceries
|
465 |
+
Noodles,"Noodles, cooked","Noodles, cooked"
|
466 |
+
Non-Food,Non-Food Item,Non-Food Item
|
467 |
+
Bagels,Bagel,Bagel
|
468 |
+
Buns,"Bread, protein (includes gluten)","Bread, protein (includes gluten)"
|
469 |
+
Snacks,"Snacks, potato sticks","Snacks, potato sticks"
|
470 |
+
Cereal,"Cereal, other, plain","Cereal, other, plain"
|
471 |
+
Sparkling Grapefruit Juice,"Grapefruit juice, pink, raw","Grapefruit juice, pink, raw"
|
472 |
+
Juice Drink,Fruit juice drink,Fruit juice drink
|
473 |
+
Crackers,"Crackers, NFS","Crackers, NFS"
|
474 |
+
Coffee,"Coffee, Cafe Mocha","Coffee, Cafe Mocha"
|
475 |
+
cold brew,"Beverages, coffee, instant, regular, prepared with water","Beverages, coffee, instant, regular, prepared with water"
|
476 |
+
protein drinks,"Nutritional drink or shake, high protein, ready-to-drink, NFS","Nutritional drink or shake, high protein, ready-to-drink, NFS"
|
477 |
+
Muffins,"Muffin, NFS","Muffin, NFS"
|
478 |
+
Donuts,"Doughnuts, cake-type, plain (includes unsugared, old-fashioned)","Doughnuts, cake-type, plain (includes unsugared, old-fashioned)"
|
479 |
+
Flat Breads,"Bread, pita, whole-wheat","Bread, pita, whole-wheat"
|
480 |
+
Snack Cakes,"Snacks, popcorn, cakes",Snack cake
|
481 |
+
Love Corn Snacks,"Snacks, corn cakes","Snacks, corn cakes"
|
482 |
+
Soda & Sparkling Water,"Water, carbonated, plain","Water, carbonated, plain"
|
483 |
+
Pepsi products,"Beverages, carbonated, reduced sugar, cola, contains caffeine and sweeteners","Beverages, carbonated, reduced sugar, cola, contains caffeine and sweeteners"
|
484 |
+
Condiments,"Salad dressing, mayonnaise, regular","Salad dressing, mayonnaise, regular"
|
485 |
+
Tuna,"Fish, tuna, NFS","Fish, tuna, NFS"
|
486 |
+
Boxed Dinners,"Macaroni and cheese, box mix with cheese sauce, unprepared","Macaroni and cheese, box mix with cheese sauce, unprepared"
|
487 |
+
Cinnamon Rolls,"Roll, sweet, cinnamon bun, frosted","Roll, sweet, cinnamon bun, frosted"
|
488 |
+
Assorted OTC Medical,"Water, bottled, generic",Non-Food Item
|
489 |
+
CVS Doantion,"Cholesterol, Cheese, swiss, slices (CA2, NC) - 18c-16-03-Chol","Cholesterol, Cheese, swiss, slices (CA2, NC) - 18c-16-03-Chol"
|
490 |
+
Misc. groceries & plastic bowls,Assorted Groceries,Assorted Groceries
|
491 |
+
Yogurt,"Yogurt, NFS","Yogurt, NFS"
|
492 |
+
Evaporated Milk,"Milk, evaporated, whole","Milk, evaporated, whole"
|
493 |
+
Coffee Creamers,"Coffee creamer, NFS","Coffee creamer, NFS"
|
494 |
+
Cheese Sauce,Cheese sauce,Cheese sauce
|
495 |
+
Pretzels,"Pretzels, NFS","Pretzels, NFS"
|
496 |
+
DR. Hygeine kits,"Water, bottled, generic","Water, bottled, generic"
|
497 |
+
Misc Food & non-Food,Mixed Food Items,Mixed Food Items
|
498 |
+
Cookies,"Cookie, NFS","Cookie, NFS"
|
499 |
+
Meats,"Meat, NFS","Meat, NFS"
|
500 |
+
Paper,Rice paper,Rice paper
|
501 |
+
Pastries,"Pastry, Pastelitos de Guava (guava pastries)","Pastry, Pastelitos de Guava (guava pastries)"
|
502 |
+
Desserts,Mixed Food Items,Mixed Food Items
|
503 |
+
Deli,"Chicken deli sandwich or sub, restaurant","Chicken deli sandwich or sub, restaurant"
|
504 |
+
Assorted salad greens,"Mixed salad greens, raw","Mixed salad greens, raw"
|
505 |
+
Misc. bakery,"Bread, multi-grain (includes whole-grain)","Bread, multi-grain (includes whole-grain)"
|
506 |
+
Mixed Candy,"Candy, NFS","Candy, NFS"
|
507 |
+
Rolls,Pizza rolls,Pizza rolls
|
508 |
+
Herbs,"Spices, parsley, dried","Spices, parsley, dried"
|
509 |
+
Butter,"Butter, NFS","Butter, NFS"
|
510 |
+
Cookie & Bread Dough,"Cookie, batter or dough, raw","Cookie, batter or dough, raw"
|
511 |
+
Breast,"Chicken, broilers or fryers, breast, meat and skin, raw","Chicken, broilers or fryers, breast, meat and skin, raw"
|
512 |
+
wings,"Chicken ""wings"", plain, from other sources","Chicken wings, plain, from other sources"
|
513 |
+
thighs,"Chicken, skin (drumsticks and thighs), raw","Chicken, skin (drumsticks and thighs), raw"
|
514 |
+
legs,"Frog legs, raw","Frog legs, raw"
|
515 |
+
tenders,"Restaurant, family style, chicken tenders","Restaurant, family style, chicken tenders"
|
516 |
+
Pasta,"Pasta with sauce, NFS","Pasta with sauce, NFS"
|
517 |
+
Sparkling Water,"Water, carbonated, plain","Water, carbonated, plain"
|
518 |
+
BakeryDesserts,"Cake or cupcake, chocolate with chocolate icing, bakery","Cake or cupcake, chocolate with chocolate icing, bakery"
|
519 |
+
Misc Sausages,"Sausage, NFS","Sausage, NFS"
|
520 |
+
chicken,Orange chicken,Chicken
|
521 |
+
Diet Green Tea,"Tea, iced, bottled, green, diet","Tea, iced, bottled, green, diet"
|
522 |
+
Frozen Pot Pies,"Beef Pot Pie, frozen entree, prepared","Beef Pot Pie, frozen entree, prepared"
|
523 |
+
Baking Chips,"Potato chips, baked, plain",chocolate chips
|
524 |
+
Sports Drinks,"Sports drink, NFS","Sports drink, NFS"
|
525 |
+
Evap Milk,"Milk, evaporated, whole","Milk, evaporated, whole"
|
526 |
+
Soup,"Soup, NFS","Soup, NFS"
|
527 |
+
Plastic Bags,Assorted Groceries,Non-Food Item
|
528 |
+
Coconut water,"Coconut water, unsweetened","Coconut water, unsweetened"
|
529 |
+
Blankets,Pig in a blanket,Pig in a blanket
|
530 |
+
Pillows,Cough drops,Non-Food Item
|
531 |
+
Cutlery,"Snacks, fruit leather, pieces",Non-Food Item
|
532 |
+
Amenity Kits,Miscellaneous Items,Miscellaneous Items
|
533 |
+
Tissues,Chicken skin,Non-Food Item
|
534 |
+
Paper Towels & Toliet paper,Rice paper,Non-Food Item
|
535 |
+
Assorted chips,"Potato chips, plain","Potato chips, plain"
|
536 |
+
Coconut Milk,Coconut milk,Coconut milk
|
537 |
+
Paper Bowls,Rice paper,Non-Food Item
|
538 |
+
Pop Tarts,"Toaster pastries, brown-sugar-cinnamon","Toaster pastries, brown-sugar-cinnamon"
|
539 |
+
Rice Krispie Treats,Rice crackers,Snacks
|
540 |
+
Misc. Snacks,"Snacks, popcorn, cakes","Snacks, popcorn, cakes"
|
541 |
+
Tortellini,"Tortellini, meat-filled, no sauce","Tortellini, meat-filled, no sauce"
|
542 |
+
Laundry Detergent,Vinegar,Non-Food Item
|
543 |
+
Halo oranges,"Oranges, raw, California, valencias","Oranges, raw, California, valencias"
|
544 |
+
Assorted Grocery Bins,Assorted Groceries,Assorted Groceries
|
545 |
+
"Mixed dishes, such as stews, mixed dishes with meat","Chicken, stewing, meat and skin, and giblets and neck, cooked, stewed","Mixed dishes, such as stews, mixed dishes with meat"
|
546 |
+
super salad greens,"Mixed salad greens, raw","Mixed salad greens, raw"
|
547 |
+
Liquid Eggs,"Egg substitute, powder","Egg substitute, powder"
|
548 |
+
Bulk pasta,"Pasta, dry, unenriched","Pasta, dry, unenriched"
|
549 |
+
bread crumbs & almonds,"Bread, pita, whole-wheat","Bread, pita, whole-wheat"
|
550 |
+
Lemonade,"Lemon juice, raw","Lemon juice, raw"
|
551 |
+
Misc Beverages,"Beverages, Mixed vegetable and fruit juice drink, with added nutrients","Beverages, Mixed vegetable and fruit juice drink, with added nutrients"
|
552 |
+
Celsius,"Celtuce, raw","Celtuce, raw"
|
553 |
+
Beef,"Beef, NFS","Beef, NFS"
|
554 |
+
Cups,"Candies, REESE'S Peanut Butter Cups","Candies, REESE'S Peanut Butter Cups"
|
555 |
+
Cereal Bars,Milk 'n Cereal bar,Milk 'n Cereal bar
|
556 |
+
Citrus,"Lemon, raw","Lemon, raw"
|
557 |
+
Sausage,"Sausage, NFS","Sausage, NFS"
|
558 |
+
bacon,Bacon,Bacon
|
559 |
+
Protien Bars,"Snacks, granola bars, soft, uncoated, peanut butter and chocolate chip","Snacks, granola bars, soft, uncoated, peanut butter and chocolate chip"
|
560 |
+
Eggs,"Eggs, whole","Eggs, whole"
|
561 |
+
Pickles,"Pickles, NFS","Pickles, NFS"
|
562 |
+
Bagged Meals with Meat,Mixed Food Items,Mixed Dishes with Meat
|
563 |
+
graham cracker crumbs,Graham crackers,Graham crackers
|
564 |
+
Milk 2%,"MILK, 2% ","MILK, 2%"
|
565 |
+
Couscous,"Couscous, cooked","Couscous, cooked"
|
566 |
+
Propel Water,"Beverages, UNILEVER, SLIMFAST Shake Mix, high protein, whey powder, 3-2-1 Plan,","Beverages, UNILEVER, SLIMFAST Shake Mix, high protein, whey powder, 3-2-1 Plan"
|
567 |
+
Non ood,"Oil, oat",Non-Food Item
|
568 |
+
Assorted soft drinks,"Soft drink, NFS","Soft drink, NFS"
|
569 |
+
Chicken Fritters,"Fritter, corn",Chicken Fritters
|
570 |
+
Sport Drinks,"Sports drink, NFS","Sports drink, NFS"
|
571 |
+
Egg Beaters,"Egg, whole, raw, fresh","Egg, whole, raw, fresh"
|
572 |
+
Household,"Restaurant, family style, hash browns",Non-Food Item
|
573 |
+
Toys,"Candies, marshmallows",Non-Food Item
|
574 |
+
Boxed Cereal,"Cereal, chocolate crispy","Cereal, chocolate crispy"
|
575 |
+
Assorted groceries,Assorted Groceries,Assorted Groceries
|
576 |
+
perishables,Mixed Food Items,Mixed Food Items
|
577 |
+
Coffee Drinks,"Beverages, coffee, instant, mocha, sweetened","Beverages, coffee, instant, mocha, sweetened"
|
578 |
+
Condensed Milk,"Milk, condensed, sweetened","Milk, condensed, sweetened"
|
579 |
+
Toppings,"Topping, fruit","Topping, fruit"
|
580 |
+
Pork sausage rolls,"Honey roll sausage, beef",Pork sausage
|
581 |
+
Snack Bars,"Candy, fruit snacks","Snack bar, oatmeal"
|
582 |
+
Jump Start Kits,Mixed Food Items,Non-Food Item
|
583 |
+
Jumbo cereal packs,"Cereals ready-to-eat, wheat, puffed, fortified","Cereals ready-to-eat, wheat, puffed, fortified"
|
584 |
+
Raspberries,"Raspberries, raw","Raspberries, raw"
|
585 |
+
Misc. Fruits,Various Fruits,Various Fruits
|
586 |
+
Sweet Potatoes,"Sweet potato, NFS","Sweet potato, NFS"
|
587 |
+
BabyFood,"Babyfood, cookie, baby, fruit","Babyfood, cookie, baby, fruit"
|
588 |
+
DR Cleaning Masks,"Fungi, Cloud ears, dried","Fungi, Cloud ears, dried"
|
589 |
+
Assorted Fresh Fruit & Vegetables,Assorted Fruit and Veg,Assorted Fruit and Veg
|
590 |
+
Medicine,Cough drops,Cough drops
|
591 |
+
Sanitizing Wipes,Dirty rice,Non-Food Item
|
audits/1718291402.csv
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input_word,original_dictionary_word,new_dictionary_word
|
2 |
+
"Mixed dishes, such as stews, mixed dishes with meat","Mixed dishes, such as stews, mixed dishes with meat","Mixed dishes, such as stews, mixed dishes with meat"
|
3 |
+
Bagged Meals with Meat,Mixed Dishes with Meat,Mixed Dishes with Meat
|
4 |
+
Chicken Fritters,Chicken Fritters,Chicken Fritters
|
5 |
+
Pork sausage rolls,Pork sausage,Pork sausage
|
6 |
+
Misc. meat,Misc Meat,Misc Meat
|
7 |
+
Assorted Soda,"Soft drink, pepper type, diet","Soft drink, pepper type, diet"
|
8 |
+
Cereral and snacks,"Snacks, banana chips","Snacks, banana chips"
|
9 |
+
Canned Vegetables,"Mixed Vegetables, canned","Mixed Vegetables, canned"
|
10 |
+
Granola Bars,"Cereal, granola",Granola Bars
|
11 |
+
Gnocchi,"Gnocchi, cheese","Gnocchi, cheese"
|
12 |
+
Flavored Water,"Water, non-carbonated, flavored","Water, non-carbonated, flavored"
|
13 |
+
Cleaning Tools,Screwdriver,Screwdriver
|
14 |
+
Water Bottles,"Water, bottled, plain","Water, bottled, plain"
|
15 |
+
Plant-based burgers & sausage,Hamburger (Burger King),Hamburger (Burger King)
|
16 |
+
Cutlery Pouches,"Snacks, fruit leather, pieces","Snacks, fruit leather, pieces"
|
17 |
+
Soap,Vinegar,Non-Food Item
|
18 |
+
Dishes,Mixed Food Items,Mixed Food Items
|
19 |
+
Blackberries,"Blackberries, raw","Blackberries, raw"
|
20 |
+
Misc. Vegetables,Misc Vegetables,Misc Vegetables
|
21 |
+
Canned green beans,"Green beans, canned, cooked with oil","Green beans, canned, cooked with oil"
|
22 |
+
Tortilla Shells,"Taco shells, baked","Taco shells, baked"
|
23 |
+
Half & Half,"Cream, fluid, half and half","Cream, fluid, half and half"
|
24 |
+
Misc Snacks,Assorted Foods,Assorted Foods
|
audits/1718300113.csv
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input_word,original_dictionary_word,new_dictionary_word
|
2 |
+
Almond Milk,Coconut milk,Coconut milk
|
3 |
+
misc grocry,Misc Grocery,Grocery Item
|
4 |
+
Chicken Broth,Fish broth,Chicken broth
|
5 |
+
Taco Mac,"Taco, NFS","Taco, NFS"
|
6 |
+
drinks,Beverages,Beverages
|
7 |
+
Assorted Quiche & Pot Pies,"Cheese quiche, meatless","Cheese quiche, meatless"
|
8 |
+
Freeze-dried Pineapples,"Pineapple, frozen","Pineapple, frozen"
|
9 |
+
Kettle Chips,Vegetable chips,Potato chips
|
10 |
+
"Meat, sliced, cooked","Meat with gravy, NS as to type of meat,","Meat with gravy, NS as to type of meat"
|
11 |
+
S&E drinks,Beverages,Beverages
|
12 |
+
canned vegs,"Mixed Vegetables, canned","Mixed Vegetables, canned"
|
13 |
+
Gatorade & Propel,Sports drink (Gatorade G),Sports drink (Gatorade G)
|
14 |
+
Frozen Fruit Juice,Frozen fruit juice bar,Frozen fruit juice bar
|
15 |
+
Chocolate Candy,Chocolate candy,Chocolate candy
|
16 |
+
waterm S&E drinks,"Water, bottled, generic","Water, bottled, generic"
|
audits/1718300232.csv
ADDED
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input_word,original_dictionary_word,new_dictionary_word
|
2 |
+
Almond Milk,Coconut milk,Coconut milk
|
3 |
+
misc grocry,Misc Grocery,Misc Grocery
|
4 |
+
Chicken Broth,Fish broth,Fish broth
|
5 |
+
Taco Mac,"Taco, NFS","Taco, NFS"
|
6 |
+
drinks,Beverages,Beverages
|
7 |
+
Assorted Quiche & Pot Pies,"Cheese quiche, meatless","Cheese quiche, meatless"
|
8 |
+
Freeze-dried Pineapples,"Pineapple, frozen","Pineapple, dried"
|
9 |
+
Kettle Chips,Vegetable chips,Vegetable chips
|
10 |
+
"Meat, sliced, cooked","Meat with gravy, NS as to type of meat,","Meat with gravy, NS as to type of meat"
|
11 |
+
S&E drinks,Beverages,Beverages
|
12 |
+
canned vegs,"Mixed Vegetables, canned","Mixed Vegetables, canned"
|
13 |
+
Gatorade & Propel,Sports drink (Gatorade G),Sports drink (Gatorade G)
|
14 |
+
Frozen Fruit Juice,Frozen fruit juice bar,Frozen fruit juice bar
|
15 |
+
Chocolate Candy,Chocolate candy,Chocolate candy
|
16 |
+
waterm S&E drinks,"Water, bottled, generic","Water, bottled, generic"
|
17 |
+
Hot Dogs,"Hot dog, NFS","Hot dog, NFS"
|
18 |
+
Creamer Half & Half,"Cream, half and half","Cream, half and half"
|
19 |
+
Cookie dough,"Cookie, batter or dough, raw","Cookie, batter or dough, raw"
|
20 |
+
pesto,Pesto sauce,Pesto sauce
|
21 |
+
Ref. dough,"Doughnuts, cake-type, plain, sugared or glazed","Doughnuts, cake-type, plain, sugared or glazed"
|
22 |
+
Graham Crackers,Graham crackers,Graham crackers
|
23 |
+
Animal Crackers,"Crackers, NFS","Crackers, NFS"
|
24 |
+
Crisps,"Crackers, crispbread","Crackers, crispbread"
|
25 |
+
Cereal and crackers,"Crackers, rice and nuts","Crackers, rice and nuts"
|
26 |
+
water & sports,"Sports drink, NFS","Sports drink, NFS"
|
27 |
+
energy,Energy Drink,Energy Drink
|
28 |
+
Flour,"Flour, barley",Flour
|
29 |
+
Bai,"Salt, table","Salt, table"
|
30 |
+
Snapple,"Snacks, rice cakes, brown rice, buckwheat",Snacks
|
31 |
+
Veg,"Mixed Vegetables, canned","Mixed Vegetables, canned"
|
32 |
+
sport & energy,Mixed Food Items,Sports drink
|
33 |
+
Sauces,"Sauce, NFS","Sauce, NFS"
|
34 |
+
Pot Pies,"Pot pie, beef","Pot pie, beef"
|
35 |
+
Dressings,"Salad dressing, french dressing, commercial, regular","Salad dressing, french dressing, commercial, regular"
|
36 |
+
snacksd,"Snacks, potato chips, plain, salted","Snacks, potato chips, plain, salted"
|
37 |
+
misc. gro. drinks,"Beverages, Mixed vegetable and fruit juice drink, with added nutrients","Beverages, Mixed vegetable and fruit juice drink, with added nutrients"
|
38 |
+
Hand Soap,Non-Food Item,Non-Food Item
|
39 |
+
ciabata bread,"Bread, Italian","Bread, Italian"
|
40 |
+
SnackBars,"Snack bar, oatmeal","Snack bar, oatmeal"
|
41 |
+
Gummy Bears,"Candy, gummy","Candy, gummy"
|
42 |
+
Boxes,"Cereal, chocolate crispy","Cereal, chocolate crispy"
|
43 |
+
fruit snacks,"Candy, fruit snacks","Candy, fruit snacks"
|
44 |
+
Pasteries,"Cookies, chocolate chip, prepared from recipe, made with margarine","Pastry, cookie type, fried"
|
45 |
+
Sandwiches,"Sandwich, NFS","Sandwich, NFS"
|
46 |
+
Puffs,"Cereal, plain puffs","Cereal, plain puffs"
|
47 |
+
Grits,"Grits, NFS","Grits, NFS"
|
48 |
+
Bars,"Snacks, granola bar, with coconut, chocolate coated","Cereal or granola bar, with coconut, chocolate coated"
|
49 |
+
Mango Nectar,Mango nectar,Mango nectar
|
50 |
+
Assorted Non-Food,Assorted Foods,Non-Food Item
|
51 |
+
Mattress,Non-Food Item,Non-Food Item
|
52 |
+
plant bases,"Chicory roots, raw","Chicory roots, raw"
|
53 |
+
Reusable Masks,"Fungi, Cloud ears, dried","Fungi, Cloud ears, dried"
|
54 |
+
Medical,Cough drops,Cough drops
|
55 |
+
Shredded Mozzarella,"Cheese, Mozzarella, NFS","Cheese, Mozzarella, NFS"
|
56 |
+
Misc. Pepsi products,"Beverages, carbonated, reduced sugar, cola, contains caffeine and sweeteners","Beverages, carbonated, reduced sugar, cola, contains caffeine and sweeteners"
|
57 |
+
Boost protein drinks,"Nutritional drink or shake, high protein, ready-to-drink, NFS","Nutritional drink or shake, high protein, ready-to-drink, NFS"
|
58 |
+
Poptarts,"Toaster pastries, brown-sugar-cinnamon","Toaster pastries, brown-sugar-cinnamon"
|
59 |
+
brkf. bars,"Cereals ready-to-eat, MALT-O-MEAL, Raisin Bran Cereal","Cereals ready-to-eat, MALT-O-MEAL, Raisin Bran Cereal"
|
60 |
+
Rockstar,"Beverages, Energy drink, ROCKSTAR",ROCKSTAR
|
61 |
+
RS Boxed Candy,"Candies, REESE'S, FAST BREAK, milk chocolate peanut butter and soft nougats","Candies, REESE'S, FAST BREAK, milk chocolate peanut butter and soft nougats"
|
62 |
+
fruit cups,"Fruit cocktail, canned, heavy syrup, drained","Fruit cocktail, canned, heavy syrup, drained"
|
63 |
+
Assorted Fruit,Various Fruits,Various Fruits
|
64 |
+
Disposalable Trays,Assorted Groceries,Assorted Groceries
|
65 |
+
Weiners,"Frankfurter, pork",Frankfurter
|
66 |
+
Salt,"Salt, table","Salt, table"
|
67 |
+
Nutrigrain Bites,"Snacks, KELLOGG, KELLOGG'S, NUTRI-GRAIN Cereal Bars, fruit","Snacks, KELLOGG, KELLOGG'S, NUTRI-GRAIN Cereal Bars, fruit"
|
68 |
+
"Sandwiches, deli, egg salad","Chicken deli sandwich or sub, restaurant",Seafood salad sandwich
|
69 |
+
Celsius Energy Drink,"Beverages, Energy drink, RED BULL, sugar free, with added caffeine, niacin, pantothenic acid, vitamins B6 and B12","Beverages, Energy drink, RED BULL, sugar free, with added caffeine, niacin, pantothenic acid, vitamins B6 and B12"
|
70 |
+
Misc. paper products,Rice paper,Rice paper
|
71 |
+
Croissants,Croissant,Croissant
|
72 |
+
Crab Meat,Imitation crab meat,Imitation crab meat
|
73 |
+
Chili,"Spices, chili powder","Spices, chili powder"
|
74 |
+
Water Gallons,"Water, NFS","Water, NFS"
|
75 |
+
Processed meat,Beef sausage with cheese,Beef sausage with cheese
|
76 |
+
Bagel Bites,Bagel chips,Bagel
|
77 |
+
V8 juice,Fruit juice drink,Fruit juice
|
78 |
+
Pet Food & Pet Supplies,Assorted Edible Items,Assorted Edible Items
|
79 |
+
Jello Cups,"Gelatin desserts, dry mix, reduced calorie, with aspartame, added phosphorus, potassium, sodium, vitamin C","Gelatin desserts, dry mix, reduced calorie, with aspartame, prepared with water"
|
80 |
+
misc food,Mixed Food Items,Mixed Food Items
|
81 |
+
"non food,water,home diapers",Non-Food Item,Non-Food Item
|
82 |
+
Water & Chips,"Chips, rice",Chips
|
83 |
+
Misc. bread & bakery,"Bread, multi-grain (includes whole-grain)","Bread, multi-grain (includes whole-grain)"
|
84 |
+
Gummies Snacks,"Candy, gummy","Candy, gummy"
|
85 |
+
waffles,"Waffle, NFS","Waffle, NFS"
|
86 |
+
Salads,"Mixed salad greens, raw","Mixed salad greens, raw"
|
87 |
+
Quiche & Pot Pies,"Pot pie, chicken","Pot pie, chicken"
|
88 |
+
raisin cereal,"Cereal, other, plain","Cereal, other, plain"
|
89 |
+
baking truffles,"Candies, truffles, prepared-from-recipe","Candies, truffles, prepared-from-recipe"
|
90 |
+
Misc Non-Food,Mixed Food Items,Mixed Food Items
|
91 |
+
Frozen pizza,"Pizza, cheese, from restaurant or fast food, NS as to type of crust","Pizza, cheese, from restaurant or fast food, NS as to type of crust"
|
92 |
+
Zucchini,"Bread, zucchini",Zucchini
|
93 |
+
Shredded Cheese,"Cheese, parmesan, shredded","Cheese, parmesan, shredded"
|
94 |
+
Breakfast Breads,"Bread, oatmeal, toasted","Bread, oatmeal, toasted"
|
95 |
+
Miscellaneous Vegetables,Assorted Vegetables,Assorted Vegetables
|
96 |
+
"Snacks, macaroni and cheese, bites","Snacks, banana chips","Snacks, macaroni and cheese, bites"
|
97 |
+
Oil,"Oil, babassu","Oil, babassu"
|
98 |
+
Grean Beans,"Beans, NFS","Beans, NFS"
|
99 |
+
Food Boxes,Various Groceries,Various Groceries
|
100 |
+
Sport drinks & crackers,"Sports drink, NFS","Sports drink, NFS"
|
101 |
+
Rye Bread,"Bread, rye","Bread, rye"
|
102 |
+
Breakfast Bowls,Mixed Food Items,Mixed Food Items
|
103 |
+
Shelf stable almond milk,"ALMOND MILK, UNSWEETENED, PLAIN, SHELF STABLE","ALMOND MILK, UNSWEETENED, PLAIN, SHELF STABLE"
|
104 |
+
Cheezits Snapd Chips,"Snacks, potato chips, made from dried potatoes, fat-free, made with olestra","Snacks, potato chips, made from dried potatoes, fat-free, made with olestra"
|
105 |
+
Pork Roast,"Pork, roast","Pork, roast"
|
106 |
+
Toothbrushes,Non-Food Item,Non-Food Item
|
107 |
+
Toothpaste,Non-Food Item,Non-Food Item
|
108 |
+
plant milk,"Beverages, almond milk, unsweetened, shelf stable","Beverages, almond milk, unsweetened, shelf stable"
|
109 |
+
Personal Hygiene Kits,Non-Food Item,Non-Food Item
|
110 |
+
Ketchup packets,Ketchup,Ketchup
|
111 |
+
Chile Peppers,"Peppers, jalapeno, raw","Peppers, jalapeno, raw"
|
112 |
+
Mini Mounds Bars,"Candies, MOUNDS Candy Bar","Candies, MOUNDS Candy Bar"
|
113 |
+
chicken sandwiches,"CHICK-FIL-A, chicken sandwich","CHICK-FIL-A, chicken sandwich"
|
114 |
+
Turkey - Frozen,"Turkey and gravy, frozen","Turkey and gravy, frozen"
|
115 |
+
drumsticks,"Chicken, broilers or fryers, meat and skin and giblets and neck, raw","Chicken, broilers or fryers, drumstick, meat and skin, raw"
|
116 |
+
Water - Gallons,"Beverages, carbonated, cola, regular","Beverages, carbonated, cola, regular"
|
117 |
+
Sweat Aid,Sports drink (Gatorade G),Sports drink (Gatorade G)
|
118 |
+
"cotton candy,misc groc","Candy, cotton","Candy, cotton"
|
119 |
+
"non food,green beans",Non-Food Item,"Green beans, raw"
|
120 |
+
Misc Dairy,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
121 |
+
Broth & misc. groceries,Various Groceries,Various Groceries
|
122 |
+
Plant based creamers,"Cream substitute, liquid, light","Cream substitute, liquid, light"
|
123 |
+
Poptart Bites,"Bread, cheese","Toaster pastries, brown-sugar-cinnamon"
|
124 |
+
Pure Leaf Tea,"Tea, hot, leaf, green","Tea, hot, leaf, green"
|
125 |
+
ocean spray juice,"Beverages, OCEAN SPRAY, White Cranberry Strawberry Flavored Juice Drink","Beverages, OCEAN SPRAY, White Cranberry Strawberry Flavored Juice Drink"
|
126 |
+
Powdered Milk,"Milk, malted","Milk, malted"
|
127 |
+
parsley & cilantro,"Parsley, raw","Parsley, raw"
|
128 |
+
Beef gravy,"Gravy, beef","Gravy, beef"
|
129 |
+
Dairy Beverages,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
130 |
+
Pork Loins,"Pork, tenderloin","Pork, tenderloin"
|
131 |
+
Tea Bags,"Tea, hot, herbal","Tea, hot, herbal"
|
132 |
+
Orange Juice,"Fruit juice, NFS","Fruit juice, NFS"
|
133 |
+
Fruit Chips,Banana chips,Banana chips
|
134 |
+
Propel watermellon flavored,"Beverages, ABBOTT, ENSURE PLUS, ready-to-drink","Beverages, ABBOTT, ENSURE PLUS, ready-to-drink"
|
135 |
+
Breakfast Sandwiches,"Crackers, sandwich","Crackers, sandwich"
|
136 |
+
Assorted crackers,"Crackers, NFS","Crackers, NFS"
|
137 |
+
Gloves,Non-Food Item,Non-Food Item
|
138 |
+
Home Goods,Grocery Items,Non-Food Item
|
139 |
+
misc freezer,Mixed Food Items,Mixed Food Items
|
140 |
+
Hoisin Sauce,Hoisin sauce,Hoisin sauce
|
141 |
+
Pringles,"Potato chips, plain","Potato chips, plain"
|
142 |
+
Crispbread Crackers,"Crackers, crispbread","Crackers, crispbread"
|
143 |
+
"Candies, bulk pieces","Candies, MOUNDS Candy Bar","Candies, MOUNDS Candy Bar"
|
144 |
+
Wraps,"Tortillas, ready-to-bake or -fry, corn","Tortillas, ready-to-bake or -fry, corn"
|
145 |
+
Slik Milk,"MILK, SKIM ","MILK, SKIM"
|
146 |
+
Biscoff Cookies,"Cookie, biscotti","Cookie, biscotti"
|
147 |
+
watermellon flavored propel water,"Beverages, PEPSICO QUAKER, Gatorade, G performance O 2, ready-to-drink.","Beverages, PEPSICO QUAKER, Gatorade, G performance O 2, ready-to-drink."
|
148 |
+
Beef Burgers - Frozen,"Beef dinner, NFS, frozen meal","Beef dinner, NFS, frozen meal"
|
149 |
+
Misc. Vegestables,"Vegetables, mixed, frozen, cooked, boiled, drained, with salt",Misc Vegetables
|
150 |
+
Biscuits,"Biscuit, NFS","Biscuit, NFS"
|
151 |
+
Sliced Meat,"Beef, cured, dried","Beef, cured, dried"
|
152 |
+
Prepared Sandwiches,Egg salad sandwich on white,Egg salad sandwich on white
|
153 |
+
"Snacks, macaroni and cheese flavor, soy-based, baked",Cheese flavored corn snacks (Cheetos),Cheese flavored corn snacks (Cheetos)
|
154 |
+
Bulk candy,"Candies, fondant, prepared-from-recipe","Candies, fondant, prepared-from-recipe"
|
155 |
+
Trays,"Snack bar, oatmeal",Non-Food Item
|
156 |
+
CerealCondiments,Mixed Food Items,Mixed Food Items
|
157 |
+
RX Bars,"Candies, NESTLE, BABY RUTH Bar","Candies, NESTLE, BABY RUTH Bar"
|
158 |
+
misc drinks,"Beverages, Mixed vegetable and fruit juice drink, with added nutrients","Beverages, Mixed vegetable and fruit juice drink, with added nutrients"
|
159 |
+
Frozen Veggies,"Vegetables, mixed, frozen, unprepared","Vegetables, mixed, frozen, unprepared"
|
160 |
+
Cereal and cereal cups,"Cereal, other, chocolate","Cereal, other, chocolate"
|
161 |
+
Pudding & Cooking Cream,"Puddings, chocolate, dry mix, instant, prepared with whole milk","Puddings, chocolate, dry mix, instant, prepared with whole milk"
|
162 |
+
apple cider vinegarette,Apple cider,Apple cider
|
163 |
+
olive oil,Olive oil,Olive oil
|
164 |
+
Juice & Craisins,"Apple juice, canned or bottled, unsweetened, without added ascorbic acid","Apple juice, canned or bottled, unsweetened, with added ascorbic acid"
|
165 |
+
Frozen mac-n-cheese,"Macaroni and cheese, frozen entree","Macaroni and cheese, frozen entree"
|
166 |
+
ceral and cat food,Mixed Food Items,Mixed Food Items
|
167 |
+
Butter & Cooking Cream,"Cream, fluid, heavy whipping","Cream, fluid, heavy whipping"
|
168 |
+
Chicken Pot Pies,"Pot pie, chicken","Pot pie, chicken"
|
169 |
+
Sides & Boullion,"McDONALD'S, Side Salad","McDONALD'S, Side Salad"
|
170 |
+
Fruit Smoothies,"Fruit smoothie, NFS","Fruit smoothie, NFS"
|
171 |
+
Elbow Macaroni (Bulk),"Pasta, vegetable, cooked","Pasta, vegetable, cooked"
|
172 |
+
Banana Peppers,"Pepper, banana, raw","Pepper, banana, raw"
|
173 |
+
Kettlecorm,"Snacks, popcorn, home-prepared, oil-popped, unsalted","Snacks, popcorn, home-prepared, oil-popped, unsalted"
|
174 |
+
Cran Grape Juice,"Beverages, cranberry-grape juice drink, bottled","Beverages, cranberry-grape juice drink, bottled"
|
175 |
+
Gingersnaps,"Cookie, gingersnaps","Cookie, gingersnaps"
|
176 |
+
Mustard Oil,"Oil, mustard","Oil, mustard"
|
177 |
+
"Pizza, Prepared Meals",Mixed Food Items,Mixed Food Items
|
178 |
+
pasta sauce,Spaghetti sauce,Spaghetti sauce
|
179 |
+
Granola Cereal,"Cereal, granola","Cereal, granola"
|
180 |
+
Onions.Soup,"Soup, NFS","Soup, NFS"
|
181 |
+
"Fruit, Bread",Assorted Fruit and Veg,Assorted Fruit and Veg
|
182 |
+
"Pastries, Lunch Meats","Pastrami, beef, 98% fat-free","Pastrami, beef, 98% fat-free"
|
183 |
+
vitamins & protein bars,Nutrition bar (South Beach Living High Protein Bar),Nutrition bar (South Beach Living High Protein Bar)
|
184 |
+
Salad dressing,"Salad dressing, light, NFS","Salad dressing, light, NFS"
|
185 |
+
bbq sauce,"Sauce, barbecue","Sauce, barbecue"
|
186 |
+
Half and Half,"Cream, fluid, half and half","Cream, fluid, half and half"
|
187 |
+
supplement,Non-Food Item,Non-Food Item
|
188 |
+
Candy Bars,"Candy, NFS","Candy, NFS"
|
189 |
+
RX Bars & Nut Butter,"Snacks, banana chips","Snacks, banana chips"
|
190 |
+
Chicken dip,"Vegetable dip, regular","Vegetable dip, regular"
|
191 |
+
Beverages and snacks,"Snacks, potato sticks","Snacks, potato sticks"
|
192 |
+
2% Milk,"MILK, 2% ","MILK, 2%"
|
audits/1718300482.csv
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input_word,original_dictionary_word,new_dictionary_word
|
2 |
+
drinks,Beverages,Beverages
|
3 |
+
"Meat, sliced, cooked","Meat with gravy, NS as to type of meat,","Meat with gravy, NS as to type of meat"
|
4 |
+
S&E drinks,Beverages,Beverages
|
5 |
+
Flour,"Flour, barley","Flour, barley"
|
6 |
+
Snapple,"Snacks, rice cakes, brown rice, buckwheat",Snacks
|
7 |
+
sport & energy,Mixed Food Items,Sports drink (Powerade)
|
8 |
+
Rockstar,"Beverages, Energy drink, ROCKSTAR","Beverages, Energy drink, ROCKSTAR"
|
9 |
+
Weiners,"Frankfurter, pork",Frankfurter
|
10 |
+
V8 juice,Fruit juice drink,Fruit juice
|
11 |
+
Water & Chips,"Chips, rice","Potato chips, plain"
|
12 |
+
Zucchini,"Bread, zucchini",Zucchini
|
13 |
+
"Snacks, macaroni and cheese, bites","Snacks, banana chips","Snacks, banana chips"
|
14 |
+
Slik Milk,"MILK, SKIM ","Milk, NFS"
|
15 |
+
Frozen mac-n-cheese,"Macaroni and cheese, frozen entree","Macaroni and cheese, frozen entree"
|
16 |
+
ceral and cat food,Mixed Food Items,Non-Food Item
|
17 |
+
Butter & Cooking Cream,"Cream, fluid, heavy whipping","Cream, fluid, heavy whipping"
|
18 |
+
Chicken Pot Pies,"Pot pie, chicken","Pot pie, chicken"
|
19 |
+
Sides & Boullion,"McDONALD'S, Side Salad","McDONALD'S, Side Salad"
|
20 |
+
Fruit Smoothies,"Fruit smoothie, NFS","Fruit smoothie, NFS"
|
21 |
+
Elbow Macaroni (Bulk),"Pasta, vegetable, cooked","Pasta, vegetable, cooked"
|
22 |
+
Banana Peppers,"Pepper, banana, raw","Pepper, banana, raw"
|
23 |
+
Kettlecorm,"Snacks, popcorn, home-prepared, oil-popped, unsalted","Snacks, popcorn, home-prepared, oil-popped, unsalted"
|
24 |
+
Cran Grape Juice,"Beverages, cranberry-grape juice drink, bottled","Beverages, cranberry-grape juice drink, bottled"
|
25 |
+
Gingersnaps,"Cookie, gingersnaps","Cookie, gingersnaps"
|
26 |
+
Mustard Oil,"Oil, mustard","Oil, mustard"
|
27 |
+
"Pizza, Prepared Meals",Mixed Food Items,Mixed Food Items
|
28 |
+
pasta sauce,Spaghetti sauce,Spaghetti sauce
|
29 |
+
Granola Cereal,"Cereal, granola","Cereal, granola"
|
30 |
+
Onions.Soup,"Soup, NFS","Soup, NFS"
|
31 |
+
"Fruit, Bread",Assorted Fruit and Veg,Bread
|
32 |
+
"Pastries, Lunch Meats","Pastrami, beef, 98% fat-free","Pastrami, beef, 98% fat-free"
|
33 |
+
vitamins & protein bars,Nutrition bar (South Beach Living High Protein Bar),Nutrition bar (South Beach Living High Protein Bar)
|
34 |
+
Salad dressing,"Salad dressing, light, NFS","Salad dressing, light, NFS"
|
35 |
+
bbq sauce,"Sauce, barbecue","Sauce, barbecue"
|
36 |
+
Half and Half,"Cream, fluid, half and half","Cream, fluid, half and half"
|
37 |
+
supplement,Non-Food Item,Non-Food Item
|
38 |
+
Candy Bars,"Candy, NFS","Candy, NFS"
|
39 |
+
RX Bars & Nut Butter,"Snacks, banana chips","Snacks, banana chips"
|
40 |
+
Chicken dip,"Vegetable dip, regular",Honey mustard dip
|
41 |
+
Beverages and snacks,"Snacks, potato sticks","Snacks, potato sticks"
|
42 |
+
2% Milk,"MILK, 2% ","MILK, 2% "
|
audits/1718300736.csv
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input_word,original_dictionary_word,new_dictionary_word
|
2 |
+
drinks,Beverages,Beverages
|
3 |
+
"Meat, sliced, cooked","Meat with gravy, NS as to type of meat,","Meat with gravy, NS as to type of meat"
|
4 |
+
S&E drinks,Beverages,Beverages
|
5 |
+
Snapple,"Snacks, rice cakes, brown rice, buckwheat",Snacks
|
audits/1718300752.csv
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input_word,original_dictionary_word,new_dictionary_word
|
2 |
+
drinks,Beverages,Beverages
|
3 |
+
"Meat, sliced, cooked","Meat with gravy, NS as to type of meat,","Meat with gravy, NS as to type of meat"
|
4 |
+
S&E drinks,Beverages,Beverages
|
5 |
+
Snapple,"Snacks, rice cakes, brown rice, buckwheat",Snacks
|
6 |
+
Weiners,"Frankfurter, pork",Frankfurter
|
7 |
+
V8 juice,Fruit juice drink,Fruit juice
|
8 |
+
Zucchini,"Bread, zucchini",Zucchini
|
9 |
+
"Fruit, Bread",Assorted Fruit and Veg,Assorted Fruit and Veg
|
10 |
+
Beverages and snacks,"Snacks, potato sticks","Snacks, potato sticks"
|
11 |
+
2% Milk,"MILK, 2%","MILK, 2%"
|
audits/1718301576.csv
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input_word,original_dictionary_word,new_dictionary_word
|
2 |
+
drinks,Beverages,Beverages
|
3 |
+
"Meat, sliced, cooked","Meat with gravy, NS as to type of meat,","Meat with gravy, NS as to type of meat"
|
4 |
+
S&E drinks,Beverages,Beverages
|
5 |
+
Snapple,Fruit juice drink,Non-Food Item
|
6 |
+
Weiners,"Frankfurter, pork",Frankfurter
|
7 |
+
V8 juice,Fruit juice drink,Fruit juice
|
8 |
+
Cooked meat,"Beef, round, bottom round, roast, separable lean only, trimmed to 0"" fat, all grades, cooked, roasted","Beef, round, bottom round, roast, separable lean only, trimmed to 0"" fat, all grades, cooked, roasted"
|
audits/1718362114.csv
ADDED
@@ -0,0 +1,1228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
input_word,original_dictionary_word,new_dictionary_word
|
2 |
+
drinks,Beverages,Beverages
|
3 |
+
"Meat, sliced, cooked","Meat with gravy, NS as to type of meat,","Meat with gravy, NS as to type of meat"
|
4 |
+
S&E drinks,Beverages,Beverages
|
5 |
+
Weiners,"Frankfurter, pork",Frankfurter
|
6 |
+
V8 juice,Fruit juice drink,Fruit juice
|
7 |
+
Cooked meat,"Beef, round, bottom round, roast, separable lean only, trimmed to 0"" fat, all grades, cooked, roasted","Beef, round, bottom round, roast, separable lean only, trimmed to 0"" fat, all grades, cooked, roasted"
|
8 |
+
Mac-n-cheese bites,"Crackers, standard snack-type, sandwich, with cheese filling","Crackers, standard snack-type, sandwich, with cheese filling"
|
9 |
+
PB misc,"Peanut butter, smooth style, with salt","Peanut butter, smooth style, with salt"
|
10 |
+
Choc covered pretzels,"Pretzels, hard, chocolate coated","Pretzels, hard, chocolate coated"
|
11 |
+
Skinny Pop popcorn,"Popcorn, NFS","Popcorn, NFS"
|
12 |
+
Fruit Juice,"Fruit juice, NFS","Fruit juice, NFS"
|
13 |
+
Hint Flavored Water,"Water, non-carbonated, flavored","Water, non-carbonated, flavored"
|
14 |
+
Noodle Soup Base,"Noodle soup, NFS","Noodle soup, NFS"
|
15 |
+
Mixed Groceries,Mixed Food Items,Various Groceries
|
16 |
+
CAKES,Snack cake,Snack cake
|
17 |
+
Misc Meat & Seafood,Misc Meat,Misc Meat
|
18 |
+
"Mixed dishes, chips, and chili from fast food","Fast foods, cheeseburger; single, large patty; with condiments, vegetables and mayonnaise","Fast foods, cheeseburger; single, large patty; with condiments, vegetables and mayonnaise"
|
19 |
+
salad lettuce,"Lettuce, raw","Lettuce, raw"
|
20 |
+
Cream of Wheat,"Cream of wheat, NFS","Cream of wheat, NFS"
|
21 |
+
"Grains, white or golden, uncooked","Rice, white, medium-grain, cooked, unenriched","Rice, white, medium-grain, cooked, unenriched"
|
22 |
+
Misc Grocey,Misc Grocery,Misc Grocery
|
23 |
+
Lids,"Tomatoes, raw","Tomatoes, raw"
|
24 |
+
Bagged Meals,Mixed Dishes with Meat,Mixed Dishes with Meat
|
25 |
+
RK treats,Snacks,Snacks
|
26 |
+
Breakfast Essentials,Mixed Food Items,Mixed Food Items
|
27 |
+
breads and sweets,"Bread, cheese",Bread
|
28 |
+
Chicken Breast,Chicken,Chicken
|
29 |
+
misc plant based,Mixed Food Items,Mixed Food Items
|
30 |
+
Detergent,Non-Food Item,Non-Food Item
|
31 |
+
Frozen Pastries and Bread,"Croissants, cheese","Croissants, cheese"
|
32 |
+
Smart Water,"Water, carbonated, flavored","Water, carbonated, flavored"
|
33 |
+
canned vegs.,"Mixed Vegetables, canned","Mixed Vegetables, canned"
|
34 |
+
Cups & lids,Non-Food Item,Non-Food Item
|
35 |
+
Gallon Milk,"Milk, whole, 3.25% milkfat, without added vitamin A and vitamin D","Milk, whole, 3.25% milkfat, without added vitamin A and vitamin D"
|
36 |
+
Sausage Links,"Sausage, NFS","Sausage, NFS"
|
37 |
+
FROZEN TORTELLINI,"Tortellini, meat-filled, no sauce","Tortellini, meat-filled, no sauce"
|
38 |
+
Specialty Bread,"Bread, wheat","Bread, wheat"
|
39 |
+
Misc. Non-Food,Non-Food Item,Non-Food Item
|
40 |
+
Thermometers,"Celtuce, raw","Celtuce, raw"
|
41 |
+
misc grocery & dairy,Misc Grocery,Misc Grocery
|
42 |
+
Mis. Grocery,Misc Grocery,Misc Grocery
|
43 |
+
misc frozen - grocery,Misc Grocery,Misc Grocery
|
44 |
+
Pers Hyg,Glug,Glug
|
45 |
+
Dinner Rolls,"Rolls, dinner, sweet","Rolls, dinner, sweet"
|
46 |
+
Terra Chips,"Potato chips, NFS","Potato chips, NFS"
|
47 |
+
Taco Shells,"Taco shells, baked","Taco shells, baked"
|
48 |
+
Turkey & Potato Meal,"Turkey with gravy, dressing, potatoes, vegetable, frozen meal","Turkey with gravy, dressing, potatoes, vegetable, frozen meal"
|
49 |
+
Sports,"Sports drink, NFS","Sports drink, NFS"
|
50 |
+
Pork Sausage,Pork sausage,Pork sausage
|
51 |
+
Toilet Paper,Non-Food Item,Non-Food Item
|
52 |
+
Fresh vegetables,Assorted Vegetables,Assorted Vegetables
|
53 |
+
Industrial Mixer,"Nuts, mixed nuts, oil roasted, with peanuts, lightly salted",Non-Food Item
|
54 |
+
Bombas Socks,"Rutabagas, raw",Non-Food Item
|
55 |
+
luncables,"Fast foods, submarine sandwich, turkey, roast beef and ham on white bread with lettuce and tomato","Fast foods, submarine sandwich, turkey, roast beef and ham on white bread with lettuce and tomato"
|
56 |
+
lunch meat,"Luncheon meat, NFS","Luncheon meat, NFS"
|
57 |
+
assorted perishables,Mixed Food Items,Mixed Food Items
|
58 |
+
assorte dinks and snacks,Mixed Food Items,Assorted Foods
|
59 |
+
Sparkling Water & Toddler Snacks,"Water, carbonated, plain",Non-Food Item
|
60 |
+
Jerky,Beef jerky,Beef jerky
|
61 |
+
grains,"Cereals, oats, regular and quick, unenriched, cooked with water (includes boiling and microwaving), without salt","Cereals, oats, regular and quick, unenriched, cooked with water (includes boiling and microwaving), without salt"
|
62 |
+
Frozen Foods,"Frozen dinner, NFS","Frozen dinner, NFS"
|
63 |
+
Cleaners,Screwdriver,Screwdriver
|
64 |
+
Straws,"Grapefruit juice, white, canned or bottled, unsweetened",Non-Food Item
|
65 |
+
Plates,Mixed Food Items,Non-Food Item
|
66 |
+
Pop,Popover,Non-Food Item
|
67 |
+
Boneless Turkey Breast,"chicken, breast, boneless, skinless","Turkey, whole, breast, meat only, raw"
|
68 |
+
misc fruit,Various Fruits,Various Fruits
|
69 |
+
Veggies,Assorted Vegetables,Assorted Vegetables
|
70 |
+
Cereal Fun Packs,"Cereals ready-to-eat, wheat, puffed, fortified","Cereals ready-to-eat, wheat, puffed, fortified"
|
71 |
+
Strudel,"Strudel, apple","Strudel, apple"
|
72 |
+
Bloody Mary Mix,Bloody Mary,Bloody Mary
|
73 |
+
Tortilla chips,"Tortilla chips, plain","Tortilla chips, plain"
|
74 |
+
Cauliflower Gnocchi,"Gnocchi, potato","Gnocchi, potato"
|
75 |
+
misc cooler,Wine cooler,Wine cooler
|
76 |
+
"freezer,yogurt,coffee,juice,eggs,soup,misc dairy,plant based",Mixed Food Items,Mixed Food Items
|
77 |
+
Assorted Juices,"Fruit juice, NFS","Fruit juice, NFS"
|
78 |
+
Cantalope,"Melons, cantaloupe, raw","Melons, cantaloupe, raw"
|
79 |
+
Diced Green Chiles,"Peppers, jalapeno, raw","Peppers, jalapeno, raw"
|
80 |
+
Dish Soap,Non-Food Item,Non-Food Item
|
81 |
+
Egg Whites,Egg whites,Egg whites
|
82 |
+
Espresso Mocha drinks,"Beverages, coffee, ready to drink, iced, mocha, milk based","Beverages, coffee, ready to drink, iced, mocha, milk based"
|
83 |
+
refrig. dough,"Bread, wheat or cracked wheat, made from home recipe or purchased at bakery","Cookie, batter or dough, raw"
|
84 |
+
Stuffing,Bread stuffing,Bread stuffing
|
85 |
+
Chewy Bars,"Snack bar, oatmeal","Snack bar, oatmeal"
|
86 |
+
Hazelnut crepes,"Pancakes, plain, prepared from recipe","Pancakes, plain, prepared from recipe"
|
87 |
+
String cheese,"Cheese, blue",String cheese
|
88 |
+
Water - Flavored - Splash,"Water, non-carbonated, flavored","Water, non-carbonated, flavored"
|
89 |
+
Sprite,"Beverages, carbonated, lemon-lime soda, no caffeine","Beverages, carbonated, lemon-lime soda, no caffeine"
|
90 |
+
Buffalo chicken,"Chicken, broilers or fryers, meat and skin and giblets and neck, cooked, fried, flour",Buffalo chicken
|
91 |
+
veggie burgers,"Veggie burgers or soyburgers, unprepared","Veggie burgers or soyburgers, unprepared"
|
92 |
+
Vegenaise,"Salad dressing, mayonnaise, soybean and safflower oil, with salt","Salad dressing, mayonnaise, soybean and safflower oil, with salt"
|
93 |
+
Canned Beans,"Green beans, canned, cooked with oil","Green beans, canned, cooked with oil"
|
94 |
+
cheses,"Cheese, cheddar",Cheese
|
95 |
+
dips,"Dip, NFS","Dip, NFS"
|
96 |
+
b read,"Bread, white, commercially prepared, toasted","Bread, white, commercially prepared"
|
97 |
+
Assorted Personal Hygiene Items,Non-Food Item,Non-Food Item
|
98 |
+
Water - Bottles,"Water, bottled, plain","Water, bottled, plain"
|
99 |
+
Cookes,"Cookies, chocolate chip, commercially prepared, soft-type","Cookies, chocolate chip, commercially prepared, soft-type"
|
100 |
+
Dirt,Dirty rice,Dirty rice
|
101 |
+
Chapstick,"Soup, cream of chicken, canned, condensed",Non-Food Item
|
102 |
+
Water - Sparkling BLk Cherry,"Water, carbonated, plain","Water, carbonated, plain"
|
103 |
+
Choc Pretzels,"Pretzels, NFS","Pretzels, NFS"
|
104 |
+
Pretzel Bites,"Pretzels, NFS","Pretzels, NFS"
|
105 |
+
Orange soda,"Beverages, carbonated, orange","Beverages, carbonated, orange"
|
106 |
+
1% Milk,"MILK, 1%","MILK, 1%"
|
107 |
+
V8,"Beverages, V8 V-FUSION Juices, Tropical","Beverages, V8 V-FUSION Juices, Tropical"
|
108 |
+
Chicken Breast Strips,"Chicken tenders or strips, NFS","Chicken tenders or strips, NFS"
|
109 |
+
Misc Cleaning supplies,Non-Food Item,Non-Food Item
|
110 |
+
Nuts,"Nuts, NFS","Nuts, NFS"
|
111 |
+
Sparkling Juice,"Water, carbonated, plain","Water, carbonated, plain"
|
112 |
+
Paper Bags,Non-Food Item,Non-Food Item
|
113 |
+
jewelry,Non-Food Item,Non-Food Item
|
114 |
+
shoes,Chicken feet,Non-Food Item
|
115 |
+
make-up,"Salad dressing, mayonnaise, regular",Non-Food Item
|
116 |
+
turnip greens,"Turnip greens, raw","Turnip greens, raw"
|
117 |
+
Assorted Dairy Products,"Soymilk (all flavors), nonfat, with added calcium, vitamins A and D","Soymilk (all flavors), nonfat, with added calcium, vitamins A and D"
|
118 |
+
Thrive Energy Drink Powder,Energy drink (Red Bull),Energy drink (Red Bull)
|
119 |
+
Dog,Greyhound,Hot dog
|
120 |
+
ginger ale,"Soft drink, ginger ale","Soft drink, ginger ale"
|
121 |
+
Body Lotions,"Cream, light",Non-Food Item
|
122 |
+
Iced Coffee,"Coffee, Iced Latte","Coffee, Iced Latte"
|
123 |
+
Kitchen ware,Non-Food Item,Non-Food Item
|
124 |
+
prot. bars,"Nutrition bar or meal replacement bar, NFS","Nutrition bar or meal replacement bar, NFS"
|
125 |
+
"Mixed Berries, frozen","Blueberries, wild, frozen (Alaska Native)","Blueberries, wild, frozen (Alaska Native)"
|
126 |
+
juuice,"Fruit juice, NFS","Fruit juice, NFS"
|
127 |
+
Tape,Non-Food Item,Non-Food Item
|
128 |
+
rice krispie,Snacks,Snacks
|
129 |
+
Baking Chocolate,"Baking chocolate, unsweetened, squares","Baking chocolate, unsweetened, squares"
|
130 |
+
Mini Cucumbers,"Cucumber, peeled, raw","Cucumber, peeled, raw"
|
131 |
+
pizza rolls,Pizza rolls,Pizza rolls
|
132 |
+
Kitchen items,Assorted Edible Items,Assorted Edible Items
|
133 |
+
auto,"Abiyuch, raw",Non-Food Item
|
134 |
+
Nutrigrain Bars,Nutrition bar (Clif Bar),Nutrition bar (Clif Bar)
|
135 |
+
Peeps,"Candies, marshmallows","Candies, marshmallows"
|
136 |
+
Variety Grocery items,Mixed Food Items,Mixed Food Items
|
137 |
+
Assorted bread,"Bread, wheat","Bread, wheat"
|
138 |
+
vegetagles,"Vegetables, mixed, canned, drained solids","Vegetables, mixed, canned, drained solids"
|
139 |
+
prot. drinks,"Beverages, Protein powder whey based","Beverages, Protein powder whey based"
|
140 |
+
pork rinds,Pork skin rinds,Pork skin rinds
|
141 |
+
Bundt cake,"Cake, angelfood, commercially prepared","Cake, pound, commercially prepared, fat-free"
|
142 |
+
Croutons,Croutons,Croutons
|
143 |
+
Eergy Drinks,"Beverages, Energy drink, RED BULL, sugar free, with added caffeine, niacin, pantothenic acid, vitamins B6 and B12",Energy Drink
|
144 |
+
Ranch Dressing,Ranch dressing,Ranch dressing
|
145 |
+
Frozen Chicken Pot Pies,"Beef Pot Pie, frozen entree, prepared","Beef Pot Pie, frozen entree, prepared"
|
146 |
+
Tea drink,"Tea, hot, herbal","Tea, hot, herbal"
|
147 |
+
Chicken Wings,"Chicken wings, plain, from other sources","Chicken wings, plain, from other sources"
|
148 |
+
Hamburger Buns,"Rolls, hamburger or hotdog, plain","Rolls, hamburger or hotdog, plain"
|
149 |
+
Syrups,"Syrup, NFS","Syrup, NFS"
|
150 |
+
assorted groc.drinks,"Soft drink, NFS",Assorted Edible Items
|
151 |
+
Silk Milk Aseptic Horizon Choc Milk,"Hot chocolate / Cocoa, ready to drink, made with nonfat milk","Hot chocolate / Cocoa, ready to drink, made with nonfat milk"
|
152 |
+
coffee syrup,"Syrup, NFS","Syrup, NFS"
|
153 |
+
Granola,"Cereal, granola","Cereal, granola"
|
154 |
+
"Pastries, Asstd Grocery","Doughnuts, yeast-leavened, glazed, enriched (includes honey buns)","Doughnuts, yeast-leavened, glazed, enriched (includes honey buns)"
|
155 |
+
Soda - Asstd.,"Beverages, carbonated, low calorie, other than cola or pepper, without caffeine","Beverages, carbonated, low calorie, other than cola or pepper, without caffeine"
|
156 |
+
Mayonnaise,Ketchup,"Mayonnaise, regular"
|
157 |
+
just eggs,"Eggs, whole","Eggs, whole"
|
158 |
+
pancakes,"Pancakes, NFS","Pancakes, NFS"
|
159 |
+
Sunny D Juice drink,Fruit juice drink (Sunny D),Fruit juice drink (Sunny D)
|
160 |
+
Bean Dip,"Dip, bean, original flavor","Bean dip, made with refried beans"
|
161 |
+
Treatments,Cough drops,Cough drops
|
162 |
+
Coffee Beans,"Beans, NFS",Coffee Beans
|
163 |
+
Water - Gallon Jugs,"Water, bottled, plain","Water, bottled, plain"
|
164 |
+
Rice Krispies Treats,Snacks,Rice Krispies Treats
|
165 |
+
Miscellaneous Produce,Miscellaneous Produce,Miscellaneous Produce
|
166 |
+
Charcoal,"Barbecue meat, NFS",Non-Food Item
|
167 |
+
Cleaning Wipes,Non-Food Item,Non-Food Item
|
168 |
+
Spa Brushes,Non-Food Item,Non-Food Item
|
169 |
+
Jumbalaya,"Rice, white, long-grain, regular, cooked, unenriched, with salt","Rice, white, long-grain, regular, cooked, unenriched, with salt"
|
170 |
+
Tofurkey,"Tofu, raw, regular, prepared with calcium sulfate","Tofu, raw, regular, prepared with calcium sulfate"
|
171 |
+
Stuffed Animals,Non-Food Item,Non-Food Item
|
172 |
+
Lettuce mix,"Lettuce, raw","Lettuce, raw"
|
173 |
+
chili sauce,Tomato chili sauce,Tomato chili sauce
|
174 |
+
baking morsels,"Candies, semisweet chocolate","Candies, semisweet chocolate"
|
175 |
+
Ketchup dip cups,Ketchup,Ketchup
|
176 |
+
razors,Non-Food Item,Non-Food Item
|
177 |
+
Espresso Shots,"Coffee, espresso","Coffee, espresso"
|
178 |
+
Romain lettuce,"Romaine lettuce, raw","Romaine lettuce, raw"
|
179 |
+
Ice sparkling water,"Water, carbonated, plain","Water, carbonated, plain"
|
180 |
+
power water,"Water, bottled, plain","Water, bottled, plain"
|
181 |
+
Flip Flops,Chicken feet,Non-Food Item
|
182 |
+
Frozen Dumplings,"Dumpling, potato- or cheese-filled, frozen","Dumpling, potato- or cheese-filled, frozen"
|
183 |
+
Work Gloves,Non-Food Item,Non-Food Item
|
184 |
+
Nesquik milk,"Chocolate milk, made from dry mix, NS as to type of milk (Nesquik)","Chocolate milk, made from dry mix, NS as to type of milk (Nesquik)"
|
185 |
+
Misc. Produce,Misc Produce,Misc Produce
|
186 |
+
brk. bars,"Snacks, granola bars, soft, uncoated, plain","Snacks, granola bars, soft, uncoated, plain"
|
187 |
+
pop corn,"Corn, raw",Popcorn
|
188 |
+
Plastic Cups,Non-Food Item,Non-Food Item
|
189 |
+
Salad Kits,"Salad dressing, ranch dressing, regular","Salad dressing, ranch dressing, regular"
|
190 |
+
Misc. salad greens,"Mixed salad greens, raw","Mixed salad greens, raw"
|
191 |
+
Prepared Gelatin,Gelatin dessert,Gelatin dessert
|
192 |
+
Canned peaches,"Peach, canned, NFS","Peach, canned, NFS"
|
193 |
+
Protein Shakes,"Nutritional drink or shake, high protein, ready-to-drink, NFS","Nutritional drink or shake, high protein, ready-to-drink, NFS"
|
194 |
+
Assorted Vegetables,Assorted Vegetables,Assorted Vegetables
|
195 |
+
Thrive - Energy Drink powder,"Beverages, Energy drink, RED BULL, sugar free, with added caffeine, niacin, pantothenic acid, vitamins B6 and B12","Beverages, Energy drink, RED BULL, sugar free, with added caffeine, niacin, pantothenic acid, vitamins B6 and B12"
|
196 |
+
Gummies,"Candy, gummy","Candy, gummy"
|
197 |
+
Cleaning Solutions,Screwdriver,Screwdriver
|
198 |
+
Frozen soup,"Tomato soup, NFS","Tomato soup, NFS"
|
199 |
+
cranberry juice,"Cranberry juice, unsweetened","Cranberry juice, unsweetened"
|
200 |
+
Galic Cloves,"Garlic, raw","Garlic, raw"
|
201 |
+
dog treats,"Hot dog, meat and poultry","Hot dog, meat and poultry"
|
202 |
+
oats,"Oats, raw","Oats, raw"
|
203 |
+
bulk macaroni,"Pasta, dry, unenriched","Pasta, dry, unenriched"
|
204 |
+
Toys:Pillows (MM),Non-Food Item,Non-Food Item
|
205 |
+
Misc. Load,Energy drink (No Fear Motherload),Energy drink (No Fear Motherload)
|
206 |
+
Assorted Beverages,"Soft drink, NFS","Soft drink, NFS"
|
207 |
+
Oatmeal,"Oatmeal, NFS","Oatmeal, NFS"
|
208 |
+
Frozen waffles,"Waffle, plain, frozen","Waffle, plain, frozen"
|
209 |
+
NutriGrain,"Snacks, KELLOGG, KELLOGG'S, NUTRI-GRAIN Cereal Bars, fruit","Snacks, KELLOGG, KELLOGG'S, NUTRI-GRAIN Cereal Bars, fruit"
|
210 |
+
ice coffee drinks,Frozen coffee drink,Frozen coffee drink
|
211 |
+
Frozen corn,"Corn, frozen, cooked with oil","Corn, frozen, cooked with oil"
|
212 |
+
CVS Donation,"Cholesterol, Cheese, swiss, slices (CA2, NC) - 18c-16-03-Chol","Cholesterol, Cheese, swiss, slices (CA2, NC) - 18c-16-03-Chol"
|
213 |
+
Bouillon - Chicken,"Vegetable broth, bouillon","Vegetable broth, bouillon"
|
214 |
+
whipped cream,"Cream, whipped","Cream, whipped"
|
215 |
+
Coke Zero,"Beverages, carbonated, reduced sugar, cola, contains caffeine and sweeteners","Beverages, carbonated, reduced sugar, cola, contains caffeine and sweeteners"
|
216 |
+
Ramen noodle soup packs,Chicken or turkey chow mein or chop suey with noodles,"Soup, ramen noodle, any flavor, dry"
|
217 |
+
Veggie crisps,"Potato chips, plain","Potato chips, plain"
|
218 |
+
sunflower seeds,"Sunflower seeds, NFS","Sunflower seeds, NFS"
|
219 |
+
Pop Tart Bites,"Toaster pastries, brown-sugar-cinnamon","Toaster pastries, brown-sugar-cinnamon"
|
220 |
+
"Vitamin B-12, added to foods, cereals, grains, and some nutritional yeasts","Milk, canned, evaporated, with added vitamin A","Milk, canned, evaporated, with added vitamin A"
|
221 |
+
Misc. greens,"Mixed salad greens, raw","Mixed salad greens, raw"
|
222 |
+
"Vegetables, Fruit Cups","Fruit cocktail, canned, NFS","Fruit cocktail, canned, NFS"
|
223 |
+
naan bread,"Bread, naan","Bread, naan"
|
224 |
+
Avacado,"Avocado, raw","Avocado, raw"
|
225 |
+
OatmealChips,"Crackers, oatmeal","Crackers, oatmeal"
|
226 |
+
Orajel,Cough drops,Cough drops
|
227 |
+
Condoms,Pig in a blanket,Non-Food Item
|
228 |
+
Taco seasoning,"Seasoning mix, dry, taco, original","Seasoning mix, dry, taco, original"
|
229 |
+
Nutri-Grain Bars,"Snacks, NUTRI-GRAIN FRUIT AND NUT BAR","Snacks, NUTRI-GRAIN FRUIT AND NUT BAR"
|
230 |
+
Assorted Frozen Product,Mixed Food Items,Mixed Food Items
|
231 |
+
alum. roast pans,"Beef, pot roast","Beef, pot roast"
|
232 |
+
Brk. bread,"Bread, wheat","Bread, wheat"
|
233 |
+
creams,heavy cream,heavy cream
|
234 |
+
Head lettuce,"Lettuce, raw","Lettuce, raw"
|
235 |
+
Apple cider donuts,"Doughnuts, cake-type, plain, chocolate-coated or frosted","Doughnuts, cake-type, plain, chocolate-coated or frosted"
|
236 |
+
Half,"Cream, fluid, half and half","Cream, fluid, half and half"
|
237 |
+
Lean cuisine,"Pork, chop, lean only eaten",Non-Food Item
|
238 |
+
mac-n-cheese,Macaroni or noodles with cheese,Macaroni or noodles with cheese
|
239 |
+
Canned Fruit,"Orange, canned, NFS",Candied fruit
|
240 |
+
Deli Salads,"Salad dressing, russian dressing, low calorie","Salad dressing, russian dressing, low calorie"
|
241 |
+
Cheez-Its,"Crackers, cheese (Cheez-It)","Crackers, cheese (Cheez-It)"
|
242 |
+
Honey Melon,"Honeydew melon, raw","Honeydew melon, raw"
|
243 |
+
Frozen potatoes,"Potatoes, o'brien, frozen, unprepared","Potatoes, o'brien, frozen, unprepared"
|
244 |
+
Hummus,Hummus,Hummus
|
245 |
+
misc. vegs.,Mixed Vegetables,Mixed Vegetables
|
246 |
+
"Kits, Misc. Grocery, Pork Tenderloin, Misc. Fruit, Milk, Creamer, Protein Bars",Mixed Food Items,Mixed Food Items
|
247 |
+
"Gelatin, Meat","Gelatin desserts, dry mix, reduced calorie, with aspartame, prepared with water","Gelatin desserts, dry mix, reduced calorie, with aspartame"
|
248 |
+
Peanut butter,Peanut butter,Peanut butter
|
249 |
+
Topo Chico - Sparkling Water,"Beverages, water, bottled, non-carbonated, CALISTOGA","Beverages, water, bottled, non-carbonated, CALISTOGA"
|
250 |
+
"Beans, Soup","Bean soup, NFS","Bean soup, NFS"
|
251 |
+
Muffin mix,"Muffin, NFS","Muffin, NFS"
|
252 |
+
FF onions,"Onions, raw","Onions, raw"
|
253 |
+
Organic Milk,"Milk, whole, 3.25% milkfat, with added vitamin D","Milk, whole, 3.25% milkfat, with added vitamin D"
|
254 |
+
Topo Chico,"Water, carbonated, plain","Water, carbonated, plain"
|
255 |
+
rice krispy treats,Snacks,Rice cakes
|
256 |
+
Cereal Kones,"Cereal, K's, plain","Cereal, K's, plain"
|
257 |
+
"Romaine,Yogurt,Half","Romaine lettuce, raw","Romaine lettuce, raw"
|
258 |
+
"Half,Vegetables","Mixed Vegetables, canned","Mixed Vegetables, canned"
|
259 |
+
Assorted Pork Products,"Pork, fresh, variety meats and by-products, mechanically separated, raw","Pork, fresh, variety meats and by-products, mechanically separated, raw"
|
260 |
+
Pretzles,"Pretzels, soft","Pretzels, soft"
|
261 |
+
Turkey lunchmeat,Turkey with gravy,Turkey with gravy
|
262 |
+
Personal Hygeine Kits,"Water, bottled, generic","Water, bottled, generic"
|
263 |
+
mustard greens,"Mustard greens, raw","Mustard greens, raw"
|
264 |
+
ho,Hoisin sauce,Hoisin sauce
|
265 |
+
Assorted groc-bakery-perishable,Mixed Food Items,Mixed Food Items
|
266 |
+
PB meat,"Beef, ground, 70% lean meat / 30% fat, raw","Beef, ground, 70% lean meat / 30% fat, raw"
|
267 |
+
veg. drink,"Carrot juice, canned","Carrot juice, canned"
|
268 |
+
batteries,Non-Food Item,Non-Food Item
|
269 |
+
Romaine,"Romaine lettuce, raw","Romaine lettuce, raw"
|
270 |
+
Green Tea Bags,"Tea, hot, herbal","Tea, hot, herbal"
|
271 |
+
Dry pasta,"Pasta, dry, unenriched","Pasta, dry, unenriched"
|
272 |
+
"Milk, dry, nonfat, regular","Milk, nonfat, fluid, with added vitamin A and vitamin D (fat free or skim)","Milk, dry, nonfat, regular, with added vitamin A and vitamin D"
|
273 |
+
aseptic milk,"Milk, lowfat, fluid, 1% milkfat, with added vitamin A and vitamin D","Milk, lowfat, fluid, 1% milkfat, with added vitamin A and vitamin D"
|
274 |
+
ND creamer,"Coffee creamer, NFS","Coffee creamer, NFS"
|
275 |
+
misc. breads,"Bread, wheat","Bread, wheat"
|
276 |
+
sweets,"Candies, sweet chocolate","Candies, sweet chocolate"
|
277 |
+
Fries,"Sweet potato fries, NFS","Sweet potato fries, NFS"
|
278 |
+
Plant-based protein bites,Hamburger (Burger King),Meat substitute
|
279 |
+
Stacy's Pita Chips,Pita chips,Pita chips
|
280 |
+
jalapeno peppers,"Peppers, jalapeno, raw","Peppers, jalapeno, raw"
|
281 |
+
Paper Towels,Non-Food Item,Non-Food Item
|
282 |
+
GreenBeans,"Green beans, raw","Green beans, raw"
|
283 |
+
Milk Assortment,"Non-dairy milk, NFS",Non-Food Item
|
284 |
+
Carckers,"Crackers, standard snack-type, regular, low salt","Crackers, standard snack-type, regular, low salt"
|
285 |
+
leaf lettuce,"Lettuce, leaf, green, raw","Lettuce, leaf, green, raw"
|
286 |
+
Pads,"Drumstick pods, raw","Drumstick pods, raw"
|
287 |
+
Sausage Crumbles,"Beef, ground, 95% lean meat / 5% fat, crumbles, cooked, pan-browned","Beef, ground, 95% lean meat / 5% fat, crumbles, cooked, pan-browned"
|
288 |
+
"Frozen entree, enchilada, whole meal, heated","Chicken dinner, NFS, frozen meal","Chicken dinner, NFS, frozen meal"
|
289 |
+
Strawberres,"Strawberries, raw","Strawberries, raw"
|
290 |
+
Condimenta,"Salad dressing, mayonnaise, regular","Salad dressing, mayonnaise, regular"
|
291 |
+
Fettuccini,"Pasta, cooked","Pasta, cooked"
|
292 |
+
choc ganache,"Frostings, chocolate, creamy, ready-to-eat","Frostings, chocolate, creamy, ready-to-eat"
|
293 |
+
Mashed Potatoes,"Potato, mashed, NFS","Potato, mashed, NFS"
|
294 |
+
Office Furniture,Non-Food Item,Non-Food Item
|
295 |
+
Assorted paper products,Rice paper,Non-Food Item
|
296 |
+
Cheeseburgers,"Cheeseburger, NFS","Cheeseburger, NFS"
|
297 |
+
Beef Hot links,"Sausage, smoked link sausage, pork and beef","Sausage, smoked link sausage, pork and beef"
|
298 |
+
Sausage Strips,"Sausage, NFS","Sausage, NFS"
|
299 |
+
Deli Meat,"Chicken deli sandwich or sub, restaurant","Chicken deli sandwich or sub, restaurant"
|
300 |
+
Breakfast Drinks,"Beverages, coffee, brewed, breakfast blend","Beverages, coffee, instant, mocha, sweetened"
|
301 |
+
Popcorners,"Popcorn, NFS","Popcorn, NFS"
|
302 |
+
Pasta Meals,"Pasta with sauce, NFS","Pasta with sauce, NFS"
|
303 |
+
Assorted cookies,"Cookie, NFS","Cookie, NFS"
|
304 |
+
Hostess bakery product,"Bread, white, made from home recipe or purchased at a bakery","Bread, white, made from home recipe or purchased at a bakery"
|
305 |
+
Hotpockets,"HOT POCKETS, CROISSANT POCKETS Chicken, Broccoli, and Cheddar Stuffed Sandwich, frozen","HOT POCKETS, CROISSANT POCKETS Chicken, Broccoli, and Cheddar Stuffed Sandwich, frozen"
|
306 |
+
Plant Based Meals,Mixed Food Items,Mixed Food Items
|
307 |
+
Bottled water,"Water, bottled, plain","Water, bottled, plain"
|
308 |
+
"powder, energy bars","Nutritional drink or shake, ready-to-drink, light (Muscle Milk)","Nutritional drink or shake, ready-to-drink, light (Muscle Milk)"
|
309 |
+
process meat,"Bacon, NS as to type of meat, cooked","Bacon, NS as to type of meat, cooked"
|
310 |
+
Cheese Sticks,"Cheese, American, nonfat or fat free","Cheese, pasteurized process, American, low fat"
|
311 |
+
frozen meatloaf dinners,"Meat loaf dinner, NFS, frozen meal","Meat loaf dinner, NFS, frozen meal"
|
312 |
+
apple cider vinegar,"Vinegar, cider","Vinegar, cider"
|
313 |
+
brownie bars,"Snack bar, oatmeal","Snack bar, oatmeal"
|
314 |
+
Seeds,"Sunflower seeds, NFS","Sunflower seeds, NFS"
|
315 |
+
Branola Bars,"Cereal, granola","Cereal, granola"
|
316 |
+
Can Peaches,"Peach, canned, NFS","Peach, canned, NFS"
|
317 |
+
Entree's,Mixed Food Items,Non-Food Item
|
318 |
+
Flavoared Water,"Beverages, Fruit flavored drink, less than 3% juice, not fortified with vitamin C","Beverages, Fruit flavored drink, less than 3% juice, not fortified with vitamin C"
|
319 |
+
Flavored Electrolyte Water,"Water, non-carbonated, flavored","Water, non-carbonated, flavored"
|
320 |
+
Ground Beef,"Beef, ground","Beef, ground"
|
321 |
+
red beets,"Beets, raw","Beets, raw"
|
322 |
+
Asst Walgreens Items,Assorted Consumables,Asst Walgreens Items
|
323 |
+
Egg rolls,"Rolls, dinner, egg","Rolls, dinner, egg"
|
324 |
+
assorted pastas,"Pasta with sauce, NFS","Pasta with sauce, NFS"
|
325 |
+
Froxzen Vegetables,"Vegetables, mixed, frozen, cooked, boiled, drained, with salt","Vegetables, mixed, frozen, cooked, boiled, drained, with salt"
|
326 |
+
Hashbrowns,"Potatoes, hash brown, frozen, plain, unprepared","Potatoes, hash brown, frozen, plain, unprepared"
|
327 |
+
Plastic Trays,Non-Food Item,Non-Food Item
|
328 |
+
Plastic Containers,Non-Food Item,Non-Food Item
|
329 |
+
chee it,"Cheese, pasteurized process, American, low fat","Cheese, pasteurized process, American, low fat"
|
330 |
+
Plantains,"Plantains, green, raw","Plantains, green, raw"
|
331 |
+
Asst CVS,"Cholesterol, Cheese, swiss, slices (CA2, NC) - 18c-16-03-Chol","Cholesterol, Cheese, swiss, slices (CA2, NC) - 18c-16-03-Chol"
|
332 |
+
Berry Punch,"Berries, NFS","Berries, NFS"
|
333 |
+
Tylenol,Cough drops,Non-Food Item
|
334 |
+
sparking water,"Water, carbonated, plain","Water, carbonated, plain"
|
335 |
+
Pork Salad Dressing,"Salad dressing, coleslaw","Salad dressing, coleslaw"
|
336 |
+
Assorted fresh vegetables,Assorted Vegetables,Assorted Vegetables
|
337 |
+
Red Wine Vinegar,"Vinegar, red wine","Vinegar, red wine"
|
338 |
+
Artichoke Hearts,"Artichoke, raw","Artichoke, raw"
|
339 |
+
misc groc,Misc Grocery,Assorted Groceries
|
340 |
+
Potato Casserole Soup,Potato and cheese soup,Potato and cheese soup
|
341 |
+
gold fish,"Fish, whitefish, mixed species, raw","Fish, whitefish, mixed species, raw"
|
342 |
+
"Pizza, frozen, cheese, prepared","Pizza, cheese and vegetables, whole wheat thick crust","Pizza, cheese and vegetables, whole wheat thick crust"
|
343 |
+
Assorted Natural Choice Products,Mixed Food Items,Mixed Food Items
|
344 |
+
chicken tenders,"Chicken tenders or strips, NFS","Chicken tenders or strips, NFS"
|
345 |
+
Marinade,Korean dressing or marinade,Korean dressing or marinade
|
346 |
+
lunchabes,Snack cake,Non-Food Item
|
347 |
+
Dr. Bronner's chocolate bars,"Candies, MR. GOODBAR Chocolate Bar","Candies, MR. GOODBAR Chocolate Bar"
|
348 |
+
Pizza Crusts,"Pizza, cheese, from restaurant or fast food, NS as to type of crust","Pizza, cheese, from restaurant or fast food, NS as to type of crust"
|
349 |
+
Corn Meal,"Corn, raw","Corn, raw"
|
350 |
+
Cheese whisps,"Cheese, parmesan, grated","Cheese, parmesan, grated"
|
351 |
+
Juice - Cranberry,"Cranberries, raw","Cranberries, raw"
|
352 |
+
Gater,Fruit flavored drink,"Beverages, PEPSICO QUAKER, Gatorade, G performance O 2, ready-to-drink"
|
353 |
+
back packs,"Cereals ready-to-eat, wheat, puffed, fortified",Non-Food Item
|
354 |
+
Pet Food,"Hot dog, meat and poultry",Pet Food
|
355 |
+
Cream Protein Drinks,"Nutritional drink or shake, high protein, ready-to-drink, NFS","Nutritional drink or shake, high protein, ready-to-drink, NFS"
|
356 |
+
softner,"Soft drink, NFS","Soft drink, NFS"
|
357 |
+
v-8 plash juice,"Beverages, V8 SPLASH Juice Drinks, Strawberry Kiwi","Beverages, V8 SPLASH Juice Drinks, Strawberry Kiwi"
|
358 |
+
Fresh lettuce,"Lettuce, raw","Lettuce, raw"
|
359 |
+
Paper Wipes,Non-Food Item,Non-Food Item
|
360 |
+
Dessert Cookie,"Cookie, chocolate chip","Cookie, chocolate chip"
|
361 |
+
lettice,"Lettuce, raw","Lettuce, raw"
|
362 |
+
Cracker Jackss,"Candies, HERSHEY, REESESTICKS crispy wafers, peanut butter, milk chocolate","Candies, HERSHEY, REESESTICKS crispy wafers, peanut butter, milk chocolate"
|
363 |
+
Flavored milk,"Chocolate milk, NFS","Chocolate milk, NFS"
|
364 |
+
choc. chips morsels,"Candies, semisweet chocolate","Candies, semisweet chocolate"
|
365 |
+
Tables,"Table fat, NFS",Non-Food Item
|
366 |
+
Printer,Rice paper,Rice paper
|
367 |
+
Misc Household,Non-Food Item,Non-Food Item
|
368 |
+
misc perishables,Mixed Food Items,Mixed Food Items
|
369 |
+
Cherry Coke Zero,"Beverages, ZEVIA, cola","Beverages, ZEVIA, cola"
|
370 |
+
Misc. Prod,Misc Produce,Misc Produce
|
371 |
+
Cubanelle Peppers,"Peppers, jalapeno, raw","Peppers, hungarian, raw"
|
372 |
+
pork skins,Pork skin rinds,Pork skin rinds
|
373 |
+
cheetos,"Snacks, tortilla chips, nacho cheese",Cheese flavored corn snacks (Cheetos)
|
374 |
+
Cheesecake kit,"Cake, cheesecake, commercially prepared","Cake, cheesecake, commercially prepared"
|
375 |
+
bulk cookies,"Cookies, sugar, commercially prepared, regular (includes vanilla)","Cookies, sugar, commercially prepared, regular (includes vanilla)"
|
376 |
+
Body Scrub,Non-Food Item,Non-Food Item
|
377 |
+
Shampoo,Non-Food Item,Non-Food Item
|
378 |
+
Side Dishes,Mixed Food Items,Mixed Food Items
|
379 |
+
Can Vegetables,"Mixed Vegetables, canned","Mixed Vegetables, canned"
|
380 |
+
Chicken mac-n-cheese,Macaroni or noodles with cheese and chicken or turkey,Macaroni or noodles with cheese and chicken or turkey
|
381 |
+
Donated,Mixed Goods,Non-Food Item
|
382 |
+
Dough,"Bread, white, commercially prepared, toasted","Bread, white, commercially prepared, toasted"
|
383 |
+
grocery sides,Mixed Food Items,Mixed Food Items
|
384 |
+
"misc, ice cream,desserts,pizza,plant meats",Mixed Food Items,Mixed Food Items
|
385 |
+
FF,Fufu,Fufu
|
386 |
+
Hot Pockets,"HOT POCKETS Ham 'N Cheese Stuffed Sandwich, frozen","HOT POCKETS Ham 'N Cheese Stuffed Sandwich, frozen"
|
387 |
+
Sweet corn,"Corn, sweet, white, raw","Corn, sweet, white, raw"
|
388 |
+
light bulbs,"Fennel bulb, raw","Fennel bulb, raw"
|
389 |
+
sausage brats,Bratwurst,Bratwurst
|
390 |
+
froz. chicken breasts,"Chicken, broilers or fryers, light meat, meat only, raw","Chicken, broilers or fryers, light meat, meat only, raw"
|
391 |
+
Corn Flake Crumbs,Graham crackers,Graham crackers
|
392 |
+
Pineapple juice,"Pineapple juice, 100%","Pineapple juice, 100%"
|
393 |
+
flav. water,"Fruit juice drink, noncitrus, carbonated","Fruit juice drink, noncitrus, carbonated"
|
394 |
+
Clorox bleach,Non-Food Item,Non-Food Item
|
395 |
+
coffe drinks,"Beverages, coffee, instant, mocha, sweetened","Beverages, coffee, instant, mocha, sweetened"
|
396 |
+
junior pops,"Cereals ready-to-eat, QUAKER, HONEY GRAHAM OH!S",Honeycomb Cereal
|
397 |
+
Chicken Bouillon,"Vegetable broth, bouillon","Vegetable broth, bouillon"
|
398 |
+
Pringles chips,"Potato chips, NFS","Potato chips, NFS"
|
399 |
+
mixed food-snacks,Snack mix,Snack mix
|
400 |
+
Filter Pack Coffee,"Beverages, coffee, brewed, prepared with tap water","Beverages, coffee, brewed, prepared with tap water"
|
401 |
+
Topo Chico mineral water,"Water, bottled, generic","Water, bottled, generic"
|
402 |
+
Fruit Punch,"Fruit punch, alcoholic","Fruit punch, alcoholic"
|
403 |
+
ice mountain water,"Water, bottled, generic","Water, bottled, generic"
|
404 |
+
Local Store Donations,Assorted Groceries,Assorted Groceries
|
405 |
+
Local Store Items,Grocery Items,Grocery Items
|
406 |
+
Misc groc.,Mixed Food Items,Assorted Groceries
|
407 |
+
Egg Noodles,"Noodles, egg, enriched, cooked","Noodles, egg, enriched, cooked"
|
408 |
+
Fresh Fruit,"Fruit, NFS","Fruit, NFS"
|
409 |
+
Juice Bottles,"Water, bottled, plain","Water, bottled, plain"
|
410 |
+
protien drink,"Beverages, Protein powder whey based","Beverages, Protein powder whey based"
|
411 |
+
"Chicken nuggets, breaded and fried, containing 50% of water and 10% of breading, raw","Chicken patty, breaded","Chicken patty, breaded"
|
412 |
+
fabrick softner,"Roll, white, soft",Non-Food Item
|
413 |
+
Mini Mounds chocolate bars,"Candies, MOUNDS Candy Bar","Candies, MOUNDS Candy Bar"
|
414 |
+
rice crispy treats,Snacks,Snacks
|
415 |
+
Hash browns,"CHICK-FIL-A, hash browns","McDONALD'S, Hash Brown"
|
416 |
+
"Coffee, ground, regular","Beverages, coffee, instant, regular, prepared with water","Beverages, coffee, instant, regular, prepared with water"
|
417 |
+
lime gelatin,"Gelatin desserts, dry mix, reduced calorie, with aspartame, prepared with water","Gelatin desserts, dry mix, reduced calorie, with aspartame"
|
418 |
+
ref. cookie dough,"Cookie, batter or dough, raw","Cookie, batter or dough, raw"
|
419 |
+
Toddler Milk,"Milk, human","Milk, human"
|
420 |
+
Honey,Honey,Honey
|
421 |
+
misc groc. misc dairy,Misc Grocery,Misc Grocery
|
422 |
+
Assortment of dry goods,Mixed Food Items,Mixed Food Items
|
423 |
+
Assorted lunch meat,"Luncheon meat, NFS","Luncheon meat, NFS"
|
424 |
+
assorted sausage,"Sausage, NFS","Sausage, NFS"
|
425 |
+
White Castle Hamburgers,"Fast foods, hamburger; single, regular patty; with condiments","Fast foods, hamburger; single, regular patty; with condiments"
|
426 |
+
Personal Hygiene,Non-Food Item,Non-Food Item
|
427 |
+
Flour Tortillas,"Tortilla, flour","Tortilla, flour"
|
428 |
+
Cheese Dip,Cheese dip,Cheese dip
|
429 |
+
misxed salad greens,"Mixed salad greens, raw","Mixed salad greens, raw"
|
430 |
+
boxed stuffing,"Bread, stuffing, dry mix, prepared","Bread, stuffing, dry mix"
|
431 |
+
Powdered Gatorade,Sports drink (Gatorade G),Sports drink (Gatorade G)
|
432 |
+
proc. meat,Misc Meat,Misc Meat
|
433 |
+
Fresh head lettuce,"Lettuce, Boston, raw","Lettuce, Boston, raw"
|
434 |
+
mixed snacks,Snack mix,Snack mix
|
435 |
+
sparkling water zero sugar,"Water, non-carbonated, bottles, natural fruit flavors, sweetened with low calorie sweetener","Water, carbonated, plain"
|
436 |
+
Stock,Mixed Goods,Mixed Goods
|
437 |
+
Gatorade Bottles,"Sports drink, low calorie (Gatorade G2)","Sports drink, low calorie (Gatorade G2)"
|
438 |
+
assorted dairy,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
439 |
+
alfredo sauces,Alfredo sauce,Alfredo sauce
|
440 |
+
Non-Dairy,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
441 |
+
Juice - Fruit Punch,"Fruit punch, made with fruit juice and soda","Fruit punch, made with fruit juice and soda"
|
442 |
+
"Water, tap, municipal","Water, tap","Water, tap"
|
443 |
+
Juice - Cranberry Juice,"Cranberry juice, unsweetened","Cranberry juice, unsweetened"
|
444 |
+
microwave popcorn,"Popcorn, microwave, NFS","Popcorn, microwave, NFS"
|
445 |
+
Lunchmeat,"Lunchmeat, ham - NFY1210OP","Lunchmeat, ham - NFY1210OP"
|
446 |
+
PB crackers,"Crackers, NFS","Crackers, sandwich, peanut butter filled"
|
447 |
+
Paper Cups,Non-Food Item,Non-Food Item
|
448 |
+
Hygiene,Non-Food Item,Non-Food Item
|
449 |
+
Misc CVS,"Cholesterol, Cheese, swiss, slices (CA2, NC) - 18c-16-03-Chol","Cholesterol, Cheese, swiss, slices (CA2, NC) - 18c-16-03-Chol"
|
450 |
+
misc. dairy,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
451 |
+
Dunkin Donuts Iced Coffee,"Coffee, Iced Latte, with non-dairy milk","Coffee, Iced Latte, with non-dairy milk"
|
452 |
+
Degreaser,Non-Food Item,Non-Food Item
|
453 |
+
misc. dry goods,Mixed Food Items,Mixed Food Items
|
454 |
+
"cheese, soup,cooked pasta",Macaroni or noodles with cheese,Macaroni or noodles with cheese
|
455 |
+
Fresh peppers,"peppers, bell, red, raw","peppers, bell, red, raw"
|
456 |
+
Toy Cars,Non-Food Item,Non-Food Item
|
457 |
+
AZG Food Boxes,Various Groceries,Various Groceries
|
458 |
+
formula,"Infant formula, NFS","Infant formula, NFS"
|
459 |
+
fruit drins,"Fruit flavored drink, with high vitamin C","Fruit flavored drink, with high vitamin C"
|
460 |
+
Dried Cheese,Cheese,Cheese
|
461 |
+
guacamole,"Guacamole, NFS","Guacamole, NFS"
|
462 |
+
Entrées,"Pasta with tomato-based sauce and meat, restaurant","Pasta with tomato-based sauce and meat, restaurant"
|
463 |
+
Bottles,"Water, bottled, plain","Water, bottled, plain"
|
464 |
+
Spiral Ham,"Ham, sliced, regular (approximately 11% fat)","Ham, sliced, regular (approximately 11% fat)"
|
465 |
+
Fruit Cups - Pears,"Pears, raw","Pears, raw"
|
466 |
+
pers. hygiene,Non-Food Item,Non-Food Item
|
467 |
+
Chicken lunch meat,"Luncheon meat, NFS","Luncheon meat, NFS"
|
468 |
+
Misc. frozen potatoes,"Potato wedges, frozen (Includes foods for USDA's Food Distribution Program)","Potato wedges, frozen (Includes foods for USDA's Food Distribution Program)"
|
469 |
+
"Snacks, pizza rolls, frozen, unprepared","Snacks, banana chips","Pizza rolls, frozen, unprepared"
|
470 |
+
Plant-based shelf stable milk,"Soymilk (all flavors), unsweetened, with added calcium, vitamins A and D","Soymilk (all flavors), unsweetened, with added calcium, vitamins A and D"
|
471 |
+
Jiffy muffin mix (PJ Star Food Boxes),"Muffins, corn, prepared from recipe, made with low fat (2%) milk","Muffins, corn, commercially prepared"
|
472 |
+
assorted grocery items,Assorted Groceries,Assorted Groceries
|
473 |
+
Meals,Mixed Food Items,Mixed Food Items
|
474 |
+
Choc Chips,"Potato chips, NFS",Chocolate chips
|
475 |
+
"TOSTITOS, SIMPLY TOSTITOS, SIMPLY BLACK BEAN","Black beans, NFS","Black beans, NFS"
|
476 |
+
Misc Frozen,"Vegetables, mixed, frozen, unprepared","Vegetables, mixed, frozen, unprepared"
|
477 |
+
Caramel Sauce,"Syrups, malt","Syrups, malt"
|
478 |
+
fabric softner,"Roll, white, soft",Non-Food Item
|
479 |
+
pancake syrup,Pancake syrup,Pancake syrup
|
480 |
+
Santizing Wipes,Non-Food Item,Non-Food Item
|
481 |
+
nutri bars,"Cereal or granola bar, peanuts , oats, sugar, wheat germ","Cereal or granola bar, peanuts, oats, sugar, wheat germ"
|
482 |
+
rice krispies,Snacks,Snacks
|
483 |
+
Whole Milk,"MILK, WHOLE ","MILK, WHOLE"
|
484 |
+
fresh chicken,"Chicken, broilers or fryers, meat and skin and giblets and neck, roasted","Chicken, broilers or fryers, meat and skin and giblets and neck, roasted"
|
485 |
+
ice cream creamer,"Ice cream, NFS","Coffee creamer, NFS"
|
486 |
+
Pumpkin Seeds,"Pumpkin seeds, NFS","Pumpkin seeds, NFS"
|
487 |
+
Bottled Tea,"Tea, hot, herbal","Tea, hot, herbal"
|
488 |
+
Swiffer Refills,Screwdriver,Screwdriver
|
489 |
+
Office Equipment,Miscellaneous Items,Miscellaneous Items
|
490 |
+
choc. morsels,Dark chocolate candy,Dark chocolate candy
|
491 |
+
Veggie straws,"Snacks, potato chips, made from dried potatoes, fat-free, made with olestra","Snacks, potato chips, made from dried potatoes, fat-free, made with olestra"
|
492 |
+
lunchmeasts,"Bacon, pre-sliced, reduced/low sodium, unprepared","Bacon, pre-sliced, reduced/low sodium, unprepared"
|
493 |
+
Picante sauce,"Sauce, salsa, ready-to-serve","Sauce, salsa, ready-to-serve"
|
494 |
+
V8 Energy drink,Energy Drink,Energy Drink
|
495 |
+
Stewed Tomatoes,"Tomatoes, red, ripe, cooked, stewed","Tomatoes, red, ripe, cooked, stewed"
|
496 |
+
mixed dry,"Cereals, whole wheat hot natural cereal, dry","Cereals, whole wheat hot natural cereal, dry"
|
497 |
+
Womens,"Chicken, broilers or fryers, breast, meat and skin, raw",Non-Food Item
|
498 |
+
Childrens,Mixed Food Items,Non-Food Item
|
499 |
+
Mens,"Milk, nonfat, fluid, protein fortified, with added vitamin A and vitamin D (fat free and skim)",Non-Food Item
|
500 |
+
heavy whipping cream,"Cream, fluid, heavy whipping","Cream, fluid, heavy whipping"
|
501 |
+
marsmellows,"Candies, marshmallows","Candies, marshmallows"
|
502 |
+
thickend lemon water,"Lemon juice, raw","Lemon juice, raw"
|
503 |
+
Popcorn Chicken,"KFC, Popcorn Chicken","KFC, Popcorn Chicken"
|
504 |
+
small salisbury steak meals,"Salisbury steak dinner, NFS, frozen meal","Salisbury steak dinner, NFS, frozen meal"
|
505 |
+
Fruit cocktail (PJS boxes),"Fruit cocktail, canned, NFS","Fruit cocktail, canned, NFS"
|
506 |
+
izze,"Yam, raw",Non-Food Item
|
507 |
+
boneless pork loin,"pork, loin, boneless",pork loin
|
508 |
+
Bodywash,Non-Food Item,Non-Food Item
|
509 |
+
Disinfecting wipes,Non-Food Item,Non-Food Item
|
510 |
+
assorted sausage links,"Sausage, pork and beef, with cheddar cheese, smoked","Sausage, pork and beef, with cheddar cheese, smoked"
|
511 |
+
Rice Sides,"Rice, white, long-grain, regular, raw, enriched","Rice, white, long-grain, regular, raw, enriched"
|
512 |
+
Veggie bites,"Veggie burgers or soyburgers, unprepared","Veggie burgers or soyburgers, unprepared"
|
513 |
+
blueberry loaves,"Muffins, blueberry, toaster-type","Muffins, blueberry, toaster-type"
|
514 |
+
double shot expresso coffee,"Beverages, coffee, brewed, espresso, restaurant-prepared","Beverages, coffee, brewed, espresso, restaurant-prepared"
|
515 |
+
Seasonings,Mixed Food Items,Mixed Food Items
|
516 |
+
vinegar,Vinegar,Vinegar
|
517 |
+
"Toilet tissue, standard roll (5"" x 4.5"")",Non-Food Item,Non-Food Item
|
518 |
+
liquid detergent,Non-Food Item,Non-Food Item
|
519 |
+
"snacks,drinks,desserts,chips,popcorn","Snacks, popcorn, cakes",Snacks
|
520 |
+
chahote squash,"Squash, summer, scallop, cooked, boiled, drained, with salt","Squash, summer, scallop, cooked, boiled, drained, with salt"
|
521 |
+
meat-misc. snacks,"Snacks, popcorn, cakes",Meat snacks
|
522 |
+
p. hygiene,Non-Food Item,Non-Food Item
|
523 |
+
Misc Cleaning,Screwdriver,Screwdriver
|
524 |
+
Prepared Snadwiches,"Fast foods, submarine sandwich, oven roasted chicken on white bread with lettuce and tomato","Fast foods, submarine sandwich, oven roasted chicken on white bread with lettuce and tomato"
|
525 |
+
-coffee,"Beverages, coffee, brewed, prepared with tap water","Beverages, coffee, brewed, prepared with tap water"
|
526 |
+
Pizza lunchables,"Pizza, meat and vegetable topping, regular crust, frozen, cooked","Pizza, meat and vegetable topping, regular crust, frozen, cooked"
|
527 |
+
nesquik drinks,"Chocolate milk, ready to drink, low fat, no sugar added (Nesquik)","Chocolate milk, ready to drink, low fat, no sugar added (Nesquik)"
|
528 |
+
Stove Top Stuffing,Bread stuffing,Bread stuffing
|
529 |
+
lard,Lard,Lard
|
530 |
+
salsa,Salsa,Salsa
|
531 |
+
Cookie dough pucks,"Cookies, chocolate chip, commercially prepared, soft-type","Cookies, chocolate chip, commercially prepared, soft-type"
|
532 |
+
Misc Grocery Frozen,Mixed Food Items,Mixed Food Items
|
533 |
+
Food Containers,Various Groceries,Various Groceries
|
534 |
+
TM TVP,"Soy protein concentrate, produced by acid wash","Soy protein concentrate, produced by acid wash"
|
535 |
+
Frozen Entrees,"Frozen dinner, NFS","Frozen dinner, NFS"
|
536 |
+
Garden Produce,Mixed Food Items,Mixed Food Items
|
537 |
+
fresh bulk pkg. chicken breast,"Chicken, broilers or fryers, breast, meat and skin, raw","Chicken, broilers or fryers, breast, meat and skin, raw"
|
538 |
+
Coffe,"Beverages, coffee, brewed, prepared with tap water","Beverages, coffee, brewed, prepared with tap water"
|
539 |
+
assoreted grocery,Grocery,Grocery
|
540 |
+
popocorn,"Snacks, popcorn, air-popped","Snacks, popcorn, air-popped"
|
541 |
+
cough syrum,Cough drops,Cough drops
|
542 |
+
mouthwash,Non-Food Item,Non-Food Item
|
543 |
+
Digiorno pizza,"DIGIORNO Pizza, supreme topping, thin crispy crust, frozen, baked","DIGIORNO Pizza, supreme topping, thin crispy crust, frozen, baked"
|
544 |
+
Salami,"Salami, NFS","Salami, NFS"
|
545 |
+
Bulk pizza,"Pizza, meat and vegetable topping, regular crust, frozen, cooked","Pizza, meat and vegetable topping, regular crust, frozen, cooked"
|
546 |
+
Mozzarella sticks,"APPLEBEE'S, mozzarella sticks","APPLEBEE'S, mozzarella sticks"
|
547 |
+
Rolled oats,"Oats, raw","Oats, whole grain, rolled, old fashioned"
|
548 |
+
coffee creamer cps,"Coffee creamer, NFS","Coffee creamer, NFS"
|
549 |
+
Egg frittatas,Chicken Fritters,Chicken Fritters
|
550 |
+
apple chips,"Potato chips, NFS","Potato chips, NFS"
|
551 |
+
Sliced Bread,"Bread, wheat","Bread, wheat"
|
552 |
+
Vegetable rice,"Rice, white, long-grain, regular, raw, enriched","Rice, white, long-grain, regular, raw, enriched"
|
553 |
+
oreo coockie crumbs,Graham crackers,Graham crackers
|
554 |
+
Misc,Mixed Food Items,Mixed Food Items
|
555 |
+
Canned water,"Water, bottled, plain","Water, bottled, plain"
|
556 |
+
Saltine Crackers,"Crackers, saltine","Crackers, saltine"
|
557 |
+
cookie pieces,"Cookies, chocolate chip, commercially prepared, regular, lower fat","Cookies, chocolate chip, commercially prepared, regular, lower fat"
|
558 |
+
frozen strawberries,"Strawberries, frozen","Strawberries, frozen"
|
559 |
+
cough syrup,Cough drops,Cough drops
|
560 |
+
Baby Formula,"Infant formula, NFS","Infant formula, NFS"
|
561 |
+
salad mix,"Mixed salad greens, raw","Mixed salad greens, raw"
|
562 |
+
tartar sauce,Tartar sauce,Tartar sauce
|
563 |
+
Ketchup,Ketchup,Ketchup
|
564 |
+
misc grocery items,Assorted Groceries,Assorted Groceries
|
565 |
+
Turkey,"Turkey, NFS","Turkey, whole, back, meat and skin, raw"
|
566 |
+
Deliwiches,"Chicken deli sandwich or sub, restaurant","Chicken deli sandwich or sub, restaurant"
|
567 |
+
dried cranberries,"Cranberries, dried","Cranberries, dried"
|
568 |
+
Mac N Cheese,Macaroni or noodles with cheese,Macaroni or noodles with cheese
|
569 |
+
Assorted canned soups,"Soup, beef and vegetables, canned, ready-to-serve","Soup, beef and vegetables, canned, ready-to-serve"
|
570 |
+
pineappoe,"Pineapple, raw","Pineapple, raw"
|
571 |
+
Canned Fruit-Diced Pears,"Pear, canned, NFS","Pear, canned, NFS"
|
572 |
+
Flashlights,Non-Food Item,Non-Food Item
|
573 |
+
Bulk Ketchup,Ketchup,Ketchup
|
574 |
+
takis chips,"Potato chips, NFS","Potato chips, NFS"
|
575 |
+
rice crisps,"Chips, rice","Chips, rice"
|
576 |
+
Boullion,"Soup, bouillon cubes and granules, low sodium, dry","Soup, chicken broth or bouillon, dry, prepared with water"
|
577 |
+
"pasta,soup,canned fruit","Crackers, saltines (includes oyster, soda, soup)","Crackers, saltines (includes oyster, soda, soup)"
|
578 |
+
"vegs.,cleaning,shelf stable milk","Non-dairy milk, NFS",Non-Food Item
|
579 |
+
tomato paste packets,"tomato, paste, canned, without salt added","tomato products, canned, paste, without salt added (Includes foods for USDA's Food Distribution Program)"
|
580 |
+
MRE's,Mixed Food Items,Mixed Food Items
|
581 |
+
vegan chicken patties,Vegetarian meatloaf or patties,Vegetarian meatloaf or patties
|
582 |
+
french fries,"Sweet potato fries, NFS","Sweet potato fries, NFS"
|
583 |
+
Green Chilies,"Peppers, sweet, green, raw","Peppers, sweet, green, raw"
|
584 |
+
entree bowls,Mixed Food Items,Burrito bowl
|
585 |
+
Cheese balls,Cheese ball,Cheese ball
|
586 |
+
perfume,Mustard,Non-Food Item
|
587 |
+
misc fry,"Fast foods, potato, french fried in vegetable oil","Fast foods, potato, french fried in vegetable oil"
|
588 |
+
cappuccino mix,"Beverages, coffee and cocoa, instant, decaffeinated, with whitener and low calorie sweetener","Beverages, coffee and cocoa, instant, decaffeinated, with whitener and low calorie sweetener"
|
589 |
+
CocaCola products,"Beverages, carbonated, reduced sugar, cola, contains caffeine and sweeteners","Beverages, carbonated, reduced sugar, cola, contains caffeine and sweeteners"
|
590 |
+
Yellow bags,Non-Food Item,Non-Food Item
|
591 |
+
pop tarts bites,"Toaster pastries, brown-sugar-cinnamon","Toaster pastries, brown-sugar-cinnamon"
|
592 |
+
Lollipops,"Candy, lollipop","Candy, lollipop"
|
593 |
+
lactaid milk,"Milk, human","Milk, human"
|
594 |
+
probiotic drinks,"Yogurt, plain, whole milk","Yogurt, plain, whole milk"
|
595 |
+
Assorted cereal,"Cereal, other, NFS","Cereal, other, NFS"
|
596 |
+
taco sauce,Taco sauce,Taco sauce
|
597 |
+
"seasoning, brownie mixes","Baking chocolate, unsweetened, squares","Baking chocolate, unsweetened, squares"
|
598 |
+
Sweet Potaotes,"Sweet potato, NFS","Sweet potato, NFS"
|
599 |
+
"Snacks, graham crackers, plain or honey",Cereal or granola bar (Quaker Granola Bites),Cereal or granola bar (Quaker Granola Bites)
|
600 |
+
misc. veg.,Mixed Vegetables,Mixed Vegetables
|
601 |
+
"groceries, sports drink,cleaning",Assorted Groceries,Assorted Groceries
|
602 |
+
Tongs,"Grits, NFS",Tongue
|
603 |
+
Bags,Non-Food Item,Non-Food Item
|
604 |
+
non-food;baby,Non-Food Item,Non-Food Item
|
605 |
+
Chicken Dumplings,Chicken or turkey with dumplings,Chicken or turkey with dumplings
|
606 |
+
tootsie pops,"Candies, chocolate, dark, NFS (45-59% cacao solids 90%; 60-69% cacao solids 5%; 70-85% cacao solids 5%)","Candies, chocolate, dark, NFS (45-59% cacao solids 90%; 60-69% cacao solids 5%; 70-85% cacao solids 5%)"
|
607 |
+
Crab Cakes,"Crab, cake",Crab
|
608 |
+
RKT,"Snacks, KELLOGG, KELLOGG'S RICE KRISPIES TREATS Squares","Snacks, KELLOGG, KELLOGG'S RICE KRISPIES TREATS Squares"
|
609 |
+
assorted breakfast bars,"Breakfast bar, NFS","Breakfast bar, NFS"
|
610 |
+
Silk almond milk,"Almond milk, unsweetened","Almond milk, unsweetened"
|
611 |
+
coffee mate,"Coffee, Cafe Mocha","Coffee, Cafe Mocha"
|
612 |
+
Misc Loads-CVS,Energy drink (No Fear Motherload),Energy drink (No Fear Motherload)
|
613 |
+
reclaimed food,Assorted Foods,Assorted Foods
|
614 |
+
adult hygiene,Non-Food Item,Non-Food Item
|
615 |
+
misc. food,Mixed Food Items,Mixed Food Items
|
616 |
+
presto,Queso Asadero,Queso cotija
|
617 |
+
apple pies,"Pie, apple","Pie, apple"
|
618 |
+
ground pork,"pork, ground, raw","pork, ground, raw"
|
619 |
+
skinny popcorn,"Popcorn, NFS","Popcorn, NFS"
|
620 |
+
"coffee,creamer,half","Coffee creamer, NFS",Coffee creamer
|
621 |
+
"half,condensed milk,breakfast drink","Milk, canned, condensed, sweetened","Milk, canned, condensed, sweetened"
|
622 |
+
peanut butter crackers,"Crackers, sandwich, peanut butter filled","Crackers, sandwich, peanut butter filled"
|
623 |
+
watermellons,"Watermelon, raw","Watermelon, raw"
|
624 |
+
Marshmallows,"Candies, marshmallows","Candies, marshmallows"
|
625 |
+
duck eggs,"Eggs, whole","Eggs, whole"
|
626 |
+
frozen burritos,"Burrito, bean and cheese, frozen","Burrito, bean and cheese, frozen"
|
627 |
+
canned jalapenos,"Jalapenos, NFS","Peppers, jalapeno, canned, solids and liquids"
|
628 |
+
Misc Office Supplies,Misc Items,Non-Food Item
|
629 |
+
Misc Office Furniture,Miscellaneous Items,Miscellaneous Items
|
630 |
+
salad dressing mix,"Salad dressing, light, NFS","Salad dressing, light, NFS"
|
631 |
+
pancake mix,"Cake, yellow, light, dry mix","Cake, yellow, light, dry mix"
|
632 |
+
soy milk,Soy milk,Soy milk
|
633 |
+
ravioli,"Ravioli, meat-filled, no sauce","Ravioli, meat-filled, no sauce"
|
634 |
+
brownie mix,"Cookies, brownies, commercially prepared","Cookies, brownies, commercially prepared"
|
635 |
+
alfredo cream sauce,Alfredo sauce,Alfredo sauce
|
636 |
+
snack crackers,"Crackers, NFS","Crackers, NFS"
|
637 |
+
frozen fruits,"Fruit mixture, frozen","Fruit mixture, frozen"
|
638 |
+
tomato pesto sauce,Pesto sauce,Pesto sauce
|
639 |
+
pretzel rods,"Snacks, pretzels, hard, plain, made with unenriched flour, salted","Snacks, pretzels, hard, plain, made with unenriched flour, salted"
|
640 |
+
meat patties,"Beef, ground, 95% lean meat / 5% fat, patty, cooked, broiled","Beef, ground, 95% lean meat / 5% fat, patty, cooked, broiled"
|
641 |
+
mix produce,Mixed Produce,Mixed Produce
|
642 |
+
evaperated milk,"Milk, evaporated, whole","Milk, evaporated, whole"
|
643 |
+
stir fry noodles,"Noodles, vegetable, cooked","Noodles, vegetable, cooked"
|
644 |
+
vegs.,"Vegetables, mixed, frozen, unprepared","Vegetables, mixed, frozen, unprepared"
|
645 |
+
vegan milk,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
646 |
+
Misc Non Food,Mixed Food Items,Mixed Food Items
|
647 |
+
Beef Taco Meat,"Taco, corn tortilla, beef, cheese","Beef taco filling: beef, cheese, tomato, taco sauce"
|
648 |
+
tomatores,"Tomatoes, raw","Tomatoes, raw"
|
649 |
+
v-8 splash,"Beverages, V8 SPLASH Juice Drinks, Diet Tropical Blend","Beverages, V8 SPLASH Juice Drinks, Diet Tropical Blend"
|
650 |
+
turkey gravy,Turkey with gravy,Turkey with gravy
|
651 |
+
jerky misc grocery,Beef jerky,Beef jerky
|
652 |
+
baguettes,Bagel,Bagel
|
653 |
+
Fresh Apples,"APPLES, RED DELICIOUS","APPLES, RED DELICIOUS"
|
654 |
+
Baker's Potatoes,"Potato, baked, NFS","Potato, baked, NFS"
|
655 |
+
misc -dairy,Mixed Food Items,Mixed Food Items
|
656 |
+
prepared salads,"Salad dressing, russian dressing, low calorie","Salad dressing, russian dressing, low calorie"
|
657 |
+
caramel sace,"Candies, caramels","Candies, caramels"
|
658 |
+
beef roasts,"Beef, roast","Beef, roast"
|
659 |
+
tostitos,"Tomato products, canned, sauce, with tomato tidbits","Tomato products, canned, sauce, with tomato tidbits"
|
660 |
+
cheetoe,Cheese flavored corn snacks (Cheetos),Cheese flavored corn snacks (Cheetos)
|
661 |
+
"misc drinks,grocery,dairy",Assorted Groceries,Assorted Groceries
|
662 |
+
"Bread, ref dough","Cookie, batter or dough, raw","Cookie, batter or dough, raw"
|
663 |
+
vegan wrap,Vegetable sandwich wrap,Vegetable sandwich wrap
|
664 |
+
organic heads of lettuce,"Lettuce, cos or romaine, raw","Lettuce, cos or romaine, raw"
|
665 |
+
Crab,Crab,Crab
|
666 |
+
frozen cheese stuffed pretzels,"Pretzels, hard, cheese filled","Pretzels, hard, cheese filled"
|
667 |
+
"snacks,tea,popcorn,donuts,pasta,icecream",Mixed Food Items,Mixed Food Items
|
668 |
+
Cat Food,"Hot dog, meat and poultry","Hot dog, meat and poultry"
|
669 |
+
mini pretzels,"Pretzels, NFS","Pretzels, NFS"
|
670 |
+
chocolate covered mini pretzels,"Pretzels, NFS","Pretzels, NFS"
|
671 |
+
pumpkin pies,"Pie, pumpkin","Pie, pumpkin"
|
672 |
+
bubly flav. water,"Water, carbonated, plain","Water, carbonated, flavored"
|
673 |
+
rockstar energy drink,"Beverages, Energy drink, ROCKSTAR","Beverages, Energy drink, ROCKSTAR"
|
674 |
+
broth bases,"Soup, beef broth or bouillon, powder, dry","Soup, beef broth or bouillon, powder, dry"
|
675 |
+
dip mix,"Spices, celery seed","Spices, celery seed"
|
676 |
+
misc vegs,Misc Vegetables,Misc Vegetables
|
677 |
+
assorted sweet rolls,"Roll, sweet, frosted","Roll, sweet, frosted"
|
678 |
+
toast,Shrimp toast,Melba toast
|
679 |
+
"vegs,chips,nuts,syrup,pet food",Mixed Food Items,Mixed Food Items
|
680 |
+
protien powder,"Nutritional powder mix, high protein, NFS","Nutritional powder mix, high protein, NFS"
|
681 |
+
"Cookies, snickerdoodle","Babyfood, cookies","Babyfood, cookies"
|
682 |
+
ripple drinks,"Alcoholic beverage, liqueur, coffee with cream, 34 proof","Alcoholic beverage, liqueur, coffee with cream, 34 proof"
|
683 |
+
boneless ribeye beef roast,"beef, ribeye steak, boneless","beef, ribeye steak, boneless"
|
684 |
+
assorted flavored dried fruit chips,"Corn chips, flavored","Candy, fruit flavored pieces"
|
685 |
+
Holiday Decorations,"Chrysanthemum, garland, raw",Non-Food Item
|
686 |
+
misc prod.,Misc Produce,Misc Produce
|
687 |
+
coffee. baby food,"Babyfood, cereal, oatmeal, with honey, dry","Babyfood, cereal, oatmeal, with honey, dry"
|
688 |
+
Personal Hygiene Items,Non-Food Item,Non-Food Item
|
689 |
+
soup bases,"Soup, beef broth or bouillon, powder, prepared with water","Soup, beef broth or bouillon, powder, prepared with water"
|
690 |
+
pringle chips,"Potato chips, NFS","Potato chips, NFS"
|
691 |
+
canteloupes,"Cantaloupe, raw","Cantaloupe, raw"
|
692 |
+
Assorted CVS,Mixed Food Items,Non-Food Item
|
693 |
+
apple juice,"Fruit juice, NFS","Fruit juice, NFS"
|
694 |
+
chicken thighs,"Chicken, broilers or fryers, dark meat, thigh, meat only, raw","Chicken, broilers or fryers, dark meat, thigh, meat only, raw"
|
695 |
+
snickerdoodle cookies,"Cookie, batter or dough, raw","Cookie, batter or dough, raw"
|
696 |
+
sunchips,"Snacks, tortilla chips, nacho cheese","Snacks, tortilla chips, nacho cheese"
|
697 |
+
Assorted Fresh Produce,Assorted Fruit and Veg,Assorted Produce
|
698 |
+
corn on cob,"Corn, sweet, yellow, raw","Corn, sweet, yellow, raw"
|
699 |
+
assorted lettuce,"Lettuce, raw","Lettuce, raw"
|
700 |
+
cauliflour,"Cauliflower, raw","Cauliflower, raw"
|
701 |
+
Emeral nuts,"Nuts, mixed nuts, oil roasted, with peanuts, lightly salted","Nuts, mixed nuts, oil roasted, with peanuts, lightly salted"
|
702 |
+
breakfast,"Breakfast pastry, NFS","Breakfast pastry, NFS"
|
703 |
+
"summer sausage, chicken sausage",Beef sausage,Beef sausage
|
704 |
+
ched. cheese crackers,"Crackers, cheese","Crackers, cheese"
|
705 |
+
dill pickles,"Pickles, dill","Pickles, dill"
|
706 |
+
"milk,cheese,yogurt,soup,pizza,hebs,misc groc",Mixed Food Items,Mixed Food Items
|
707 |
+
"drinks,plant based,breads,desserts,produce",Mixed Food Items,Mixed Food Items
|
708 |
+
begetabes,"Vegetables, mixed, canned, drained solids",Non-Food Item
|
709 |
+
Juice Concentrate,Raspberry juice concentrate,Raspberry juice concentrate
|
710 |
+
"coffe,babyfood","Beverages, coffee, instant, decaffeinated, prepared with water","Beverages, coffee, instant, decaffeinated, prepared with water"
|
711 |
+
"vitamins,coffeemate,hot choc. mix","Fruit juice drink, with high vitamin C","Fruit flavored drink, with high vitamin C"
|
712 |
+
ships,"Dock, raw",Non-Food Item
|
713 |
+
rice a roni,"Rice, white, medium-grain, enriched, cooked","Rice, white, medium-grain, enriched, cooked"
|
714 |
+
steak,"Beef, steak, NFS","Beef, steak, NFS"
|
715 |
+
misc breakfast,Mixed Food Items,Mixed Food Items
|
716 |
+
pretzel crisps,"Pretzels, soft","Pretzels, soft"
|
717 |
+
fresh corn,"Corn, raw","Corn, raw"
|
718 |
+
pie crust base,"Pie crust, standard-type, frozen, ready-to-bake, enriched, baked","Pie crust, standard-type, frozen, ready-to-bake, enriched, baked"
|
719 |
+
simply lemonade,"Lemon juice, raw","Lemon juice, raw"
|
720 |
+
Kimchee,Kimchi,Kimchi
|
721 |
+
prot. bars.[asta.saice.spda.water.snacks,Nutrition bar (Snickers Marathon Protein Bar),"Snacks, granola bar, with coconut, chocolate coated"
|
722 |
+
Clothes,Non-Food Item,Non-Food Item
|
723 |
+
Misc. dairy-grocery-drinks,Mixed Food Items,Mixed Food Items
|
724 |
+
face mask,"Fungi, Cloud ears, dried",Non-Food Item
|
725 |
+
deviled egg kits,"Egg, whole, cooked, scrambled",Non-Food Item
|
726 |
+
grass milk,"Milk, whole, 3.25% milkfat, without added vitamin A and vitamin D","Milk, whole, 3.25% milkfat, without added vitamin A and vitamin D"
|
727 |
+
sliced cake,"Cake, angelfood, commercially prepared","Cake, angelfood, commercially prepared"
|
728 |
+
Nestle water,"Water, non-carbonated, bottles, natural fruit flavors, sweetened with low calorie sweetener",Non-Food Item
|
729 |
+
frozen cookies,"Cookies, chocolate chip, prepared from recipe, made with margarine","Cookies, chocolate chip, prepared from recipe, made with margarine"
|
730 |
+
box mixes,"Bread, cornbread, dry mix, unenriched (includes corn muffin mix)","Bread, cornbread, dry mix, unenriched (includes corn muffin mix)"
|
731 |
+
KOE organic watermelon Kombucha,"Tea, kombucha","Tea, kombucha"
|
732 |
+
Heavy cream,heavy cream,heavy cream
|
733 |
+
cheesy frie chip,"Potato, french fries, fast food","Potato, french fries, fast food"
|
734 |
+
"Beef, base, dehydrated","Beef, stew meat",Beef jerky
|
735 |
+
misc health,"Beverages, Mixed vegetable and fruit juice drink, with added nutrients","Beverages, Mixed vegetable and fruit juice drink, with added nutrients"
|
736 |
+
misc returned items,Misc Items,Misc Items
|
737 |
+
package tea,"Beverages, tea, black, brewed, prepared with tap water","Beverages, tea, black, brewed, prepared with tap water"
|
738 |
+
plant based nuggets,"Chicken nuggets, from other sources","Chicken nuggets, from other sources"
|
739 |
+
KEO probiotic Kombucha,Mixed Food Items,Kombucha
|
740 |
+
frozen meals,"Frozen dinner, NFS","Frozen dinner, NFS"
|
741 |
+
canned coffee drinks,"Coffee, bottled/canned","Coffee, bottled/canned"
|
742 |
+
Starbuck coffee,"Beverages, coffee, brewed, prepared with tap water","Beverages, coffee, brewed, prepared with tap water"
|
743 |
+
mixed dairy,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
744 |
+
misc snacks-groc.-meat,"Snacks, popcorn, cakes",Assorted Foods
|
745 |
+
"seafood,soup,bagels,cakes,misc groc",Mixed Food Items,Mixed Food Items
|
746 |
+
smoothie fruit cubes,"Fruit smoothie, NFS","Fruit smoothie, NFS"
|
747 |
+
mac bites,"McDONALD'S, Chicken McNUGGETS","McDONALD'S, Chicken McNUGGETS"
|
748 |
+
choc syrup,Chocolate syrup,Chocolate syrup
|
749 |
+
Cliff bars,Cereal or granola bar (KIND Fruit and Nut Bar),Cereal or granola bar (KIND Fruit and Nut Bar)
|
750 |
+
AA Batteries,"Fruit punch, alcoholic",Non-Food Item
|
751 |
+
cereal crumbs,Graham crackers,Graham crackers
|
752 |
+
baby diapers,Baby Toddler crunchies,Baby Toddler crunchies
|
753 |
+
mutri bars,"Snack bar, oatmeal","Snack bar, oatmeal"
|
754 |
+
hot choc. baby food,"Babyfood, cookie, baby, fruit","Babyfood, cookie, baby, fruit"
|
755 |
+
misc groc.-snacks-drinks,Misc Grocery,Misc Grocery
|
756 |
+
entres,"Chicken, broilers or fryers, meat and skin and giblets and neck, raw","Chicken, broilers or fryers, meat and skin and giblets and neck, raw"
|
757 |
+
almond butter,Almond butter,Almond butter
|
758 |
+
soft soap,Non-Food Item,Non-Food Item
|
759 |
+
coctail cucumbers,"Cucumber, peeled, raw","Cucumber, peeled, raw"
|
760 |
+
milo tea,"Beverages, tea, instant, unsweetened, powder","Beverages, tea, instant, unsweetened, powder"
|
761 |
+
plant based protien,"Vegetarian chili, made with meat substitute","Meat substitute, cereal- and vegetable protein-based, fried"
|
762 |
+
dark choc. peanut butter cups,"Candies, REESE'S Peanut Butter Cups","Candies, REESE'S Peanut Butter Cups"
|
763 |
+
green grapes,"Grapes, raw","Grapes, raw"
|
764 |
+
small cucumbers,"Cucumber, peeled, raw","Cucumber, with peel, raw"
|
765 |
+
bulk baby cereal,"Baby Toddler cereal, NFS","Baby Toddler cereal, NFS"
|
766 |
+
celery hearts,"celery, raw","celery, raw"
|
767 |
+
vanilla yogurt,"Frozen yogurt, vanilla","Frozen yogurt, vanilla"
|
768 |
+
shredded chicken,"Chicken, ground, raw","Chicken, ground, raw"
|
769 |
+
fruit drinks,Fruit juice drink,Fruit juice drink
|
770 |
+
Paw patrol graham crackers,"Cookies, graham crackers, plain or honey (includes cinnamon)","Cookies, graham crackers, plain or honey (includes cinnamon)"
|
771 |
+
SHRIMP-CHICK-TURKEY BASES,"Salt, table","Salt, table"
|
772 |
+
ondiments,"Salad dressing, mayonnaise, regular","Salad dressing, mayonnaise, regular"
|
773 |
+
shredded lettuce,"Lettuce, raw","Lettuce, raw"
|
774 |
+
cold coffee drinks,"Iced Coffee, brewed","Iced Coffee, brewed"
|
775 |
+
cheetos popcorn,"Popcorn, NFS","Popcorn, NFS"
|
776 |
+
canned diced green chilis,"Peppers, chili, green, canned","Peppers, chili, green, canned"
|
777 |
+
star fruit,"Starfruit, raw","Starfruit, raw"
|
778 |
+
assorted drinks,"Soft drink, NFS","Soft drink, NFS"
|
779 |
+
schredded lettuce,"Lettuce, cooked","Lettuce, raw"
|
780 |
+
misc breakfast foods,"Pancakes, plain, dry mix, complete (includes buttermilk)","Pancakes, plain, dry mix, complete (includes buttermilk)"
|
781 |
+
heinze ketchup,"Ketchup, restaurant","Ketchup, restaurant"
|
782 |
+
Cold coffee,"Iced Coffee, brewed","Iced Coffee, brewed"
|
783 |
+
cobb salade,"Cobb salad, no dressing","Cobb salad, no dressing"
|
784 |
+
peopel,"Eppaw, raw","Pineapple, raw"
|
785 |
+
protien shake,"Beverages, Protein powder whey based","Beverages, Protein powder whey based"
|
786 |
+
sour cr.,"Sour cream, reduced fat","Sour cream, reduced fat"
|
787 |
+
Nestle strawberry milk,"Strawberry milk, NFS","Strawberry milk, NFS"
|
788 |
+
Zevia Soda,"Beverages, ZEVIA, cola","Beverages, ZEVIA, cola"
|
789 |
+
organic blackberries,"Blackberries, raw","Blackberries, raw"
|
790 |
+
misc food-non food,Mixed Food Items,Mixed Food Items
|
791 |
+
"Mixed fruit tray, with strawberries, grapes, melon, and pineapple","Fruit salad, (peach and pear and apricot and pineapple and cherry), canned, juice pack, solids and liquids","Fruit salad, (peach and pear and apricot and pineapple and cherry), canned, juice pack, solids and liquids"
|
792 |
+
green onions,"Onions, green, raw","Onions, green, raw"
|
793 |
+
rice meal pkgs.,"Rice, white, long-grain, regular, raw, unenriched","Rice, white, long-grain, regular, raw, unenriched"
|
794 |
+
misc stacks,Mixed Food Items,Mixed Food Items
|
795 |
+
"beef roasts,desserts,entres,pasta,rice",Mixed Food Items,Non-Food Item
|
796 |
+
veg.,"Vegetables, mixed, canned, drained solids","Vegetables, mixed, canned, drained solids"
|
797 |
+
granola bites,"Cereal, granola","Cereal, granola"
|
798 |
+
english muffins,"Muffin, English","Muffin, English"
|
799 |
+
biscuit roll ups,"Biscuits, plain or buttermilk, prepared from recipe","Biscuits, plain or buttermilk, prepared from recipe"
|
800 |
+
mango juice drink,"Beverages, V8 SPLASH Juice Drinks, Mango Peach",Fruit juice drink
|
801 |
+
oyster crackers,"Crackers, oyster","Crackers, oyster"
|
802 |
+
ginger roodt beer,"Soft drink, ginger ale","Soft drink, ginger ale"
|
803 |
+
power strips,"BURGER KING, Chicken Strips","BURGER KING, Chicken Strips"
|
804 |
+
frozen vegs.,"Vegetables, mixed, frozen, cooked, boiled, drained, with salt","Vegetables, mixed, frozen, cooked, boiled, drained, with salt"
|
805 |
+
misc dry food items,Assorted Edible Items,Assorted Edible Items
|
806 |
+
boods,Papad,Papad
|
807 |
+
copy paper,Rice paper,Non-Food Item
|
808 |
+
quik strawberry drink,"Strawberries, raw","Strawberries, raw"
|
809 |
+
rice meals,"Rice, cooked, NFS","Rice, white, long-grain, regular, raw, enriched"
|
810 |
+
cut pineapple in bags,"Pineapple, raw, extra sweet variety","Pineapple, raw, extra sweet variety"
|
811 |
+
soup cups w,"Potato soup, cream of, prepared with milk","Potato soup, cream of, prepared with milk"
|
812 |
+
baby snacks,"Baby Toddler snack, NFS","Baby Toddler snack, NFS"
|
813 |
+
"Beverages, high protein, ready to drink","Nutritional drink or shake, ready-to-drink, NFS","Nutritional drink or shake, ready-to-drink, NFS"
|
814 |
+
"non food,misc grocery,chips,fruit snacks",Assorted Edible Items,Assorted Edible Items
|
815 |
+
red bell peppers,"peppers, bell, red, raw","peppers, bell, red, raw"
|
816 |
+
meat bowls,"Beef, ground","Beef, ground"
|
817 |
+
cupcakes,"Cake or cupcake, NFS","Cake or cupcake, NFS"
|
818 |
+
brisket hot dogs,"Beef, brisket","Beef, brisket"
|
819 |
+
veg. pocket pies,"Beef Pot Pie, frozen entree, prepared","Beef Pot Pie, frozen entree, prepared"
|
820 |
+
diced vegetables,"Vegetables, mixed, frozen, cooked, boiled, drained, with salt",Mixed Vegetables
|
821 |
+
cranberries,"Cranberries, raw","Cranberries, raw"
|
822 |
+
frozen mashed potatoes,"Potatoes, mashed, ready-to-eat","Potatoes, mashed, ready-to-eat"
|
823 |
+
"Crackers, plain, a7 highlights","Crackers, melba toast, plain","Crackers, melba toast, plain"
|
824 |
+
cremer,"Cream, fluid, heavy whipping","Cream, fluid, heavy whipping"
|
825 |
+
cucumers,"Cucumber, raw","Cucumber, raw"
|
826 |
+
mixed lettuce-grapes-tomatoes,"Vegetables, mixed, canned, drained solids","Vegetables, mixed, canned, drained solids"
|
827 |
+
mrice,Non-Food Item,Rice
|
828 |
+
dondiments,"Salad dressing, mayonnaise, regular","Salad dressing, mayonnaise, regular"
|
829 |
+
canned pineapple,"Pineapple, canned, NFS","Pineapple, canned, NFS"
|
830 |
+
milo energy drink,Energy Drink,Energy Drink
|
831 |
+
protien shake mix,"Beverages, Protein powder whey based","Beverages, Protein powder whey based"
|
832 |
+
banas,"Banana, raw","Banana, raw"
|
833 |
+
mixed vegs,Mixed Fruits and Vegetables,Mixed Vegetables
|
834 |
+
gr. onion,"Onions, raw","Onions, raw"
|
835 |
+
Vanilla ice cream cones,"Ice creams, vanilla","Ice creams, vanilla"
|
836 |
+
disinfeting wipes,Non-Food Item,Non-Food Item
|
837 |
+
vanilla cones,"Ice cream cone, scooped, vanilla","Ice cream cone, scooped, vanilla"
|
838 |
+
gatoade,"Sports drink, low calorie (Gatorade G2)","Sports drink, low calorie (Gatorade G2)"
|
839 |
+
plant thins,"Peas, green, raw","Bean sprouts, raw"
|
840 |
+
chopped broc,"Broccoli, cooked, as ingredient","Broccoli, cooked, as ingredient"
|
841 |
+
"cauliflower, pizza pockets","White pizza, cheese, with meat and vegetables, thick crust","White pizza, cheese, with meat and vegetables, thick crust"
|
842 |
+
chocolate milk,"Chocolate milk, NFS","Chocolate milk, NFS"
|
843 |
+
fruit smoothie cubes,"Fruit smoothie, NFS","Fruit smoothie, NFS"
|
844 |
+
plant based chicken nuggets,"Fast foods, chicken tenders","Fast foods, chicken tenders"
|
845 |
+
protein mix,"Nutritional powder mix, protein, NFS","Nutritional powder mix, protein, NFS"
|
846 |
+
misc baby,"Mixed salad greens, raw","Mixed salad greens, raw"
|
847 |
+
cocoa mix,"Beverages, Cocoa mix, powder","Beverages, Cocoa mix, powder, prepared with water"
|
848 |
+
PB creamer,"Coffee creamer, NFS","Coffee creamer, NFS"
|
849 |
+
niagra water,"Water, carbonated, plain","Water, carbonated, plain"
|
850 |
+
pecan milk,"Pie, pecan","Pie, pecan"
|
851 |
+
misc bread,"Bread, wheat","Bread, wheat"
|
852 |
+
sausage patties,"Sausage, NFS",Pork sausage
|
853 |
+
breakfast burrito,"Burrito, NFS","Burrito, NFS"
|
854 |
+
blax milk,"Milk, NFS","Milk, NFS"
|
855 |
+
powerade drinks,Sports drink (Powerade),Sports drink (Powerade)
|
856 |
+
club crackers,"Crackers, cheese, sandwich-type with peanut butter filling","Crackers, cheese, sandwich-type with peanut butter filling"
|
857 |
+
misc drink mix,"Beverages, Mixed vegetable and fruit juice drink, with added nutrients","Beverages, Mixed vegetable and fruit juice drink, with added nutrients"
|
858 |
+
Evap. milk,"Milk, evaporated, whole","Milk, evaporated, whole"
|
859 |
+
White choc sauce,Dessert sauce,Dessert sauce
|
860 |
+
Cond. milk,"Milk, NFS","Milk, NFS"
|
861 |
+
per hygiene,Non-Food Item,Non-Food Item
|
862 |
+
two seater childs electric cars,Baby Toddler wheels,Baby Toddler wheels
|
863 |
+
turkey wings,"Turkey, whole, wing, meat only, raw","Turkey, whole, wing, meat only, raw"
|
864 |
+
frozen rice sides,"Rice, white, long-grain, regular, raw, enriched","Rice, white, long-grain, regular, raw, enriched"
|
865 |
+
veg. bowls,"Classic mixed vegetables, NS as to form, cooked","Classic mixed vegetables, NS as to form, cooked"
|
866 |
+
deviled eggs,"Egg, deviled","Egg, deviled"
|
867 |
+
ilk,"Milk, whole, 3.25% milkfat, with added vitamin D","Milk, whole, 3.25% milkfat, with added vitamin D"
|
868 |
+
key limes,"Limes, raw","Limes, raw"
|
869 |
+
hot choc. mix,"Beverages, rich chocolate, powder","Beverages, rich chocolate, powder"
|
870 |
+
peach-mango sparkling water,"Beverages, V8 SPLASH Juice Drinks, Mango Peach","Beverages, V8 SPLASH Juice Drinks, Mango Peach"
|
871 |
+
ToFurkey roast,"Tofu, raw, regular, prepared with calcium sulfate","Tofu, raw, regular, prepared with calcium sulfate"
|
872 |
+
PB cheese,"Peanut butter, smooth style, with salt","Peanut butter, smooth style, with salt"
|
873 |
+
"sweets,chips,snack cakes","Snacks, popcorn, cakes",Snacks
|
874 |
+
Food gift boxes from El Lilly Co.,Various Groceries,Various Groceries
|
875 |
+
lunchable meals,Mixed Food Items,Mixed Food Items
|
876 |
+
turkey sticks,"Turkey sticks, breaded, battered, fried","Turkey sticks, breaded, battered, fried"
|
877 |
+
plant based sausage,Hamburger (Burger King),Hamburger (Burger King)
|
878 |
+
salmon,"Fish, salmon, NFS","Fish, salmon, NFS"
|
879 |
+
al. milk,"Milk, NFS","Milk, NFS"
|
880 |
+
chick. bowls,"Chicken, broilers or fryers, meat and skin and giblets and neck, cooked, fried, flour","Chicken, broilers or fryers, meat and skin and giblets and neck, cooked, fried, flour"
|
881 |
+
Popcorners Chips,"Popcorn chips, plain","Popcorn chips, plain"
|
882 |
+
Ripple milk,"Beverages, almond milk, unsweetened, shelf stable","Beverages, almond milk, unsweetened, shelf stable"
|
883 |
+
Plant Based Milk,"Milk, nonfat, fluid, protein fortified, with added vitamin A and vitamin D (fat free and skim)","Milk, nonfat, fluid, with added vitamin A and vitamin D (fat free or skim)"
|
884 |
+
Sprite Regular 16.9oz,"Dessert topping, powdered, 1.5 ounce prepared with 1/2 cup milk","Dessert topping, powdered, 1.5 ounce prepared with 1/2 cup milk"
|
885 |
+
Silk,"SILK Plus Fiber, soymilk","SILK Plus Fiber, soymilk"
|
886 |
+
Dairy Asstd.,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
887 |
+
Dry Goods,"FLOUR, ALL PURPOSE (ENRICHED) (BLEACHED)","FLOUR, ALL PURPOSE (ENRICHED) (BLEACHED)"
|
888 |
+
Sweet Tea,"Tea, hot, herbal","Tea, hot, herbal"
|
889 |
+
Frozen Biscuits,"Biscuits, plain or buttermilk, frozen, baked","Biscuits, plain or buttermilk, frozen, baked"
|
890 |
+
Asstd. Pickles,"Pickles, NFS","Pickles, NFS"
|
891 |
+
Mixed Canned Foods,"Mixed Vegetables, canned",Non-Food Item
|
892 |
+
VARIOUS FLAVORED WATER,"Water, non-carbonated, flavored","Water, non-carbonated, flavored"
|
893 |
+
VARIOUS WATER,"Water, NFS","Water, NFS"
|
894 |
+
Bundaberg Ginger Beer,"Soft drink, ginger ale, diet","Soft drink, ginger ale, diet"
|
895 |
+
dairy products,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
896 |
+
MIsc Non-Food Items,Non-Food Item,Non-Food Item
|
897 |
+
Frozen goods,"Chicken, fried, with potatoes, vegetable, dessert, frozen meal, large meat portion",Frozen meal
|
898 |
+
Asstd Food Products,Assorted Edible Items,Assorted Edible Items
|
899 |
+
Teething Wafers,"Babyfood, snack, GERBER, GRADUATES, YOGURT MELTS","Babyfood, snack, GERBER, GRADUATES, YOGURT MELTS"
|
900 |
+
Frozen Sausage,"Pork sausage, link/patty, fully cooked, unheated","Pork sausage, link/patty, fully cooked, unheated"
|
901 |
+
Snack Puffs,"Cereal, flavored puffs","Cereal, flavored puffs"
|
902 |
+
Hot Sauce,Hot pepper sauce,Hot pepper sauce
|
903 |
+
Assorted Plant Based Milk,"Milk, nonfat, fluid, protein fortified, with added vitamin A and vitamin D (fat free and skim)","Milk, nonfat, fluid, protein fortified, with added vitamin A and vitamin D (fat free and skim)"
|
904 |
+
Fruit Juice Concentrate,Raspberry juice concentrate,Raspberry juice concentrate
|
905 |
+
Breakfast Shake,"Milk shake, fast food, chocolate","Milk shake, fast food, chocolate"
|
906 |
+
Asstd. Pickels,"Pickles, cucumber, dill or kosher dill","Pickles, cucumber, dill or kosher dill"
|
907 |
+
Mixed Products,"Mixed dishes, such as stews, mixed dishes with meat","Mixed dishes, such as stews, mixed dishes with meat"
|
908 |
+
Agua Fresca,"Agave, raw (Southwest)","Agave, raw (Southwest)"
|
909 |
+
Soulboost Drinks,"Beverages, Energy drink, ROCKSTAR","Beverages, Energy drink, ROCKSTAR"
|
910 |
+
Baby Food Asstd.,"Babyfood, dinner, vegetables and noodles and turkey, junior","Babyfood, dinner, vegetables and noodles and turkey, junior"
|
911 |
+
Half-Half,"Cream, fluid, half and half","Cream, fluid, half and half"
|
912 |
+
Assorted Food,Assorted Foods,Assorted Foods
|
913 |
+
Frozen Ham Slices,"Ham, sliced, restaurant","Ham, sliced, restaurant"
|
914 |
+
Mixed Delta goods,Mixed Food Items,Mixed Goods
|
915 |
+
Internation Delight Coffee Creamer,"Coffee creamer, NFS","Coffee creamer, NFS"
|
916 |
+
Assorted Milk product,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
917 |
+
Food,Mixed Food Items,Mixed Food Items
|
918 |
+
International Delight Creamer,SILK Original Creamer,Coffee creamer
|
919 |
+
Iced Tea,Long Island iced tea,Iced Tea
|
920 |
+
Fanta Soft Drinks,"Beverages, carbonated, orange","Beverages, carbonated, orange"
|
921 |
+
Sprite Soft Drinks,"Soft drink, NFS","Soft drink, NFS"
|
922 |
+
Bowls,Non-Food Item,Non-Food Item
|
923 |
+
Mugs,"Candies, REESE'S Peanut Butter Cups","Candies, REESE'S Peanut Butter Cups"
|
924 |
+
Mixed dairy products,"Cereal or granola bar, nonfat","Cereal or granola bar, nonfat"
|
925 |
+
International Delight Coffee Creamer,"Coffee creamer, NFS","Coffee creamer, NFS"
|
926 |
+
Assorted Cheese,"Cheese, cheddar","Cheese, cheddar"
|
927 |
+
PowerWater,"Water, tap","Water, tap"
|
928 |
+
Tissue Paper,Non-Food Item,Non-Food Item
|
929 |
+
Mixed food items,Mixed Food Items,Mixed Food Items
|
930 |
+
household items,Miscellaneous Items,Miscellaneous Items
|
931 |
+
Refrigerated Dough,"Cookies, chocolate chip, refrigerated dough","Cookies, chocolate chip, refrigerated dough"
|
932 |
+
Coffee Drinks Pickles,"Beverages, coffee, brewed, prepared with tap water","Beverages, coffee, brewed, prepared with tap water"
|
933 |
+
Wraps Cheese,"Sandwich wrap, NFS","Sandwich wrap, NFS"
|
934 |
+
Pickles - Dressing,"Pickles, NFS","Pickles, NFS"
|
935 |
+
2% Chocolate Milk,"MILK, 2% ","MILK, 2% "
|
936 |
+
Tumaro's Wraps,"Tortillas, ready-to-bake or -fry, flour, refrigerated","Tortillas, ready-to-bake or -fry, flour, refrigerated"
|
937 |
+
Diary,"Milk, nonfat, fluid, with added vitamin A and vitamin D (fat free or skim)","Milk, nonfat, fluid, with added vitamin A and vitamin D (fat free or skim)"
|
938 |
+
Non dairy milks,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
939 |
+
Asstd Food,Assorted Foods,Assorted Foods
|
940 |
+
Frozen Potato Fries,"Sweet potato fries, frozen","Sweet potato fries, frozen"
|
941 |
+
Drinks Asstd.,Fruit flavored drink,Fruit flavored drink
|
942 |
+
Asstd. Milk,"Milk, NFS","Milk, NFS"
|
943 |
+
OJ,"Fruit juice, NFS","Fruit juice, NFS"
|
944 |
+
Dairy Asstd,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
945 |
+
Milk Asstd,"Milk, NFS","Milk, NFS"
|
946 |
+
Misc. Airplane kitchenware,Non-Food Item,Non-Food Item
|
947 |
+
Antibacterial Wipes,Non-Food Item,Non-Food Item
|
948 |
+
wipes,Non-Food Item,Non-Food Item
|
949 |
+
Pasta Asstd,"Pasta with sauce, NFS","Pasta with sauce, NFS"
|
950 |
+
Plastic Pencil Boxes; 23 lbs,Non-Food Item,Non-Food Item
|
951 |
+
case,"Milk, human",Non-Food Item
|
952 |
+
Simply Juice,"Fruit juice, NFS","Fruit juice, NFS"
|
953 |
+
Flavored Smartwater,"Water, non-carbonated, flavored","Water, non-carbonated, flavored"
|
954 |
+
Mixed frozen food,"Fruit mixture, frozen","Fruit mixture, frozen"
|
955 |
+
Plant Based Cream cheese,"Cream substitute, powdered","Cream substitute, powdered"
|
956 |
+
Assorted frozen,Mixed Food Items,Mixed Food Items
|
957 |
+
chilled foods,Mixed Food Items,Mixed Food Items
|
958 |
+
MM Punch,"Fruit punch, alcoholic","Fruit punch, alcoholic"
|
959 |
+
Simply fruit juices (primarily),"Fruit juice, NFS","Fruit juice, NFS"
|
960 |
+
Assorted Frozen Food,Assorted Edible Items,Assorted Edible Items
|
961 |
+
Gold Peak Tea,"Beverages, tea, instant, unsweetened, prepared with water","Beverages, tea, instant, unsweetened, prepared with water"
|
962 |
+
"Lemonade, low calorie, with non-nutritive sweetener","Water, non-carbonated, bottles, natural fruit flavors, sweetened with low calorie sweetener","Water, non-carbonated, bottles, natural fruit flavors, sweetened with low calorie sweetener"
|
963 |
+
Variety Pack Soda,"Beverages, carbonated, cola, regular","Beverages, carbonated, cola, regular"
|
964 |
+
Dunkin Donuts Coffee Drinks,"Beverages, coffee, brewed, prepared with tap water","Beverages, coffee, brewed, prepared with tap water"
|
965 |
+
Nestle Cookie Dough,"Cookie, batter or dough, raw","Cookie, batter or dough, raw"
|
966 |
+
Some creamer,"Coffee creamer, NFS","Coffee creamer, NFS"
|
967 |
+
Silk Soy,"SILK Plain, soymilk","SILK Plain, soymilk"
|
968 |
+
Utensils,Non-Food Item,Non-Food Item
|
969 |
+
Bleach,Non-Food Item,Non-Food Item
|
970 |
+
Sneakers,Chicken feet,Chicken feet
|
971 |
+
100%,"Apple juice, 100%","Apple juice, 100%"
|
972 |
+
Assorted Pork,"Pork, NFS","Pork, NFS"
|
973 |
+
Women's Hygiene,Non-Food Item,Non-Food Item
|
974 |
+
Shortening,"Shortening, NS as to vegetable or animal","Shortening, NS as to vegetable or animal"
|
975 |
+
cooking oil,"Vegetable oil, NFS","Vegetable oil, NFS"
|
976 |
+
Coffee Products,"Beverages, coffee, instant, mocha, sweetened","Beverages, coffee, instant, mocha, sweetened"
|
977 |
+
Tampons,Non-Food Item,Non-Food Item
|
978 |
+
English cucumbers,"Cucumber, raw","Cucumber, raw"
|
979 |
+
Assorted Product,Assorted Consumables,Assorted Consumables
|
980 |
+
Frozen Entree's,"Chicken dinner, NFS, frozen meal","Frozen dinner, NFS"
|
981 |
+
Containers,"Water, bottled, plain",Non-Food Item
|
982 |
+
Seasoned Canned Beans,"Green beans, canned, cooked with oil","Beans, snap, canned, all styles, seasoned, solids and liquids"
|
983 |
+
Dry Beans,"Beans, Dry, Black (0% moisture)","Beans, Dry, Black (0% moisture)"
|
984 |
+
Sourpatch - Watermelon,"Candies, gumdrops, starch jelly pieces","Candies, gumdrops, starch jelly pieces"
|
985 |
+
Assorted Meat,Assorted Foods,Assorted Foods
|
986 |
+
Bulk Rice,"Rice, white, long-grain, regular, raw, unenriched","Rice, white, long-grain, regular, raw, unenriched"
|
987 |
+
Pop-Tart Bites,"Toaster pastries, brown-sugar-cinnamon","Toaster pastries, brown-sugar-cinnamon"
|
988 |
+
Medicine - Supplements,Cough drops,Cough drops
|
989 |
+
Frozen Dinners,"Frozen dinner, NFS","Frozen dinner, NFS"
|
990 |
+
Assorted Pet Food,"Hot dog, meat and poultry",Assorted Pet Food
|
991 |
+
Medical supplements,Non-Food Item,Non-Food Item
|
992 |
+
protein powder,"Nutritional powder mix, protein, NFS","Nutritional powder mix, protein, NFS"
|
993 |
+
Misc medical supplies,Non-Food Item,Non-Food Item
|
994 |
+
Assorted Grocery - Frozen,Mixed Food Items,Mixed Food Items
|
995 |
+
Whole Chicken,"Chicken, broilers or fryers, meat and skin and giblets and neck, raw","Chicken, broilers or fryers, meat and skin and giblets and neck, raw"
|
996 |
+
Assorted,Assorted Consumables,Assorted Consumables
|
997 |
+
Assorted Dressings,"Salad dressing, thousand island, commercial, regular","Salad dressing, thousand island, commercial, regular"
|
998 |
+
Body Wash,Non-Food Item,Non-Food Item
|
999 |
+
Instant Coffee,"Coffee, instant, reconstituted","Coffee, instant, reconstituted"
|
1000 |
+
Chocolate Syrup,Chocolate syrup,Chocolate syrup
|
1001 |
+
Crystal Light,"Lemonade, powder, prepared with water","Beverages, lemonade-flavor drink, powder, prepared with water"
|
1002 |
+
Skin,Chicken skin,Chicken skin
|
1003 |
+
Cosmetics,Non-Food Item,Non-Food Item
|
1004 |
+
Repack,"Oranges, raw, with peel","Oranges, raw, with peel"
|
1005 |
+
Conditioner,Non-Food Item,Non-Food Item
|
1006 |
+
Hair,"Parsley, raw",Non-Food Item
|
1007 |
+
Disposable,Non-Food Item,Non-Food Item
|
1008 |
+
Appliances,Non-Food Item,Non-Food Item
|
1009 |
+
Microwave Dinners,"Soup, vegetable beef, microwavable, ready-to-serve, single brand","Soup, vegetable beef, microwavable, ready-to-serve, single brand"
|
1010 |
+
Chocolate Chips,Chocolate chips,Chocolate chips
|
1011 |
+
Variety,Mixed Food Items,Mixed Food Items
|
1012 |
+
Powder,Tomato powder,Tomato powder
|
1013 |
+
100% Juice,"Apple juice, 100%","Apple juice, 100%"
|
1014 |
+
2%,"MILK, 2% ","MILK, 2%"
|
1015 |
+
Local Store Produce,Mixed Food Items,Mixed Food Items
|
1016 |
+
Local Store Bakery,"Bread, white, made from home recipe or purchased at a bakery","Bread, white, made from home recipe or purchased at a bakery"
|
1017 |
+
Local Store Dairy,"Non-dairy milk, NFS","Non-dairy milk, NFS"
|
1018 |
+
Local Store Meat,"Meat, ground, NFS","Meat, ground, NFS"
|
1019 |
+
"Paper, Plastic Containers",Non-Food Item,Non-Food Item
|
1020 |
+
Cracker Jacks,"Snacks, popcorn, home-prepared, oil-popped, unsalted","Snacks, popcorn, home-prepared, oil-popped, unsalted"
|
1021 |
+
"Marshmallows, miniature","Candies, marshmallows","Candies, marshmallows"
|
1022 |
+
cashews,"cashews, raw","cashews, raw"
|
1023 |
+
juice boxes,"Fruit juice, NFS","Fruit juice, NFS"
|
1024 |
+
Mess,Mixed Food Items,Mixed Food Items
|
1025 |
+
Packets,"Sweeteners, tabletop, aspartame, EQUAL, packets","Sweeteners, tabletop, aspartame, EQUAL, packets"
|
1026 |
+
Quaker,"Cereals ready-to-eat, QUAKER, QUAKER Honey Graham LIFE Cereal","Cereals ready-to-eat, QUAKER, QUAKER Honey Graham LIFE Cereal"
|
1027 |
+
Pita,"Bread, pita","Bread, pita"
|
1028 |
+
Any Type,Mixed Food Items,Mixed Food Items
|
1029 |
+
40ct,"Celtuce, raw",Non-Food Item
|
1030 |
+
32ct,"Celtuce, raw","Celtuce, raw"
|
1031 |
+
24ct,"Proximates, Salsa, PACE CHUNKY, MEDIUM (CA2,NC) - NFY090KXS",Non-Food Item
|
1032 |
+
Cans,"Tomatoes, canned",Non-Food Item
|
1033 |
+
"Potatoes, Refrigerated, Sliced","Potatoes, hash brown, frozen, plain, unprepared","Potatoes, hash brown, frozen, plain, unprepared"
|
1034 |
+
20oz,"Peppers, sweet, green, raw",Non-Food Item
|
1035 |
+
"Entrees, Bagged Meal",Mixed Dishes with Meat,Mixed Dishes with Meat
|
1036 |
+
"No Meat, Refrigerated",Mixed Food Items,Mixed Food Items
|
1037 |
+
Local Store Frozen (Non-Meat),Assorted Foods,Frozen meal
|
1038 |
+
"Condiments, Jam","Salad dressing, mayonnaise, regular",Jams and preserves
|
1039 |
+
1%,"MILK, 1%","MILK, 1%"
|
1040 |
+
All purpose,"FLOUR, ALL PURPOSE (ENRICHED) (BLEACHED)","FLOUR, ALL PURPOSE (ENRICHED) (BLEACHED)"
|
1041 |
+
Disposable bags,Non-Food Item,Non-Food Item
|
1042 |
+
Saltines,"Crackers, saltine","Crackers, saltine"
|
1043 |
+
Patties,"Double cheeseburger, from fast food, 2 small patties","Double cheeseburger, from fast food, 2 small patties"
|
1044 |
+
Club,Canadian Club and soda,"Club sandwich or sub, restaurant"
|
1045 |
+
Filter Packs,Non-Food Item,Non-Food Item
|
1046 |
+
Capsules,Non-Food Item,Non-Food Item
|
1047 |
+
Spaghetti Sauce,Spaghetti sauce,Spaghetti sauce
|
1048 |
+
"Lunchables, Meat","Luncheon meat, NFS","Luncheon meat, NFS"
|
1049 |
+
Cottage,"Cheese, cottage, NFS",Cottage cheese
|
1050 |
+
Jump Start Breakfast Kits,Assorted Edible Items,Assorted Edible Items
|
1051 |
+
Nut Butter,Almond butter,Almond butter
|
1052 |
+
In Syrup,"Syrup, NFS","Syrup, NFS"
|
1053 |
+
Pouches,"Snacks, fruit leather, pieces",Snacks
|
1054 |
+
Shallots,"Shallots, raw","Shallots, raw"
|
1055 |
+
Liquid,"Water, NFS","Water, NFS"
|
1056 |
+
Toddler Foods,"Baby Toddler food, NFS","Baby Toddler food, NFS"
|
1057 |
+
Grounds,"Turkey, Ground, raw",Non-Food Item
|
1058 |
+
Repack adjustment,Meat extender,Non-Food Item
|
1059 |
+
"wafers, Repack","Cookies, sugar wafers with creme filling, regular","Cookies, sugar wafers with creme filling, regular"
|
1060 |
+
85% Lean,"Beef, ground, 70% lean meat / 30% fat, raw","Beef, ground, 80% lean meat / 20% fat, raw"
|
1061 |
+
Holiday,"Sandwich, NFS",Non-Food Item
|
1062 |
+
Canned Goods,Mixed Food Items,Mixed Food Items
|
1063 |
+
Community,Non-Food Item,Non-Food Item
|
1064 |
+
Gallon,"Hamburger, from fast food, 1 large patty",Non-Food Item
|
1065 |
+
2-Pack,"Cereals ready-to-eat, wheat, puffed, fortified",Non-Food Item
|
1066 |
+
Blends,Mixed Food Items,Mixed nuts
|
1067 |
+
Soil,Barley,Barley
|
1068 |
+
Pasta Sides,"Pasta, homemade, made with egg, cooked","Pasta, homemade, made with egg, cooked"
|
1069 |
+
Turkey Legs,"Turkey, all classes, leg, meat and skin, raw","Turkey, all classes, leg, meat and skin, raw"
|
1070 |
+
Wheat,"Bread, wheat","Bread, wheat"
|
1071 |
+
Local Store Grocery,Grocery,Grocery
|
1072 |
+
Assorted Produce,Assorted Produce,Assorted Produce
|
1073 |
+
Link,"Bratwurst, pork, beef, link","Bratwurst, pork, beef, link"
|
1074 |
+
Shelf Stable Strawberry Milk,"Strawberry milk, whole","Strawberry milk, whole"
|
1075 |
+
"Specialty Bread, Garlic, Frozen","Garlic bread, frozen","Garlic bread, frozen"
|
1076 |
+
Bread Bakery Grocery,"Bread, white, made from home recipe or purchased at a bakery","Bread, white, made from home recipe or purchased at a bakery"
|
1077 |
+
#10 Cans,"Tomatoes, canned",Non-Food Item
|
1078 |
+
vegetables assorted,Assorted Vegetables,Assorted Vegetables
|
1079 |
+
Melts,"Melons, cantaloupe, raw","Melons, cantaloupe, raw"
|
1080 |
+
Corn Dogs,Corn dog,Corn dog
|
1081 |
+
Eggnog,Eggnog,Eggnog
|
1082 |
+
Dried Potatoes,"Potatoes, mashed, dehydrated, flakes without milk, dry form","Potatoes, mashed, dehydrated, flakes without milk, dry form"
|
1083 |
+
Monster,Energy drink (Monster),Energy drink (Monster)
|
1084 |
+
Flatbreads,"Crackers, flatbread","Crackers, flatbread"
|
1085 |
+
Misc Beans,"Beans, NFS","Beans, NFS"
|
1086 |
+
GAP Passion City Food Bag,Non-Food Item,Non-Food Item
|
1087 |
+
Maple,"Syrup, maple, Canadian","Syrup, maple, Canadian"
|
1088 |
+
Kool-Aid,"Beverages, fruit-flavored drink, powder, with high vitamin C with other added vitamins, low calorie","Beverages, fruit-flavored drink, powder, with high vitamin C with other added vitamins, low calorie"
|
1089 |
+
Nutrition,"Beverages, Energy Drink, Monster, fortified with vitamins C, B2, B3, B6, B12","Beverages, Energy Drink, Monster, fortified with vitamins C, B2, B3, B6, B12"
|
1090 |
+
Local Store Deli,"Chicken deli sandwich or sub, restaurant","Chicken deli sandwich or sub, restaurant"
|
1091 |
+
With Beans,"Gordita, with beans","Gordita, with beans"
|
1092 |
+
Taco,"Taco, NFS","Taco, NFS"
|
1093 |
+
Ham Hocks,"Pork, ham hocks","Pork, ham hocks"
|
1094 |
+
Sausage Crumble Toppings,"Pork, ground, 96% lean / 4% fat, cooked, crumbles","Pork, ground, 96% lean / 4% fat, cooked, crumbles"
|
1095 |
+
Whole Wheat,"Bread, whole wheat","Bread, whole wheat"
|
1096 |
+
pet bulk,"Pasta, dry, unenriched","Pasta, dry, unenriched"
|
1097 |
+
Toasted Coconut,"Coconut, fresh",Non-Food Item
|
1098 |
+
supplies from mezzanine,Miscellaneous Items,Miscellaneous Items
|
1099 |
+
Mineral,"Salt, table",Non-Food Item
|
1100 |
+
Canned Peas,"Green beans, canned, cooked with oil","Green beans, canned, cooked with oil"
|
1101 |
+
Canned Tomatoes,"Tomatoes, canned","Tomatoes, canned"
|
1102 |
+
Canned Tea,"Tea, hot, herbal","Tea, hot, herbal"
|
1103 |
+
128oz,"Kiwi fruit, raw",Non-Food Item
|
1104 |
+
Round roast,"Beef, roast","Beef, roast"
|
1105 |
+
Cheddar,"Cheese, cheddar","Cheese, cheddar"
|
1106 |
+
Raisins,Raisins,Raisins
|
1107 |
+
Latte,"Coffee, Latte","Coffee, Latte"
|
1108 |
+
Lentils,"Lentils, raw","Lentils, raw"
|
1109 |
+
Strips,"BURGER KING, Chicken Strips","BURGER KING, Chicken Strips"
|
1110 |
+
Buttermilk,"Buttermilk, whole","Buttermilk, whole"
|
1111 |
+
Gelato,"Gelato, vanilla","Gelato, vanilla"
|
1112 |
+
Boneless,"chicken, breast, boneless, skinless",Non-Food Item
|
1113 |
+
Shippers,Grocery Items,Grocery Items
|
1114 |
+
Frozen Kale,"Kale, frozen, unprepared","Kale, frozen, unprepared"
|
1115 |
+
Soda Crackers,"Crackers, saltine","Crackers, saltine"
|
1116 |
+
Craisins,"Raisins, golden, seedless","Raisins, golden, seedless"
|
1117 |
+
"Potatoes, French Fries","Potato, french fries, NFS","Potato, french fries, NFS"
|
1118 |
+
Fruit Bars,"Snack bar, oatmeal","Snack bar, oatmeal"
|
1119 |
+
assorted milk shelf stable,"Milk substitutes, fluid, with lauric acid oil","Milk substitutes, fluid, with lauric acid oil"
|
1120 |
+
Apple Jacks,"Snacks, KELLOGG, KELLOGG'S, NUTRI-GRAIN Cereal Bars, fruit","Cereal, ready-to-eat, NFS"
|
1121 |
+
Kone,"Kohlrabi, raw","Kohlrabi, raw"
|
1122 |
+
Chocolate Sauce,Dessert sauce,Dessert sauce
|
1123 |
+
Dipping Sauce,"Sauce, salsa, ready-to-serve","Sauce, salsa, ready-to-serve"
|
1124 |
+
Paper goods,Rice paper,Rice paper
|
1125 |
+
Purel water,"Water, bottled, generic","Water, bottled, generic"
|
1126 |
+
Assorted Office Supplies,Assorted Consumables,Assorted Consumables
|
1127 |
+
Rockstar Beverages,"Beverages, Energy drink, ROCKSTAR","Beverages, Energy drink, ROCKSTAR"
|
1128 |
+
Eggnogg,"Egg, whole, raw",Eggnog
|
1129 |
+
Cheese Wheels,"Cheese, gouda","Cheese, gouda"
|
1130 |
+
Granola Bars Assorted,"Cereal, granola","Cereal, granola"
|
1131 |
+
Bulk Cheeze Its,"Crackers, melba toast, rye (includes pumpernickel)","Crackers, melba toast, rye (includes pumpernickel)"
|
1132 |
+
Pork Patties,"Pork, cured, ham, patties, unheated","Pork, cured, ham, patties, unheated"
|
1133 |
+
Lettuce Assorted,"Lettuce, raw","Lettuce, raw"
|
1134 |
+
Citrus Assorted,"Lemon, raw","Lemon, raw"
|
1135 |
+
FaceMasks,Pig in a blanket,Non-Food Item
|
1136 |
+
Tomotoes,"Tomatoes, raw","Tomatoes, raw"
|
1137 |
+
Rice Roller Snacks,"Snacks, rice cracker brown rice, plain","Snacks, rice cracker brown rice, plain"
|
1138 |
+
Water 8 oz Bottles,"Water, bottled, plain","Water, bottled, plain"
|
1139 |
+
Masks,"Fungi, Cloud ears, dried","Fungi, Cloud ears, dried"
|
1140 |
+
Pillow Cases,Non-Food Item,Non-Food Item
|
1141 |
+
Milk Assorted,"Milk, NFS","Milk, NFS"
|
1142 |
+
Office,Rice paper,Non-Food Item
|
1143 |
+
Cereal Bulk,"Cereal, other, plain","Cereal, other, plain"
|
1144 |
+
Potatoes Dehydrated,"Potatoes, mashed, dehydrated, granules without milk, dry form","Potatoes, mashed, dehydrated, granules without milk, dry form"
|
1145 |
+
Hawaiian Rolls,"Rolls, french","Rolls, french"
|
1146 |
+
PetFood,"Babyfood, cookie, baby, fruit",PetFood
|
1147 |
+
Instant Potatoes,"Potatoes, mashed, dehydrated, granules without milk, dry form","Potatoes, mashed, dehydrated, granules without milk, dry form"
|
1148 |
+
Mixed Office Supplies,"Nuts, mixed nuts, oil roasted, with peanuts, lightly salted",Non-Food Item
|
1149 |
+
Misc Scacks,"Snacks, popcorn, cakes","Snacks, popcorn, cakes"
|
1150 |
+
Reclamation,Vinegar,Non-Food Item
|
1151 |
+
Misc Office,"Bread, multi-grain (includes whole-grain)",Non-Food Item
|
1152 |
+
Chiken,"Chicken, broilers or fryers, breast, meat and skin, cooked, roasted","Chicken, broilers or fryers, breast, meat and skin, cooked, roasted"
|
1153 |
+
Water Assorted,"Water, NFS","Water, NFS"
|
1154 |
+
Potatoe Pearls,"Potatoes, hash brown, home-prepared","Potatoes, hash brown, home-prepared"
|
1155 |
+
Bars of Soap in 55gal Drums,Non-Food Item,Non-Food Item
|
1156 |
+
Disinfectant,Non-Food Item,Non-Food Item
|
1157 |
+
"Mixed Meat, raw","Meat, ground, NFS",Mixed Food Items
|
1158 |
+
Ham - Some Bulk,"Pork, cured, ham, boneless, extra lean and regular, roasted","Pork, cured, ham, boneless, extra lean and regular, roasted"
|
1159 |
+
Assorted Meats - Bulk Load,"Meat, ground, NFS",Mixed Food Items
|
1160 |
+
Assorted Meats - Some Bulk,"Pork, fresh, leg (ham), rump half, separable lean and fat, cooked, roasted","Pork, fresh, leg (ham), rump half, separable lean and fat, cooked, roasted"
|
1161 |
+
Dinners,"Macaroni and cheese, box mix with cheese sauce, unprepared","Macaroni and cheese, box mix with cheese sauce, unprepared"
|
1162 |
+
Books,Rice paper,Non-Food Item
|
1163 |
+
Pasta Bulk,"Pasta, dry, unenriched","Pasta, dry, unenriched"
|
1164 |
+
Cleaning Supplies,Non-Food Item,Non-Food Item
|
1165 |
+
Misc Office Items,Misc Items,Misc Items
|
1166 |
+
Makeup Products,"Beverages, carbonated, reduced sugar, cola, contains caffeine and sweeteners",Non-Food Item
|
1167 |
+
Beveerages,Mixed Food Items,Non-Food Item
|
1168 |
+
EnergyDrinks,"Beverages, Energy drink, RED BULL, sugar free, with added caffeine, niacin, pantothenic acid, vitamins B6 and B12","Beverages, Energy drink, RED BULL, sugar free, with added caffeine, niacin, pantothenic acid, vitamins B6 and B12"
|
1169 |
+
Coleslaw Mix,Coleslaw,Coleslaw
|
1170 |
+
Clorex Cleaning Wipes,Non-Food Item,Non-Food Item
|
1171 |
+
Soy Meats,Soy nuts,Soy nuts
|
1172 |
+
Eggo Pancakes,"Pancakes, fruit","Pancakes, fruit"
|
1173 |
+
Chips Assorted,"Potato chips, plain","Potato chips, plain"
|
1174 |
+
Vitimins,"applesauce, unsweetened, with vit C added","applesauce, unsweetened, with vit C added"
|
1175 |
+
Breakfast Prepared Meals,Mixed Food Items,Mixed Food Items
|
1176 |
+
Office Binders,Rice paper,Non-Food Item
|
1177 |
+
Misc Mixed Grocery,Misc Grocery,Misc Grocery
|
1178 |
+
Soy Chicken Products,"Chicken, broilers or fryers, light meat, meat only, cooked, roasted","Chicken, broilers or fryers, light meat, meat only, cooked, roasted"
|
1179 |
+
Sanitizer,Non-Food Item,Non-Food Item
|
1180 |
+
MacNCheese,"Macaroni and Cheese, canned entree","Macaroni and Cheese, canned entree"
|
1181 |
+
Assorted Soy Meat Products,Soy protein isolate,Soy protein isolate
|
1182 |
+
Body Armor Beverages,Mixed Food Items,Non-Food Item
|
1183 |
+
Boxed Meals,"Macaroni and cheese, box mix with cheese sauce, unprepared","Macaroni and cheese, box mix with cheese sauce, unprepared"
|
1184 |
+
GranolaBars,"Cereal, granola","Cereal, granola"
|
1185 |
+
Fried Rice Prepared Meals,"Rice, fried, NFS","Rice, fried, NFS"
|
1186 |
+
Home items,Miscellaneous Items,Miscellaneous Items
|
1187 |
+
Napkiins,"Mushrooms, raw","Mushrooms, raw"
|
1188 |
+
Pasta Assorted,"Pasta with sauce, NFS","Pasta with sauce, NFS"
|
1189 |
+
Turkeyy,"Turkey, all classes, back, meat and skin, cooked, roasted","Turkey, all classes, back, meat and skin, cooked, roasted"
|
1190 |
+
Baked Goods,"Bread, white, commercially prepared, toasted","Bread, white, commercially prepared"
|
1191 |
+
Gatorade Beverages,Sports drink (Gatorade G),Sports drink (Gatorade G)
|
1192 |
+
Clorex Wipes,Non-Food Item,Non-Food Item
|
1193 |
+
Misc Grocery Food Drive,Mixed Food Items,Mixed Food Items
|
1194 |
+
Cheese Its Bulk,"Crackers, cheese, regular","Crackers, cheese, regular"
|
1195 |
+
Amnity Kits,Miscellaneous Items,Miscellaneous Items
|
1196 |
+
Crackers Bulk,"Crackers, standard snack-type, regular","Crackers, standard snack-type, regular"
|
1197 |
+
Eggo Pancake Bites,"Pancakes, plain, frozen","Pancakes, plain, frozen"
|
1198 |
+
Churros,Churros,Churros
|
1199 |
+
dogFood,"Hot dog, meat and poultry","Hot dog, meat and poultry"
|
1200 |
+
energy Driinks,"Beverages, Energy drink, RED BULL, sugar free, with added caffeine, niacin, pantothenic acid, vitamins B6 and B12","Beverages, Energy drink, RED BULL, sugar free, with added caffeine, niacin, pantothenic acid, vitamins B6 and B12"
|
1201 |
+
Copier Paper,Rice paper,Rice paper
|
1202 |
+
Graham Crackers Bulk,"Graham crackers, reduced fat","Graham crackers, reduced fat"
|
1203 |
+
Tortillas Assorted,"Tortilla, NFS","Tortilla, NFS"
|
1204 |
+
Houshold Items,Miscellaneous Items,Non-Food Item
|
1205 |
+
Leafy Vegetables,Assorted Vegetables,Assorted Vegetables
|
1206 |
+
Assorted Dry,Mixed Food Items,Mixed Food Items
|
1207 |
+
Frozen Mac N Cheese,"Macaroni and cheese, frozen entree","Macaroni and cheese, frozen entree"
|
1208 |
+
"Mixed dishes, assortment of taiwanese appetizer","Restaurant, Chinese, chicken and vegetables","Mixed dishes, assortment of taiwanese appetizer"
|
1209 |
+
Heat n Serve,Mixed Food Items,Mixed Food Items
|
1210 |
+
Greek Yogurt,"Yogurt, Greek, fruit, whole milk","Yogurt, Greek, fruit, whole milk"
|
1211 |
+
Chicken patties,Chicken Fritters,Chicken Fritters
|
1212 |
+
Cleaining,"Clams, NFS","Clams, NFS"
|
1213 |
+
Cleaning,Screwdriver,Screwdriver
|
1214 |
+
"Dinner rolls, Hawaiian, prepared from recipe, 1 roll","Rolls, dinner, plain, commercially prepared (includes brown-and-serve)","Rolls, dinner, plain, commercially prepared (includes brown-and-serve)"
|
1215 |
+
Pull Apart Cinnamon Rolls,"Sweet rolls, cinnamon, commercially prepared with raisins","Sweet rolls, cinnamon, commercially prepared with raisins"
|
1216 |
+
King Hawaiian Hoagie Rolls,"Rolls, dinner, wheat","Rolls, dinner, wheat"
|
1217 |
+
Pull Apart Dough,"Cookie, batter or dough, raw","Cookie, batter or dough, raw"
|
1218 |
+
Surface Cleaner,Screwdriver,Screwdriver
|
1219 |
+
Creamed Corn Chubs,"Corn, creamed","Corn, creamed"
|
1220 |
+
Dry Wipes,Non-Food Item,Non-Food Item
|
1221 |
+
King Hawaiian Rolls,Ham and cheese loaf or roll,Ham and cheese loaf or roll
|
1222 |
+
Cleaning Spray,Non-Food Item,Non-Food Item
|
1223 |
+
Rancheros,Huevos rancheros,Huevos rancheros
|
1224 |
+
Creamed Corn,"Corn, creamed","Corn, creamed"
|
1225 |
+
Eggwich,Ham biscuit sandwich,Ham biscuit sandwich
|
1226 |
+
Egg Bites,"Turnover, filled with egg, meat and cheese, frozen","Turnover, filled with egg, meat and cheese, frozen"
|
1227 |
+
Fast Bites,"Fast foods, cheeseburger; single, large patty; with condiments, vegetables and mayonnaise","Fast foods, cheeseburger; single, large patty; with condiments, vegetables and mayonnaise"
|
1228 |
+
Fresh Green Beans,"Green beans, raw","Green beans, raw"
|
category_mapper.py
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import csv
|
3 |
+
import json
|
4 |
+
import pandas as pd
|
5 |
+
from tqdm import tqdm
|
6 |
+
from openai import OpenAI
|
7 |
+
from dotenv import load_dotenv
|
8 |
+
|
9 |
+
|
10 |
+
load_dotenv()
|
11 |
+
|
12 |
+
api_key = os.getenv("OPENAI_API_KEY")
|
13 |
+
client = OpenAI(api_key=api_key)
|
14 |
+
|
15 |
+
# Load your Excel file
|
16 |
+
file_path = './dictionary/final_corrected_wweia_food_category_complete - final_corrected_wweia_food_category_complete.csv'
|
17 |
+
spreadsheet = pd.read_csv(file_path)
|
18 |
+
|
19 |
+
def find_best_category(food_item, category, dataframe):
|
20 |
+
filtered_df = dataframe[dataframe['closest_category'] == category]
|
21 |
+
if not filtered_df.empty:
|
22 |
+
descriptions = filtered_df['wweia_food_category_description'].tolist()
|
23 |
+
|
24 |
+
prompt = (
|
25 |
+
f"Given the food item '{food_item}' and the category '{category}', choose the most appropriate category from the following options:\n{descriptions}\n\n"
|
26 |
+
f"You should respond in json format with an object that has the key `guess`, and the value is the categoy."
|
27 |
+
)
|
28 |
+
|
29 |
+
completion = client.chat.completions.create(
|
30 |
+
messages=[
|
31 |
+
{"role": "system", "content": "You are a helpful assistant."},
|
32 |
+
{"role": "user", "content": prompt}
|
33 |
+
],
|
34 |
+
model="gpt-3.5-turbo-1106",
|
35 |
+
response_format={"type": "json_object"},
|
36 |
+
)
|
37 |
+
response = completion.choices[0].message.content
|
38 |
+
parsed = parse_response(response)
|
39 |
+
return parsed
|
40 |
+
|
41 |
+
# Define the function to parse the GPT response
|
42 |
+
def parse_response(response):
|
43 |
+
try:
|
44 |
+
result = json.loads(response)
|
45 |
+
return result['guess']
|
46 |
+
except (json.JSONDecodeError, KeyError) as e:
|
47 |
+
print(f"Error parsing response: {response} - {e}")
|
48 |
+
return None
|
49 |
+
|
50 |
+
# open up the current dictionary csv file
|
51 |
+
csv_file_path = './dictionary/dictionary.csv'
|
52 |
+
df_dictionary = pd.read_csv(csv_file_path)
|
53 |
+
|
54 |
+
for index, row in tqdm(df_dictionary.iterrows(), desc="Processing input words"):
|
55 |
+
# Get the food item and category
|
56 |
+
food_item = row['description']
|
57 |
+
category = row['food_category']
|
58 |
+
|
59 |
+
if pd.notna(row['wweia_category']) and row['wweia_category'] != "" and row['wweia_category'] != "nan" and row is not None:
|
60 |
+
# print(f"Skipping '{food_item}' as it already has a category {row['wweia_category']}")
|
61 |
+
continue
|
62 |
+
else:
|
63 |
+
print(f"Processing '{food_item}'")
|
64 |
+
|
65 |
+
# Find the best category for the food item
|
66 |
+
best_category = find_best_category(food_item, category, spreadsheet)
|
67 |
+
print(f"Q: '{food_item}'")
|
68 |
+
print(f"A: '{best_category}'")
|
69 |
+
print()
|
70 |
+
|
71 |
+
# Update the dictionary.csv file by adding the best category to the wweia_category column
|
72 |
+
if best_category:
|
73 |
+
df_dictionary.loc[index, 'wweia_category'] = best_category
|
74 |
+
|
75 |
+
df_dictionary.to_csv(csv_file_path, index=False)
|
chatgpt_audit.py
ADDED
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import csv
|
3 |
+
import json
|
4 |
+
import time
|
5 |
+
import heapq
|
6 |
+
import pandas as pd
|
7 |
+
from openai import OpenAI
|
8 |
+
from dotenv import load_dotenv
|
9 |
+
from Levenshtein import distance
|
10 |
+
from tqdm import tqdm
|
11 |
+
from db.db_utils import get_connection, store_mapping_to_db, get_mapping_from_db
|
12 |
+
from ask_gpt import query_gpt
|
13 |
+
|
14 |
+
# For any unreviewed mappings, we ask chatgpt to consider:
|
15 |
+
# 1. The similar_words list
|
16 |
+
# 2. Similar words from the dictionary based on small levenstein distance
|
17 |
+
|
18 |
+
# ChatGPT should confirm that the current mapping is the best one. If not, they should provide the better mapping.
|
19 |
+
# If its a Non-Food Item, we should confirm that
|
20 |
+
# If it's a homogenous or hetergeneous mixture, we should confirm that
|
21 |
+
|
22 |
+
load_dotenv()
|
23 |
+
|
24 |
+
api_key = os.getenv("OPENAI_API_KEY")
|
25 |
+
client = OpenAI(api_key=api_key)
|
26 |
+
|
27 |
+
output_file_path = f'./audits/{int(time.time())}.csv'
|
28 |
+
|
29 |
+
def update_csv(results):
|
30 |
+
df_results = pd.DataFrame(results, columns=['input_word', 'original_dictionary_word', 'new_dictionary_word',])
|
31 |
+
df_results.to_csv(output_file_path, index=False)
|
32 |
+
|
33 |
+
def find_close_levenshtein_words(input_word, dictionary, threshold=3):
|
34 |
+
# Calculate Levenshtein distances for each word in the dictionary
|
35 |
+
close_words = [word for word in dictionary if distance(input_word, word) <= threshold]
|
36 |
+
return close_words
|
37 |
+
|
38 |
+
def query_gpt(food_item, dictionary_word, similar_words):
|
39 |
+
line_separated_words = '\n'.join(similar_words)
|
40 |
+
|
41 |
+
prompt = (
|
42 |
+
f"""I have a particular food item and a mapping to a USDA word. Can you confirm if the food item is most similar to the mapping?
|
43 |
+
|
44 |
+
Generally, you should prefer the mapped word, but if you believe there is a better fit, please provide it.
|
45 |
+
|
46 |
+
I will also provide a list of other similar words that you could be a better fit.
|
47 |
+
|
48 |
+
This is important: only return a word from the list of words I provide.
|
49 |
+
|
50 |
+
If it's not a food item or pet food, return 'Non-Food Item'.
|
51 |
+
|
52 |
+
You should respond in JSON format with an object that has the key `guess`, and the value is the most similar food item.
|
53 |
+
|
54 |
+
The food item is: "{food_item}"
|
55 |
+
It has been mapped to: "{dictionary_word}"
|
56 |
+
|
57 |
+
Similar words:
|
58 |
+
{line_separated_words}"""
|
59 |
+
)
|
60 |
+
|
61 |
+
completion = client.chat.completions.create(
|
62 |
+
messages=[
|
63 |
+
{"role": "system", "content": "You are a helpful assistant."},
|
64 |
+
{"role": "user", "content": prompt}
|
65 |
+
],
|
66 |
+
model="gpt-3.5-turbo-1106",
|
67 |
+
response_format={"type": "json_object"},
|
68 |
+
)
|
69 |
+
response = completion.choices[0].message.content
|
70 |
+
parsed = parse_response(response)
|
71 |
+
print(f"Q: '{food_item}'")
|
72 |
+
print(f"A: '{parsed}'")
|
73 |
+
print()
|
74 |
+
return parsed
|
75 |
+
|
76 |
+
# Define the function to parse the GPT response
|
77 |
+
def parse_response(response):
|
78 |
+
try:
|
79 |
+
result = json.loads(response)
|
80 |
+
return result['guess']
|
81 |
+
except (json.JSONDecodeError, KeyError) as e:
|
82 |
+
print(f"Error parsing response: {response} - {e}")
|
83 |
+
return None
|
84 |
+
|
85 |
+
|
86 |
+
csv_file_paths = ['./dictionary/dictionary.csv','./dictionary/additions.csv']
|
87 |
+
dictionary = []
|
88 |
+
for csv_file_path in csv_file_paths:
|
89 |
+
df_dictionary = pd.read_csv(csv_file_path)
|
90 |
+
_dictionary = df_dictionary['description'].astype(str).tolist()
|
91 |
+
stripped_dictionary = [word.strip() for word in _dictionary]
|
92 |
+
dictionary.extend(stripped_dictionary)
|
93 |
+
|
94 |
+
db_conn = get_connection()
|
95 |
+
db_cursor = db_conn.cursor()
|
96 |
+
|
97 |
+
# select all mappings that have not been reviewed
|
98 |
+
db_cursor.execute("SELECT input_word, dictionary_word, similar_words FROM mappings WHERE reviewed = 0")
|
99 |
+
results = db_cursor.fetchall()
|
100 |
+
|
101 |
+
# iterate through each row, grab the input_word and ask chatgpt to compare it to the dictionary_word
|
102 |
+
|
103 |
+
print("Soft drink, NFS" in dictionary)
|
104 |
+
|
105 |
+
csv_data = []
|
106 |
+
for row in results:
|
107 |
+
input_word = row[0]
|
108 |
+
dictionary_word = row[1]
|
109 |
+
similar_words = [item.strip() for item in row[2].split('|')]
|
110 |
+
|
111 |
+
# find words from the dictionary list based on small levenstein distance between input_word and each word in the dictionary
|
112 |
+
levenshtein_words = find_close_levenshtein_words(input_word, dictionary)
|
113 |
+
print(f"Input: {input_word}")
|
114 |
+
print(f" - dictionary_word: {dictionary_word}")
|
115 |
+
print(f" - similar_words: {similar_words}")
|
116 |
+
print(f" - levenshtein_words: {levenshtein_words}")
|
117 |
+
|
118 |
+
# concatenate the similar_words and levenshtein_words
|
119 |
+
all_words = similar_words + levenshtein_words
|
120 |
+
all_words = list(set(all_words)) # remove duplicates
|
121 |
+
response = query_gpt(input_word, dictionary_word, all_words)
|
122 |
+
if response:
|
123 |
+
csv_data.append({
|
124 |
+
'input_word': input_word,
|
125 |
+
'original_dictionary_word': dictionary_word,
|
126 |
+
'new_dictionary_word': response
|
127 |
+
})
|
128 |
+
if response == dictionary_word and response in dictionary:
|
129 |
+
print(f" - Mapping is correct")
|
130 |
+
db_cursor.execute("UPDATE mappings SET reviewed = 1 WHERE input_word = ?", (input_word,))
|
131 |
+
else:
|
132 |
+
# We should update the mapping in the database
|
133 |
+
# We should replace dictionary_word with response
|
134 |
+
# We should set reviewed to 1
|
135 |
+
# first confirm that the response is in the dictionary
|
136 |
+
if response in dictionary:
|
137 |
+
print(f" - Updating mapping with {response}")
|
138 |
+
db_cursor.execute("UPDATE mappings SET dictionary_word = ?, reviewed = 1 WHERE input_word = ?", (response, input_word))
|
139 |
+
db_conn.commit()
|
140 |
+
else:
|
141 |
+
print(f" - Response {response} is not in the dictionary")
|
142 |
+
|
143 |
+
update_csv(csv_data)
|
144 |
+
|
145 |
+
db_conn.close()
|
db/db_utils.py
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import psycopg2
|
3 |
+
from dotenv import load_dotenv
|
4 |
+
|
5 |
+
load_dotenv()
|
6 |
+
|
7 |
+
|
8 |
+
def get_connection():
|
9 |
+
DATABASE_URL = os.environ['DATABASE_URL']
|
10 |
+
print(f" - Connecting to db: {DATABASE_URL}")
|
11 |
+
conn = psycopg2.connect(DATABASE_URL, sslmode='require')
|
12 |
+
initialize_db(conn)
|
13 |
+
return conn
|
14 |
+
|
15 |
+
def initialize_db(conn):
|
16 |
+
cursor = conn.cursor()
|
17 |
+
cursor.execute('''
|
18 |
+
CREATE TABLE IF NOT EXISTS mappings (
|
19 |
+
input_word TEXT PRIMARY KEY,
|
20 |
+
cleaned_word TEXT,
|
21 |
+
matching_word TEXT,
|
22 |
+
dictionary_word TEXT,
|
23 |
+
similarity_score REAL,
|
24 |
+
confidence_score REAL,
|
25 |
+
food_category TEXT,
|
26 |
+
similar_words TEXT,
|
27 |
+
is_food BOOLEAN,
|
28 |
+
food_nonfood_score REAL,
|
29 |
+
reviewed BOOLEAN DEFAULT FALSE,
|
30 |
+
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
|
31 |
+
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
32 |
+
)
|
33 |
+
''')
|
34 |
+
conn.commit()
|
35 |
+
|
36 |
+
def get_mapping_from_db(cursor, cleaned_word):
|
37 |
+
cursor.execute('SELECT * FROM mappings WHERE cleaned_word = %s', (cleaned_word,))
|
38 |
+
row = cursor.fetchone()
|
39 |
+
if row:
|
40 |
+
columns = [col[0] for col in cursor.description]
|
41 |
+
return dict(zip(columns, row))
|
42 |
+
return None
|
43 |
+
|
44 |
+
def store_mapping_to_db(cursor, conn, mapping):
|
45 |
+
try:
|
46 |
+
cursor.execute('''
|
47 |
+
INSERT INTO mappings (input_word, cleaned_word, matching_word, dictionary_word, similarity_score, confidence_score, similar_words, is_food, food_nonfood_score)
|
48 |
+
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
|
49 |
+
''', (
|
50 |
+
mapping['input_word'],
|
51 |
+
mapping['cleaned_word'],
|
52 |
+
mapping['matching_word'],
|
53 |
+
mapping['dictionary_word'],
|
54 |
+
mapping['similarity_score'],
|
55 |
+
mapping['confidence_score'],
|
56 |
+
mapping['similar_words'],
|
57 |
+
mapping['is_food'],
|
58 |
+
mapping['food_nonfood_score']
|
59 |
+
))
|
60 |
+
conn.commit()
|
61 |
+
except Exception as e:
|
62 |
+
print(f" - Error storing mapping to db: {e}")
|
63 |
+
conn.rollback()
|
64 |
+
return False
|
dictionary/additions.csv
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
description,food_category
|
2 |
+
"Mixed Produce", "Heterogeneous Mixture"
|
3 |
+
"Miscellaneous", "Heterogeneous Mixture"
|
4 |
+
"Assorted Vegetables", "Heterogeneous Mixture"
|
5 |
+
"Various Fruits", "Heterogeneous Mixture"
|
6 |
+
"Assorted Produce", "Heterogeneous Mixture"
|
7 |
+
"Mixed Vegetables", "Heterogeneous Mixture"
|
8 |
+
"Mixed Vegetables, canned", "Heterogeneous Mixture"
|
9 |
+
"Miscellaneous Items", "Heterogeneous Mixture"
|
10 |
+
"Mixed Goods", "Heterogeneous Mixture"
|
11 |
+
"Assorted Groceries", "Heterogeneous Mixture"
|
12 |
+
"Various Groceries", "Heterogeneous Mixture"
|
13 |
+
"Mixed Food Items", "Heterogeneous Mixture"
|
14 |
+
"Assorted Foods", "Heterogeneous Mixture"
|
15 |
+
"Varied Produce", "Heterogeneous Mixture"
|
16 |
+
"Assorted Fruit and Veg", "Heterogeneous Mixture"
|
17 |
+
"Mixed Fruits and Vegetables", "Heterogeneous Mixture"
|
18 |
+
"Miscellaneous Produce", "Heterogeneous Mixture"
|
19 |
+
"Assorted Consumables", "Heterogeneous Mixture"
|
20 |
+
"Various Edibles", "Heterogeneous Mixture"
|
21 |
+
"Mixed Edibles", "Heterogeneous Mixture"
|
22 |
+
"Assorted Edible Items", "Heterogeneous Mixture"
|
23 |
+
"Mixed Fresh Produce", "Heterogeneous Mixture"
|
24 |
+
"Various Produce Items", "Heterogeneous Mixture"
|
25 |
+
"Misc Grocery", "Heterogeneous Mixture"
|
26 |
+
"Misc Meat", "Heterogeneous Mixture"
|
27 |
+
"Misc Produce", "Heterogeneous Mixture"
|
28 |
+
"Misc Vegetables", "Heterogeneous Mixture"
|
29 |
+
"Grocery Items", "Heterogeneous Mixture"
|
30 |
+
"Grocery", "Heterogeneous Mixture"
|
31 |
+
"Misc Items", "Non-Food Item"
|
32 |
+
"Non-Food Item", "Non-Food Item"
|
dictionary/dictionary.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
dictionary/final_corrected_wweia_food_category_complete - final_corrected_wweia_food_category_complete.csv
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
wweia_food_category,wweia_food_category_description,closest_category,,Leakage Food Group Category,,,,
|
2 |
+
1002,"Milk, whole",Dairy and Egg Products,,Beverage milks,12%,,closest_category,
|
3 |
+
1004,"Milk, reduced fat",Dairy and Egg Products,,Beverage milks,12%,,Dairy and Egg Products,12%
|
4 |
+
1006,"Milk, lowfat",Dairy and Egg Products,,Beverage milks,12%,,Beef Products,4%
|
5 |
+
1008,"Milk, nonfat",Dairy and Egg Products,,Beverage milks,12%,,Pork Products,4%
|
6 |
+
1202,"Flavored milk, whole",Dairy and Egg Products,,Beverage milks,12%,,"Lamb, Veal, and Game Products",4%
|
7 |
+
1204,"Flavored milk, reduced fat",Dairy and Egg Products,,Beverage milks,12%,,Poultry Products,4%
|
8 |
+
1206,"Flavored milk, lowfat",Dairy and Egg Products,,Beverage milks,12%,,Finfish and Shellfish Products,8%
|
9 |
+
1208,"Flavored milk, nonfat",Dairy and Egg Products,,Beverage milks,12%,,Sausages and Luncheon Meats,4%
|
10 |
+
1402,Milk shakes and other dairy drinks,Dairy and Egg Products,,Beverage milks,12%,,Beans and Lentils,6%
|
11 |
+
1404,Milk substitutes,Dairy and Egg Products,,Beverage milks,12%,,Nut and Seed Products,6%
|
12 |
+
1602,Cheese,Dairy and Egg Products,,Cheese,6%,,Legumes and Legume Products,6%
|
13 |
+
1604,Cottage/ricotta cheese,Dairy and Egg Products,,Cheese,6%,,"Meals, Entrees, and Side Dishes",10%
|
14 |
+
1820,"Yogurt, regular",Dairy and Egg Products,,Dairy products,11%,,Baked Products,10%
|
15 |
+
1822,"Yogurt, Greek",Dairy and Egg Products,,Dairy products,11%,,"Soups, Sauces, and Gravies",10%
|
16 |
+
2002,"Beef, excludes ground",Beef Products,,Meat,4%,,Cereal Grains and Pasta,12%
|
17 |
+
2004,Ground beef,Beef Products,,Meat,4%,,Snacks,10%
|
18 |
+
2006,Pork,Pork Products,,Meat,4%,,Sweets,10%
|
19 |
+
2008,"Lamb, goat, game","Lamb, Veal, and Game Products",,Meat,4%,,Fruits and Fruit Juices,12%
|
20 |
+
2010,Liver and organ meats,Beef Products,,Meat,4%,,Vegetable and Vegetable Products,9%
|
21 |
+
2202,"Chicken, whole pieces",Poultry Products,,Meat,4%,,Beverages,10%
|
22 |
+
2204,"Chicken patties, nuggets and tenders",Poultry Products,,Meat,4%,,Alcoholic Beverages,10%
|
23 |
+
2206,"Turkey, duck, other poultry",Poultry Products,,Meat,4%,,Fats and Oils,21%
|
24 |
+
2402,Fish,Finfish and Shellfish Products,,Fish and seafood,8%,,Condiments and Sauces,10%
|
25 |
+
2404,Shellfish,Finfish and Shellfish Products,,Fish and seafood,8%,,Baby Foods,12%
|
26 |
+
2502,Eggs and omelets,Dairy and Egg Products,,Eggs,7%,,Supplements,10%
|
27 |
+
2602,Cold cuts and cured meats,Sausages and Luncheon Meats,,Meat,4%,,,
|
28 |
+
2604,Bacon,Pork Products,,Meat,4%,,,
|
29 |
+
2606,Frankfurters,Sausages and Luncheon Meats,,Meat,4%,,,
|
30 |
+
2608,Sausages,Sausages and Luncheon Meats,,Meat,4%,,,
|
31 |
+
2802,"Beans, peas, legumes",Beans and Lentils,,Legumes,6%,,,
|
32 |
+
2804,Nuts and seeds,Nut and Seed Products,,Nuts,6%,,,
|
33 |
+
2806,Processed soy products,Legumes and Legume Products,,Legumes,6%,,,
|
34 |
+
3002,Meat mixed dishes,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
35 |
+
3004,Poultry mixed dishes,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
36 |
+
3006,Seafood mixed dishes,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
37 |
+
3102,"Bean, pea, legume dishes","Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
38 |
+
3104,Vegetable dishes,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
39 |
+
3202,Rice mixed dishes,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
40 |
+
3204,"Pasta mixed dishes, excludes macaroni and cheese","Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
41 |
+
3206,Macaroni and cheese,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
42 |
+
3208,Turnovers and other grain-based items,Baked Products,,Miscellaneous,10%,,,
|
43 |
+
3402,Fried rice and lo/chow mein,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
44 |
+
3404,Stir-fry and soy-based sauce mixtures,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
45 |
+
3406,"Egg rolls, dumplings, sushi","Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
46 |
+
3502,Burritos and tacos,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
47 |
+
3504,Nachos,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
48 |
+
3506,Other Mexican mixed dishes,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
49 |
+
3602,Pizza,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
50 |
+
3702,Burgers,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
51 |
+
3703,Frankfurter sandwiches,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
52 |
+
3704,Chicken fillet sandwiches,Poultry Products,,Miscellaneous,10%,,,
|
53 |
+
3706,Egg/breakfast sandwiches,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
54 |
+
3708,Other sandwiches (single code),"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
55 |
+
3720,Cheese sandwiches,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
56 |
+
3722,Peanut butter and jelly sandwiches,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
57 |
+
3730,Seafood sandwiches,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
58 |
+
3802,Soups,"Soups, Sauces, and Gravies",,Miscellaneous,10%,,,
|
59 |
+
4002,Rice,Cereal Grains and Pasta,,Grains,12%,,,
|
60 |
+
4004,"Pasta, noodles, cooked grains",Cereal Grains and Pasta,,Grains,12%,,,
|
61 |
+
4202,Yeast breads,Baked Products,,Miscellaneous,10%,,,
|
62 |
+
4204,Rolls and buns,Baked Products,,Miscellaneous,10%,,,
|
63 |
+
4206,Bagels and English muffins,Baked Products,,Miscellaneous,10%,,,
|
64 |
+
4208,Tortillas,Baked Products,,Miscellaneous,10%,,,
|
65 |
+
4402,"Biscuits, muffins, quick breads",Baked Products,,Miscellaneous,10%,,,
|
66 |
+
4404,"Pancakes, waffles, French toast",Baked Products,,Miscellaneous,10%,,,
|
67 |
+
4602,"Ready-to-eat cereal, higher sugar (>21.2g/100g)",Cereal Grains and Pasta,,Grains,12%,,,
|
68 |
+
4604,"Ready-to-eat cereal, lower sugar (=<21.2g/100g)",Cereal Grains and Pasta,,Grains,12%,,,
|
69 |
+
4802,Oatmeal,Cereal Grains and Pasta,,Grains,12%,,,
|
70 |
+
4804,Grits and other cooked cereals,Cereal Grains and Pasta,,Grains,12%,,,
|
71 |
+
5002,Potato chips,Snacks,,Miscellaneous,10%,,,
|
72 |
+
5004,"Tortilla, corn, other chips",Snacks,,Miscellaneous,10%,,,
|
73 |
+
5006,Popcorn,Snacks,,Miscellaneous,10%,,,
|
74 |
+
5008,Pretzels/snack mix,Snacks,,Miscellaneous,10%,,,
|
75 |
+
5202,"Crackers, excludes saltines",Snacks,,Miscellaneous,10%,,,
|
76 |
+
5204,Saltine crackers,Snacks,,Miscellaneous,10%,,,
|
77 |
+
5402,Cereal bars,Snacks,,Miscellaneous,10%,,,
|
78 |
+
5404,Nutrition bars,Snacks,,Miscellaneous,10%,,,
|
79 |
+
5502,Cakes and pies,Baked Products,,Miscellaneous,10%,,,
|
80 |
+
5504,Cookies and brownies,Baked Products,,Miscellaneous,10%,,,
|
81 |
+
5506,"Doughnuts, sweet rolls, pastries",Baked Products,,Miscellaneous,10%,,,
|
82 |
+
5702,Candy containing chocolate,Sweets,,Miscellaneous,10%,,,
|
83 |
+
5704,Candy not containing chocolate,Sweets,,Miscellaneous,10%,,,
|
84 |
+
5802,Ice cream and frozen dairy desserts,Sweets,,Dairy products,11%,,,
|
85 |
+
5804,Pudding,Sweets,,Miscellaneous,10%,,,
|
86 |
+
5806,"Gelatins, ices, sorbets",Sweets,,Miscellaneous,10%,,,
|
87 |
+
6002,Apples,Fruits and Fruit Juices,,Fruits,12%,,,
|
88 |
+
6004,Bananas,Fruits and Fruit Juices,,Fruits,12%,,,
|
89 |
+
6006,Grapes,Fruits and Fruit Juices,,Fruits,12%,,,
|
90 |
+
6008,Peaches and nectarines,Fruits and Fruit Juices,,Fruits,12%,,,
|
91 |
+
6009,Strawberries,Fruits and Fruit Juices,,Fruits,12%,,,
|
92 |
+
6011,Blueberries and other berries,Fruits and Fruit Juices,,Fruits,12%,,,
|
93 |
+
6012,Citrus fruits,Fruits and Fruit Juices,,Fruits,12%,,,
|
94 |
+
6014,Melons,Fruits and Fruit Juices,,Fruits,12%,,,
|
95 |
+
6016,Dried fruits,Fruits and Fruit Juices,,Fruits,12%,,,
|
96 |
+
6018,Other fruits and fruit salads,Fruits and Fruit Juices,,Fruits,12%,,,
|
97 |
+
6020,Pears,Fruits and Fruit Juices,,Fruits,12%,,,
|
98 |
+
6022,Pineapple,Fruits and Fruit Juices,,Fruits,12%,,,
|
99 |
+
6024,Mango and papaya,Fruits and Fruit Juices,,Fruits,12%,,,
|
100 |
+
6402,Tomatoes,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
101 |
+
6404,Carrots,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
102 |
+
6406,Other red and orange vegetables,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
103 |
+
6407,Broccoli,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
104 |
+
6409,Spinach,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
105 |
+
6410,Lettuce and lettuce salads,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
106 |
+
6411,Other dark green vegetables,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
107 |
+
6412,String beans,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
108 |
+
6413,Cabbage,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
109 |
+
6414,Onions,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
110 |
+
6416,Corn,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
111 |
+
6418,Other starchy vegetables,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
112 |
+
6420,Other vegetables and combinations,Vegetable and Vegetable Products,,Vegetables,9%,,,
|
113 |
+
6430,Fried vegetables,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
114 |
+
6432,"Coleslaw, non-lettuce salads","Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
115 |
+
6489,Vegetables on a sandwich,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
116 |
+
6802,"White potatoes, baked or boiled",Vegetable and Vegetable Products,,Vegetables,9%,,,
|
117 |
+
6804,French fries and other fried white potatoes,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
118 |
+
6806,Mashed potatoes and white potato mixtures,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
119 |
+
7002,Citrus juice,Fruits and Fruit Juices,,Fruits,12%,,,
|
120 |
+
7004,Apple juice,Fruits and Fruit Juices,,Fruits,12%,,,
|
121 |
+
7006,Other fruit juice,Fruits and Fruit Juices,,Fruits,12%,,,
|
122 |
+
7008,Vegetable juice,Beverages,,Miscellaneous,10%,,,
|
123 |
+
7102,Diet soft drinks,Beverages,,Miscellaneous,10%,,,
|
124 |
+
7104,Diet sport and energy drinks,Beverages,,Miscellaneous,10%,,,
|
125 |
+
7106,Other diet drinks,Beverages,,Miscellaneous,10%,,,
|
126 |
+
7202,Soft drinks,Beverages,,Miscellaneous,10%,,,
|
127 |
+
7204,Fruit drinks,Beverages,,Miscellaneous,10%,,,
|
128 |
+
7206,Sport and energy drinks,Beverages,,Miscellaneous,10%,,,
|
129 |
+
7208,Nutritional beverages,Beverages,,Miscellaneous,10%,,,
|
130 |
+
7220,Smoothies and grain drinks,Beverages,,Miscellaneous,10%,,,
|
131 |
+
7302,Coffee,Beverages,,Miscellaneous,10%,,,
|
132 |
+
7304,Tea,Beverages,,Miscellaneous,10%,,,
|
133 |
+
7502,Beer,Alcoholic Beverages,,Miscellaneous,10%,,,
|
134 |
+
7504,Wine,Alcoholic Beverages,,Miscellaneous,10%,,,
|
135 |
+
7506,Liquor and cocktails,Alcoholic Beverages,,Miscellaneous,10%,,,
|
136 |
+
7702,Tap water,Beverages,,Miscellaneous,10%,,,
|
137 |
+
7704,Bottled water,Beverages,,Miscellaneous,10%,,,
|
138 |
+
7802,Flavored or carbonated water,Beverages,,Miscellaneous,10%,,,
|
139 |
+
7804,Enhanced water,Beverages,,Miscellaneous,10%,,,
|
140 |
+
8002,Butter and animal fats,Fats and Oils,,Fats,21%,,,
|
141 |
+
8004,Margarine,Fats and Oils,,Fats,21%,,,
|
142 |
+
8006,"Cream cheese, sour cream, whipped cream",Dairy and Egg Products,,Dairy products,11%,,,
|
143 |
+
8008,Cream and cream substitutes,Dairy and Egg Products,,Dairy products,11%,,,
|
144 |
+
8010,Mayonnaise,Condiments and Sauces,,Miscellaneous,10%,,,
|
145 |
+
8012,Salad dressings and vegetable oils,Fats and Oils,,Oils,21%,,,
|
146 |
+
8402,Tomato-based condiments,Condiments and Sauces,,Miscellaneous,10%,,,
|
147 |
+
8404,Soy-based condiments,Condiments and Sauces,,Miscellaneous,10%,,,
|
148 |
+
8406,Mustard and other condiments,Condiments and Sauces,,Miscellaneous,10%,,,
|
149 |
+
8408,"Olives, pickles, pickled vegetables",Vegetable and Vegetable Products,,Vegetables,9%,,,
|
150 |
+
8410,"Pasta sauces, tomato-based",Condiments and Sauces,,Miscellaneous,10%,,,
|
151 |
+
8412,"Dips, gravies, other sauces",Condiments and Sauces,,Miscellaneous,10%,,,
|
152 |
+
8802,Sugars and honey,Sweets,,Miscellaneous,10%,,,
|
153 |
+
8804,Sugar substitutes,Sweets,,Miscellaneous,10%,,,
|
154 |
+
8806,"Jams, syrups, toppings",Sweets,,Miscellaneous,10%,,,
|
155 |
+
9002,Baby food: cereals,Baby Foods,,Grains,12%,,,
|
156 |
+
9004,Baby food: fruit,Baby Foods,,Fruits,12%,,,
|
157 |
+
9006,Baby food: vegetable,Baby Foods,,Vegetables,9%,,,
|
158 |
+
9008,Baby food: meat and dinners,Baby Foods,,Miscellaneous,10%,,,
|
159 |
+
9010,Baby food: yogurt,Baby Foods,,Dairy products,11%,,,
|
160 |
+
9012,Baby food: snacks and sweets,Baby Foods,,Miscellaneous,10%,,,
|
161 |
+
9202,Baby juice,Fruits and Fruit Juices,,Fruits,12%,,,
|
162 |
+
9204,Baby water,Baby Foods,,Miscellaneous,10%,,,
|
163 |
+
9402,"Formula, ready-to-feed",Baby Foods,,Beverage milks,12%,,,
|
164 |
+
9404,"Formula, prepared from powder",Baby Foods,,Dairy products,11%,,,
|
165 |
+
9406,"Formula, prepared from concentrate",Baby Foods,,Dairy products,11%,,,
|
166 |
+
9602,Human milk,Baby Foods,,Miscellaneous,10%,,,
|
167 |
+
9802,Protein and nutritional powders,Supplements,,Miscellaneous,10%,,,
|
168 |
+
9999,Not included in a food category,,,Miscellaneous,10%,,,
|
169 |
+
9007,Baby food: mixtures,Baby Foods,,Miscellaneous,10%,,,
|
170 |
+
3740,Deli and cured meat sandwiches,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
171 |
+
3742,Meat and BBQ sandwiches,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
172 |
+
3744,Vegetable sandwiches/burgers,"Meals, Entrees, and Side Dishes",,Miscellaneous,10%,,,
|
env
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
pyenv activate brightly-python
|
flagged/log.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
name,intensity,output,flag,username,timestamp
|
2 |
+
brian,6,Hello Hello Hello Hello Hello Hello brian!,,,2024-06-14 06:59:50.164190
|
food_nonfood.py
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import random
|
2 |
+
import numpy as np
|
3 |
+
import torch
|
4 |
+
from transformers import pipeline
|
5 |
+
|
6 |
+
# Load a pre-trained SBERT model
|
7 |
+
|
8 |
+
# Set seeds for reproducibility of zero-shot classification
|
9 |
+
def set_seed(seed):
|
10 |
+
random.seed(seed)
|
11 |
+
np.random.seed(seed)
|
12 |
+
torch.manual_seed(seed)
|
13 |
+
torch.cuda.manual_seed_all(seed)
|
14 |
+
torch.backends.cudnn.deterministic = True
|
15 |
+
torch.backends.cudnn.benchmark = False
|
16 |
+
|
17 |
+
set_seed(1)
|
18 |
+
|
19 |
+
# Load a pre-trained model and tokenizer
|
20 |
+
classifier = pipeline("zero-shot-classification", model="roberta-large-mnli")
|
21 |
+
|
22 |
+
# Classify item as food or non-food
|
23 |
+
def classify_as_food_nonfood(item):
|
24 |
+
cleaned_item = item.strip().lower()
|
25 |
+
result = classifier(cleaned_item, candidate_labels=["food", "non-food"])
|
26 |
+
label = result["labels"][0]
|
27 |
+
score = result["scores"][0]
|
28 |
+
# print(f"Item: {item}, Label: {label}, Score: {score}")
|
29 |
+
return label, score
|
30 |
+
|
31 |
+
def pessimistic_food_nonfood_score(food_nonfood, similarity_score):
|
32 |
+
# For us to truly believe that the word is nonfood, we need to be confident that it is nonfood.
|
33 |
+
#
|
34 |
+
# Three conditions need to be met:
|
35 |
+
# 1. The word must be classified as nonfood
|
36 |
+
# 2. The food_nonfood_score must be greater than a threshold
|
37 |
+
|
38 |
+
is_food = food_nonfood[0] == 'food'
|
39 |
+
food_nonfood_score = food_nonfood[1]
|
40 |
+
|
41 |
+
if is_food == False and food_nonfood_score >= 0.7:
|
42 |
+
is_food = False
|
43 |
+
else:
|
44 |
+
is_food = True
|
45 |
+
|
46 |
+
return is_food, food_nonfood_score
|
multi-item-experiments/classification_results2.csv
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Item List,Category,Non-Food Items
|
2 |
+
Misc Grocery/Yogurt/Coffee/Baking Chips/Coffeemate Creamer/Baby Food/Sports,heterogeneous mixture,sports
|
3 |
+
Drinks/Cond Milk/Evap Milk/Coffee Syrup/Soup,heterogeneous mixture,
|
4 |
+
"Plastic Bags, Water, Snacks, Grocery, Meat, Candy",heterogeneous mixture,"plastic bags, water"
|
5 |
+
Bread/BakeryDesserts/Deli/Seafood,heterogeneous mixture,
|
6 |
+
Mixed Vegetables/Lettuce Assorted,heterogeneous mixture,
|
7 |
+
Rolls/Fruit/Vegetables/Herbs/Butter/Oatmeal/Bread/Salad Greens,heterogeneous mixture,herbs
|
8 |
+
"Breast,wings,thighs,legs,tenders",heterogeneous mixture,wings
|
9 |
+
"Swiss Cheese, Provolone cheese, cheddar, mozzarella",heterogeneous mixture,
|
multi-item-experiments/multifood2.py
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import re
|
2 |
+
import csv
|
3 |
+
import random
|
4 |
+
import numpy as np
|
5 |
+
import torch
|
6 |
+
from tqdm import tqdm
|
7 |
+
from transformers import pipeline
|
8 |
+
from sentence_transformers import SentenceTransformer, util
|
9 |
+
from db.db_utils import get_connection, initialize_db, get_mapping_from_db, store_mapping_to_db
|
10 |
+
|
11 |
+
# Load a pre-trained SBERT model
|
12 |
+
model = SentenceTransformer('all-MiniLM-L6-v2')
|
13 |
+
|
14 |
+
# Set seeds for reproducibility of zero-shot classification
|
15 |
+
def set_seed(seed):
|
16 |
+
random.seed(seed)
|
17 |
+
np.random.seed(seed)
|
18 |
+
torch.manual_seed(seed)
|
19 |
+
torch.cuda.manual_seed_all(seed)
|
20 |
+
torch.backends.cudnn.deterministic = True
|
21 |
+
torch.backends.cudnn.benchmark = False
|
22 |
+
|
23 |
+
set_seed(1)
|
24 |
+
|
25 |
+
# Load a pre-trained model and tokenizer
|
26 |
+
classifier = pipeline("zero-shot-classification", model="roberta-large-mnli")
|
27 |
+
|
28 |
+
# Load food categories from CSV
|
29 |
+
def load_food_categories(csv_file):
|
30 |
+
food_categories = set()
|
31 |
+
with open(csv_file, newline='') as csvfile:
|
32 |
+
reader = csv.DictReader(csvfile)
|
33 |
+
for row in reader:
|
34 |
+
food_categories.add(row['food_category'])
|
35 |
+
return list(food_categories)
|
36 |
+
|
37 |
+
# Path to the CSV file with food categories
|
38 |
+
csv_file_path = 'dictionary/dictionary.csv'
|
39 |
+
food_categories = load_food_categories(csv_file_path)
|
40 |
+
|
41 |
+
# Precompute embeddings for food categories
|
42 |
+
category_embeddings = model.encode(food_categories, convert_to_tensor=True)
|
43 |
+
|
44 |
+
# Classify item as food or non-food
|
45 |
+
def classify_as_food_nonfood(item, cursor):
|
46 |
+
if item == 'Non-Food Item':
|
47 |
+
return "non-food", 1.0, None
|
48 |
+
|
49 |
+
cleaned_item = item.strip().lower()
|
50 |
+
db_record = get_mapping_from_db(cursor, cleaned_item)
|
51 |
+
if db_record and 'is_food' in db_record:
|
52 |
+
is_food = db_record['is_food']
|
53 |
+
if is_food is not None:
|
54 |
+
print(f"Item: {item} found in database with is_food: {is_food}")
|
55 |
+
return ("food" if is_food else "non-food"), 1.0, db_record
|
56 |
+
|
57 |
+
result = classifier(item, candidate_labels=["food", "non-food"])
|
58 |
+
label = result["labels"][0]
|
59 |
+
score = result["scores"][0]
|
60 |
+
print(f"Item: {item}, Label: {label}, Score: {score}")
|
61 |
+
return label, score, db_record
|
62 |
+
|
63 |
+
# Determine the category of a food item
|
64 |
+
def determine_category(item):
|
65 |
+
item_embedding = model.encode(item, convert_to_tensor=True)
|
66 |
+
similarities = util.pytorch_cos_sim(item_embedding, category_embeddings)
|
67 |
+
category_idx = similarities.argmax()
|
68 |
+
category = food_categories[category_idx]
|
69 |
+
|
70 |
+
top_3_indices = torch.topk(similarities, 3).indices[0].tolist()
|
71 |
+
top_3_scores = torch.topk(similarities, 3).values[0].tolist()
|
72 |
+
|
73 |
+
top_3_categories = [(food_categories[idx], score) for idx, score in zip(top_3_indices, top_3_scores)]
|
74 |
+
|
75 |
+
print("=========================================")
|
76 |
+
print(f"item: {item}")
|
77 |
+
for category, score in top_3_categories:
|
78 |
+
print(f"Category: {category}, Similarity Score: {score:.4f}")
|
79 |
+
|
80 |
+
return category
|
81 |
+
|
82 |
+
# Categorize food items
|
83 |
+
def categorize_food_items(items):
|
84 |
+
categories_found = set()
|
85 |
+
for item in items:
|
86 |
+
category = determine_category(item)
|
87 |
+
categories_found.add(category)
|
88 |
+
print(f"Categories found: {categories_found}")
|
89 |
+
if len(categories_found) == 1:
|
90 |
+
return list(categories_found)[0]
|
91 |
+
elif len(categories_found) > 1:
|
92 |
+
return "heterogeneous mixture"
|
93 |
+
else:
|
94 |
+
return "food"
|
95 |
+
|
96 |
+
# List of items to test
|
97 |
+
items_to_test = [
|
98 |
+
"Misc Grocery/Yogurt/Coffee/Baking Chips/Coffeemate Creamer/Baby Food/Sports",
|
99 |
+
"Drinks/Cond Milk/Evap Milk/Coffee Syrup/Soup",
|
100 |
+
"Plastic Bags, Water, Snacks, Grocery, Meat, Candy",
|
101 |
+
"Bread/BakeryDesserts/Deli/Seafood",
|
102 |
+
"Mixed Vegetables/Lettuce Assorted",
|
103 |
+
"Rolls/Fruit/Vegetables/Herbs/Butter/Oatmeal/Bread/Salad Greens",
|
104 |
+
"Breast,wings,thighs,legs,tenders",
|
105 |
+
"Swiss Cheese, Provolone cheese, cheddar, mozzarella"
|
106 |
+
]
|
107 |
+
|
108 |
+
# Initialize database connection
|
109 |
+
conn = get_connection()
|
110 |
+
cursor = conn.cursor()
|
111 |
+
|
112 |
+
# Collect results
|
113 |
+
results = []
|
114 |
+
|
115 |
+
for items in items_to_test:
|
116 |
+
items_list = [item.strip().lower() for item in re.split(r'[\/,]', items)]
|
117 |
+
item_labels = [classify_as_food_nonfood(item, cursor) for item in items_list]
|
118 |
+
|
119 |
+
non_food_items = [(item, score, db_record) for item, (label, score, db_record) in zip(items_list, item_labels) if label == "non-food" and score > 0.75]
|
120 |
+
|
121 |
+
for (item, score, db_record) in non_food_items:
|
122 |
+
# Store non-food items in the database
|
123 |
+
if db_record is None:
|
124 |
+
mapping = (item, item, "Non-Food Item", score, None, None, False)
|
125 |
+
store_mapping_to_db(cursor, conn, mapping)
|
126 |
+
|
127 |
+
list_label = categorize_food_items(items_list)
|
128 |
+
|
129 |
+
non_food_items_str = ", ".join([item for item, _, _ in non_food_items])
|
130 |
+
results.append([items, list_label, non_food_items_str])
|
131 |
+
|
132 |
+
# Write results to a CSV file
|
133 |
+
with open('multi-item-experiments/classification_results2.csv', 'w', newline='') as csvfile:
|
134 |
+
csvwriter = csv.writer(csvfile)
|
135 |
+
csvwriter.writerow(['Item List', 'Category', 'Non-Food Items'])
|
136 |
+
csvwriter.writerows(results)
|
137 |
+
|
138 |
+
# Close the SQLite connection
|
139 |
+
conn.close()
|
multi-item-experiments/multifood_viz.py
ADDED
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import re
|
2 |
+
import csv
|
3 |
+
import random
|
4 |
+
import numpy as np
|
5 |
+
import torch
|
6 |
+
from tqdm import tqdm
|
7 |
+
from transformers import pipeline
|
8 |
+
from sentence_transformers import SentenceTransformer, util
|
9 |
+
from sklearn.manifold import TSNE
|
10 |
+
import matplotlib.pyplot as plt
|
11 |
+
from db.db_utils import get_connection, get_mapping_from_db
|
12 |
+
|
13 |
+
# Load a pre-trained SBERT model
|
14 |
+
model = SentenceTransformer('all-MiniLM-L6-v2')
|
15 |
+
|
16 |
+
# Set seeds for reproducibility of zero-shot classification
|
17 |
+
def set_seed(seed):
|
18 |
+
random.seed(seed)
|
19 |
+
np.random.seed(seed)
|
20 |
+
torch.manual_seed(seed)
|
21 |
+
torch.cuda.manual_seed_all(seed)
|
22 |
+
torch.backends.cudnn.deterministic = True
|
23 |
+
torch.backends.cudnn.benchmark = False
|
24 |
+
|
25 |
+
set_seed(1)
|
26 |
+
|
27 |
+
# Load a pre-trained model and tokenizer
|
28 |
+
classifier = pipeline("zero-shot-classification", model="roberta-large-mnli")
|
29 |
+
|
30 |
+
|
31 |
+
# Load food categories from CSV
|
32 |
+
def load_food_categories(csv_file):
|
33 |
+
food_categories = set()
|
34 |
+
with open(csv_file, newline='') as csvfile:
|
35 |
+
reader = csv.DictReader(csvfile)
|
36 |
+
for row in reader:
|
37 |
+
food_categories.add(row['food_category'])
|
38 |
+
return list(food_categories)
|
39 |
+
|
40 |
+
# Path to the CSV file with food categories
|
41 |
+
csv_file_path = 'dictionary/dictionary.csv'
|
42 |
+
food_categories = load_food_categories(csv_file_path)
|
43 |
+
|
44 |
+
# Precompute embeddings for food categories
|
45 |
+
category_embeddings = model.encode(food_categories, convert_to_tensor=True)
|
46 |
+
|
47 |
+
# Classify item as food or non-food
|
48 |
+
def classify_item(item, cursor):
|
49 |
+
# Check database for item
|
50 |
+
cleaned_item = item.strip().lower()
|
51 |
+
mapping = get_mapping_from_db(cursor, cleaned_item)
|
52 |
+
if mapping and 'is_food' in mapping:
|
53 |
+
is_food = mapping['is_food']
|
54 |
+
if is_food is not None:
|
55 |
+
print(f"Item: {item} found in database with is_food: {is_food}")
|
56 |
+
return ("food" if is_food else "non-food"), 1.0
|
57 |
+
|
58 |
+
# If not found in database, classify using the model
|
59 |
+
result = classifier(item, candidate_labels=["food", "non-food"])
|
60 |
+
label = result["labels"][0]
|
61 |
+
score = result["scores"][0]
|
62 |
+
print(f"Item: {item}, Label: {label}, Score: {score}")
|
63 |
+
return label, score
|
64 |
+
|
65 |
+
# Determine the category of a food item
|
66 |
+
def determine_category(item):
|
67 |
+
item_embedding = model.encode(item, convert_to_tensor=True)
|
68 |
+
similarities = util.pytorch_cos_sim(item_embedding, category_embeddings)
|
69 |
+
category_idx = similarities.argmax()
|
70 |
+
category = food_categories[category_idx]
|
71 |
+
|
72 |
+
# Assuming 'similarities' is a tensor of similarity scores and 'food_categories' is the list of category names
|
73 |
+
top_3_indices = torch.topk(similarities, 3).indices[0].tolist()
|
74 |
+
top_3_scores = torch.topk(similarities, 3).values[0].tolist()
|
75 |
+
|
76 |
+
top_3_categories = [(food_categories[idx], score) for idx, score in zip(top_3_indices, top_3_scores)]
|
77 |
+
|
78 |
+
print("=========================================")
|
79 |
+
print(f"item: {item}")
|
80 |
+
for category, score in top_3_categories:
|
81 |
+
print(f"Category: {category}, Similarity Score: {score:.4f}")
|
82 |
+
|
83 |
+
return category
|
84 |
+
|
85 |
+
# Visualize embeddings
|
86 |
+
def visualize_embeddings(items, categories, item_embeddings, category_embeddings):
|
87 |
+
tsne = TSNE(n_components=2, random_state=1)
|
88 |
+
embeddings = torch.cat([item_embeddings, category_embeddings], dim=0)
|
89 |
+
tsne_embeddings = tsne.fit_transform(embeddings.detach().cpu().numpy())
|
90 |
+
|
91 |
+
plt.figure(figsize=(10, 10))
|
92 |
+
for i, label in enumerate(items + categories):
|
93 |
+
x, y = tsne_embeddings[i]
|
94 |
+
plt.scatter(x, y)
|
95 |
+
plt.text(x+0.1, y+0.1, label, fontsize=9)
|
96 |
+
plt.show()
|
97 |
+
|
98 |
+
# Categorize food items
|
99 |
+
def categorize_food_items(items):
|
100 |
+
categories_found = set()
|
101 |
+
for item in items:
|
102 |
+
category = determine_category(item)
|
103 |
+
categories_found.add(category)
|
104 |
+
print(f"Categories found: {categories_found}")
|
105 |
+
if len(categories_found) == 1:
|
106 |
+
return list(categories_found)[0]
|
107 |
+
elif len(categories_found) > 1:
|
108 |
+
return "heterogeneous mixture"
|
109 |
+
else:
|
110 |
+
return "food"
|
111 |
+
|
112 |
+
# List of items to test
|
113 |
+
items_to_test = [
|
114 |
+
"Swiss Cheese, Provolone cheese, cheddar, mozzarella"
|
115 |
+
]
|
116 |
+
|
117 |
+
# Initialize database connection
|
118 |
+
conn = get_connection()
|
119 |
+
cursor = conn.cursor()
|
120 |
+
|
121 |
+
# Collect results and visualize embeddings
|
122 |
+
results = []
|
123 |
+
item_embeddings = []
|
124 |
+
items_list = []
|
125 |
+
|
126 |
+
for items in items_to_test:
|
127 |
+
# Split items by both "/" and "," and strip extra spaces
|
128 |
+
items_list = [item.strip().lower() for item in re.split(r'[\/,]', items)]
|
129 |
+
item_labels = [classify_item(item, cursor) for item in items_list]
|
130 |
+
|
131 |
+
non_food_items = [item for item, (label, _) in zip(items_list, item_labels) if label == "non-food"]
|
132 |
+
|
133 |
+
# Get embeddings for visualization
|
134 |
+
item_embeddings.extend(model.encode(items_list, convert_to_tensor=True))
|
135 |
+
|
136 |
+
list_label = categorize_food_items(items_list)
|
137 |
+
results.append([items, list_label, ", ".join(non_food_items)])
|
138 |
+
|
139 |
+
# Visualize embeddings
|
140 |
+
visualize_embeddings(items_list, food_categories, torch.stack(item_embeddings), category_embeddings)
|
141 |
+
|
142 |
+
# Write results to a CSV file
|
143 |
+
with open('multi-item-experiments/classification_results2.csv', 'w', newline='') as csvfile:
|
144 |
+
csvwriter = csv.writer(csvfile)
|
145 |
+
csvwriter.writerow(['Item List', 'Category', 'Non-Food Items'])
|
146 |
+
csvwriter.writerows(results)
|
147 |
+
|
148 |
+
# Close the SQLite connection
|
149 |
+
conn.close()
|
multi_food_item_detector.py
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import spacy
|
2 |
+
import re
|
3 |
+
|
4 |
+
# Load the spaCy model
|
5 |
+
nlp = spacy.load("en_core_web_sm")
|
6 |
+
|
7 |
+
def get_nouns(text):
|
8 |
+
doc = nlp(text)
|
9 |
+
nouns = [token.text for token in doc if token.pos_ == "NOUN"]
|
10 |
+
return nouns
|
11 |
+
|
12 |
+
def extract_food_phrases(text):
|
13 |
+
# Determine the delimiter
|
14 |
+
if '/' in text:
|
15 |
+
delimiter = '/'
|
16 |
+
elif ',' in text:
|
17 |
+
delimiter = ','
|
18 |
+
else:
|
19 |
+
# if it's not comma or slash delimited, return the text as is
|
20 |
+
# this will be an edge-case and we'll handle it later
|
21 |
+
return [text]
|
22 |
+
|
23 |
+
# Split the text using the identified delimiter
|
24 |
+
items = [item.strip() for item in text.split(delimiter)]
|
25 |
+
|
26 |
+
# Process each item to find food items
|
27 |
+
food_items = []
|
28 |
+
for item in items:
|
29 |
+
doc = nlp(item)
|
30 |
+
tokens = [token.text for token in doc]
|
31 |
+
# Check if any noun in the list of known nouns is present in the tokens
|
32 |
+
for token in doc:
|
33 |
+
if token.pos_ == "NOUN":
|
34 |
+
food_items.append(item.strip())
|
35 |
+
break
|
36 |
+
|
37 |
+
return food_items
|
38 |
+
|
old_experiments/bert.py
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from transformers import BertTokenizer, BertModel
|
3 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
4 |
+
import torch
|
5 |
+
import numpy as np
|
6 |
+
import re
|
7 |
+
|
8 |
+
# Load pre-trained BERT model and tokenizer
|
9 |
+
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
|
10 |
+
model = BertModel.from_pretrained('bert-base-uncased')
|
11 |
+
|
12 |
+
# Load dictionary from CSV file
|
13 |
+
csv_file_path = './dictionary/dictionary.csv'
|
14 |
+
df = pd.read_csv(csv_file_path)
|
15 |
+
dictionary = df['description'].tolist()
|
16 |
+
|
17 |
+
# Method to compute cosine similarity between two embeddings
|
18 |
+
def compute_cosine_similarity(embedding1, embedding2):
|
19 |
+
return cosine_similarity(embedding1, embedding2)[0][0]
|
20 |
+
|
21 |
+
# Method to get BERT embeddings
|
22 |
+
def get_bert_embedding(text):
|
23 |
+
inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True)
|
24 |
+
outputs = model(**inputs)
|
25 |
+
return outputs.last_hidden_state.mean(dim=1).detach().numpy()
|
26 |
+
|
27 |
+
# Method to find the best match for the input word in the dictionary
|
28 |
+
def match_word(input_word, dictionary):
|
29 |
+
# Extract words from the input
|
30 |
+
words = re.findall(r'\w+', input_word.lower())
|
31 |
+
|
32 |
+
# Filter dictionary based on words
|
33 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
34 |
+
|
35 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
36 |
+
# print(f"Filtered dictionary: {filtered_dictionary}")
|
37 |
+
|
38 |
+
# Proceed with BERT embeddings and cosine similarity on the filtered dictionary
|
39 |
+
input_embedding = get_bert_embedding(input_word)
|
40 |
+
similarities = []
|
41 |
+
|
42 |
+
for entry in filtered_dictionary:
|
43 |
+
entry_embedding = get_bert_embedding(entry)
|
44 |
+
similarity_score = compute_cosine_similarity(input_embedding, entry_embedding)
|
45 |
+
similarities.append((entry, similarity_score))
|
46 |
+
|
47 |
+
# print(similarities)
|
48 |
+
|
49 |
+
if similarities:
|
50 |
+
best_match = max(similarities, key=lambda x: x[1])
|
51 |
+
return best_match[0] if best_match[1] > 0.7 else None
|
52 |
+
else:
|
53 |
+
return None
|
54 |
+
|
55 |
+
# Example usage
|
56 |
+
input_words = ["Yellow Squash", "Cauliflower", "Habanero Pepper", "Bananas (12 lbs)", "Squash mix italian/yellow (30 lbs )"]
|
57 |
+
|
58 |
+
# Filtered dictionary size: 224
|
59 |
+
# Input word: Yellow Squash
|
60 |
+
# Matched entry: None
|
61 |
+
|
62 |
+
# Filtered dictionary size: 37
|
63 |
+
# Input word: Cauliflower
|
64 |
+
# Matched entry: Fried cauliflower
|
65 |
+
|
66 |
+
# Filtered dictionary size: 185
|
67 |
+
# Input word: Habanero Pepper
|
68 |
+
# Matched entry: Peppers, ancho, dried
|
69 |
+
|
70 |
+
# Filtered dictionary size: 414
|
71 |
+
# Input word: Bananas (12 lbs)
|
72 |
+
# Matched entry: Bananas, raw
|
73 |
+
|
74 |
+
# Filtered dictionary size: 784
|
75 |
+
# Input word: Squash mix italian/yellow (30 lbs )
|
76 |
+
# Matched entry: Nutritional powder mix (Slim Fast)
|
77 |
+
|
78 |
+
|
79 |
+
|
80 |
+
for input_word in input_words:
|
81 |
+
matched_entry = match_word(input_word, dictionary)
|
82 |
+
print("Input word:", input_word)
|
83 |
+
print("Matched entry:", matched_entry)
|
84 |
+
print()
|
old_experiments/bert2.py
ADDED
File without changes
|
old_experiments/experiment2.py
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import pickle
|
3 |
+
import pandas as pd
|
4 |
+
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
|
5 |
+
import torch
|
6 |
+
import re
|
7 |
+
from tqdm import tqdm
|
8 |
+
from sklearn.metrics.pairwise import cosine_similarity as sklearn_cosine_similarity
|
9 |
+
from sklearn.feature_extraction.text import TfidfVectorizer
|
10 |
+
|
11 |
+
# Check if MPS is available
|
12 |
+
device = torch.device('mps' if torch.backends.mps.is_available() else 'cpu')
|
13 |
+
print("Device:", device)
|
14 |
+
|
15 |
+
# Load model and tokenizer
|
16 |
+
model_id = "meta-llama/Meta-Llama-3-8B"
|
17 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
18 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16).to(device)
|
19 |
+
|
20 |
+
# Preprocess the dictionary words
|
21 |
+
# We should remove the word "raw" from the dictionary words
|
22 |
+
# Also, if the dictionary word is comma separated, we should remove the comma and reverse the order
|
23 |
+
# So, for example, "Tomato, Roma" should be converted to "Roma Tomato"
|
24 |
+
|
25 |
+
def preprocess_dictionary_word(text):
|
26 |
+
# lowercase the word and remove leading/trailing whitespaces
|
27 |
+
text = text.strip().lower()
|
28 |
+
|
29 |
+
# Remove the word "raw"
|
30 |
+
text = text.replace(", raw", "").replace(" raw", "")
|
31 |
+
|
32 |
+
# Remove the word "nfs" (not further specified)
|
33 |
+
text = text.replace(", nfs", "").replace(" nfs", "")
|
34 |
+
|
35 |
+
# If the text contains a comma, reverse the order
|
36 |
+
if ',' in text:
|
37 |
+
parts = [part.strip() for part in text.split(',')]
|
38 |
+
text = ' '.join(reversed(parts))
|
39 |
+
|
40 |
+
return text
|
41 |
+
|
42 |
+
def generate_embedding(sentence):
|
43 |
+
inputs = tokenizer(sentence, return_tensors='pt').to(device)
|
44 |
+
with torch.no_grad():
|
45 |
+
outputs = model(**inputs)
|
46 |
+
embeddings = outputs.logits.mean(dim=1).squeeze().cpu()
|
47 |
+
return embeddings
|
48 |
+
|
49 |
+
def cosine_similarity(embedding1, embedding2):
|
50 |
+
return torch.nn.functional.cosine_similarity(embedding1, embedding2, dim=0).item()
|
51 |
+
|
52 |
+
|
53 |
+
# Load the dictionary
|
54 |
+
csv_file_path = './dictionary/dictionary.csv'
|
55 |
+
df_dictionary = pd.read_csv(csv_file_path)
|
56 |
+
dictionary = df_dictionary['description'].astype(str).tolist()
|
57 |
+
|
58 |
+
# Load the input words
|
59 |
+
input_file_path = 'raw/food-forward-2023-raw-data - food-forward-2023-raw-data.csv'
|
60 |
+
df_input = pd.read_csv(input_file_path)
|
61 |
+
input_words = df_input['description'].astype(str).tolist()
|
62 |
+
|
63 |
+
# Check if the embeddings pickle file exists
|
64 |
+
pickle_file_path = './dictionary_embeddings_llama.pkl'
|
65 |
+
if os.path.exists(pickle_file_path):
|
66 |
+
with open(pickle_file_path, 'rb') as f:
|
67 |
+
dictionary_embeddings = pickle.load(f)
|
68 |
+
else:
|
69 |
+
# Generate embeddings for dictionary words
|
70 |
+
dictionary_embeddings = {}
|
71 |
+
for desc in tqdm(dictionary, desc="Generating embeddings for dictionary words"):
|
72 |
+
dictionary_embeddings[desc] = generate_embedding(preprocess_dictionary_word(desc))
|
73 |
+
|
74 |
+
# Save the embeddings to a pickle file
|
75 |
+
with open(pickle_file_path, 'wb') as f:
|
76 |
+
pickle.dump(dictionary_embeddings, f)
|
77 |
+
|
78 |
+
# Find the most similar word in the dictionary for each input word
|
79 |
+
results = []
|
80 |
+
for input_word in tqdm(input_words, desc="Processing input words"):
|
81 |
+
if not isinstance(input_word, str) or not input_word:
|
82 |
+
continue
|
83 |
+
|
84 |
+
input_word_clean = re.sub(r'\(.*?\)', '', input_word).strip()
|
85 |
+
|
86 |
+
print(f"Processing input word: {input_word}\nCleaned: {input_word_clean}")
|
87 |
+
input_embedding = generate_embedding(input_word_clean)
|
88 |
+
|
89 |
+
similarities = [(desc, cosine_similarity(input_embedding, dict_embedding))
|
90 |
+
for desc, dict_embedding in dictionary_embeddings.items()]
|
91 |
+
most_similar_word, highest_score = max(similarities, key=lambda x: x[1])
|
92 |
+
print(f"Most similar word: {most_similar_word}")
|
93 |
+
|
94 |
+
# Calculate confidence score
|
95 |
+
high_similarities = [(desc, score) for desc, score in similarities if abs(score - highest_score) <= 0.05]
|
96 |
+
high_similarities.sort(key=lambda x: x[1], reverse=True)
|
97 |
+
confidence_score = 1 if len(high_similarities) <= 1 else 0
|
98 |
+
|
99 |
+
print(f"Most similar word: {most_similar_word}")
|
100 |
+
|
101 |
+
similar_words = []
|
102 |
+
if confidence_score == 0:
|
103 |
+
similar_words = [desc for desc, score in high_similarities[:5]] # Limit to top 5 similar words
|
104 |
+
|
105 |
+
results.append((input_word, input_word_clean, most_similar_word, highest_score, confidence_score, similar_words))
|
106 |
+
|
107 |
+
|
108 |
+
# Print the results
|
109 |
+
for input_word, input_word_clean, most_similar_word, score, confidence, similar_words in results:
|
110 |
+
print(f"Input word: {input_word}")
|
111 |
+
print(f"Cleaned word: {input_word_clean}")
|
112 |
+
print(f"Most similar word: {most_similar_word}")
|
113 |
+
print(f"Similarity score: {score}")
|
114 |
+
print(f"Confidence score: {confidence}")
|
115 |
+
print(f"Similar words: {similar_words}\n")
|
116 |
+
|
117 |
+
# Export results to CSV
|
118 |
+
output_file_path = './results/experiment2.csv'
|
119 |
+
df_results = pd.DataFrame(results, columns=['input_word', 'input_word_clean', 'match_word', 'similarity_score', 'confidence_score', 'similar_words'])
|
120 |
+
df_results.to_csv(output_file_path, index=False)
|
121 |
+
|
122 |
+
|
123 |
+
|
124 |
+
# If there are a number of results that are within 0.01 of each other, then we need to consider all of them
|
125 |
+
|
126 |
+
|
127 |
+
# cosine_similarity(generate_embedding("Italian Squash"), generate_embedding("Squash, Italian, raw"))
|
128 |
+
# cosine_similarity(generate_embedding("Italian Squash"), generate_embedding("Italian Sausage"))
|
129 |
+
|
130 |
+
# cosine_similarity(generate_embedding("Tomato - Beefsteak Tomato"), generate_embedding("Beef with tomato-based sauce"))
|
131 |
+
|
132 |
+
# cosine_similarity(generate_embedding("Tomato - Beefsteak Tomato"), generate_embedding("Tomato, Roma"))
|
133 |
+
|
134 |
+
# cosine_similarity(generate_embedding("Tomato - Beefsteak Tomato"), generate_embedding("Tomato, raw"))
|
135 |
+
|
136 |
+
# cosine_similarity(generate_embedding("Eggplant"), generate_embedding("Eggplant dip"))
|
137 |
+
# cosine_similarity(generate_embedding("Eggplant"), generate_embedding("Eggplant,raw"))
|
138 |
+
# cosine_similarity(generate_embedding("Eggplant"), generate_embedding("Eggplant raw"))
|
139 |
+
# cosine_similarity(generate_embedding("Eggplant"), generate_embedding("raw Eggplant"))
|
old_experiments/llama3-gpu-compare.py
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
|
3 |
+
import torch
|
4 |
+
import re
|
5 |
+
from tqdm import tqdm
|
6 |
+
|
7 |
+
# Check if MPS is available
|
8 |
+
device = torch.device('mps' if torch.backends.mps.is_available() else 'cpu')
|
9 |
+
|
10 |
+
print("Device:", device)
|
11 |
+
|
12 |
+
# Load model and tokenizer
|
13 |
+
model_id = "meta-llama/Meta-Llama-3-8B"
|
14 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
15 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16).to(device)
|
16 |
+
|
17 |
+
# Load dictionary from CSV file
|
18 |
+
csv_file_path = '/Users/bw/Webstuff/btest/test/dictionary.csv'
|
19 |
+
df = pd.read_csv(csv_file_path)
|
20 |
+
dictionary = df['description'].tolist()
|
21 |
+
|
22 |
+
# Define the prompt with instructions for comparison
|
23 |
+
compare_prompt = "Compare the following two texts and rate their similarity on a scale from 0 to 1. Text 1: {} Text 2: {}. Similarity score: "
|
24 |
+
|
25 |
+
# Method to generate embeddings using the text generation pipeline
|
26 |
+
def generate_embedding(sentence):
|
27 |
+
input_text = sentence
|
28 |
+
inputs = tokenizer(input_text, return_tensors='pt').to(device)
|
29 |
+
with torch.no_grad():
|
30 |
+
outputs = model(**inputs)
|
31 |
+
embeddings = outputs.logits.mean(dim=1).squeeze().cpu()
|
32 |
+
return embeddings
|
33 |
+
|
34 |
+
# Method to get similarity score using Llama model's comprehension
|
35 |
+
def get_similarity_score(text1, text2):
|
36 |
+
input_text = compare_prompt.format(text1, text2)
|
37 |
+
inputs = tokenizer(input_text, return_tensors='pt').to(device)
|
38 |
+
with torch.no_grad():
|
39 |
+
outputs = model.generate(**inputs, max_new_tokens=50)
|
40 |
+
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
41 |
+
try:
|
42 |
+
score = float(re.findall(r"\d+\.\d+", generated_text)[-1])
|
43 |
+
except:
|
44 |
+
score = 0.0
|
45 |
+
|
46 |
+
print(text1, text2, score)
|
47 |
+
|
48 |
+
return score
|
49 |
+
|
50 |
+
# Method to find the best match for the input word in the dictionary
|
51 |
+
def match_word(input_word, dictionary):
|
52 |
+
# Remove text in parentheses
|
53 |
+
input_word_clean = re.sub(r'\(.*?\)', '', input_word).strip()
|
54 |
+
words = re.findall(r'\w+', input_word_clean.lower())
|
55 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
56 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
57 |
+
|
58 |
+
similarities = []
|
59 |
+
|
60 |
+
for entry in tqdm(filtered_dictionary, desc="Processing Entries"):
|
61 |
+
score = get_similarity_score(input_word_clean, entry)
|
62 |
+
if 'raw' in entry.lower() and len(words) == 1:
|
63 |
+
score += 0.1 # Boost for raw version and single-word input
|
64 |
+
similarities.append((entry, score))
|
65 |
+
|
66 |
+
if similarities:
|
67 |
+
best_match = max(similarities, key=lambda x: x[1])
|
68 |
+
return best_match if best_match[1] > 0.7 else None
|
69 |
+
else:
|
70 |
+
return None
|
71 |
+
|
72 |
+
# Example usage
|
73 |
+
input_words = [
|
74 |
+
"Pepper - Habanero Pepper", "Bananas (12 lbs)", "Squash - Yellow Squash", "Cauliflower",
|
75 |
+
"Squash mix italian/yellow (30 lbs)", "Tomato - Roma Tomato", "Tomato - Grape Tomato",
|
76 |
+
"Squash - Mexican Squash", "Pepper - Bell Pepper", "Squash - Italian Squash",
|
77 |
+
"Pepper - Red Fresno Pepper", "Tomato - Cherry Tomato", "Pepper - Serrano Pepper",
|
78 |
+
"Kale ( 5 lbs)", "Tomato - Beefsteak Tomato", "Pepper - Anaheim Pepper",
|
79 |
+
"Banana - Burro Banana", "Squash - Butternut Squash", "Apricot ( 10 lbs)",
|
80 |
+
"Squash - Acorn Squash", "Tomato - Heirloom Tomato", "Pepper - Pasilla Pepper",
|
81 |
+
"Pepper - Jalapeno Pepper", "carrot (10 lbs )"
|
82 |
+
]
|
83 |
+
|
84 |
+
for input_word in tqdm(input_words, desc="Matching Words"):
|
85 |
+
print("Input word:", input_word)
|
86 |
+
matched_entry = match_word(input_word, dictionary)
|
87 |
+
if matched_entry:
|
88 |
+
print("Matched entry:", matched_entry[0])
|
89 |
+
print("Similarity score:", matched_entry[1])
|
90 |
+
else:
|
91 |
+
print("Matched entry: None")
|
92 |
+
print()
|
old_experiments/llama3-gpu-compare2.py
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
3 |
+
import torch
|
4 |
+
import re
|
5 |
+
from tqdm import tqdm
|
6 |
+
import json
|
7 |
+
|
8 |
+
# Check if MPS is available
|
9 |
+
device = torch.device('mps' if torch.backends.mps.is_available() else 'cpu')
|
10 |
+
|
11 |
+
print("Device:", device)
|
12 |
+
|
13 |
+
# Load model and tokenizer
|
14 |
+
model_id = "meta-llama/Meta-Llama-3-8B-instruct"
|
15 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
16 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16).to(device)
|
17 |
+
|
18 |
+
# Load dictionary from CSV file
|
19 |
+
csv_file_path = '/Users/bw/Webstuff/btest/test/dictionary.csv'
|
20 |
+
df = pd.read_csv(csv_file_path)
|
21 |
+
dictionary = df['description'].tolist()
|
22 |
+
|
23 |
+
# Define the prompt with instructions for comparison
|
24 |
+
compare_prompt = "Instructions: Provide a one item answer, do not response with a sentence. Respond in JSON format. Q: What food item from this list is most similar to: '{}'?\nList:\n- {}\nA:"
|
25 |
+
|
26 |
+
# Method to get similarity score using Llama model's comprehension
|
27 |
+
def get_similarity_score(input_word, dictionary):
|
28 |
+
dictionary_list_str = "\n- ".join(dictionary)
|
29 |
+
input_text = compare_prompt.format(input_word, dictionary_list_str)
|
30 |
+
inputs = tokenizer(input_text, return_tensors='pt').to(device)
|
31 |
+
with torch.no_grad():
|
32 |
+
outputs = model.generate(**inputs, max_new_tokens=50, do_sample=True, top_k=50, top_p=0.9, temperature=0.7)
|
33 |
+
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
34 |
+
# Extract the matched word from the generated text
|
35 |
+
print("Generated text:", generated_text)
|
36 |
+
match = re.search(r'Q:.*?\nA:\s*(.*)', generated_text)
|
37 |
+
result = match.group(1).strip() if match else None
|
38 |
+
|
39 |
+
# Format the result as JSON
|
40 |
+
response_json = json.dumps({"input_word": input_word, "matched_entry": result})
|
41 |
+
return response_json
|
42 |
+
|
43 |
+
# Method to find the best match for the input word in the dictionary
|
44 |
+
def match_word(input_word, dictionary):
|
45 |
+
# Remove text in parentheses and split into words
|
46 |
+
input_word_clean = re.sub(r'\(.*?\)', '', input_word).strip()
|
47 |
+
words = re.findall(r'\w+', input_word_clean.lower())
|
48 |
+
|
49 |
+
# Filter dictionary entries containing any of the words
|
50 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
51 |
+
|
52 |
+
# remove duplicate entries
|
53 |
+
filtered_dictionary = list(set(filtered_dictionary))
|
54 |
+
|
55 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
56 |
+
|
57 |
+
if not filtered_dictionary:
|
58 |
+
return None
|
59 |
+
|
60 |
+
# Get similarity score
|
61 |
+
result = get_similarity_score(input_word_clean, filtered_dictionary)
|
62 |
+
return result
|
63 |
+
|
64 |
+
# Example usage
|
65 |
+
input_words = [
|
66 |
+
"Pepper - Habanero Pepper", "Bananas (12 lbs)", "Squash - Yellow Squash", "Cauliflower",
|
67 |
+
"Squash mix italian/yellow (30 lbs)", "Tomato - Roma Tomato", "Tomato - Grape Tomato",
|
68 |
+
"Squash - Mexican Squash", "Pepper - Bell Pepper", "Squash - Italian Squash",
|
69 |
+
"Pepper - Red Fresno Pepper", "Tomato - Cherry Tomato", "Pepper - Serrano Pepper",
|
70 |
+
"Kale ( 5 lbs)", "Tomato - Beefsteak Tomato", "Pepper - Anaheim Pepper",
|
71 |
+
"Banana - Burro Banana", "Squash - Butternut Squash", "Apricot ( 10 lbs)",
|
72 |
+
"Squash - Acorn Squash", "Tomato - Heirloom Tomato", "Pepper - Pasilla Pepper",
|
73 |
+
"Pepper - Jalapeno Pepper", "carrot (10 lbs )"
|
74 |
+
]
|
75 |
+
|
76 |
+
for input_word in tqdm(input_words, desc="Matching Words"):
|
77 |
+
print("Input word:", input_word)
|
78 |
+
matched_entry = match_word(input_word, dictionary)
|
79 |
+
print("Matched entry (JSON):", matched_entry if matched_entry else "None")
|
80 |
+
print()
|
old_experiments/llama3-gpu-instructions.py
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
|
3 |
+
import torch
|
4 |
+
import re
|
5 |
+
from tqdm import tqdm
|
6 |
+
|
7 |
+
# Check if MPS is available
|
8 |
+
device = torch.device('mps' if torch.backends.mps.is_available() else 'cpu')
|
9 |
+
|
10 |
+
print("Device:", device)
|
11 |
+
|
12 |
+
# Load model and tokenizer
|
13 |
+
model_id = "meta-llama/Meta-Llama-3-8B"
|
14 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
15 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16).to(device)
|
16 |
+
|
17 |
+
# Load dictionary from CSV file
|
18 |
+
csv_file_path = '/Users/bw/Webstuff/btest/test/dictionary.csv'
|
19 |
+
df = pd.read_csv(csv_file_path)
|
20 |
+
dictionary = df['description'].tolist()
|
21 |
+
|
22 |
+
# Define the prompt with instructions
|
23 |
+
prompt = "The text sometimes comes hyphenated, where the part before the hyphen is the general category, and the item after the hyphen is the more specific item. Please generate an embedding for the following text: "
|
24 |
+
|
25 |
+
# Method to generate embeddings using the text generation pipeline
|
26 |
+
def generate_embedding(sentence):
|
27 |
+
# Combine the prompt with the sentence
|
28 |
+
input_text = prompt + sentence
|
29 |
+
inputs = tokenizer(input_text, return_tensors='pt').to(device)
|
30 |
+
with torch.no_grad():
|
31 |
+
outputs = model(**inputs)
|
32 |
+
embeddings = outputs.logits.mean(dim=1).squeeze().cpu()
|
33 |
+
return embeddings
|
34 |
+
|
35 |
+
# Cosine Similarity
|
36 |
+
def cosine_similarity(embedding1, embedding2):
|
37 |
+
return torch.nn.functional.cosine_similarity(embedding1, embedding2, dim=0).item()
|
38 |
+
|
39 |
+
# Custom scoring function
|
40 |
+
def custom_score(input_word, input_embedding, entry_embedding, entry_text):
|
41 |
+
# Calculate cosine similarity
|
42 |
+
similarity_score = cosine_similarity(input_embedding, entry_embedding)
|
43 |
+
|
44 |
+
# Boost score if the input word is a single word and the entry contains preferred keywords
|
45 |
+
if 'raw' in entry_text.lower() and len(re.findall(r'\w+', input_word.lower())) == 1:
|
46 |
+
similarity_score += 0.1 # Adjust this value as needed
|
47 |
+
|
48 |
+
return similarity_score
|
49 |
+
|
50 |
+
# Method to find the best match for the input word in the dictionary
|
51 |
+
def match_word(input_word, dictionary):
|
52 |
+
# Remove text in parentheses
|
53 |
+
input_word_clean = re.sub(r'\(.*?\)', '', input_word).strip()
|
54 |
+
words = re.findall(r'\w+', input_word_clean.lower())
|
55 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
56 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
57 |
+
|
58 |
+
input_embedding = generate_embedding(input_word_clean)
|
59 |
+
similarities = []
|
60 |
+
|
61 |
+
for entry in tqdm(filtered_dictionary, desc="Processing Entries"):
|
62 |
+
entry_embedding = generate_embedding(entry)
|
63 |
+
score = custom_score(input_word_clean, input_embedding, entry_embedding, entry)
|
64 |
+
similarities.append((entry, score))
|
65 |
+
|
66 |
+
if similarities:
|
67 |
+
best_match = max(similarities, key=lambda x: x[1])
|
68 |
+
return best_match if best_match[1] > 0.7 else None
|
69 |
+
else:
|
70 |
+
return None
|
71 |
+
|
72 |
+
# Example usage
|
73 |
+
input_words = [
|
74 |
+
"Pepper - Habanero Pepper", "Bananas (12 lbs)", "Squash - Yellow Squash", "Cauliflower",
|
75 |
+
"Squash mix italian/yellow (30 lbs)", "Tomato - Roma Tomato", "Tomato - Grape Tomato",
|
76 |
+
"Squash - Mexican Squash", "Pepper - Bell Pepper", "Squash - Italian Squash",
|
77 |
+
"Pepper - Red Fresno Pepper", "Tomato - Cherry Tomato", "Pepper - Serrano Pepper",
|
78 |
+
"Kale ( 5 lbs)", "Tomato - Beefsteak Tomato", "Pepper - Anaheim Pepper",
|
79 |
+
"Banana - Burro Banana", "Squash - Butternut Squash", "Apricot ( 10 lbs)",
|
80 |
+
"Squash - Acorn Squash", "Tomato - Heirloom Tomato", "Pepper - Pasilla Pepper",
|
81 |
+
"Pepper - Jalapeno Pepper", "carrot (10 lbs )"
|
82 |
+
]
|
83 |
+
|
84 |
+
for input_word in tqdm(input_words, desc="Matching Words"):
|
85 |
+
print("Input word:", input_word)
|
86 |
+
matched_entry = match_word(input_word, dictionary)
|
87 |
+
if matched_entry:
|
88 |
+
print("Matched entry:", matched_entry[0])
|
89 |
+
print("Similarity score:", matched_entry[1])
|
90 |
+
else:
|
91 |
+
print("Matched entry: None")
|
92 |
+
print()
|
old_experiments/llama3-gpu.py
ADDED
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import pickle
|
3 |
+
import pandas as pd
|
4 |
+
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
|
5 |
+
import torch
|
6 |
+
import re
|
7 |
+
from tqdm import tqdm
|
8 |
+
|
9 |
+
# Check if MPS is available
|
10 |
+
device = torch.device('mps' if torch.backends.mps.is_available() else 'cpu')
|
11 |
+
|
12 |
+
print("Device:", device)
|
13 |
+
|
14 |
+
# Load model and tokenizer
|
15 |
+
model_id = "meta-llama/Meta-Llama-3-8B"
|
16 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
17 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16).to(device)
|
18 |
+
|
19 |
+
# Load dictionary from CSV file
|
20 |
+
csv_file_path = './dictionary/dictionary.csv'
|
21 |
+
df = pd.read_csv(csv_file_path)
|
22 |
+
dictionary = df['description'].tolist()
|
23 |
+
|
24 |
+
# Cosine Similarity
|
25 |
+
def cosine_similarity(embedding1, embedding2):
|
26 |
+
return torch.nn.functional.cosine_similarity(embedding1, embedding2, dim=0).item()
|
27 |
+
|
28 |
+
# Euclidean Distance
|
29 |
+
def euclidean_distance(embedding1, embedding2):
|
30 |
+
return -torch.dist(embedding1, embedding2).item() # Negative to keep similarity comparison consistent
|
31 |
+
|
32 |
+
# Method to generate embeddings using the text generation pipeline
|
33 |
+
def generate_embedding(sentence):
|
34 |
+
inputs = tokenizer(sentence, return_tensors='pt').to(device)
|
35 |
+
with torch.no_grad():
|
36 |
+
outputs = model(**inputs)
|
37 |
+
embeddings = outputs.logits.mean(dim=1).squeeze().cpu()
|
38 |
+
return embeddings
|
39 |
+
|
40 |
+
# Method to find the best match for the input word in the dictionary
|
41 |
+
def match_word(input_word, dictionary, similarity_measure):
|
42 |
+
# Remove anything in parentheses (i.e. (12 oz))
|
43 |
+
input_word_clean = re.sub(r'\(.*?\)', '', input_word).strip()
|
44 |
+
|
45 |
+
# Check for substring relationship and adjust input_word_clean
|
46 |
+
if '-' in input_word_clean:
|
47 |
+
left_term, right_term = map(str.strip, input_word_clean.split('-'))
|
48 |
+
if left_term.lower() in right_term.lower():
|
49 |
+
input_word_clean = right_term
|
50 |
+
|
51 |
+
words = re.findall(r'\w+', input_word_clean.lower())
|
52 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
53 |
+
# print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
54 |
+
|
55 |
+
input_embedding = generate_embedding(input_word_clean)
|
56 |
+
similarities = []
|
57 |
+
|
58 |
+
for entry in filtered_dictionary:
|
59 |
+
entry_embedding = dictionary_embeddings[entry] # Use pre-computed embedding
|
60 |
+
similarity_score = similarity_measure(input_embedding, entry_embedding)
|
61 |
+
similarities.append((entry, similarity_score))
|
62 |
+
|
63 |
+
if similarities:
|
64 |
+
best_match = max(similarities, key=lambda x: x[1])
|
65 |
+
return best_match if best_match[1] > 0.7 else None
|
66 |
+
else:
|
67 |
+
return None
|
68 |
+
|
69 |
+
# Check if the pickle file exists
|
70 |
+
if os.path.exists('dictionary_embeddings.pkl'):
|
71 |
+
# Load the pre-computed embeddings from the pickle file
|
72 |
+
with open('dictionary_embeddings.pkl', 'rb') as f:
|
73 |
+
dictionary_embeddings = pickle.load(f)
|
74 |
+
else:
|
75 |
+
# Generate embeddings for all entries in the dictionary
|
76 |
+
dictionary_embeddings = {}
|
77 |
+
for entry in tqdm(dictionary, desc="Generating Embeddings"):
|
78 |
+
dictionary_embeddings[entry] = generate_embedding(entry)
|
79 |
+
|
80 |
+
# Save the pre-computed embeddings to a pickle file
|
81 |
+
with open('dictionary_embeddings.pkl', 'wb') as f:
|
82 |
+
pickle.dump(dictionary_embeddings, f)
|
83 |
+
|
84 |
+
|
85 |
+
input_file_path = 'raw/food-forward-2023-raw-data - food-forward-2023-raw-data.csv'
|
86 |
+
df = pd.read_csv(input_file_path)
|
87 |
+
input_words = df['description'].tolist()
|
88 |
+
|
89 |
+
similarity_measure = cosine_similarity
|
90 |
+
results = []
|
91 |
+
for input_word in tqdm(input_words, desc="Matching Words"):
|
92 |
+
# print("Input word:", input_word)
|
93 |
+
try:
|
94 |
+
matched_entry = match_word(input_word, dictionary, similarity_measure)
|
95 |
+
if (matched_entry):
|
96 |
+
# print("Matched entry:", matched_entry[0])
|
97 |
+
# print("Similarity score:", matched_entry[1])
|
98 |
+
results.append({
|
99 |
+
'input_word': input_word,
|
100 |
+
'matched_word': matched_entry[0],
|
101 |
+
'score': matched_entry[1]
|
102 |
+
})
|
103 |
+
else:
|
104 |
+
# print("Matched entry: None")
|
105 |
+
results.append({
|
106 |
+
'input_word': input_word,
|
107 |
+
'matched_word': None,
|
108 |
+
'score': None
|
109 |
+
})
|
110 |
+
print()
|
111 |
+
except Exception as e:
|
112 |
+
print("Error:", e)
|
113 |
+
results.append({
|
114 |
+
'input_word': input_word,
|
115 |
+
'matched_word': None,
|
116 |
+
'score': None
|
117 |
+
})
|
118 |
+
# print()
|
119 |
+
|
120 |
+
df_results = pd.DataFrame(results)
|
121 |
+
csv_file_path = f'results/results.csv'
|
122 |
+
df_results.to_csv(csv_file_path, index=False)
|
old_experiments/llama3-gpu2.py
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from sentence_transformers import SentenceTransformer, util
|
2 |
+
import pandas as pd
|
3 |
+
from tqdm import tqdm
|
4 |
+
import os
|
5 |
+
import pickle
|
6 |
+
|
7 |
+
# Load pre-trained sentence transformer model
|
8 |
+
model = SentenceTransformer('all-MiniLM-L6-v2')
|
9 |
+
|
10 |
+
def generate_st_embedding(sentence):
|
11 |
+
return model.encode(sentence, convert_to_tensor=True)
|
12 |
+
|
13 |
+
def cosine_similarity_st(embedding1, embedding2):
|
14 |
+
return util.pytorch_cos_sim(embedding1, embedding2).item()
|
15 |
+
|
16 |
+
# Load the dictionary
|
17 |
+
csv_file_path = './dictionary/dictionary.csv'
|
18 |
+
df_dictionary = pd.read_csv(csv_file_path)
|
19 |
+
dictionary = df_dictionary['description'].tolist()
|
20 |
+
|
21 |
+
# Load the input words
|
22 |
+
input_file_path = 'raw/test.csv'
|
23 |
+
df_input = pd.read_csv(input_file_path)
|
24 |
+
input_words = df_input['description'].tolist()
|
25 |
+
|
26 |
+
print("Everything loaded...")
|
27 |
+
|
28 |
+
# Check if the embeddings pickle file exists
|
29 |
+
pickle_file_path = './sbert_dictionary_embeddings.pkl'
|
30 |
+
if os.path.exists(pickle_file_path):
|
31 |
+
with open(pickle_file_path, 'rb') as f:
|
32 |
+
dictionary_embeddings = pickle.load(f)
|
33 |
+
else:
|
34 |
+
# Generate embeddings for dictionary words
|
35 |
+
dictionary_embeddings = {}
|
36 |
+
for desc in tqdm(dictionary, desc="Generating embeddings for dictionary words"):
|
37 |
+
dictionary_embeddings[desc] = generate_st_embedding(desc)
|
38 |
+
|
39 |
+
# Save the embeddings to a pickle file
|
40 |
+
with open(pickle_file_path, 'wb') as f:
|
41 |
+
pickle.dump(dictionary_embeddings, f)
|
42 |
+
|
43 |
+
# Find the most similar word in the dictionary for each input word
|
44 |
+
results = []
|
45 |
+
for input_word in tqdm(input_words, desc="Processing input words"):
|
46 |
+
input_embedding = generate_st_embedding(input_word)
|
47 |
+
similarities = [(desc, cosine_similarity_st(input_embedding, dict_embedding))
|
48 |
+
for desc, dict_embedding in dictionary_embeddings.items()]
|
49 |
+
most_similar_word, highest_score = max(similarities, key=lambda x: x[1])
|
50 |
+
results.append((input_word, most_similar_word, highest_score))
|
51 |
+
|
52 |
+
# Print the results
|
53 |
+
for input_word, most_similar_word, score in results:
|
54 |
+
print(f"Input word: {input_word}")
|
55 |
+
print(f"Most similar word: {most_similar_word}")
|
56 |
+
print(f"Similarity score: {score}\n")
|
old_experiments/llama3-simple.py
ADDED
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
2 |
+
|
3 |
+
food = ["Cheese dip with chili pepper",
|
4 |
+
"Pepperoni, NFS",
|
5 |
+
"Pepperoni, reduced fat",
|
6 |
+
"Pepperoni, reduced sodium",
|
7 |
+
"Stuffed green pepper, Puerto Rican style",
|
8 |
+
"Pepper steak",
|
9 |
+
"Sausage and peppers, no sauce",
|
10 |
+
"Pepperpot soup",
|
11 |
+
"Pizza with pepperoni, from frozen, thin crust",
|
12 |
+
"Pizza with pepperoni, from frozen, medium crust",
|
13 |
+
"Pizza with pepperoni, from frozen, thick crust",
|
14 |
+
"Pizza with pepperoni, from restaurant or fast food, NS as to type of crust",
|
15 |
+
"Pizza with pepperoni, from restaurant or fast food, thin crust",
|
16 |
+
"Pizza with pepperoni, from restaurant or fast food, medium crust",
|
17 |
+
"Pizza with pepperoni, from restaurant or fast food, thick crust",
|
18 |
+
"Pizza with pepperoni, stuffed crust",
|
19 |
+
"Pizza with pepperoni, from school lunch, thin crust",
|
20 |
+
"Pizza, with pepperoni, from school lunch, medium crust",
|
21 |
+
"Pizza with pepperoni, from school lunch, thick crust",
|
22 |
+
"Pizza with meat other than pepperoni, from frozen, thin crust",
|
23 |
+
"Pizza with meat other than pepperoni, from frozen, medium crust",
|
24 |
+
"Pizza with meat other than pepperoni, from frozen, thick crust",
|
25 |
+
"Pizza with meat other than pepperoni, from restaurant or fast food, NS as to type of crust",
|
26 |
+
"Pizza with meat other than pepperoni, from restaurant or fast food, thin crust",
|
27 |
+
"Pizza with meat other than pepperoni, from restaurant or fast food, medium crust",
|
28 |
+
"Pizza with meat other than pepperoni, from restaurant or fast food, thick crust",
|
29 |
+
"Pizza, with meat other than pepperoni, stuffed crust",
|
30 |
+
"Pizza, with meat other than pepperoni, from school lunch, medium crust",
|
31 |
+
"Pizza, with meat other than pepperoni, from school lunch, thin crust",
|
32 |
+
"Pizza, with meat other than pepperoni, from school lunch, thick crust",
|
33 |
+
"Stuffed pepper, with meat",
|
34 |
+
"Stuffed pepper, with rice and meat",
|
35 |
+
"Stuffed pepper, with rice, meatless",
|
36 |
+
"Pepper, hot chili, raw",
|
37 |
+
"Pepper, raw, NFS",
|
38 |
+
"Pepper, sweet, green, raw",
|
39 |
+
"Pepper, sweet, red, raw",
|
40 |
+
"Pepper, banana, raw",
|
41 |
+
"Seven-layer salad, lettuce salad made with a combination of onion, celery, green pepper, peas, mayonnaise, cheese, eggs, and/or bacon",
|
42 |
+
"Peppers, green, cooked",
|
43 |
+
"Peppers, red, cooked",
|
44 |
+
"Hot peppers, cooked",
|
45 |
+
"Peppers and onions, cooked, no added fat",
|
46 |
+
"Peppers and onions, cooked, fat added",
|
47 |
+
"Stuffed jalapeno pepper",
|
48 |
+
"Hot pepper sauce",
|
49 |
+
"Peppers, pickled",
|
50 |
+
"Pepper, hot, pickled",
|
51 |
+
"Pepper, for use on a sandwich",
|
52 |
+
"Soft drink, pepper type",
|
53 |
+
"Soft drink, pepper type, diet",
|
54 |
+
"Soft drink, pepper type, decaffeinated",
|
55 |
+
"Soft drink, pepper type, decaffeinated, diet",
|
56 |
+
"Green pepper, cooked, as ingredient",
|
57 |
+
"Red pepper, cooked, as ingredient",
|
58 |
+
"Pepperidge Farm, Goldfish, Baked Snack Crackers, Original",
|
59 |
+
"Pepperidge Farm, Goldfish, Baked Snack Crackers, Parmesan",
|
60 |
+
"Pepperidge Farm, Goldfish, Baked Snack Crackers, Pizza",
|
61 |
+
"Candies, YORK Peppermint Pattie",
|
62 |
+
"Pepperidge Farm, Goldfish, Baked Snack Crackers, Cheddar",
|
63 |
+
"Pepperidge Farm, Goldfish, Baked Snack Crackers, Explosive Pizza",
|
64 |
+
"Salad dressing, peppercorn dressing, commercial, regular",
|
65 |
+
"HORMEL ALWAYS TENDER, Pork Tenderloin, Peppercorn-Flavored",
|
66 |
+
"Peppers, sweet, red, canned, solids and liquids",
|
67 |
+
"Peppers, sweet, red, frozen, chopped, unprepared",
|
68 |
+
"Peppers, sweet, red, frozen, chopped, boiled, drained, without salt",
|
69 |
+
"Peppers, sweet, red, frozen, chopped, boiled, drained, with salt",
|
70 |
+
"Peppers, sweet, red, sauteed",
|
71 |
+
"Peppers, hot chile, sun-dried",
|
72 |
+
"Peppers, jalapeno, raw",
|
73 |
+
"Peppers, chili, green, canned",
|
74 |
+
"Peppers, hungarian, raw",
|
75 |
+
"Peppers, pasilla, dried",
|
76 |
+
"Corn with red and green peppers, canned, solids and liquids",
|
77 |
+
"Peppers, sweet, red, freeze-dried",
|
78 |
+
"Peppers, sweet, yellow, raw",
|
79 |
+
"Peppers, serrano, raw",
|
80 |
+
"Peppers, ancho, dried",
|
81 |
+
"Peppers, hot pickled, canned",
|
82 |
+
"Peppers, sweet, green, frozen, chopped, unprepared",
|
83 |
+
"Peppers, sweet, green, frozen, chopped, boiled, drained, without salt",
|
84 |
+
"Peppers, sweet, green, sauteed",
|
85 |
+
"Peppers, jalapeno, canned, solids and liquids",
|
86 |
+
"Peppers, hot chili, red, raw",
|
87 |
+
"Peppers, hot chili, red, canned, excluding seeds, solids and liquids",
|
88 |
+
"Peppers, sweet, red, raw",
|
89 |
+
"Peppers, sweet, green, cooked, boiled, drained, with salt",
|
90 |
+
"Peppers, sweet, red, cooked, boiled, drained, without salt",
|
91 |
+
"PIZZA HUT 14' Pepperoni Pizza, THIN 'N CRISPY Crust",
|
92 |
+
"DOMINO'S 14' Pepperoni Pizza, Crunchy Thin Crust",
|
93 |
+
"Peppers, hot chili, green, canned, pods, excluding seeds, solids and liquids",
|
94 |
+
"Peppers, sweet, green, raw",
|
95 |
+
"Peppers, sweet, green, cooked, boiled, drained, without salt",
|
96 |
+
"Peppers, sweet, green, canned, solids and liquids",
|
97 |
+
"Tomato products, canned, sauce, with onions, green peppers, and celery",
|
98 |
+
"Peppers, hot chili, green, raw",
|
99 |
+
"Peppers, sweet, red, cooked, boiled, drained, with salt",
|
100 |
+
"Peppers, sweet, green, frozen, chopped, cooked, boiled, drained, with salt",
|
101 |
+
"School Lunch, pizza, BIG DADDY'S LS 16' 51% Whole Grain Rolled Edge Turkey Pepperoni Pizza, frozen",
|
102 |
+
"School Lunch, pizza, TONY'S SMARTPIZZA Whole Grain 4x6 Pepperoni Pizza 50/50 Cheese, frozen",
|
103 |
+
"DIGIORNO Pizza, pepperoni topping, cheese stuffed crust, frozen, baked",
|
104 |
+
"DIGIORNO Pizza, pepperoni topping, rising crust, frozen, baked",
|
105 |
+
"DIGIORNO Pizza, pepperoni topping, thin crispy crust, frozen, baked",
|
106 |
+
"Fast Food, Pizza Chain, 14' pizza, pepperoni topping, thin crust",
|
107 |
+
"School Lunch, pizza, pepperoni topping, thin crust, whole grain, frozen, cooked",
|
108 |
+
"School Lunch, pizza, pepperoni topping, thick crust, whole grain, frozen, cooked",
|
109 |
+
"Spices, pepper, black",
|
110 |
+
"Spices, pepper, red or cayenne",
|
111 |
+
"Spices, pepper, white",
|
112 |
+
"Sauce, peppers, hot, chili, mature red, canned",
|
113 |
+
"Sauce, chili, peppers, hot, immature green, canned",
|
114 |
+
"Beverages, carbonated, low calorie, cola or pepper-types, with sodium saccharin, contains caffeine",
|
115 |
+
"DOMINO'S 14' Pepperoni Pizza, Classic Hand-Tossed Crust",
|
116 |
+
"DOMINO'S 14' Pepperoni Pizza, Ultimate Deep Dish Crust",
|
117 |
+
"LITTLE CAESARS 14' Original Round Pepperoni Pizza, Regular Crust",
|
118 |
+
"PIZZA HUT 14' Pepperoni Pizza, Hand-Tossed Crust",
|
119 |
+
"PIZZA HUT 14' Pepperoni Pizza, Pan Crust",
|
120 |
+
"Pizza, pepperoni topping, regular crust, frozen, cooked",
|
121 |
+
"Beverages, carbonated, low calorie, other than cola or pepper, without caffeine",
|
122 |
+
"Beverages, carbonated, low calorie, other than cola or pepper, with aspartame, contains caffeine",
|
123 |
+
"Beverages, carbonated, pepper-type, contains caffeine",
|
124 |
+
"PIZZA HUT 12' Pepperoni Pizza, Hand-Tossed Crust",
|
125 |
+
"PIZZA HUT 12' Pepperoni Pizza, Pan Crust",
|
126 |
+
"PAPA JOHN'S 14' Pepperoni Pizza, Original Crust",
|
127 |
+
"LITTLE CAESARS 14' Pepperoni Pizza, Large Deep Dish Crust",
|
128 |
+
"Fast Food, Pizza Chain, 14' pizza, pepperoni topping, regular crust",
|
129 |
+
"Fast Food, Pizza Chain, 14' pizza, pepperoni topping, thick crust",
|
130 |
+
"Peppermint, fresh",
|
131 |
+
"Sauce, ready-to-serve, pepper or hot",
|
132 |
+
"Sauce, ready-to-serve, pepper, TABASCO",
|
133 |
+
"Peppered loaf, pork, beef",
|
134 |
+
"Pepperoni, beef and pork, sliced",
|
135 |
+
"Hormel Pillow Pak Sliced Turkey Pepperoni",
|
136 |
+
"Turkey, breast, smoked, lemon pepper flavor, 97% fat-free",
|
137 |
+
"Beverages, carbonated, low calorie, cola or pepper-type, with aspartame, without caffeine",
|
138 |
+
"Beverages, carbonated, low calorie, cola or pepper-type, with aspartame, contains caffeine",
|
139 |
+
"Carbonated beverage, low calorie, other than cola or pepper, with sodium saccharin, without caffeine",
|
140 |
+
"NFY0907NU",
|
141 |
+
"NFY0907N6",
|
142 |
+
"NFY0907OU",
|
143 |
+
"OATMEAL COOKIES WITH RAISINS, PEPPERIDGE FARM SOFT BAKED",
|
144 |
+
"Peppers, bell, green, raw",
|
145 |
+
"Peppers, bell, yellow, raw",
|
146 |
+
"Peppers, bell, red, raw",
|
147 |
+
"Peppers, bell, orange, raw",
|
148 |
+
"peppers, bell, green, raw",
|
149 |
+
"peppers, bell, red, raw",
|
150 |
+
"peppers, bell, yellow, raw",
|
151 |
+
"peppers, bell, orange, raw",
|
152 |
+
"peppers, bell, red, raw, mini ",
|
153 |
+
"peppers, bell, orange, raw, mini "]
|
154 |
+
|
155 |
+
# Load the tokenizer and model from Hugging Face
|
156 |
+
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-instruct")
|
157 |
+
model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-instruct")
|
158 |
+
|
159 |
+
# Define the input message
|
160 |
+
input_text = "Return the name in a short JSON object. What item from this list is most similar to: 'Pepper - Habanero Pepper'. List: " + "; ".join(food)
|
161 |
+
|
162 |
+
# Tokenize the input
|
163 |
+
inputs = tokenizer(input_text, return_tensors="pt")
|
164 |
+
|
165 |
+
# Generate the response
|
166 |
+
outputs = model.generate(inputs["input_ids"], max_new_tokens=50, pad_token_id=tokenizer.eos_token_id)
|
167 |
+
|
168 |
+
# Decode the output
|
169 |
+
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
170 |
+
|
171 |
+
print(response)
|
old_experiments/llama3.py
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from transformers import pipeline
|
3 |
+
import torch
|
4 |
+
import re
|
5 |
+
|
6 |
+
model_id = "meta-llama/Meta-Llama-3-8B"
|
7 |
+
|
8 |
+
generator = pipeline(
|
9 |
+
"text-generation",
|
10 |
+
model="meta-llama/Meta-Llama-3-8B",
|
11 |
+
model_kwargs={"torch_dtype": torch.bfloat16},
|
12 |
+
device=-1
|
13 |
+
)
|
14 |
+
|
15 |
+
# Load dictionary from CSV file
|
16 |
+
csv_file_path = './dictionary/dictionary.csv'
|
17 |
+
df = pd.read_csv(csv_file_path)
|
18 |
+
dictionary = df['description'].tolist()
|
19 |
+
|
20 |
+
# Method to generate embeddings using the text generation pipeline
|
21 |
+
def generate_embedding(sentence):
|
22 |
+
# Generate a text embedding using the pipeline
|
23 |
+
inputs = generator.tokenizer(sentence, return_tensors='pt')['input_ids']
|
24 |
+
with torch.no_grad():
|
25 |
+
outputs = generator.model(inputs)
|
26 |
+
# Extract the embeddings from the logits
|
27 |
+
embeddings = outputs.logits.mean(dim=1).squeeze()
|
28 |
+
return embeddings
|
29 |
+
|
30 |
+
# Method to find the best match for the input word in the dictionary
|
31 |
+
def match_word(input_word, dictionary):
|
32 |
+
# Extract words from the input
|
33 |
+
words = re.findall(r'\w+', input_word.lower())
|
34 |
+
|
35 |
+
# Filter dictionary based on words
|
36 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
37 |
+
|
38 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
39 |
+
# print(f"Filtered dictionary: {filtered_dictionary}")
|
40 |
+
|
41 |
+
# Generate embeddings and calculate cosine similarity on the filtered dictionary
|
42 |
+
input_embedding = generate_embedding(input_word)
|
43 |
+
similarities = []
|
44 |
+
|
45 |
+
for entry in filtered_dictionary:
|
46 |
+
entry_embedding = generate_embedding(entry)
|
47 |
+
similarity_score = torch.nn.functional.cosine_similarity(input_embedding, entry_embedding, dim=0).item()
|
48 |
+
similarities.append((entry, similarity_score))
|
49 |
+
|
50 |
+
# print(similarities)
|
51 |
+
|
52 |
+
if similarities:
|
53 |
+
best_match = max(similarities, key=lambda x: x[1])
|
54 |
+
return best_match if best_match[1] > 0.7 else None
|
55 |
+
else:
|
56 |
+
return None
|
57 |
+
|
58 |
+
# Example usage
|
59 |
+
input_words = [
|
60 |
+
"Pepper - Habanero Pepper", "Bananas (12 lbs)", "Squash - Yellow Squash", "Cauliflower",
|
61 |
+
"Squash mix italian/yellow (30 lbs)", "Tomato - Roma Tomato", "Tomato - Grape Tomato",
|
62 |
+
"Squash - Mexican Squash", "Pepper - Bell Pepper", "Squash - Italian Squash",
|
63 |
+
"Pepper - Red Fresno Pepper", "Tomato - Cherry Tomato", "Pepper - Serrano Pepper",
|
64 |
+
"Kale ( 5 lbs)", "Tomato - Beefsteak Tomato", "Pepper - Anaheim Pepper",
|
65 |
+
"Banana - Burro Banana", "Squash - Butternut Squash", "Apricot ( 10 lbs)",
|
66 |
+
"Squash - Acorn Squash", "Tomato - Heirloom Tomato", "Pepper - Pasilla Pepper",
|
67 |
+
"Pepper - Jalapeno Pepper", "carrot (10 lbs )"
|
68 |
+
]
|
69 |
+
|
70 |
+
for input_word in input_words:
|
71 |
+
matched_entry = match_word(input_word, dictionary)
|
72 |
+
if matched_entry:
|
73 |
+
print("Input word:", input_word)
|
74 |
+
print("Matched entry:", matched_entry[0])
|
75 |
+
print("Similarity score:", matched_entry[1])
|
76 |
+
else:
|
77 |
+
print("Input word:", input_word)
|
78 |
+
print("Matched entry: None")
|
79 |
+
print()
|
old_experiments/mistral.py
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
from mistralai.client import MistralClient
|
3 |
+
from mistralai.models.chat_completion import ChatMessage
|
4 |
+
|
5 |
+
api_key = os.environ["MISTRAL_API_KEY"]
|
6 |
+
model = "mistral-large-latest"
|
7 |
+
|
8 |
+
client = MistralClient(api_key=api_key)
|
9 |
+
|
10 |
+
# Return the name in a short JSON object with a single key called name. Only return the json object. What item from this list is most similar to: 'Pepper - Habanero Pepper'. List: Stuffed pepper, with rice and meat; Stuffed pepper, with rice, meatless; Pepper, hot chili, raw; Pepper, raw, NFS; Pepper, sweet, green, raw; Pepper, sweet, red, raw; Pepper, banana
|
11 |
+
|
12 |
+
messages = [
|
13 |
+
ChatMessage(role="user", content="""
|
14 |
+
Return the name in a short JSON object. What item from this list is most similar to: 'Pepper - Habanero Pepper'. List:
|
15 |
+
- Stuffed pepper, with rice and meat
|
16 |
+
- Stuffed pepper, with rice, meatless
|
17 |
+
- Pepper, hot chili, raw
|
18 |
+
- Pepper, raw, NFS
|
19 |
+
- Pepper, sweet, green, raw
|
20 |
+
- Pepper, sweet, red, raw
|
21 |
+
- Pepper, banana, raw
|
22 |
+
""")
|
23 |
+
]
|
24 |
+
|
25 |
+
chat_response = client.chat(
|
26 |
+
model=model,
|
27 |
+
response_format={"type": "json_object"},
|
28 |
+
messages=messages,
|
29 |
+
)
|
30 |
+
|
31 |
+
print(chat_response.choices[0].message.content)
|
old_experiments/mistral2.py
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
2 |
+
|
3 |
+
# Load the tokenizer and model
|
4 |
+
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.3")
|
5 |
+
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.3")
|
6 |
+
|
7 |
+
# Prepare your input
|
8 |
+
input_text = "What is the most similar item to 'Pepper - Habanero Pepper'?"
|
9 |
+
inputs = tokenizer(input_text, return_tensors="pt")
|
10 |
+
|
11 |
+
# Generate output
|
12 |
+
outputs = model.generate(**inputs, max_new_tokens=50)
|
13 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
old_experiments/qa.py
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import LlamaForQuestionAnswering, LlamaTokenizer
|
2 |
+
import torch
|
3 |
+
|
4 |
+
# Load the pre-trained LLaMA-2 model and tokenizer
|
5 |
+
# model_name = "meta-llama/llama-2-question-answering"
|
6 |
+
model_name = "meta-llama/Meta-Llama-3-8B"
|
7 |
+
model = LlamaForQuestionAnswering.from_pretrained(model_name)
|
8 |
+
tokenizer = LlamaTokenizer.from_pretrained(model_name)
|
9 |
+
|
10 |
+
# Prepare a question and context
|
11 |
+
question = "What is the capital of France?"
|
12 |
+
context = "France, a country in Western Europe, is known for its medieval cities, alpine villages, and Mediterranean beaches. Its capital, Paris, is famed for its fashion, gastronomy, and culture."
|
13 |
+
|
14 |
+
inputs = tokenizer(question, context, return_tensors="pt")
|
15 |
+
|
16 |
+
# Perform the question-answering
|
17 |
+
with torch.no_grad():
|
18 |
+
outputs = model(**inputs)
|
19 |
+
answer_start_index = outputs.start_logits.argmax()
|
20 |
+
answer_end_index = outputs.end_logits.argmax()
|
21 |
+
answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(inputs.input_ids[0][answer_start_index:answer_end_index+1]))
|
22 |
+
|
23 |
+
print(f"Answer: {answer}")
|
old_experiments/roberta.py
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from transformers import RobertaTokenizer, RobertaModel
|
3 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
4 |
+
import torch
|
5 |
+
import numpy as np
|
6 |
+
import re
|
7 |
+
|
8 |
+
# Load pre-trained RoBERTa model and tokenizer
|
9 |
+
tokenizer = RobertaTokenizer.from_pretrained('roberta-base')
|
10 |
+
model = RobertaModel.from_pretrained('roberta-base')
|
11 |
+
|
12 |
+
# Load dictionary from CSV file
|
13 |
+
csv_file_path = './dictionary/dictionary.csv'
|
14 |
+
df = pd.read_csv(csv_file_path)
|
15 |
+
dictionary = df['description'].tolist()
|
16 |
+
|
17 |
+
# Method to compute cosine similarity between two embeddings
|
18 |
+
def compute_cosine_similarity(embedding1, embedding2):
|
19 |
+
return cosine_similarity(embedding1, embedding2)[0][0]
|
20 |
+
|
21 |
+
# Method to get RoBERTa embeddings
|
22 |
+
def get_roberta_embedding(text):
|
23 |
+
inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True)
|
24 |
+
outputs = model(**inputs)
|
25 |
+
return outputs.last_hidden_state.mean(dim=1).detach().numpy()
|
26 |
+
|
27 |
+
# Method to find the best match for the input word in the dictionary
|
28 |
+
def match_word(input_word, dictionary):
|
29 |
+
# Extract words from the input
|
30 |
+
words = re.findall(r'\w+', input_word.lower())
|
31 |
+
|
32 |
+
# Filter dictionary based on words
|
33 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
34 |
+
|
35 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
36 |
+
# print(f"Filtered dictionary: {filtered_dictionary}")
|
37 |
+
|
38 |
+
# Proceed with RoBERTa embeddings and cosine similarity on the filtered dictionary
|
39 |
+
input_embedding = get_roberta_embedding(input_word)
|
40 |
+
similarities = []
|
41 |
+
|
42 |
+
for entry in filtered_dictionary:
|
43 |
+
entry_embedding = get_roberta_embedding(entry)
|
44 |
+
similarity_score = compute_cosine_similarity(input_embedding, entry_embedding)
|
45 |
+
similarities.append((entry, similarity_score))
|
46 |
+
|
47 |
+
if similarities:
|
48 |
+
best_match = max(similarities, key=lambda x: x[1])
|
49 |
+
return best_match[0] if best_match[1] > 0.7 else None
|
50 |
+
else:
|
51 |
+
return None
|
52 |
+
|
53 |
+
# Example usage
|
54 |
+
|
55 |
+
# Filtered dictionary size: 224
|
56 |
+
# Input word: Squash - Yellow Squash
|
57 |
+
# Matched entry: Squash, Indian, raw (Navajo)
|
58 |
+
|
59 |
+
# Filtered dictionary size: 37
|
60 |
+
# Input word: Cauliflower
|
61 |
+
# Matched entry: Cauliflower, raw
|
62 |
+
|
63 |
+
# Filtered dictionary size: 185
|
64 |
+
# Input word: Pepper - Habanero Pepper
|
65 |
+
# Matched entry: Stuffed green pepper, Puerto Rican style
|
66 |
+
|
67 |
+
# Filtered dictionary size: 414
|
68 |
+
# Input word: Bananas (12 lbs)
|
69 |
+
# Matched entry: Bananas, slightly ripe
|
70 |
+
|
71 |
+
# Filtered dictionary size: 784
|
72 |
+
# Input word: Squash mix italian/yellow (30 lbs )
|
73 |
+
# Matched entry: Squash, Indian, cooked, boiled (Navajo)
|
74 |
+
|
75 |
+
for input_word in input_words:
|
76 |
+
matched_entry = match_word(input_word, dictionary)
|
77 |
+
print("Input word:", input_word)
|
78 |
+
print("Matched entry:", matched_entry)
|
79 |
+
print()
|
old_experiments/run.py
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from transformers import BertTokenizer, BertModel
|
3 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
4 |
+
import torch
|
5 |
+
import numpy as np
|
6 |
+
import re
|
7 |
+
|
8 |
+
# Load pre-trained BERT model and tokenizer
|
9 |
+
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
|
10 |
+
model = BertModel.from_pretrained('bert-base-uncased')
|
11 |
+
|
12 |
+
# Load dictionary from CSV file
|
13 |
+
csv_file_path = './dictionary/dictionary.csv'
|
14 |
+
df = pd.read_csv(csv_file_path)
|
15 |
+
dictionary = df['description'].tolist()
|
16 |
+
|
17 |
+
# Method to compute cosine similarity between two embeddings
|
18 |
+
def compute_cosine_similarity(embedding1, embedding2):
|
19 |
+
return cosine_similarity(embedding1, embedding2)[0][0]
|
20 |
+
|
21 |
+
# Method to get BERT embeddings
|
22 |
+
def get_bert_embedding(text):
|
23 |
+
inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True)
|
24 |
+
outputs = model(**inputs)
|
25 |
+
return outputs.last_hidden_state.mean(dim=1).detach().numpy()
|
26 |
+
|
27 |
+
# Method to find the best match for the input word in the dictionary
|
28 |
+
def match_word(input_word, dictionary):
|
29 |
+
# Extract words from the input
|
30 |
+
words = re.findall(r'\w+', input_word.lower())
|
31 |
+
|
32 |
+
# Filter dictionary based on words
|
33 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
34 |
+
|
35 |
+
# Proceed with BERT embeddings and cosine similarity on the filtered dictionary
|
36 |
+
input_embedding = get_bert_embedding(input_word)
|
37 |
+
similarities = []
|
38 |
+
|
39 |
+
for entry in filtered_dictionary:
|
40 |
+
entry_embedding = get_bert_embedding(entry)
|
41 |
+
similarity_score = compute_cosine_similarity(input_embedding, entry_embedding)
|
42 |
+
similarities.append((entry, similarity_score))
|
43 |
+
|
44 |
+
if similarities:
|
45 |
+
best_match = max(similarities, key=lambda x: x[1])
|
46 |
+
return best_match[0] if best_match[1] > 0.7 else None
|
47 |
+
else:
|
48 |
+
return None
|
49 |
+
|
50 |
+
# Example usage
|
51 |
+
input_words = ["Pepper - Habanero Pepper", "Bananas (12 lbs)"]
|
52 |
+
|
53 |
+
for input_word in input_words:
|
54 |
+
matched_entry = match_word(input_word, dictionary)
|
55 |
+
print("Input word:", input_word)
|
56 |
+
print("Matched entry:", matched_entry)
|
57 |
+
print()
|
old_experiments/run2.py
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from transformers import BertTokenizer, BertModel
|
3 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
4 |
+
import torch
|
5 |
+
import numpy as np
|
6 |
+
import re
|
7 |
+
|
8 |
+
# Load pre-trained BERT model and tokenizer
|
9 |
+
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
|
10 |
+
model = BertModel.from_pretrained('bert-base-uncased')
|
11 |
+
|
12 |
+
# Load dictionary from CSV file
|
13 |
+
csv_file_path = './dictionary/dictionary.csv'
|
14 |
+
df = pd.read_csv(csv_file_path)
|
15 |
+
dictionary = df['description'].tolist()
|
16 |
+
|
17 |
+
# Method to compute cosine similarity between two embeddings
|
18 |
+
def compute_cosine_similarity(embedding1, embedding2):
|
19 |
+
return cosine_similarity(embedding1, embedding2)[0][0]
|
20 |
+
|
21 |
+
# Method to get BERT embeddings
|
22 |
+
def get_bert_embedding(text):
|
23 |
+
inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True)
|
24 |
+
outputs = model(**inputs)
|
25 |
+
return outputs.last_hidden_state.mean(dim=1).detach().numpy()
|
26 |
+
|
27 |
+
# Method to find the best match for the input word in the dictionary
|
28 |
+
def match_word(input_word, dictionary):
|
29 |
+
# Extract words from the input
|
30 |
+
words = re.findall(r'\w+', input_word.lower())
|
31 |
+
|
32 |
+
# Filter dictionary based on words
|
33 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
34 |
+
|
35 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
36 |
+
print(f"Filtered dictionary: {filtered_dictionary}")
|
37 |
+
|
38 |
+
# Proceed with BERT embeddings and cosine similarity on the filtered dictionary
|
39 |
+
input_embedding = get_bert_embedding(input_word)
|
40 |
+
similarities = []
|
41 |
+
|
42 |
+
for entry in filtered_dictionary:
|
43 |
+
entry_embedding = get_bert_embedding(entry)
|
44 |
+
similarity_score = compute_cosine_similarity(input_embedding, entry_embedding)
|
45 |
+
similarities.append((entry, similarity_score))
|
46 |
+
|
47 |
+
print(similarities)
|
48 |
+
|
49 |
+
if similarities:
|
50 |
+
best_match = max(similarities, key=lambda x: x[1])
|
51 |
+
return best_match[0] if best_match[1] > 0.7 else None
|
52 |
+
else:
|
53 |
+
return None
|
54 |
+
|
55 |
+
# Example usage
|
56 |
+
input_words = ["Pepper - Habanero Pepper", "Bananas (12 lbs)"]
|
57 |
+
|
58 |
+
for input_word in input_words:
|
59 |
+
matched_entry = match_word(input_word, dictionary)
|
60 |
+
print("Input word:", input_word)
|
61 |
+
print("Matched entry:", matched_entry)
|
62 |
+
print()
|
old_experiments/sbert.py
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from sentence_transformers import SentenceTransformer, util
|
3 |
+
import re
|
4 |
+
|
5 |
+
# Load pre-trained SBERT model
|
6 |
+
model = SentenceTransformer('all-mpnet-base-v2')
|
7 |
+
|
8 |
+
# Load dictionary from CSV file
|
9 |
+
csv_file_path = './dictionary/dictionary.csv'
|
10 |
+
df = pd.read_csv(csv_file_path)
|
11 |
+
dictionary = df['description'].tolist()
|
12 |
+
|
13 |
+
def match_word(input_word, dictionary):
|
14 |
+
# Extract words from the input
|
15 |
+
words = re.findall(r'\w+', input_word.lower())
|
16 |
+
|
17 |
+
# Filter dictionary based on words
|
18 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
19 |
+
|
20 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
21 |
+
# print(f"Filtered dictionary: {filtered_dictionary}")
|
22 |
+
|
23 |
+
# Proceed with SBERT embeddings and cosine similarity on the filtered dictionary
|
24 |
+
input_embedding = model.encode(input_word, convert_to_tensor=True)
|
25 |
+
similarities = []
|
26 |
+
|
27 |
+
for entry in filtered_dictionary:
|
28 |
+
entry_embedding = model.encode(entry, convert_to_tensor=True)
|
29 |
+
similarity_score = util.pytorch_cos_sim(input_embedding, entry_embedding).item()
|
30 |
+
similarities.append((entry, similarity_score))
|
31 |
+
|
32 |
+
# print(similarities)
|
33 |
+
|
34 |
+
if similarities:
|
35 |
+
best_match = max(similarities, key=lambda x: x[1])
|
36 |
+
return best_match if best_match[1] > 0.7 else None
|
37 |
+
else:
|
38 |
+
return None
|
39 |
+
|
40 |
+
# Example usage
|
41 |
+
input_words = [
|
42 |
+
"Pepper - Habanero Pepper", "Bananas (12 lbs)", "Squash - Yellow Squash", "Cauliflower",
|
43 |
+
"Squash mix italian/yellow (30 lbs)", "Tomato - Roma Tomato", "Tomato - Grape Tomato",
|
44 |
+
"Squash - Mexican Squash", "Pepper - Bell Pepper", "Squash - Italian Squash",
|
45 |
+
"Pepper - Red Fresno Pepper", "Tomato - Cherry Tomato", "Pepper - Serrano Pepper",
|
46 |
+
"Kale ( 5 lbs)", "Tomato - Beefsteak Tomato", "Pepper - Anaheim Pepper",
|
47 |
+
"Banana - Burro Banana", "Squash - Butternut Squash", "Apricot ( 10 lbs)",
|
48 |
+
"Squash - Acorn Squash", "Tomato - Heirloom Tomato", "Pepper - Pasilla Pepper",
|
49 |
+
"Pepper - Jalapeno Pepper", "carrot (10 lbs )"
|
50 |
+
]
|
51 |
+
|
52 |
+
for input_word in input_words:
|
53 |
+
print("Input word:", input_word)
|
54 |
+
matched_entry = match_word(input_word, dictionary)
|
55 |
+
if matched_entry:
|
56 |
+
print("Matched entry:", matched_entry[0])
|
57 |
+
print("Similarity score:", matched_entry[1])
|
58 |
+
else:
|
59 |
+
print("Matched entry: None")
|
60 |
+
print()
|
old_experiments/sbert2.py
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This code includes a secondary filtering step that checks for the presence of specific keywords (like "pepper" in this case).
|
2 |
+
|
3 |
+
|
4 |
+
import pandas as pd
|
5 |
+
from sentence_transformers import SentenceTransformer, util
|
6 |
+
import re
|
7 |
+
|
8 |
+
# Load pre-trained SBERT model
|
9 |
+
model = SentenceTransformer('all-MiniLM-L6-v2') # Smaller and faster, but you can choose a larger model if needed
|
10 |
+
|
11 |
+
# Load dictionary from CSV file
|
12 |
+
csv_file_path = './dictionary/dictionary.csv'
|
13 |
+
df = pd.read_csv(csv_file_path)
|
14 |
+
dictionary = df['description'].tolist()
|
15 |
+
|
16 |
+
# Method to compute refined similarity
|
17 |
+
def refined_similarity(input_word, filtered_dictionary):
|
18 |
+
input_embedding = model.encode(input_word, convert_to_tensor=True)
|
19 |
+
similarities = []
|
20 |
+
|
21 |
+
for entry in filtered_dictionary:
|
22 |
+
entry_embedding = model.encode(entry, convert_to_tensor=True)
|
23 |
+
similarity_score = util.pytorch_cos_sim(input_embedding, entry_embedding).item()
|
24 |
+
similarities.append((entry, similarity_score))
|
25 |
+
|
26 |
+
return similarities
|
27 |
+
|
28 |
+
# Method to find the best match for the input word in the dictionary
|
29 |
+
def match_word(input_word, dictionary):
|
30 |
+
# Extract words from the input
|
31 |
+
words = re.findall(r'\w+', input_word.lower())
|
32 |
+
|
33 |
+
# Filter dictionary based on words
|
34 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
35 |
+
|
36 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
37 |
+
|
38 |
+
# Refined filtering by checking for exact word presence
|
39 |
+
further_filtered = [desc for desc in filtered_dictionary if "pepper" in desc.lower()]
|
40 |
+
|
41 |
+
# If further_filtered is empty, fallback to filtered_dictionary
|
42 |
+
if further_filtered:
|
43 |
+
filtered_dictionary = further_filtered
|
44 |
+
|
45 |
+
print(f"Further filtered dictionary size: {len(filtered_dictionary)}")
|
46 |
+
# print(f"Filtered dictionary: {filtered_dictionary}")
|
47 |
+
|
48 |
+
# Proceed with SBERT embeddings and cosine similarity on the filtered dictionary
|
49 |
+
similarities = refined_similarity(input_word, filtered_dictionary)
|
50 |
+
|
51 |
+
# print(similarities)
|
52 |
+
|
53 |
+
if similarities:
|
54 |
+
best_match = max(similarities, key=lambda x: x[1])
|
55 |
+
return best_match if best_match[1] > 0.7 else None
|
56 |
+
else:
|
57 |
+
return None
|
58 |
+
|
59 |
+
# Example usage
|
60 |
+
input_words = [
|
61 |
+
"Carrot (10 lbs )",
|
62 |
+
"Pepper - Habanero Pepper", "Bananas (12 lbs)", "Squash - Yellow Squash", "Cauliflower",
|
63 |
+
"Squash mix italian/yellow (30 lbs)", "Tomato - Roma Tomato", "Tomato - Grape Tomato",
|
64 |
+
"Squash - Mexican Squash", "Pepper - Bell Pepper", "Squash - Italian Squash",
|
65 |
+
"Pepper - Red Fresno Pepper", "Tomato - Cherry Tomato", "Pepper - Serrano Pepper",
|
66 |
+
"Kale ( 5 lbs)", "Tomato - Beefsteak Tomato", "Pepper - Anaheim Pepper",
|
67 |
+
"Banana - Burro Banana", "Squash - Butternut Squash", "Apricot ( 10 lbs)",
|
68 |
+
"Squash - Acorn Squash", "Tomato - Heirloom Tomato", "Pepper - Pasilla Pepper",
|
69 |
+
"Pepper - Jalapeno Pepper"
|
70 |
+
]
|
71 |
+
|
72 |
+
for input_word in input_words:
|
73 |
+
print("Input word:", input_word)
|
74 |
+
matched_entry = match_word(input_word, dictionary)
|
75 |
+
if matched_entry:
|
76 |
+
print("Matched entry:", matched_entry[0])
|
77 |
+
print("Similarity score:", matched_entry[1])
|
78 |
+
else:
|
79 |
+
print("Matched entry: None")
|
80 |
+
print()
|
old_experiments/sbert3.py
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from sentence_transformers import SentenceTransformer, util
|
3 |
+
import re
|
4 |
+
|
5 |
+
# Load pre-trained SBERT model
|
6 |
+
model = SentenceTransformer('all-mpnet-base-v2') # Larger and more accurate model
|
7 |
+
|
8 |
+
# Load dictionary from CSV file
|
9 |
+
csv_file_path = './dictionary/dictionary.csv'
|
10 |
+
df = pd.read_csv(csv_file_path)
|
11 |
+
dictionary = df['description'].tolist()
|
12 |
+
|
13 |
+
# Method to preprocess the input word
|
14 |
+
def preprocess_input(input_word):
|
15 |
+
# Remove text within parentheses
|
16 |
+
input_word = re.sub(r'\(.*?\)', '', input_word).strip()
|
17 |
+
|
18 |
+
# Handle broad category and specific item separately when there's a hyphen
|
19 |
+
if ' - ' in input_word:
|
20 |
+
broad_category, specific_item = input_word.split(' - ', 1)
|
21 |
+
return specific_item.strip(), broad_category.strip()
|
22 |
+
|
23 |
+
return input_word
|
24 |
+
|
25 |
+
# Method to create regex pattern for filtering
|
26 |
+
def create_regex_pattern(input_word):
|
27 |
+
words = re.findall(r'\w+', input_word.lower())
|
28 |
+
pattern = '|'.join([re.escape(word) for word in words])
|
29 |
+
return pattern
|
30 |
+
|
31 |
+
# Method to find the best match for the input word in the dictionary
|
32 |
+
def match_word(input_word, dictionary):
|
33 |
+
processed_input = preprocess_input(input_word)
|
34 |
+
|
35 |
+
if isinstance(processed_input, tuple):
|
36 |
+
specific_item, broad_category = processed_input
|
37 |
+
specific_pattern = create_regex_pattern(specific_item)
|
38 |
+
broad_pattern = create_regex_pattern(broad_category)
|
39 |
+
filtered_dictionary = [desc for desc in dictionary if re.search(specific_pattern, desc.lower()) or re.search(broad_pattern, desc.lower())]
|
40 |
+
else:
|
41 |
+
specific_item = processed_input
|
42 |
+
specific_pattern = create_regex_pattern(specific_item)
|
43 |
+
filtered_dictionary = [desc for desc in dictionary if re.search(specific_pattern, desc.lower())]
|
44 |
+
|
45 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
46 |
+
|
47 |
+
input_embedding = model.encode(input_word, convert_to_tensor=True)
|
48 |
+
similarities = []
|
49 |
+
|
50 |
+
for entry in filtered_dictionary:
|
51 |
+
entry_embedding = model.encode(entry, convert_to_tensor=True)
|
52 |
+
similarity_score = util.pytorch_cos_sim(input_embedding, entry_embedding).item()
|
53 |
+
similarities.append((entry, similarity_score))
|
54 |
+
|
55 |
+
if similarities:
|
56 |
+
best_match = max(similarities, key=lambda x: x[1])
|
57 |
+
return best_match if best_match[1] > 0.7 else None
|
58 |
+
else:
|
59 |
+
return None
|
60 |
+
|
61 |
+
# Example usage
|
62 |
+
input_words = [
|
63 |
+
"Carrot (10 lbs )",
|
64 |
+
"Pepper - Habanero Pepper", "Bananas (12 lbs)", "Squash - Yellow Squash", "Cauliflower",
|
65 |
+
"Squash mix italian/yellow (30 lbs)", "Tomato - Roma Tomato", "Tomato - Grape Tomato",
|
66 |
+
"Squash - Mexican Squash", "Pepper - Bell Pepper", "Squash - Italian Squash",
|
67 |
+
"Pepper - Red Fresno Pepper", "Tomato - Cherry Tomato", "Pepper - Serrano Pepper",
|
68 |
+
"Kale ( 5 lbs)", "Tomato - Beefsteak Tomato", "Pepper - Anaheim Pepper",
|
69 |
+
"Banana - Burro Banana", "Squash - Butternut Squash", "Apricot ( 10 lbs)",
|
70 |
+
"Squash - Acorn Squash", "Tomato - Heirloom Tomato", "Pepper - Pasilla Pepper",
|
71 |
+
"Pepper - Jalapeno Pepper"
|
72 |
+
]
|
73 |
+
|
74 |
+
for input_word in input_words:
|
75 |
+
print("Input word:", input_word)
|
76 |
+
matched_entry = match_word(input_word, dictionary)
|
77 |
+
if matched_entry:
|
78 |
+
print("Matched entry:", matched_entry[0])
|
79 |
+
print("Similarity score:", matched_entry[1])
|
80 |
+
else:
|
81 |
+
print("Matched entry: None")
|
82 |
+
print()
|
old_experiments/t5.py
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from transformers import T5Tokenizer, T5Model
|
3 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
4 |
+
import torch
|
5 |
+
import numpy as np
|
6 |
+
import re
|
7 |
+
|
8 |
+
# Load pre-trained T5 model and tokenizer
|
9 |
+
tokenizer = T5Tokenizer.from_pretrained('t5-base')
|
10 |
+
model = T5Model.from_pretrained('t5-base')
|
11 |
+
|
12 |
+
# Load dictionary from CSV file
|
13 |
+
csv_file_path = './dictionary/dictionary.csv'
|
14 |
+
df = pd.read_csv(csv_file_path)
|
15 |
+
dictionary = df['description'].tolist()
|
16 |
+
|
17 |
+
# Method to compute cosine similarity between two embeddings
|
18 |
+
def compute_cosine_similarity(embedding1, embedding2):
|
19 |
+
return cosine_similarity(embedding1, embedding2)[0][0]
|
20 |
+
|
21 |
+
# Method to get T5 embeddings
|
22 |
+
def get_t5_embedding(text):
|
23 |
+
inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True)
|
24 |
+
outputs = model(**inputs)
|
25 |
+
return outputs.last_hidden_state.mean(dim=1).detach().numpy()
|
26 |
+
|
27 |
+
# Method to find the best match for the input word in the dictionary
|
28 |
+
def match_word(input_word, dictionary):
|
29 |
+
# Extract words from the input
|
30 |
+
words = re.findall(r'\w+', input_word.lower())
|
31 |
+
|
32 |
+
# Filter dictionary based on words
|
33 |
+
filtered_dictionary = [desc for desc in dictionary if any(word in desc.lower() for word in words)]
|
34 |
+
|
35 |
+
print(f"Filtered dictionary size: {len(filtered_dictionary)}")
|
36 |
+
print(f"Filtered dictionary: {filtered_dictionary}")
|
37 |
+
|
38 |
+
# Proceed with T5 embeddings and cosine similarity on the filtered dictionary
|
39 |
+
input_embedding = get_t5_embedding(input_word)
|
40 |
+
similarities = []
|
41 |
+
|
42 |
+
for entry in filtered_dictionary:
|
43 |
+
entry_embedding = get_t5_embedding(entry)
|
44 |
+
similarity_score = compute_cosine_similarity(input_embedding, entry_embedding)
|
45 |
+
similarities.append((entry, similarity_score))
|
46 |
+
|
47 |
+
print(similarities)
|
48 |
+
|
49 |
+
if similarities:
|
50 |
+
best_match = max(similarities, key=lambda x: x[1])
|
51 |
+
return best_match[0] if best_match[1] > 0.7 else None
|
52 |
+
else:
|
53 |
+
return None
|
54 |
+
|
55 |
+
# Example usage
|
56 |
+
input_words = ["Pepper - Habanero Pepper", "Bananas (12 lbs)", "Squash - Yellow Squash", "Cauliflower", "Squash mix italian/yellow (30 lbs)"]
|
57 |
+
|
58 |
+
for input_word in input_words:
|
59 |
+
matched_entry = match_word(input_word, dictionary)
|
60 |
+
print("Input word:", input_word)
|
61 |
+
print("Matched entry:", matched_entry)
|
62 |
+
print()
|
playground.py
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import csv
|
3 |
+
import json
|
4 |
+
import time
|
5 |
+
import heapq
|
6 |
+
import pandas as pd
|
7 |
+
from openai import OpenAI
|
8 |
+
from dotenv import load_dotenv
|
9 |
+
from Levenshtein import distance
|
10 |
+
from tqdm import tqdm
|
11 |
+
from db.db_utils import get_connection, store_mapping_to_db, get_mapping_from_db
|
12 |
+
from ask_gpt import query_gpt
|
13 |
+
|
14 |
+
# For any unreviewed mappings, we ask chatgpt to consider:
|
15 |
+
# 1. The similar_words list
|
16 |
+
# 2. Similar words from the dictionary based on small levenstein distance
|
17 |
+
|
18 |
+
# ChatGPT should confirm that the current mapping is the best one. If not, they should provide the better mapping.
|
19 |
+
# If its a Non-Food Item, we should confirm that
|
20 |
+
# If it's a homogenous or hetergeneous mixture, we should confirm that
|
21 |
+
|
22 |
+
load_dotenv()
|
23 |
+
|
24 |
+
api_key = os.getenv("OPENAI_API_KEY")
|
25 |
+
client = OpenAI(api_key=api_key)
|
26 |
+
|
27 |
+
|
28 |
+
def save_to_csv(results):
|
29 |
+
output_file_path = f'./audits/{int(time.time())}.csv'
|
30 |
+
df_results = pd.DataFrame(results, columns=['input_word', 'original_dictionary_word', 'new_dictionary_word',])
|
31 |
+
df_results.to_csv(output_file_path, index=False)
|
32 |
+
|
33 |
+
def find_close_levenshtein_words(input_word, dictionary, threshold=3):
|
34 |
+
# Calculate Levenshtein distances for each word in the dictionary
|
35 |
+
close_words = [word for word in dictionary if distance(input_word, word) <= threshold]
|
36 |
+
return close_words
|
37 |
+
|
38 |
+
def query_gpt(food_item, dictionary_word, similar_words):
|
39 |
+
line_separated_words = '\n'.join(similar_words)
|
40 |
+
|
41 |
+
prompt = (
|
42 |
+
f"""I have a particular food item and a mapping to a USDA word. Can you confirm if the food item is most similar to the mapping?
|
43 |
+
|
44 |
+
Generally, you should prefer the mapped word, but if you believe there is a better fit, please provide it.
|
45 |
+
|
46 |
+
I will also provide a list of other similar words that you could be a better fit.
|
47 |
+
|
48 |
+
If it's not a food item, return 'Non-Food Item'.
|
49 |
+
|
50 |
+
You should respond in JSON format with an object that has the key `guess`, and the value is the most similar food item.
|
51 |
+
|
52 |
+
The food item is: "{food_item}"
|
53 |
+
It has been mapped to: "{dictionary_word}"
|
54 |
+
|
55 |
+
Similar words:
|
56 |
+
{line_separated_words}"""
|
57 |
+
)
|
58 |
+
|
59 |
+
completion = client.chat.completions.create(
|
60 |
+
messages=[
|
61 |
+
{"role": "system", "content": "You are a helpful assistant."},
|
62 |
+
{"role": "user", "content": prompt}
|
63 |
+
],
|
64 |
+
model="gpt-3.5-turbo-1106",
|
65 |
+
response_format={"type": "json_object"},
|
66 |
+
)
|
67 |
+
response = completion.choices[0].message.content
|
68 |
+
parsed = parse_response(response)
|
69 |
+
print(f"Q: '{food_item}'")
|
70 |
+
print(f"A: '{parsed}'")
|
71 |
+
print()
|
72 |
+
return parsed
|
73 |
+
|
74 |
+
# Define the function to parse the GPT response
|
75 |
+
def parse_response(response):
|
76 |
+
try:
|
77 |
+
result = json.loads(response)
|
78 |
+
return result['guess']
|
79 |
+
except (json.JSONDecodeError, KeyError) as e:
|
80 |
+
print(f"Error parsing response: {response} - {e}")
|
81 |
+
return None
|
82 |
+
|
83 |
+
|
84 |
+
csv_file_paths = ['./dictionary/dictionary.csv','./dictionary/additions.csv']
|
85 |
+
dictionary = []
|
86 |
+
for csv_file_path in csv_file_paths:
|
87 |
+
df_dictionary = pd.read_csv(csv_file_path)
|
88 |
+
_dictionary = df_dictionary['description'].astype(str).tolist()
|
89 |
+
dictionary.extend(_dictionary)
|
90 |
+
|
91 |
+
db_conn = get_connection()
|
92 |
+
db_cursor = db_conn.cursor()
|
93 |
+
|
94 |
+
# select all mappings that have not been reviewed
|
95 |
+
db_cursor.execute("SELECT input_word, dictionary_word, similar_words FROM mappings")
|
96 |
+
results = db_cursor.fetchall()
|
97 |
+
|
98 |
+
# iterate through each row, grab the input_word and ask chatgpt to compare it to the dictionary_word
|
99 |
+
csv_data = []
|
100 |
+
for row in results:
|
101 |
+
input_word = row[0]
|
102 |
+
print(f"input_word: {input_word}")
|
103 |
+
dictionary_word = row[1]
|
104 |
+
if dictionary_word not in dictionary:
|
105 |
+
db_cursor.execute("UPDATE mappings SET reviewed = 0 WHERE input_word = ?", (input_word,))
|
106 |
+
|
107 |
+
|
108 |
+
print(csv_data)
|
preseed.py
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import csv
|
3 |
+
import json
|
4 |
+
import pandas as pd
|
5 |
+
from openai import OpenAI
|
6 |
+
from dotenv import load_dotenv
|
7 |
+
|
8 |
+
|
9 |
+
load_dotenv()
|
10 |
+
|
11 |
+
api_key = os.getenv("OPENAI_API_KEY")
|
12 |
+
client = OpenAI(api_key=api_key)
|
13 |
+
|
14 |
+
input_file_path = f'dictionary/dictionary.csv'
|
15 |
+
df_input = pd.read_csv(input_file_path)
|
16 |
+
input_words = df_input['description'].astype(str).tolist()
|
17 |
+
|
18 |
+
# take first 10 words for testing
|
19 |
+
food_items = input_words[:1000]
|
20 |
+
|
21 |
+
# offset the first 1000 words
|
22 |
+
# food_items = input_words[1000:2000]
|
23 |
+
|
24 |
+
# Define the function to query the GPT API
|
25 |
+
def query_gpt(food_item):
|
26 |
+
prompt = (
|
27 |
+
f"I'm attempting to pre-seed a database with similar items to known food items.\n\n"
|
28 |
+
f"I'm going to give you a string of text. I need you to find the food item, and come up with 5-10 variations of this food item that would have similar dry matter content.\n\n"
|
29 |
+
f"For example, if I give you: \"lemons, whole, canned, solids and liquids, with salt added\" you should know that the food item is \"lemon\" and you should give me a list of varieties of lemons, like: \"meyer lemons\", \"eureka lemons\", \"lisbon lemons\", etc.\n\n"
|
30 |
+
f"However, if I say \"eggplant\", you should not say \"eggplant dip\", because eggplant dip has a different dry matter content than eggplant.\n\n"
|
31 |
+
f"You should respond in json format with an object with three keys: \"original\", \"food_item\", and \"similar\". The \"original\" key should have the original food item, \"food_item\" should be the isolated food item, and the \"similar\" key should have a list of similar food items.\n\n"
|
32 |
+
f"Your first string is: \"{food_item}\""
|
33 |
+
)
|
34 |
+
|
35 |
+
|
36 |
+
completion = client.chat.completions.create(
|
37 |
+
messages=[
|
38 |
+
{"role": "system", "content": "You are a helpful assistant."},
|
39 |
+
{"role": "user", "content": prompt}
|
40 |
+
],
|
41 |
+
model="gpt-3.5-turbo-1106",
|
42 |
+
response_format={"type": "json_object"},
|
43 |
+
)
|
44 |
+
print("completion")
|
45 |
+
print(completion)
|
46 |
+
return completion.choices[0].message.content
|
47 |
+
|
48 |
+
# Define the function to parse the GPT response
|
49 |
+
def parse_response(response):
|
50 |
+
try:
|
51 |
+
result = json.loads(response)
|
52 |
+
return result["original"], result["food_item"], result["similar"]
|
53 |
+
except (json.JSONDecodeError, KeyError) as e:
|
54 |
+
print(f"Error parsing response: {response} - {e}")
|
55 |
+
return None, None, None
|
56 |
+
|
57 |
+
# Open a CSV file to write the results
|
58 |
+
with open('preseed.csv', mode='w', newline='') as file:
|
59 |
+
writer = csv.writer(file)
|
60 |
+
writer.writerow(["original", "food_item", "similar"])
|
61 |
+
|
62 |
+
for item in food_items:
|
63 |
+
response = query_gpt(item)
|
64 |
+
original, food_item, similar = parse_response(response)
|
65 |
+
|
66 |
+
if original and food_item and similar:
|
67 |
+
writer.writerow([original, food_item, similar])
|
68 |
+
|
69 |
+
print("Food variations saved to preseed.csv")
|