beweinreich commited on
Commit
b1335de
1 Parent(s): 54daf6f

replace with foundation category

Browse files
Files changed (5) hide show
  1. algo.py +4 -4
  2. app.py +2 -2
  3. category_mapper.py +1 -1
  4. db/db_utils.py +4 -4
  5. mapping_template.py +1 -1
algo.py CHANGED
@@ -145,7 +145,7 @@ class Algo:
145
  'is_food': False,
146
  'food_nonfood_score': 1.0,
147
  'wweia_category': 'Non-Food Item',
148
- 'usda_category': 'Non-Food Item',
149
  'water_content': None,
150
  'dry_matter_content': None,
151
  'leakage': None
@@ -187,7 +187,7 @@ class Algo:
187
  'matching_word': 'Heterogeneous Mixture',
188
  'dictionary_word': 'Heterogeneous Mixture',
189
  'wweia_category': 'Heterogeneous Mixture',
190
- 'usda_category': 'Heterogeneous Mixture',
191
  'dry_matter_content': 0.27,
192
  'water_content': 0.73,
193
  'leakage': 0.1
@@ -197,7 +197,7 @@ class Algo:
197
  'matching_word': most_conservative_mapping['matching_word'],
198
  'dictionary_word': f"{most_conservative_mapping['dictionary_word']} (Lowest DMC)",
199
  'wweia_category': most_conservative_mapping['wweia_category'],
200
- 'usda_category': most_conservative_mapping['usda_category'],
201
  'dry_matter_content': most_conservative_mapping['dry_matter_content'],
202
  'water_content': most_conservative_mapping['water_content'],
203
  'leakage': most_conservative_mapping['leakage']
@@ -283,7 +283,7 @@ class Algo:
283
 
284
  mapping.update({
285
  'wweia_category': dictionary_result['wweia_category'] if dictionary_result else None,
286
- 'usda_category': dictionary_result['usda_category'] if dictionary_result else None,
287
  'water_content': dictionary_result['water_content'] if dictionary_result else None,
288
  'dry_matter_content': dictionary_result['dry_matter_content'] if dictionary_result else None,
289
  'leakage': dictionary_result['leakage'] if dictionary_result else None,
 
145
  'is_food': False,
146
  'food_nonfood_score': 1.0,
147
  'wweia_category': 'Non-Food Item',
148
+ 'foundation_category': 'Non-Food Item',
149
  'water_content': None,
150
  'dry_matter_content': None,
151
  'leakage': None
 
187
  'matching_word': 'Heterogeneous Mixture',
188
  'dictionary_word': 'Heterogeneous Mixture',
189
  'wweia_category': 'Heterogeneous Mixture',
190
+ 'foundation_category': 'Heterogeneous Mixture',
191
  'dry_matter_content': 0.27,
192
  'water_content': 0.73,
193
  'leakage': 0.1
 
197
  'matching_word': most_conservative_mapping['matching_word'],
198
  'dictionary_word': f"{most_conservative_mapping['dictionary_word']} (Lowest DMC)",
199
  'wweia_category': most_conservative_mapping['wweia_category'],
200
+ 'foundation_category': most_conservative_mapping['foundation_category'],
201
  'dry_matter_content': most_conservative_mapping['dry_matter_content'],
202
  'water_content': most_conservative_mapping['water_content'],
203
  'leakage': most_conservative_mapping['leakage']
 
283
 
284
  mapping.update({
285
  'wweia_category': dictionary_result['wweia_category'] if dictionary_result else None,
286
+ 'foundation_category': dictionary_result['foundation_category'] if dictionary_result else None,
287
  'water_content': dictionary_result['water_content'] if dictionary_result else None,
288
  'dry_matter_content': dictionary_result['dry_matter_content'] if dictionary_result else None,
289
  'leakage': dictionary_result['leakage'] if dictionary_result else None,
app.py CHANGED
@@ -25,10 +25,10 @@ def process_input(input_text, csv_file):
25
 
26
 
27
  print(f" - result -> {results}")
28
- df = pd.DataFrame(results, columns=["input_word", "cleaned_word", 'matching_word', 'dictionary_word', 'usda_category', 'wweia_category', 'dry_matter_content',
29
  'water_content', 'similarity_score', 'confidence_score', 'similar_words', 'is_food', 'food_nonfood_score'])
30
  # Filter to only required columns
31
- df_filtered = df[["input_word", "dictionary_word", "is_food", "usda_category", 'wweia_category', 'dry_matter_content', "water_content", "similarity_score", "food_nonfood_score"]]
32
  return df_filtered
33
 
34
  # Gradio interface
 
25
 
26
 
27
  print(f" - result -> {results}")
28
+ df = pd.DataFrame(results, columns=["input_word", "cleaned_word", 'matching_word', 'dictionary_word', 'foundation_category', 'wweia_category', 'dry_matter_content',
29
  'water_content', 'similarity_score', 'confidence_score', 'similar_words', 'is_food', 'food_nonfood_score'])
30
  # Filter to only required columns
31
+ df_filtered = df[["input_word", "dictionary_word", "is_food", "foundation_category", 'wweia_category', 'dry_matter_content', "water_content", "similarity_score", "food_nonfood_score"]]
32
  return df_filtered
33
 
34
  # Gradio interface
category_mapper.py CHANGED
@@ -86,7 +86,7 @@ for row in tqdm(rows, desc="Processing"):
86
  print()
87
  fdc_id = row['fdc_id']
88
  food_item = row['description']
89
- category = row['usda_category']
90
 
91
  print(f"Processing '{food_item}'")
92
 
 
86
  print()
87
  fdc_id = row['fdc_id']
88
  food_item = row['description']
89
+ category = row['foundation_category']
90
 
91
  print(f"Processing '{food_item}'")
92
 
db/db_utils.py CHANGED
@@ -44,7 +44,7 @@ def initialize_db(conn):
44
  CREATE TABLE IF NOT EXISTS dictionary (
45
  fdc_id INTEGER PRIMARY KEY,
46
  description TEXT,
47
- usda_category TEXT,
48
  wweia_category TEXT,
49
  water_content REAL,
50
  dry_matter_content REAL,
@@ -63,7 +63,7 @@ def initialize_db(conn):
63
  dictionary_word TEXT,
64
  is_food BOOLEAN,
65
  wweia_category TEXT,
66
- usda_category TEXT,
67
  dry_matter_content REAL,
68
  leakage REAL,
69
  weight REAL,
@@ -153,7 +153,7 @@ def store_mapping_to_db(cursor, conn, mapping):
153
  def store_result_to_db(cursor, conn, run_key, result):
154
  try:
155
  cursor.execute('''
156
- INSERT INTO results (run_key, run_row, date, input_word, dictionary_word, is_food, usda_category, wweia_category, dry_matter_content, leakage, weight, weight_metric_tonnes, donor, similarity_score, food_nonfood_score, distance, ef, mt_lb_mile, baseline_emissions, leakage_emissions, project_emissions, total_emissions_reduction)
157
  VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
158
  ''', (
159
  run_key,
@@ -162,7 +162,7 @@ def store_result_to_db(cursor, conn, run_key, result):
162
  result['input_word'],
163
  result['dictionary_word'],
164
  result['is_food'],
165
- result['usda_category'],
166
  result['wweia_category'],
167
  result['dry_matter_content'],
168
  result['leakage'],
 
44
  CREATE TABLE IF NOT EXISTS dictionary (
45
  fdc_id INTEGER PRIMARY KEY,
46
  description TEXT,
47
+ foundation_category TEXT,
48
  wweia_category TEXT,
49
  water_content REAL,
50
  dry_matter_content REAL,
 
63
  dictionary_word TEXT,
64
  is_food BOOLEAN,
65
  wweia_category TEXT,
66
+ foundation_category TEXT,
67
  dry_matter_content REAL,
68
  leakage REAL,
69
  weight REAL,
 
153
  def store_result_to_db(cursor, conn, run_key, result):
154
  try:
155
  cursor.execute('''
156
+ INSERT INTO results (run_key, run_row, date, input_word, dictionary_word, is_food, foundation_category, wweia_category, dry_matter_content, leakage, weight, weight_metric_tonnes, donor, similarity_score, food_nonfood_score, distance, ef, mt_lb_mile, baseline_emissions, leakage_emissions, project_emissions, total_emissions_reduction)
157
  VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
158
  ''', (
159
  run_key,
 
162
  result['input_word'],
163
  result['dictionary_word'],
164
  result['is_food'],
165
+ result['foundation_category'],
166
  result['wweia_category'],
167
  result['dry_matter_content'],
168
  result['leakage'],
mapping_template.py CHANGED
@@ -9,7 +9,7 @@ def empty_template(input_word):
9
  'food_nonfood_score': None,
10
  'matching_word': None,
11
  'dictionary_word': None,
12
- 'usda_category': None,
13
  'wweia_category': None,
14
  'dry_matter_content': None,
15
  'water_content': None,
 
9
  'food_nonfood_score': None,
10
  'matching_word': None,
11
  'dictionary_word': None,
12
+ 'foundation_category': None,
13
  'wweia_category': None,
14
  'dry_matter_content': None,
15
  'water_content': None,