Spaces:
Paused
Paused
File size: 14,946 Bytes
22bb999 47d890f 9189e38 efa7589 b72dd6f efa7589 9189e38 b72dd6f 9189e38 f2740a4 54daf6f 9189e38 d3d3a5b e5de092 22bb999 9189e38 b9a27ee b43643f 71df5fb 9189e38 184aa9e 9189e38 77cf600 b1f9aab 9189e38 c4f0a69 e5de092 c4f0a69 713485e c4f0a69 e5de092 c4f0a69 9189e38 42e3a31 e5de092 42e3a31 9189e38 b43643f e5de092 9189e38 b72dd6f 9189e38 71df5fb 9189e38 b72dd6f 9189e38 f2740a4 9189e38 ecfb899 b72dd6f 9189e38 3534b4d 9189e38 ecfb899 b0e080a ecfb899 a04fda8 ecfb899 e5de092 ecfb899 b1c94e2 ecfb899 e5de092 ecfb899 b0e080a 68d1a5f b0e080a 68d1a5f be25015 68d1a5f 034c968 b0e080a 68d1a5f 46a46af be25015 46a46af 68d1a5f b0e080a e5de092 e9b9609 e5de092 e9b9609 df3751f 9189e38 bdee24c 9189e38 c4f0a69 9189e38 c4f0a69 9189e38 016ed0e 9189e38 e5de092 9189e38 d839108 bbe1fe8 9189e38 d839108 b1c94e2 bbe1fe8 b1c94e2 df3751f b1c94e2 f2740a4 b1c94e2 8d827d2 1c28270 8d827d2 f2740a4 b1c94e2 9189e38 c5c929e e3179bc c5c929e 13b3103 c5c929e 01a709c 4afe3a5 01a709c 9a6b725 e9b9609 9a6b725 01a709c 47d890f e3179bc 01a709c e3179bc 7e5979c 62c7d90 7e5979c 8826d52 b72dd6f e3179bc c5c929e 9189e38 b1f9aab 13b3103 22bb999 13b3103 f2740a4 4edd87e f2740a4 4edd87e f2740a4 4edd87e f2740a4 4edd87e 9189e38 22bb999 e3179bc efa7589 22bb999 b9a27ee 22bb999 efa7589 22bb999 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 |
# algo.py
import math
import time
import queue
import logging
import threading
import pandas as pd
from tqdm import tqdm
from pluralizer import Pluralizer
from similarity_fast import SimilarityFast
from food_nonfood import classify_as_food_nonfood, pessimistic_food_nonfood_score
from utils import clean_word, is_empty_word
from db.db_utils import store_mapping_to_db, cached_get_mapping_from_db, get_dictionary_data_from_db, store_result_to_db
from ask_gpt import query_gpt
from multi_food_item_detector import extract_items, has_delimiters
from mapping_template import empty_template, heterogeneous_template, multi_item_template, nonfood_template, usda_template
from tasks import insert_result
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
similarity_threshold = 0.78
class Algo:
def __init__(self, db_conn, run_key=None):
self.db_conn = db_conn
self.run_key = run_key if run_key else int(time.time())
self.db_cursor = db_conn.cursor()
self.similarity_fast = SimilarityFast(self.db_cursor)
# self.similarity_slow = SimilaritySlow(self.db_cursor, self.db_conn)
self.pluralizer = Pluralizer()
self.mappings_with_dictionary = self.initialize_mappings()
def initialize_mappings(self):
self.db_cursor.execute('SELECT cleaned_word, dictionary_word, is_food, similarity_score, food_nonfood_score, wweia_category, sr_legacy_food_category, water_content, dry_matter_content, leakage, ignore from mappings join dictionary on mappings.dictionary_word = dictionary.description')
rows = self.db_cursor.fetchall()
mappings_with_dictionary = {}
for row in rows:
mappings_with_dictionary[row[0]] = {
'cleaned_word': row[0],
'dictionary_word': row[1],
'is_food': row[2],
'similarity_score': row[3],
'food_nonfood_score': row[4],
'wweia_category': row[5],
'sr_legacy_food_category': row[6],
'water_content': row[7],
'dry_matter_content': row[8],
'leakage': row[9],
'ignore': row[10]
}
return mappings_with_dictionary
def perform_mapping(self, input_word, attempts=0):
# if the input word is a USDA food item, we can skip the similarity check
# this is a special case because the USDA food items are Government Donation (Not Counted) items
if 'usda' in input_word.lower():
return usda_template(input_word, clean_word(input_word))
mapping = self.similarity_fast.find_most_similar_word(input_word)
logging.info(f" - Simlarity Fast mapping: {mapping}")
# check if the cleaned_word is a substring of the most_similar_word
is_substring = mapping['cleaned_word'] in mapping['most_similar_word']
if mapping['similarity_score'] < similarity_threshold and not is_substring:
logging.info(" - Attempting GPT mapping")
try:
gpt_recommended_word = query_gpt(input_word)
if gpt_recommended_word:
if gpt_recommended_word == 'Non-Food Item':
mapping.update(
{
'similarity_score': 1.0,
'confidence_score': 1.0,
'is_food': False,
'food_nonfood_score': 1.0
}
)
return mapping
elif gpt_recommended_word == 'Mixed Food Items':
mapping.update(
{
'dictionary_word': 'Mixed Food Items', 'similarity_score': 1.0,
'confidence_score': 1.0
}
)
return mapping
elif gpt_recommended_word == 'Broad Category':
category_mapping = self.similarity_fast.find_most_similar_word(input_word, True)
mapping.update(
{
'dictionary_word': category_mapping['dictionary_word'],
'similarity_score': category_mapping['similarity_score'],
'confidence_score': category_mapping['confidence_score']
}
)
else:
gpt_mapping = self.similarity_fast.find_most_similar_word(gpt_recommended_word)
if gpt_mapping['similarity_score'] > mapping['similarity_score']:
gpt_mapping.update(
{
'input_word': input_word,
'cleaned_word': mapping['cleaned_word']
}
)
mapping = gpt_mapping
except Exception as e:
logging.info(f" - Error querying GPT: {e}")
return mapping
def handle_multi_item(self, input_word):
# The input word has a comma or a slash in it
# If it has more commas, its comma-delimited
# If it has more slashes, its slash-delimited
# If it has equal number of commas and slashes, we'll go with slashes
logging.info(f"Handling multi-item {input_word}")
input_word_parts = extract_items(input_word)
logging.info(f" - Extracted items: {input_word_parts}")
mappings = []
for part in input_word_parts:
mapping = self.handle_single_item(part)
if mapping:
# Some words in the mapping can be ignored because they are
# just filler words that don't add any value to the mapping
if mapping['ignore'] == False:
mappings.append(mapping)
# look up the dictionary values for each mapping
# find the wweia category
# if all mappings have the same wweia category, return "homogenous", else "heterogeneous"
# if is_food is False for any mappings, return "Non-Food Item" as dictionary word
for mapping in mappings:
if mapping['is_food'] == False:
return nonfood_template(
input_word,
mapping['cleaned_word'],
mapping['food_nonfood_score']
)
break
dictionary_words = [mapping['dictionary_word'] for mapping in mappings]
if len(set(dictionary_words)) == 0:
return empty_template(input_word)
# check if "heterogeneous" is in the wweia category of any of the mappings
# otherwise we find the mapping with the lowest DMC value, and return that as the dictionary word, dmc, wc, and leakage values
heterogeneous_exists = False
most_conservative_mapping = None
for mapping in mappings:
if mapping['sr_legacy_food_category'] == "Heterogeneous Mixture":
heterogeneous_exists = True
break
else:
dry_matter_content = mapping.get('dry_matter_content')
if dry_matter_content is not None:
if most_conservative_mapping is None or dry_matter_content < most_conservative_mapping.get('dry_matter_content', float('inf')):
most_conservative_mapping = mapping
if heterogeneous_exists:
return heterogeneous_template(input_word)
elif most_conservative_mapping is not None:
return multi_item_template(input_word, None, most_conservative_mapping)
else:
logging.warning(f" - No mappings found for {input_word}")
return None
def handle_single_item(self, input_word):
input_word_clean = clean_word(input_word)
if not input_word_clean:
return None
if input_word_clean == "":
return None
# try the singular form of the word
singular = self.pluralizer.pluralize(input_word_clean, 1)
# mapping = cached_get_mapping_from_db(self.db_cursor, singular)
mapping_with_dict = self.mappings_with_dictionary.get(singular)
if mapping_with_dict:
mapping_with_dict.update({
'input_word': input_word,
})
logging.info(f" - Found mapping in db: {mapping_with_dict}")
return mapping_with_dict
# try the plural form of the word
plural = self.pluralizer.pluralize(input_word_clean, 2)
mapping_with_dict = self.mappings_with_dictionary.get(plural)
if mapping_with_dict:
mapping_with_dict.update({
'input_word': input_word,
})
logging.info(f" - Found mapping in db: {mapping_with_dict}")
return mapping_with_dict
food_nonfood = classify_as_food_nonfood(input_word_clean)
# if we're very confident that the word is non-food, let's not even classify it
if food_nonfood[1] > 0.9 and food_nonfood[0] == False:
mapping = nonfood_template(input_word, input_word_clean, food_nonfood[1])
store_mapping_to_db(self.db_cursor, self.db_conn, mapping)
self.mappings_with_dictionary[input_word_clean] = mapping
return self.wrap_mapping_with_dictionary_data(mapping)
mapping = self.perform_mapping(input_word)
food_nonfood_pessimistic = pessimistic_food_nonfood_score(food_nonfood, mapping['similarity_score'])
mapping.update({
'is_food': food_nonfood_pessimistic[0],
'food_nonfood_score': food_nonfood_pessimistic[1]
})
store_mapping_to_db(self.db_cursor, self.db_conn, mapping)
self.mappings_with_dictionary[input_word_clean] = mapping
return self.wrap_mapping_with_dictionary_data(mapping)
def wrap_mapping_with_dictionary_data(self, mapping):
if not mapping:
return None
dictionary_result = get_dictionary_data_from_db(self.db_cursor, mapping['dictionary_word'])
# set default on ignore
ignore = mapping['ignore'] if 'ignore' in mapping else False
mapping.update({
'wweia_category': dictionary_result['wweia_category'] if dictionary_result else None,
'sr_legacy_food_category': dictionary_result['sr_legacy_food_category'] if dictionary_result else None,
'water_content': dictionary_result['water_content'] if dictionary_result else None,
'dry_matter_content': dictionary_result['dry_matter_content'] if dictionary_result else None,
'leakage': dictionary_result['leakage'] if dictionary_result else None,
'ignore': ignore
})
return mapping
def add_carbon_credit_data(self, mapping, donor, date, weight):
if not mapping:
return None
mapping.update({
'donor': donor
})
try:
weight = float(weight)
except ValueError:
weight = 0
except Exception as e:
logging.info(f" - Error converting weight to float: {e}")
weight = 0
if math.isnan(weight):
weight = 0
mapping.update({
'date': date,
'weight': weight,
'weight_metric_tonnes': weight * 0.000453592,
'distance': 250,
'ef': 2.968073544,
'mt_lb_mile': 0.0000000809,
})
required_fields_exist = 'leakage' in mapping and mapping['leakage'] is not None and 'dry_matter_content' in mapping and mapping['dry_matter_content'] is not None
if mapping['is_food'] == False or required_fields_exist == False:
return {
'baseline_emissions': None,
'leakage_emissions': None,
'project_emissions': None,
'total_emissions_reduction': None,
**mapping
}
logging.info(f" - Calculating carbon credits for: {mapping}")
baseline_emissions = mapping['weight_metric_tonnes'] * mapping['dry_matter_content'] * mapping['ef']
leakage_emissions = mapping['leakage'] * baseline_emissions
project_emissions = mapping['distance'] * mapping['mt_lb_mile'] * baseline_emissions
total_emissions_reduction = baseline_emissions - leakage_emissions - project_emissions
mapping.update({
'baseline_emissions': baseline_emissions,
'leakage_emissions': leakage_emissions,
'project_emissions': project_emissions,
'total_emissions_reduction': total_emissions_reduction
})
return mapping
def match_words(self, input_data):
# input_data is a list of tuples, where each tuple is (description, donor)
# results = []
result_batch = []
for input_item in tqdm(input_data, desc="Processing input words"):
input_word = input_item[0]
input_word_alt = input_item[1] if len(input_item) > 1 else None
input_row_num = input_item[2] if len(input_item) > 2 else None
input_donor = input_item[3] if len(input_item) > 3 else None
input_date = input_item[4] if len(input_item) > 4 else None
input_weight = input_item[5] if len(input_item) > 5 else None
logging.info("")
logging.info(f"Processing: {input_word}")
is_empty = False
if is_empty_word(input_word):
if is_empty_word(input_word_alt):
mapping = empty_template(input_word)
is_empty = True
else:
input_word = input_word_alt
if not is_empty:
if has_delimiters(input_word):
mapping = self.handle_multi_item(input_word)
else:
mapping = self.handle_single_item(input_word)
if mapping:
mapping = dict(mapping)
mapping = self.add_carbon_credit_data(mapping, input_donor, input_date, input_weight)
mapping.update({
'run_row': input_row_num
})
result_batch.append(mapping)
# store_result_to_db(self.db_cursor, self.db_conn, self.run_key, mapping)
# results.append(mapping)
if len(result_batch) >= 100:
insert_result.delay(self.run_key, result_batch)
result_batch = []
if len(result_batch) > 0:
insert_result.delay(self.run_key, result_batch)
result_batch = []
# return results
|