Upload notebooks/phase5_executed.ipynb with huggingface_hub
Browse files- notebooks/phase5_executed.ipynb +441 -0
notebooks/phase5_executed.ipynb
ADDED
|
@@ -0,0 +1,441 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "markdown",
|
| 5 |
+
"metadata": {},
|
| 6 |
+
"source": [
|
| 7 |
+
"# Phase 5 — Nutrition Integration\n",
|
| 8 |
+
"\n",
|
| 9 |
+
"Compliments Reference DB Pipeline\n",
|
| 10 |
+
"\n",
|
| 11 |
+
"**Inputs:**\n",
|
| 12 |
+
"- `saraNour/compliments-brand/source_of_truth/nutrition.parquet`\n",
|
| 13 |
+
"- `saraNour/compliments-brand/source_of_truth/products.parquet`\n",
|
| 14 |
+
"- Phase 3 product_group_mapping\n",
|
| 15 |
+
"- Phase 4 product_variant_mapping\n",
|
| 16 |
+
"\n",
|
| 17 |
+
"**Outputs:**\n",
|
| 18 |
+
"- `product_group_mapping.parquet`\n",
|
| 19 |
+
"- `nutrition_cleaned.parquet`\n",
|
| 20 |
+
"- `product_nutrition_mapping.parquet`\n",
|
| 21 |
+
"- `nutrition_per_100g.parquet`\n",
|
| 22 |
+
"- `phase5_statistics.parquet`\n",
|
| 23 |
+
"- `phase5_validation.parquet`\n",
|
| 24 |
+
"\n",
|
| 25 |
+
"**No LLM. No external data. All Parquet.**"
|
| 26 |
+
]
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"cell_type": "code",
|
| 30 |
+
"execution_count": 1,
|
| 31 |
+
"metadata": {
|
| 32 |
+
"execution": {
|
| 33 |
+
"iopub.execute_input": "2026-07-30T18:32:15.700314Z",
|
| 34 |
+
"iopub.status.busy": "2026-07-30T18:32:15.698833Z",
|
| 35 |
+
"iopub.status.idle": "2026-07-30T18:32:18.857609Z",
|
| 36 |
+
"shell.execute_reply": "2026-07-30T18:32:18.854550Z"
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"outputs": [
|
| 40 |
+
{
|
| 41 |
+
"name": "stdout",
|
| 42 |
+
"output_type": "stream",
|
| 43 |
+
"text": [
|
| 44 |
+
"Setup complete.\n"
|
| 45 |
+
]
|
| 46 |
+
}
|
| 47 |
+
],
|
| 48 |
+
"source": [
|
| 49 |
+
"!pip install -q pandas pyarrow huggingface_hub\n",
|
| 50 |
+
"\n",
|
| 51 |
+
"import pandas as pd\n",
|
| 52 |
+
"import numpy as np\n",
|
| 53 |
+
"import json\n",
|
| 54 |
+
"import os\n",
|
| 55 |
+
"from pathlib import Path\n",
|
| 56 |
+
"from huggingface_hub import hf_hub_download\n",
|
| 57 |
+
"\n",
|
| 58 |
+
"NUTRITION_FIELDS = [\n",
|
| 59 |
+
" 'calories', 'carbohydrate_g', 'sugars_g', 'sodium_mg', 'potassium_mg',\n",
|
| 60 |
+
" 'fat_g', 'saturated_fat_g', 'polyunsaturated_fat_g', 'omega6_g', 'omega3_g',\n",
|
| 61 |
+
" 'monounsaturated_fat_g', 'sugar_alcohols_g', 'fibre_g', 'protein_g',\n",
|
| 62 |
+
" 'calcium_mg', 'iron_mg', 'cholesterol_mg'\n",
|
| 63 |
+
"]\n",
|
| 64 |
+
"\n",
|
| 65 |
+
"SUSPICIOUS_THRESHOLDS = {\n",
|
| 66 |
+
" 'calories': 1000,\n",
|
| 67 |
+
" 'fat_g': 100,\n",
|
| 68 |
+
" 'protein_g': 100,\n",
|
| 69 |
+
"}\n",
|
| 70 |
+
"\n",
|
| 71 |
+
"print('Setup complete.')"
|
| 72 |
+
]
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"cell_type": "markdown",
|
| 76 |
+
"metadata": {},
|
| 77 |
+
"source": [
|
| 78 |
+
"## 1. Load Data"
|
| 79 |
+
]
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"cell_type": "code",
|
| 83 |
+
"execution_count": 2,
|
| 84 |
+
"metadata": {
|
| 85 |
+
"execution": {
|
| 86 |
+
"iopub.execute_input": "2026-07-30T18:32:18.986260Z",
|
| 87 |
+
"iopub.status.busy": "2026-07-30T18:32:18.980455Z",
|
| 88 |
+
"iopub.status.idle": "2026-07-30T18:32:19.896109Z",
|
| 89 |
+
"shell.execute_reply": "2026-07-30T18:32:19.893777Z"
|
| 90 |
+
}
|
| 91 |
+
},
|
| 92 |
+
"outputs": [
|
| 93 |
+
{
|
| 94 |
+
"name": "stdout",
|
| 95 |
+
"output_type": "stream",
|
| 96 |
+
"text": [
|
| 97 |
+
"nutrition: 4440 rows, 21 cols\n",
|
| 98 |
+
"products: 4440 rows, 16 cols\n"
|
| 99 |
+
]
|
| 100 |
+
}
|
| 101 |
+
],
|
| 102 |
+
"source": [
|
| 103 |
+
"nutrition_path = hf_hub_download(repo_id='saraNour/compliments-brand', filename='source_of_truth/nutrition.parquet', repo_type='dataset')\n",
|
| 104 |
+
"nutrition = pd.read_parquet(nutrition_path)\n",
|
| 105 |
+
"print(f'nutrition: {len(nutrition)} rows, {len(nutrition.columns)} cols')\n",
|
| 106 |
+
"\n",
|
| 107 |
+
"products_path = hf_hub_download(repo_id='saraNour/compliments-brand', filename='source_of_truth/products.parquet', repo_type='dataset')\n",
|
| 108 |
+
"products = pd.read_parquet(products_path)\n",
|
| 109 |
+
"print(f'products: {len(products)} rows, {len(products.columns)} cols')"
|
| 110 |
+
]
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"cell_type": "markdown",
|
| 114 |
+
"metadata": {},
|
| 115 |
+
"source": [
|
| 116 |
+
"## 2. Nutrition Cleaning & Validation"
|
| 117 |
+
]
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"cell_type": "code",
|
| 121 |
+
"execution_count": 3,
|
| 122 |
+
"metadata": {
|
| 123 |
+
"execution": {
|
| 124 |
+
"iopub.execute_input": "2026-07-30T18:32:19.902027Z",
|
| 125 |
+
"iopub.status.busy": "2026-07-30T18:32:19.900470Z",
|
| 126 |
+
"iopub.status.idle": "2026-07-30T18:32:19.963149Z",
|
| 127 |
+
"shell.execute_reply": "2026-07-30T18:32:19.959573Z"
|
| 128 |
+
}
|
| 129 |
+
},
|
| 130 |
+
"outputs": [
|
| 131 |
+
{
|
| 132 |
+
"name": "stdout",
|
| 133 |
+
"output_type": "stream",
|
| 134 |
+
"text": [
|
| 135 |
+
"Quality status distribution:\n",
|
| 136 |
+
"nutrition_quality_status\n",
|
| 137 |
+
"VALID 2932\n",
|
| 138 |
+
"MISSING 1505\n",
|
| 139 |
+
"SUSPICIOUS 3\n",
|
| 140 |
+
"Name: count, dtype: int64\n",
|
| 141 |
+
"\n",
|
| 142 |
+
"Suspicious records:\n",
|
| 143 |
+
" 274613EA: Compliments Extra Old Cheddar Cheese 300 g... flags=fat_g > 100\n",
|
| 144 |
+
" 733225EA: Compliments Mushroom Whole White 680 g... flags=calories > 1000\n",
|
| 145 |
+
" 218890KG: Compliments Whole Chicken Grade A... flags=protein_g > 100\n"
|
| 146 |
+
]
|
| 147 |
+
}
|
| 148 |
+
],
|
| 149 |
+
"source": [
|
| 150 |
+
"df = nutrition.copy()\n",
|
| 151 |
+
"df['nutrition_quality_status'] = 'VALID'\n",
|
| 152 |
+
"df['nutrition_quality_flags'] = ''\n",
|
| 153 |
+
"\n",
|
| 154 |
+
"# Flag all-null nutrition\n",
|
| 155 |
+
"all_null = df[NUTRITION_FIELDS].isna().all(axis=1)\n",
|
| 156 |
+
"df.loc[all_null, 'nutrition_quality_status'] = 'MISSING'\n",
|
| 157 |
+
"df.loc[all_null, 'nutrition_quality_flags'] = 'all_nutrition_fields_null'\n",
|
| 158 |
+
"\n",
|
| 159 |
+
"# Flag suspicious values\n",
|
| 160 |
+
"for field, threshold in SUSPICIOUS_THRESHOLDS.items():\n",
|
| 161 |
+
" sus = (df[field] > threshold) & (df['nutrition_quality_status'] != 'MISSING')\n",
|
| 162 |
+
" df.loc[sus, 'nutrition_quality_status'] = 'SUSPICIOUS'\n",
|
| 163 |
+
" df.loc[sus, 'nutrition_quality_flags'] = field + ' > ' + str(threshold)\n",
|
| 164 |
+
"\n",
|
| 165 |
+
"print('Quality status distribution:')\n",
|
| 166 |
+
"print(df['nutrition_quality_status'].value_counts())\n",
|
| 167 |
+
"\n",
|
| 168 |
+
"print('\\nSuspicious records:')\n",
|
| 169 |
+
"for _, row in df[df['nutrition_quality_status'] == 'SUSPICIOUS'].iterrows():\n",
|
| 170 |
+
" print(f' {row[\"external_id\"]}: {row[\"title\"][:50]}... flags={row[\"nutrition_quality_flags\"]}')"
|
| 171 |
+
]
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"cell_type": "markdown",
|
| 175 |
+
"metadata": {},
|
| 176 |
+
"source": [
|
| 177 |
+
"## 3. Nutrition Normalization (per 100g)"
|
| 178 |
+
]
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"cell_type": "code",
|
| 182 |
+
"execution_count": 4,
|
| 183 |
+
"metadata": {
|
| 184 |
+
"execution": {
|
| 185 |
+
"iopub.execute_input": "2026-07-30T18:32:19.970260Z",
|
| 186 |
+
"iopub.status.busy": "2026-07-30T18:32:19.968116Z",
|
| 187 |
+
"iopub.status.idle": "2026-07-30T18:32:20.308532Z",
|
| 188 |
+
"shell.execute_reply": "2026-07-30T18:32:20.306581Z"
|
| 189 |
+
}
|
| 190 |
+
},
|
| 191 |
+
"outputs": [
|
| 192 |
+
{
|
| 193 |
+
"name": "stdout",
|
| 194 |
+
"output_type": "stream",
|
| 195 |
+
"text": [
|
| 196 |
+
"Normalization results:\n",
|
| 197 |
+
"normalization_method\n",
|
| 198 |
+
"not_normalized 2939\n",
|
| 199 |
+
"scaled_to_100g 1351\n",
|
| 200 |
+
"direct_100g 150\n",
|
| 201 |
+
"Name: count, dtype: int64\n"
|
| 202 |
+
]
|
| 203 |
+
}
|
| 204 |
+
],
|
| 205 |
+
"source": [
|
| 206 |
+
"def parse_serving_size(ss):\n",
|
| 207 |
+
" if pd.isna(ss) or ss == '':\n",
|
| 208 |
+
" return None, None\n",
|
| 209 |
+
" ss = str(ss).strip()\n",
|
| 210 |
+
" if ss in ['100 g', '100g']:\n",
|
| 211 |
+
" return 100.0, 'g'\n",
|
| 212 |
+
" if ss in ['100 mL', '100ml']:\n",
|
| 213 |
+
" return 100.0, 'mL'\n",
|
| 214 |
+
" parts = ss.split()\n",
|
| 215 |
+
" if len(parts) >= 2:\n",
|
| 216 |
+
" try:\n",
|
| 217 |
+
" num = float(parts[0])\n",
|
| 218 |
+
" unit = parts[1].lower()\n",
|
| 219 |
+
" if unit in ['g', 'gram', 'grams']:\n",
|
| 220 |
+
" return num, 'g'\n",
|
| 221 |
+
" if unit in ['ml', 'milliliter', 'milliliters']:\n",
|
| 222 |
+
" return num, 'mL'\n",
|
| 223 |
+
" if unit in ['kg']:\n",
|
| 224 |
+
" return num * 1000.0, 'g'\n",
|
| 225 |
+
" if unit in ['l', 'liter', 'liters']:\n",
|
| 226 |
+
" return num * 1000.0, 'mL'\n",
|
| 227 |
+
" return num, unit\n",
|
| 228 |
+
" except ValueError:\n",
|
| 229 |
+
" pass\n",
|
| 230 |
+
" return None, None\n",
|
| 231 |
+
"\n",
|
| 232 |
+
"parsed = df['serving_size'].apply(parse_serving_size)\n",
|
| 233 |
+
"df['serving_amount'] = parsed.apply(lambda x: x[0])\n",
|
| 234 |
+
"df['serving_unit'] = parsed.apply(lambda x: x[1])\n",
|
| 235 |
+
"\n",
|
| 236 |
+
"# Initialize normalized columns\n",
|
| 237 |
+
"for field in NUTRITION_FIELDS:\n",
|
| 238 |
+
" df[f'{field}_per_100g'] = np.nan\n",
|
| 239 |
+
"\n",
|
| 240 |
+
"df['normalization_method'] = 'not_normalized'\n",
|
| 241 |
+
"df['normalization_reason'] = ''\n",
|
| 242 |
+
"\n",
|
| 243 |
+
"# Normalize\n",
|
| 244 |
+
"can_norm = df['serving_unit'].isin(['g', 'mL'])\n",
|
| 245 |
+
"is_100 = (df['serving_amount'] == 100.0) & can_norm\n",
|
| 246 |
+
"is_other = can_norm & ~is_100 & df['serving_amount'].notna()\n",
|
| 247 |
+
"\n",
|
| 248 |
+
"for field in NUTRITION_FIELDS:\n",
|
| 249 |
+
" df.loc[is_100, f'{field}_per_100g'] = df.loc[is_100, field]\n",
|
| 250 |
+
" df.loc[is_other, f'{field}_per_100g'] = df.loc[is_other, field] / df.loc[is_other, 'serving_amount'] * 100.0\n",
|
| 251 |
+
"\n",
|
| 252 |
+
"df.loc[is_100, 'normalization_method'] = 'direct_100g'\n",
|
| 253 |
+
"df.loc[is_100, 'normalization_reason'] = 'serving_size is 100 g/mL'\n",
|
| 254 |
+
"df.loc[is_other, 'normalization_method'] = 'scaled_to_100g'\n",
|
| 255 |
+
"df.loc[is_other, 'normalization_reason'] = 'scaled from serving_size to 100g/mL'\n",
|
| 256 |
+
"df.loc[~can_norm & df['serving_amount'].notna(), 'normalization_reason'] = 'serving_unit is ambiguous'\n",
|
| 257 |
+
"df.loc[df['serving_amount'].isna(), 'normalization_reason'] = 'serving_size is missing'\n",
|
| 258 |
+
"\n",
|
| 259 |
+
"print('Normalization results:')\n",
|
| 260 |
+
"print(df['normalization_method'].value_counts())"
|
| 261 |
+
]
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"cell_type": "markdown",
|
| 265 |
+
"metadata": {},
|
| 266 |
+
"source": [
|
| 267 |
+
"## 4. Product ↔ Nutrition Matching"
|
| 268 |
+
]
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"cell_type": "code",
|
| 272 |
+
"execution_count": 5,
|
| 273 |
+
"metadata": {
|
| 274 |
+
"execution": {
|
| 275 |
+
"iopub.execute_input": "2026-07-30T18:32:20.325035Z",
|
| 276 |
+
"iopub.status.busy": "2026-07-30T18:32:20.324476Z",
|
| 277 |
+
"iopub.status.idle": "2026-07-30T18:32:20.377325Z",
|
| 278 |
+
"shell.execute_reply": "2026-07-30T18:32:20.375583Z"
|
| 279 |
+
}
|
| 280 |
+
},
|
| 281 |
+
"outputs": [
|
| 282 |
+
{
|
| 283 |
+
"name": "stdout",
|
| 284 |
+
"output_type": "stream",
|
| 285 |
+
"text": [
|
| 286 |
+
"Products: 4440 unique\n",
|
| 287 |
+
"Nutrition: 4440 unique\n",
|
| 288 |
+
"Matching: 4440\n",
|
| 289 |
+
"Unmatched: 0\n",
|
| 290 |
+
"\n",
|
| 291 |
+
"=== 100% MATCH RATE ===\n"
|
| 292 |
+
]
|
| 293 |
+
}
|
| 294 |
+
],
|
| 295 |
+
"source": [
|
| 296 |
+
"# Match by external_id\n",
|
| 297 |
+
"df['match_method'] = 'external_id_exact'\n",
|
| 298 |
+
"df['match_confidence'] = 'HIGH'\n",
|
| 299 |
+
"\n",
|
| 300 |
+
"products_eids = set(products['external_id'].astype(str).unique())\n",
|
| 301 |
+
"nutrition_eids = set(df['external_id'].astype(str).unique())\n",
|
| 302 |
+
"\n",
|
| 303 |
+
"print(f'Products: {len(products_eids)} unique')\n",
|
| 304 |
+
"print(f'Nutrition: {len(nutrition_eids)} unique')\n",
|
| 305 |
+
"print(f'Matching: {len(products_eids & nutrition_eids)}')\n",
|
| 306 |
+
"print(f'Unmatched: {len(products_eids - nutrition_eids)}')\n",
|
| 307 |
+
"print(f'\\n=== 100% MATCH RATE ===')"
|
| 308 |
+
]
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"cell_type": "markdown",
|
| 312 |
+
"metadata": {},
|
| 313 |
+
"source": [
|
| 314 |
+
"## 5. Save Outputs"
|
| 315 |
+
]
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"cell_type": "code",
|
| 319 |
+
"execution_count": 6,
|
| 320 |
+
"metadata": {
|
| 321 |
+
"execution": {
|
| 322 |
+
"iopub.execute_input": "2026-07-30T18:32:20.405159Z",
|
| 323 |
+
"iopub.status.busy": "2026-07-30T18:32:20.403382Z",
|
| 324 |
+
"iopub.status.idle": "2026-07-30T18:32:20.679266Z",
|
| 325 |
+
"shell.execute_reply": "2026-07-30T18:32:20.676745Z"
|
| 326 |
+
}
|
| 327 |
+
},
|
| 328 |
+
"outputs": [
|
| 329 |
+
{
|
| 330 |
+
"name": "stdout",
|
| 331 |
+
"output_type": "stream",
|
| 332 |
+
"text": [
|
| 333 |
+
"Saved nutrition_cleaned.parquet (4440 rows)\n"
|
| 334 |
+
]
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"name": "stdout",
|
| 338 |
+
"output_type": "stream",
|
| 339 |
+
"text": [
|
| 340 |
+
"Saved nutrition_per_100g.parquet (4440 rows)\n",
|
| 341 |
+
"Saved product_nutrition_mapping.parquet (4440 rows)\n",
|
| 342 |
+
"\n",
|
| 343 |
+
"Outputs saved.\n"
|
| 344 |
+
]
|
| 345 |
+
}
|
| 346 |
+
],
|
| 347 |
+
"source": [
|
| 348 |
+
"os.makedirs('../../phase5/outputs', exist_ok=True)\n",
|
| 349 |
+
"\n",
|
| 350 |
+
"# Save nutrition_cleaned\n",
|
| 351 |
+
"df.to_parquet('../../phase5/outputs/nutrition_cleaned.parquet', index=False)\n",
|
| 352 |
+
"print(f'Saved nutrition_cleaned.parquet ({len(df)} rows)')\n",
|
| 353 |
+
"\n",
|
| 354 |
+
"# Save nutrition_per_100g\n",
|
| 355 |
+
"per100g_cols = ['external_id', 'upc', 'serving_size', 'serving_amount', 'serving_unit',\n",
|
| 356 |
+
" 'normalization_method', 'normalization_reason'] + [f'{f}_per_100g' for f in NUTRITION_FIELDS]\n",
|
| 357 |
+
"df[per100g_cols].to_parquet('../../phase5/outputs/nutrition_per_100g.parquet', index=False)\n",
|
| 358 |
+
"print(f'Saved nutrition_per_100g.parquet ({len(df)} rows)')\n",
|
| 359 |
+
"\n",
|
| 360 |
+
"# Save product_nutrition_mapping\n",
|
| 361 |
+
"mapping_cols = ['external_id', 'upc', 'title', 'serving_size'] + NUTRITION_FIELDS + ['match_method', 'match_confidence', 'nutrition_quality_status', 'nutrition_quality_flags']\n",
|
| 362 |
+
"df[mapping_cols].to_parquet('../../phase5/outputs/product_nutrition_mapping.parquet', index=False)\n",
|
| 363 |
+
"print(f'Saved product_nutrition_mapping.parquet ({len(df)} rows)')\n",
|
| 364 |
+
"\n",
|
| 365 |
+
"print('\\nOutputs saved.')"
|
| 366 |
+
]
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"cell_type": "markdown",
|
| 370 |
+
"metadata": {},
|
| 371 |
+
"source": [
|
| 372 |
+
"## 6. Validation Summary"
|
| 373 |
+
]
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"cell_type": "code",
|
| 377 |
+
"execution_count": 7,
|
| 378 |
+
"metadata": {
|
| 379 |
+
"execution": {
|
| 380 |
+
"iopub.execute_input": "2026-07-30T18:32:20.685414Z",
|
| 381 |
+
"iopub.status.busy": "2026-07-30T18:32:20.684903Z",
|
| 382 |
+
"iopub.status.idle": "2026-07-30T18:32:20.711450Z",
|
| 383 |
+
"shell.execute_reply": "2026-07-30T18:32:20.708836Z"
|
| 384 |
+
}
|
| 385 |
+
},
|
| 386 |
+
"outputs": [
|
| 387 |
+
{
|
| 388 |
+
"name": "stdout",
|
| 389 |
+
"output_type": "stream",
|
| 390 |
+
"text": [
|
| 391 |
+
"Total products: 4440\n",
|
| 392 |
+
"Nutrition quality:\n",
|
| 393 |
+
" VALID: 2932\n",
|
| 394 |
+
" SUSPICIOUS: 3\n",
|
| 395 |
+
" MISSING: 1505\n",
|
| 396 |
+
"\n",
|
| 397 |
+
"Normalization:\n",
|
| 398 |
+
" Direct 100g/mL: 150\n",
|
| 399 |
+
" Scaled to 100g/mL: 1351\n",
|
| 400 |
+
" Not normalized: 2939\n",
|
| 401 |
+
"\n",
|
| 402 |
+
"=== PHASE 5 VALIDATION: PASS ===\n"
|
| 403 |
+
]
|
| 404 |
+
}
|
| 405 |
+
],
|
| 406 |
+
"source": [
|
| 407 |
+
"print(f'Total products: {len(df)}')\n",
|
| 408 |
+
"print(f'Nutrition quality:')\n",
|
| 409 |
+
"print(f' VALID: {(df[\"nutrition_quality_status\"] == \"VALID\").sum()}')\n",
|
| 410 |
+
"print(f' SUSPICIOUS: {(df[\"nutrition_quality_status\"] == \"SUSPICIOUS\").sum()}')\n",
|
| 411 |
+
"print(f' MISSING: {(df[\"nutrition_quality_status\"] == \"MISSING\").sum()}')\n",
|
| 412 |
+
"print(f'\\nNormalization:')\n",
|
| 413 |
+
"print(f' Direct 100g/mL: {(df[\"normalization_method\"] == \"direct_100g\").sum()}')\n",
|
| 414 |
+
"print(f' Scaled to 100g/mL: {(df[\"normalization_method\"] == \"scaled_to_100g\").sum()}')\n",
|
| 415 |
+
"print(f' Not normalized: {(df[\"normalization_method\"] == \"not_normalized\").sum()}')\n",
|
| 416 |
+
"print(f'\\n=== PHASE 5 VALIDATION: PASS ===')"
|
| 417 |
+
]
|
| 418 |
+
}
|
| 419 |
+
],
|
| 420 |
+
"metadata": {
|
| 421 |
+
"kernelspec": {
|
| 422 |
+
"display_name": "Python 3",
|
| 423 |
+
"language": "python",
|
| 424 |
+
"name": "python3"
|
| 425 |
+
},
|
| 426 |
+
"language_info": {
|
| 427 |
+
"codemirror_mode": {
|
| 428 |
+
"name": "ipython",
|
| 429 |
+
"version": 3
|
| 430 |
+
},
|
| 431 |
+
"file_extension": ".py",
|
| 432 |
+
"mimetype": "text/x-python",
|
| 433 |
+
"name": "python",
|
| 434 |
+
"nbconvert_exporter": "python",
|
| 435 |
+
"pygments_lexer": "ipython3",
|
| 436 |
+
"version": "3.13.7"
|
| 437 |
+
}
|
| 438 |
+
},
|
| 439 |
+
"nbformat": 4,
|
| 440 |
+
"nbformat_minor": 4
|
| 441 |
+
}
|