File size: 4,144 Bytes
1cd137c | 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 | from pathlib import Path
import pandas as pd
BASE_DIR = Path(__file__).resolve().parents[3]
PRODUCTION_DIR = BASE_DIR / "data" / "production"
FILES = {
"product_metadata": PRODUCTION_DIR / "product_metadata.parquet",
"product_groups": PRODUCTION_DIR / "product_groups.parquet",
"product_variants": PRODUCTION_DIR / "product_variants.parquet",
"product_nutrition": PRODUCTION_DIR / "product_nutrition.parquet",
"product_scores": PRODUCTION_DIR / "product_scores.parquet",
}
def load_production():
return {
name: pd.read_parquet(path)
for name, path in FILES.items()
}
def validate_production():
tables = load_production()
metadata = tables["product_metadata"]
groups = tables["product_groups"]
variants = tables["product_variants"]
nutrition = tables["product_nutrition"]
scores = tables["product_scores"]
errors = []
# 1. Product-level uniqueness
for name, df in {
"product_metadata": metadata,
"product_nutrition": nutrition,
"product_scores": scores,
}.items():
if "external_id" not in df.columns:
errors.append(f"{name}: missing external_id")
elif df["external_id"].duplicated().any():
errors.append(
f"{name}: duplicate external_id values"
)
# 2. Group-level uniqueness
if groups["group_id"].duplicated().any():
errors.append("product_groups: duplicate group_id values")
# 3. Variant-level uniqueness
if variants["variant_id"].duplicated().any():
errors.append("product_variants: duplicate variant_id values")
# 4. Product coverage
metadata_ids = set(metadata["external_id"])
nutrition_ids = set(nutrition["external_id"])
score_ids = set(scores["external_id"])
missing_nutrition = metadata_ids - nutrition_ids
missing_scores = metadata_ids - score_ids
if missing_nutrition:
errors.append(
f"Products missing from nutrition: {len(missing_nutrition)}"
)
if missing_scores:
errors.append(
f"Products missing from scores: {len(missing_scores)}"
)
# 5. Group coverage
group_ids = set(groups["group_id"])
for name, df in {
"product_metadata": metadata,
"product_nutrition": nutrition,
"product_scores": scores,
}.items():
if "group_id" in df.columns:
referenced = set(df["group_id"].dropna())
orphan_groups = referenced - group_ids
if orphan_groups:
errors.append(
f"{name}: {len(orphan_groups)} orphan group_id values"
)
# 6. Variant coverage
variant_ids = set(variants["variant_id"])
for name, df in {
"product_nutrition": nutrition,
"product_scores": scores,
}.items():
if "variant_id" in df.columns:
referenced = set(df["variant_id"].dropna())
orphan_variants = referenced - variant_ids
if orphan_variants:
errors.append(
f"{name}: {len(orphan_variants)} orphan variant_id values"
)
# 7. Basic row-count expectations
expected_counts = {
"product_metadata": 4440,
"product_groups": 3845,
"product_variants": 4320,
"product_nutrition": 4440,
"product_scores": 4440,
}
for name, expected in expected_counts.items():
actual = len(tables[name])
if actual != expected:
errors.append(
f"{name}: expected {expected} rows, found {actual}"
)
# Final result
print("\n=== Production Validation ===")
for name, df in tables.items():
print(
f"{name}: {len(df):,} rows × {len(df.columns)} columns"
)
if errors:
print("\n❌ VALIDATION FAILED")
for error in errors:
print(f"- {error}")
raise SystemExit(1)
print("\n✅ VALIDATION PASSED")
print("All production tables are structurally consistent.")
if __name__ == "__main__":
validate_production()
|