scripts/staffing/fixup_phone_type.py

@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+"""
+fixup_phone_type.py — Decision D from the synthetic-data gap report.
+
+Converts workers_500k.parquet `phone` column from int64 → string. Phones
+in this dataset are 11-digit US numbers (1 + area + 7), e.g. 13122277740.
+Stored as int64, the column compares fine numerically but breaks join
+keys with string-typed phone columns elsewhere (formatted "+1...", or
+loaded from a CSV).
+
+Backs up the original to workers_500k.parquet.bak-<date> before write.
+Idempotent: detects when the fix has already been applied and exits 0.
+
+Usage:
+    python3 scripts/staffing/fixup_phone_type.py
+"""
+
+import datetime as dt
+import shutil
+import sys
+from pathlib import Path
+
+import pyarrow as pa
+import pyarrow.compute as pc
+import pyarrow.parquet as pq
+
+REPO = Path(__file__).resolve().parents[2]
+TARGET = REPO / "data" / "datasets" / "workers_500k.parquet"
+
+
+def main() -> int:
+    if not TARGET.exists():
+        print(f"missing: {TARGET}", file=sys.stderr)
+        return 1
+
+    table = pq.read_table(TARGET)
+    phone_field = table.schema.field("phone")
+    if phone_field.type == pa.string():
+        print(f"phone is already string — no-op")
+        return 0
+
+    today = dt.date.today().isoformat()
+    backup = TARGET.with_suffix(f".parquet.bak-{today}")
+    if not backup.exists():
+        shutil.copy2(TARGET, backup)
+        print(f"backup: {backup.relative_to(REPO)}")
+
+    phone_str = pc.cast(table["phone"], pa.string())
+    new_table = table.set_column(
+        table.schema.get_field_index("phone"),
+        pa.field("phone", pa.string()),
+        phone_str,
+    )
+
+    pq.write_table(new_table, TARGET, compression="snappy")
+    rounds_trip = pq.read_table(TARGET, columns=["phone"])
+    sample = rounds_trip["phone"].slice(0, 3).to_pylist()
+    print(f"wrote: {TARGET.relative_to(REPO)}")
+    print(f"phone type: {rounds_trip.schema.field('phone').type}")
+    print(f"sample: {sample}")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())