P1

task1/01_clean.py

@@ -0,0 +1,58 @@
+import pandas as pd
+
+
+INPUT_XLSX = "data.xlsx"
+OUTPUT_XLSX = "task1/01_clean.xlsx"
+SHEET_NAME = "addresses2019 updated"
+
+
+def main() -> None:
+    df_raw = pd.read_excel(INPUT_XLSX, sheet_name=SHEET_NAME)
+
+    required = [
+        "Site Name",
+        "latitude",
+        "longitude",
+        "Number of Visits in 2019",
+        "Average Demand per Visit",
+        "StDev(Demand per Visit)",
+    ]
+    missing = [c for c in required if c not in df_raw.columns]
+    if missing:
+        raise ValueError(f"Missing required columns: {missing}")
+
+    df = df_raw[required].copy()
+    df = df.rename(
+        columns={
+            "Site Name": "site_name",
+            "latitude": "lat",
+            "longitude": "lon",
+            "Number of Visits in 2019": "visits_2019",
+            "Average Demand per Visit": "mu_clients_per_visit",
+            "StDev(Demand per Visit)": "sd_clients_per_visit",
+        }
+    )
+
+    df.insert(0, "site_id", range(1, len(df) + 1))
+
+    numeric_cols = ["lat", "lon", "visits_2019", "mu_clients_per_visit", "sd_clients_per_visit"]
+    for col in numeric_cols:
+        df[col] = pd.to_numeric(df[col], errors="coerce")
+
+    if df["site_name"].isna().any():
+        raise ValueError("Found missing site_name values.")
+    if df[numeric_cols].isna().any().any():
+        bad = df[df[numeric_cols].isna().any(axis=1)][["site_id", "site_name"] + numeric_cols]
+        raise ValueError(f"Found missing numeric values:\n{bad}")
+    if (df["mu_clients_per_visit"] < 0).any() or (df["sd_clients_per_visit"] < 0).any():
+        raise ValueError("Found negative mu/sd values; expected nonnegative.")
+    if (df["visits_2019"] <= 0).any():
+        raise ValueError("Found non-positive visits_2019; expected >0 for all 70 regular sites.")
+
+    with pd.ExcelWriter(OUTPUT_XLSX, engine="openpyxl") as writer:
+        df.to_excel(writer, index=False, sheet_name="sites")
+
+
+if __name__ == "__main__":
+    main()
+