P1: rebuild

task1/01_clean.py

@@ -1,58 +1,92 @@
+"""
+Step 01: 数据清洗与标准化
+
+输入: ../data.xlsx (原始数据)
+输出: 01_clean.xlsx (清洗后的标准化数据)
+
+功能:
+1. 读取原始数据
+2. 保留有效列并重命名为标准字段名
+3. 生成 site_id (1-70)
+4. 检查缺失值和数据质量
+"""
+
 import pandas as pd
+import numpy as np
+from pathlib import Path
+
+# 路径配置
+INPUT_PATH = Path(__file__).parent.parent / "data.xlsx"
+OUTPUT_PATH = Path(__file__).parent / "01_clean.xlsx"
+
+# 列名映射: 原始列名 -> 标准列名
+COLUMN_MAPPING = {
+    'Site Name': 'site_name',
+    'latitude': 'lat',
+    'longitude': 'lon',
+    'Number of Visits in 2019': 'visits_2019',
+    'Average Demand per Visit': 'mu',
+    'StDev(Demand per Visit)': 'sigma'
+}
 
 
-INPUT_XLSX = "data.xlsx"
-OUTPUT_XLSX = "task1/01_clean.xlsx"
-SHEET_NAME = "addresses2019 updated"
+def main():
+    print("=" * 60)
+    print("Step 01: 数据清洗与标准化")
+    print("=" * 60)
 
+    # 1. 读取原始数据
+    print(f"\n[1] 读取原始数据: {INPUT_PATH}")
+    df_raw = pd.read_excel(INPUT_PATH)
+    print(f"    原始数据: {df_raw.shape[0]} 行, {df_raw.shape[1]} 列")
 
-def main() -> None:
-    df_raw = pd.read_excel(INPUT_XLSX, sheet_name=SHEET_NAME)
+    # 2. 选择并重命名列
+    print(f"\n[2] 选择有效列并重命名")
+    df = df_raw[list(COLUMN_MAPPING.keys())].copy()
+    df = df.rename(columns=COLUMN_MAPPING)
 
-    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}")
+    # 3. 生成 site_id
+    print(f"\n[3] 生成 site_id (1-70)")
+    df.insert(0, 'site_id', range(1, len(df) + 1))
 
-    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",
-        }
-    )
+    # 4. 数据质量检查
+    print(f"\n[4] 数据质量检查")
+    print(f"    缺失值统计:")
+    missing = df.isnull().sum()
+    for col, count in missing.items():
+        if count > 0:
+            print(f"      - {col}: {count} 个缺失值")
+    if missing.sum() == 0:
+        print(f"      - 无缺失值")
 
-    df.insert(0, "site_id", range(1, len(df) + 1))
+    # 5. 数据统计摘要
+    print(f"\n[5] 关键字段统计:")
+    print(f"    站点数: {len(df)}")
+    print(f"    μ (单次服务人数均值):")
+    print(f"      - 范围: [{df['mu'].min():.1f}, {df['mu'].max():.1f}]")
+    print(f"      - 均值: {df['mu'].mean():.1f}")
+    print(f"      - μ > 250 的站点数: {(df['mu'] > 250).sum()}")
+    print(f"    σ (单次服务人数标准差):")
+    print(f"      - 范围: [{df['sigma'].min():.1f}, {df['sigma'].max():.1f}]")
+    print(f"    2019年访问次数:")
+    print(f"      - 总计: {df['visits_2019'].sum()}")
+    print(f"      - 范围: [{df['visits_2019'].min()}, {df['visits_2019'].max()}]")
 
-    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")
+    # 6. 保存输出
+    print(f"\n[6] 保存输出: {OUTPUT_PATH}")
+    df.to_excel(OUTPUT_PATH, index=False)
+    print(f"    已保存 {len(df)} 条记录")
 
-    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.")
+    # 7. 显示前5行
+    print(f"\n[7] 输出数据预览 (前5行):")
+    print(df.head().to_string(index=False))
 
-    with pd.ExcelWriter(OUTPUT_XLSX, engine="openpyxl") as writer:
-        df.to_excel(writer, index=False, sheet_name="sites")
+    print("\n" + "=" * 60)
+    print("Step 01 完成")
+    print("=" * 60)
+
+    return df
 
 
 if __name__ == "__main__":
     main()
-