DataOps-platform/analyze_more.py

import pandas as pd

# 读取Excel文件
df = pd.read_excel('酒店职位名称20250519.xlsx', sheet_name='汇总版')

print("=== 更详细的数据分析 ===")
print(f"总共 {len(df)} 条记录")

print("\n=== 前10行完整数据 ===")
for i in range(min(10, len(df))):
    row = df.iloc[i]
    print(f"第{i+1}行:")
    for col in df.columns:
        print(f"  {col}: {row[col]}")
    print()

print("\n=== 各列唯一值数量 ===")
for col in df.columns:
    unique_count = df[col].nunique()
    print(f"{col}: {unique_count} 个唯一值")

print("\n=== 各列是否有空值 ===")
for col in df.columns:
    null_count = df[col].isnull().sum()
    print(f"{col}: {null_count} 个空值")

print("\n=== 部门统计 ===")
dept_counts = df['部门（中文）'].value_counts()
print(dept_counts)

print("\n=== 职级统计 ===")
level_counts = df['职级（中文）'].value_counts()
print(level_counts)