Pandas数据帧分组和排序

import pandas as pd

data = {
    'Region': ['North', 'South', 'North', 'East', 'West', 'South'],
    'Sales': [200, 300, 150, 400, 250, 350]
}

df = pd.DataFrame(data)

grouped = df.groupby('Region')['Sales'].sum()
print(grouped)

Region
East     400
North    350
South    650
West     250
Name: Sales, dtype: int64

sorted_df = df.sort_values(by='Sales', ascending=False)
print(sorted_df)

  Region  Sales
3   East     400
5  South     350
1  South     300
4   West     250
2  North     150
0  North     200

# 错误的列名
grouped = df.groupby('WrongColumn')['Sales'].sum()  # 这将引发 KeyError

# 正确的列名
grouped = df.groupby('Region')['Sales'].sum()

# 处理缺失值
df = df.dropna(subset=['Sales'])

# 确保数据类型一致
df['Sales'] = df['Sales'].astype(int)

sorted_df = df.sort_values(by='Sales', ascending=False)