用条件计算多指标序列/数据帧

import pandas as pd

data = {
    'A': [1, 2, 3, 4, 5],
    'B': [10, 20, 30, 40, 50],
    'C': [100, 200, 300, 400, 500]
}

df = pd.DataFrame(data)

filtered_df = df[df['A'] > 2]
print(filtered_df)

   A   B    C
2  3  30  300
3  4  40  400
4  5  50  500

df['B'] = df['B'].apply(lambda x: 0 if x > 25 else x)
print(df)

   A    B    C
0  1   10  100
1  2   20  200
2  3    0  300
3  4    0  400
4  5    0  500

grouped_df = df.groupby('A')['B'].mean()
print(grouped_df)

A
1    10.0
2    20.0
3    0.0
4    0.0
5    0.0
Name: B, dtype: float64

# 错误示例
filtered_df = df[df['A'] => 2]  # 应该是 >= 而不是 =>

# 正确示例
filtered_df = df[df['A'] >= 2]

# 错误示例
df['A'] = df['A'].astype(str)  # 将整数列转换为字符串列
filtered_df = df[df['A'] > 2]  # 无法进行比较

# 正确示例
df['A'] = df['A'].astype(int)  # 确保数据类型一致
filtered_df = df[df['A'] > 2]

# 使用向量化操作
filtered_df = df[df['A'] > 2]

# 使用索引
df.set_index('A', inplace=True)
filtered_df = df.loc[3:]