Python:查找NA值高于阈值的列的名称

import pandas as pd

def find_columns_with_high_na(df, threshold):
    na_counts = df.isna().sum()
    high_na_columns = na_counts[na_counts > threshold].index.tolist()
    return high_na_columns

# 示例数据
data = {'A': [1, 2, 3, None, None],
        'B': [4, 5, None, None, None],
        'C': [None, None, None, None, None],
        'D': [7, 8, 9, 10, None]}
df = pd.DataFrame(data)

# 设置阈值为2
threshold = 2

# 查找缺失值超过阈值的列
high_na_columns = find_columns_with_high_na(df, threshold)
print(high_na_columns)