删除Pandas中重复NaN值超过阈值的行

import pandas as pd

df.drop_duplicates(keep=False, inplace=True)

nan_counts = df.isnull().sum(axis=1)

threshold = 2
rows_to_drop = nan_counts[nan_counts > threshold].index

df.drop(rows_to_drop, inplace=True)

import pandas as pd

# 创建DataFrame对象，假设为df
df = pd.DataFrame({'A': [1, 2, None, None, 5],
                   'B': [None, None, None, 4, 5],
                   'C': [None, None, None, None, None]})

# 设置阈值
threshold = 2

# 删除重复行
df.drop_duplicates(keep=False, inplace=True)

# 计算每行中NaN值的数量
nan_counts = df.isnull().sum(axis=1)

# 找到超过阈值的行的索引
rows_to_drop = nan_counts[nan_counts > threshold].index

# 删除超过阈值的行
df.drop(rows_to_drop, inplace=True)

print(df)