python中dropna()函数的作用举例说明

import pandas as pd

# 创建包含缺失值的数据框
data = {'A': [1, 2, None, 4],
        'B': [None, 6, 7, 8],
        'C': [9, 10, 11, 12]}
df = pd.DataFrame(data)

# 删除包含缺失值的行
cleaned_df = df.dropna()

# 删除包含缺失值的列
cleaned_df = df.dropna(axis=1)

# 只删除整行或整列都是缺失值的行或列
cleaned_df = df.dropna(how='all')

# 至少需要2个非缺失值才保留行或列
cleaned_df = df.dropna(thresh=2)

# 只在特定列中检查缺失值
cleaned_df = df.dropna(subset=['A', 'C'])

# 在原始数据上进行就地修改
df.dropna(inplace=True)

import numpy as np
import pandas as pd
 
a = np.ones((11,10))
for i in range(len(a)):
    a[i,:i] = np.nan
 
d = pd.DataFrame(data=a)
print(d)

# 按行删除：存在空值，即删除该行
print(d.dropna(axis=0, how='any'))

#  按行删除：所有数据都为空值，即删除该行
print(d.dropna(axis=0, how='all'))

# 按列删除：该列非空元素小于5个的，即删除该列
print(d.dropna(axis='columns', thresh=5))

# 设置子集：删除第0、5、6、7列都为空的行
print(d.dropna(axis='index', how='all', subset=[0,5,6,7]))

# 设置子集：删除第5、6、7行存在空值的列
print(d.dropna(axis=1, how='any', subset=[5,6,7]))

# 原地修改
print(d.dropna(axis=0, how='any', inplace=True))
print("==============================")
print(d)