Pandas中pd.dropna()函数详解：过滤缺失数据的方法与参数说明

DataFrame.dropna(axis=0, how='any', thresh=None, subset=None, inplace=False)
Remove missing values.

import pandas as pd
import numpy as np
df = pd.DataFrame(np.random.randn(5, 3), index = list('abcde'), columns = ['one', 'two', 'three'])        # 随机产生5行3列的数据    
df.ix[1, :-1] = np.nan        # 将指定数据定义为缺失
df.ix[1:-1, 2] = np.nan
print(df)

df.dropna()   #删除所有带缺失数据的行

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)