我認爲如果需要使用布爾索引:
df = df[~df.isnull().any(axis=1)]
但更好的是隻使用:
df = df.dropna()
樣品:
df = pd.DataFrame({'A':[np.nan,5,4,5,5,np.nan],
'B':[7,8,9,4,2,np.nan],
'C':[1,3,5,7,1,np.nan],
'D':[5,3,6,9,2,np.nan]})
print (df)
A B C D
0 NaN 7.0 1.0 5.0
1 5.0 8.0 3.0 3.0
2 4.0 9.0 5.0 6.0
3 5.0 4.0 7.0 9.0
4 5.0 2.0 1.0 2.0
5 NaN NaN NaN NaN
#get True for NaN
print (df.isnull())
A B C D
0 True False False False
1 False False False False
2 False False False False
3 False False False False
4 False False False False
5 True True True True
#check at least one True per row
print (df.isnull().any(axis=1))
0 True
1 False
2 False
3 False
4 False
5 True
dtype: bool
#boolen indexing with inverting `~` (need select NO NaN rows)
print (df[~df.isnull().any(axis=1)])
A B C D
1 5.0 8.0 3.0 3.0
2 4.0 9.0 5.0 6.0
3 5.0 4.0 7.0 9.0
4 5.0 2.0 1.0 2.0
#get True for not NaN
print (df.notnull())
A B C D
0 False True True True
1 True True True True
2 True True True True
3 True True True True
4 True True True True
5 False False False False
#get True if all values per row are True
print (df.notnull().all(axis=1))
0 False
1 True
2 True
3 True
4 True
5 False
dtype: bool
#boolean indexing
print (df[df.notnull().all(axis=1)])
A B C D
1 5.0 8.0 3.0 3.0
2 4.0 9.0 5.0 6.0
3 5.0 4.0 7.0 9.0
4 5.0 2.0 1.0 2.0
#simpliest solution
print (df.dropna())
A B C D
1 5.0 8.0 3.0 3.0
2 4.0 9.0 5.0 6.0
3 5.0 4.0 7.0 9.0
4 5.0 2.0 1.0 2.0
也許'NaN'是字符串,那麼需要'df.replace('NaN',np.nan)' – jezrael
你可以添加數據樣本嗎? 3,4行? – jezrael
或者需要在read_csv中定義自定義的'Na'值 - [docs](http://pandas.pydata.org/pandas-docs/stable/io.html#na-values) – jezrael