Python pandas处理缺失值方法详解(dropna、drop、fillna)

 	   	      df = pd.DataFrame(
                                        {"name": ['Alfred', 'Batman', 'Catwoman'],         
                                          "toy": [np.nan, 'Batmobile', 'Bullwhip'],
                                         "born": [pd.NaT, pd.Timestamp("1940-04-25")     
                                                        pd.NaT]})
 			>>> df
 			       name        toy       born
 			0    Alfred        NaN        NaT
 			1    Batman  Batmobile 1940-04-25
 			2  Catwoman   Bullwhip        NaT
 			
 			# Drop the rows where at least one element is missing.
 			>>> df.dropna()
 			     name        toy       born
 			1  Batman  Batmobile 1940-04-25
 			
 			# Drop the columns where at least one element is missing.
 			>>> df.dropna(axis='columns')
 			       name
 			0    Alfred
 			1    Batman
 			2  Catwoman
 			
 			# Drop the rows where all elements are missing.
 			>>> df.dropna(how='all')
 			       name        toy       born
 			0    Alfred        NaN        NaT
 			1    Batman  Batmobile 1940-04-25
 			2  Catwoman   Bullwhip        NaT
 			
 			# Keep only the rows with at least 2 non-NA values.
 			>>> df.dropna(thresh=2)
 			       name        toy       born
 			1    Batman  Batmobile 1940-04-25
 			2  Catwoman   Bullwhip        NaT
 			
 			# Define in which columns to look for missing values.
 			>>> df.dropna(subset=['name', 'born'])
 			       name        toy       born
 			1    Batman  Batmobile 1940-04-25
 			
 			# Keep the DataFrame with valid entries in the same variable.	
 			>>> df.dropna(inplace=True)
 			>>> df
 			     name        toy       born
 			1  Batman  Batmobile 1940-04-25

	df = pd.DataFrame(np.arange(12).reshape(3,4),                 
	                  columns=['A', 'B', 'C', 'D'])
	
	>>>df
	   	   A  B   C   D
		0  0  1   2   3
		1  4  5   6   7
		2  8  9  10  11

	# 删除列
	>>> df.drop(['B', 'C'], axis=1)
	   A   D
	0  0   3
	1  4   7
	2  8  11
	>>> df.drop(columns=['B', 'C'])
	   A   D
	0  0   3
	1  4   7
	2  8  11
	
	# 删除行（索引）
	>>> df.drop([0, 1])
	   A  B   C   D
	2  8  9  10  11

f = pd.DataFrame([[np.nan, 2, np.nan, 0],
                   [3, 4, np.nan, 1],
                   [np.nan, np.nan, np.nan, 5],
                   [np.nan, 3, np.nan, 4]],
                   columns=list('ABCD'))
 >>> df
     A    B   C  D
0  NaN  2.0 NaN  0
1  3.0  4.0 NaN  1
2  NaN  NaN NaN  5
3  NaN  3.0 NaN  4

# 使用0代替所有的缺失值
>>> df.fillna(0)
    A   B   C   D
0   0.0 2.0 0.0 0
1   3.0 4.0 0.0 1
2   0.0 0.0 0.0 5
3   0.0 3.0 0.0 4

# 使用后边或前边的值填充缺失值
>>> df.fillna(method='ffill')
    A   B   C   D
0   NaN 2.0 NaN 0
1   3.0 4.0 NaN 1
2   3.0 4.0 NaN 5
3   3.0 3.0 NaN 4

>>>df.fillna(method='bfill')
     A	B	C	D
0	3.0	2.0	NaN	0
1	3.0	4.0	NaN	1
2	NaN	3.0	NaN	5
3	NaN	3.0	NaN	4

# Replace all NaN elements in column ‘A', ‘B', ‘C', and ‘D', with 0, 1, 2, and 3 respectively.
# 每一列使用不同的缺失值
>>> values = {'A': 0, 'B': 1, 'C': 2, 'D': 3}
>>> df.fillna(value=values)
    A   B   C   D
0   0.0 2.0 2.0 0
1   3.0 4.0 2.0 1
2   0.0 1.0 2.0 5
3   0.0 3.0 2.0 4

#只替换第一个缺失值
 >>>df.fillna(value=values, limit=1)
    A   B   C   D
0   0.0 2.0 2.0 0
1   3.0 4.0 NaN 1
2   NaN 1.0 NaN 5
3   NaN 3.0 NaN 4

# option 1 将含有缺失值的行去掉
housing.dropna(subset=["total_bedrooms"])  

# option 2 将"total_bedrooms"这一列从数据中去掉
housing.drop("total_bedrooms", axis=1)  

 # option 3 使用"total_bedrooms"的中值填充缺失值
median = housing["total_bedrooms"].median()
housing["total_bedrooms"].fillna(median)