1、DataFrame中的selecting和reindex操作
（1）选择selecting
import pandas as pd
imdb=pd.read_csv('movie_metadata.csv')
imdb.head(4) #默认返回前5行
imdb.shape
imdb.tail()
s1 =imdb['color']
imdb[['color','director_name']].head() #如果选择多行则里面是一个列表
sub_df = imdb[['color','director_name','movie_title']]
sub_df.iloc[10:20,:] #返回10~20行
sub_df.iloc[10:20,0:2]
sub_df.loc[15:17,:'director_name'] #包括“director_name”
（2）Reindex
s1 = pd.Series([1, 2, 3, 4],index=['A','B','C','D'])
s1.reindex(index=['A','B','C','D','E']) #原来不存在的索引，补充值为nan
s1.reindex(index=['A','B','C','D','E'],fill_value=10)#把不存在的值填充为10
s2= pd.Series(['A','B','C'],index=[1, 5, 10])
s2.reindex(index=range(15))
s2.reindex(index=range(15),method='ffill') # forward
import numpy as np
df1 = pd.DataFrame(np.random.rand(25).reshape(5,5),index=['A','B','D','E','F'],columns=['c1','c2','c3','c4','c5'])
df1.reindex(index=['A','B','C','D','E','F'])
df1.reindex(index=['A','B','C','D','E','F'])
（3）Drop
s1.drop('A') #去掉一行
df1.drop('A',axis=0) #指定索引是行
df1.drop('c1',axis=1)#指定删除的为列
2、NAN值
import string
import pandas as pd
import numpy as np
n= np.nan
type(n)
m = 1
m + n #与nan值相加，得到的结果为nan
s1 = pd.Series([1, 2, np.nan,3 , 4],index=list(string.ascii_uppercase[:5]))
s1.isnull() #返回是否为nan
s1.notnull()
s1.dropna() # 删除为nan的行
# dataframe
dframe = pd.DataFrame([[1,2,3],[np.nan,5,6],[7,np.nan,9],[np.nan,np.nan,np.nan]])
dframe.isnull()
dframe.notnull()
dframe.dropna() #只要存在nan的行都被删掉
dframe.dropna(axis=1) #存在nan的列都被删掉
dframe.dropna(axis=0,how='all') # how值默认是any ，all是所有为nan才会删除
dframe2= pd.DataFrame([[1,2,3,np.nan],[2,np.nan,5,6],[np.nan,np.nan,np.nan,9],[1,np.nan,np.nan,np.nan]])
dframe2
# thresh=2 是将大于2 的nan删掉
dframe2.dropna(thresh=2)
dframe2.fillna(value=1) #把为nan的位置都填充为2
#列
dframe2.fillna(value={0:1,1:5,2:7,3:8})
3、多级index
import numpy as np
import pandas as pd
s1 = pd.Series(np.random.rand(6),index=[['1','1','1','2','2','2'],['a','b','c','a','b','c']])
In [5]:
s1
Out[5]:
1 a 0.928077
b 0.188681
c 0.362011
2 a 0.970636
b 0.333167
c 0.389710
dtype: float64
In [7]:
s1['1']
Out[7]:
a 0.928077
b 0.188681
c 0.362011
dtype: float64
In [8]:
s1['1']['a']
Out[8]:
0.9280770733545052
In [10]:
s1[:,'a']
Out[10]:
1 0.928077
2 0.970636
dtype: float64
df1 = s1.unstack() #不堆叠，变成二维
df1
Out[17]:
a b c
1 0.928077 0.188681 0.362011
2 0.970636 0.333167 0.389710
In [15]:
pd.DataFrame([s1['1'],s1['2']])
Out[15]:
a b c
0 0.928077 0.188681 0.362011
1 0.970636 0.333167 0.389710
In [19]:
df1.unstack()
Out[19]:
a 1 0.928077
2 0.970636
b 1 0.188681
2 0.333167
c 1 0.362011
2 0.389710
dtype: float64
In [20]:
s1
Out[20]:
1 a 0.928077
b 0.188681
c 0.362011
2 a 0.970636
b 0.333167
c 0.389710
dtype: float64
In [22]:
df1.T.unstack()
Out[22]:
1 a 0.928077
b 0.188681
c 0.362011
2 a 0.970636
b 0.333167
c 0.389710
dtype: float64
In [27]:
#dataframe
df = pd.DataFrame(np.arange(16).reshape(4,4),index=[['a','a','b','b'],['1','1','2','2']],columns=[['BJ','BJ','SH','GZ'],[8,9,8,8]])
df
Out[27]:
BJ SH GZ
8 9 8 8
a 1 0 1 2 3
1 4 5 6 7
b 2 8 9 10 11
2 12 13 14 15
In [28]:
df['BJ']
Out[28]:
8 9
a 1 0 1
1 4 5
b 2 8 9
2 12 13
In [29]:
df['BJ'][8]
Out[29]:
a 1 0
1 4
b 2 8
2 12
Name: 8, dtype: int32
