Pandas玩转数据（二) -- Series和DataFrame排序

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

# Series排序
s1 = Series(np.random.randn(10))
s1
Out[5]: 
0   -1.293472
1    0.017588
2   -0.654741
3    0.495720
4   -1.626396
5   -0.651238
6    0.776535
7   -0.746762
8   -1.358951
9    0.247930
dtype: float64

# 值排序
s2 = s1.sort_values()
s2
Out[10]: 
4   -1.626396
8   -1.358951
0   -1.293472
7   -0.746762
2   -0.654741
5   -0.651238
1    0.017588
9    0.247930
3    0.495720
6    0.776535
dtype: float64

# 降序排序 
s2 = s1.sort_values(ascending=False)
s2
Out[13]: 
6    0.776535
3    0.495720
9    0.247930
1    0.017588
5   -0.651238
2   -0.654741
7   -0.746762
0   -1.293472
8   -1.358951
4   -1.626396
dtype: float64
# 对index进行排序,降序同样修改ascending为False就好
s2.sort_index()
Out[14]: 
0   -1.293472
1    0.017588
2   -0.654741
3    0.495720
4   -1.626396
5   -0.651238
6    0.776535
7   -0.746762
8   -1.358951
9    0.247930
dtype: float64

# DataFrame排序
df1 = DataFrame(np.random.randn(40).reshape(8,5), columns=['A','B','C','D','E'])
df1
Out[17]: 
          A         B         C         D         E
0 -0.364749 -2.234539  0.560983 -0.205768 -0.685511
1  1.500545  0.669751 -0.810748 -1.499093 -0.369835
2  0.894716 -0.282788  0.293292  1.260618 -0.107138
3 -0.262395  1.970482  1.268629 -0.626314 -0.726878
4 -1.756154  0.471681 -0.204594 -0.978793 -2.082535
5  0.476344  0.588654 -0.303897  1.863167 -1.466623
6 -1.704993 -0.136662 -0.034966  0.159871 -0.848923
7  1.117809  0.548713 -1.713026  1.153380 -1.529988

# 某一列Series排序
df1['A'].sort_values()
Out[18]: 
4   -1.756154
6   -1.704993
0   -0.364749
3   -0.262395
5    0.476344
2    0.894716
7    1.117809
1    1.500545
Name: A, dtype: float64

# DataFrame对某列进行排序
df1.sort_values('A')
Out[19]: 
          A         B         C         D         E
4 -1.756154  0.471681 -0.204594 -0.978793 -2.082535
6 -1.704993 -0.136662 -0.034966  0.159871 -0.848923
0 -0.364749 -2.234539  0.560983 -0.205768 -0.685511
3 -0.262395  1.970482  1.268629 -0.626314 -0.726878
5  0.476344  0.588654 -0.303897  1.863167 -1.466623
2  0.894716 -0.282788  0.293292  1.260618 -0.107138
7  1.117809  0.548713 -1.713026  1.153380 -1.529988
1  1.500545  0.669751 -0.810748 -1.499093 -0.369835

# 降序排序
df2 = df1.sort_values('A', ascending=False)
df2
Out[22]: 
          A         B         C         D         E
1  1.500545  0.669751 -0.810748 -1.499093 -0.369835
7  1.117809  0.548713 -1.713026  1.153380 -1.529988
2  0.894716 -0.282788  0.293292  1.260618 -0.107138
5  0.476344  0.588654 -0.303897  1.863167 -1.466623
3 -0.262395  1.970482  1.268629 -0.626314 -0.726878
0 -0.364749 -2.234539  0.560983 -0.205768 -0.685511
6 -1.704993 -0.136662 -0.034966  0.159871 -0.848923
4 -1.756154  0.471681 -0.204594 -0.978793 -2.082535

# 对index进行排序
df2.sort_index()
Out[23]: 
          A         B         C         D         E
0 -0.364749 -2.234539  0.560983 -0.205768 -0.685511
1  1.500545  0.669751 -0.810748 -1.499093 -0.369835
2  0.894716 -0.282788  0.293292  1.260618 -0.107138
3 -0.262395  1.970482  1.268629 -0.626314 -0.726878
4 -1.756154  0.471681 -0.204594 -0.978793 -2.082535
5  0.476344  0.588654 -0.303897  1.863167 -1.466623
6 -1.704993 -0.136662 -0.034966  0.159871 -0.848923
7  1.117809  0.548713 -1.713026  1.153380 -1.529988

# 一个简单的小例子,对movie_metadata.csv的imdb进行排序
f = open('movie_metadata.csv')
movie = pd.read_csv(f)
imdb = movie[["movie_title", "director_name","imdb_score"]].sort_values("imdb_score", ascending=False)
imdb.to_csv('imdb.csv')