python数据分析-05DataFrame深入

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

#df1 = DataFrame({'城市':["北京","上海","广州"],'人口':[1000,2000,1500]})
# print(df1)
#    城市    人口
# 0  北京  1000
# 1  上海  2000
# 2  广州  1500

#方法1：
# df1["GDP"] = Series([1000,2000,1500])
# print(df1)
#    城市    人口   GDP
# 0  北京  1000  1000
# 1  上海  2000  2000
# 2  广州  1500  1500

#方法2：
# df2 = DataFrame({'城市':["北京","上海","广州"],'人口':[1000,2000,1500]},index=["A","B","C"])
# gdp_map = {"北京":1000,"上海":2000,"广州":1500}
# df2["GDP"] = df2["城市"].map(gdp_map)
# print(df2)
#    城市    人口   GDP
# A  北京  1000  1000
# B  上海  2000  2000
# C  广州  1500  1500

# df3 = DataFrame({'城市':["北京","上海","广州"],'人口':[1000,2000,1500]},index=["A","B","C"])#不在是默认index时，需要使用指定添加
# df3["GDP"] = Series([1000,2000,1500])
# print(df3)#无法填充进去
#    城市    人口  GDP
# A  北京  1000  NaN
# B  上海  2000  NaN
# C  广州  1500  NaN

# df3["GDP"] = Series([1000,2000,1500],index=["A","B","C"])
# print(df3)
#    城市    人口   GDP
# A  北京  1000  1000
# B  上海  2000  2000
# C  广州  1500  1500


#-----------------------------
#replace in Series
#s1 = Series(np.arange(10))
#print(s1)
# 0    0
# 1    1
# 2    2
# 3    3
# 4    4
# 5    5
# 6    6
# 7    7
# 8    8
# 9    9
# dtype: int32

#print(s1.replace(1,np.nan))
# 0    0.0
# 1    NaN
# 2    2.0
# 3    3.0
# 4    4.0
# 5    5.0
# 6    6.0
# 7    7.0
# 8    8.0
# 9    9.0
# dtype: float64

#print(s1.replace([1,2,3],[10,20,30]))
# 0     0
# 1    10
# 2    20
# 3    30
# 4     4
# 5     5
# 6     6
# 7     7
# 8     8
# 9     9
# dtype: int64


#-----------------------
#Series 和 DataFrame的简单数学运算
# s1 = Series([1,2,3],index=["A","B","C"])
# s2 = Series([4,5,6,7],index=["B","C","D","E"])
# print(s1)
# A    1
# B    2
# C    3
# dtype: int64
# print(s2)
# B    4
# C    5
# D    6
# E    7
# dtype: int64
# print(s1+s2)
# A    NaN
# B    6.0
# C    8.0
# D    NaN
# E    NaN
# dtype: float64

#DataFrame的运算
# df1 = DataFrame(np.arange(4).reshape(2,2),index=["A","B"],columns=["BJ","SH"])
# print(df1)
#    BJ  SH
# A   0   1
# B   2   3
# df2 = DataFrame(np.arange(9).reshape(3,3),index=["A","B","C"],columns=["BJ","SH","GZ"])
# print(df2)
#    BJ  SH  GZ
# A   0   1   2
# B   3   4   5
# C   6   7   8
# print(df1+df2)
#     BJ  GZ   SH
# A  0.0 NaN  2.0
# B  5.0 NaN  7.0
# C  NaN NaN  NaN

# df3 = DataFrame([[1,2,3],[4,5,np.nan],[7,8,9]],index=["A","B","C"],columns=["c1","c2","c3"])
# print(df3)
#    c1  c2   c3
# A   1   2  3.0
# B   4   5  NaN
# C   7   8  9.0
# print(df3.sum())
# c1    12.0
# c2    15.0
# c3    12.0
# dtype: float64
# print(df3.sum(axis=1))
# A     6.0
# B     9.0
# C    24.0
# dtype: float64
# print(df3.min())
# c1    1.0
# c2    2.0
# c3    3.0
# dtype: float64
# print(df3.max())
# c1    7.0
# c2    8.0
# c3    9.0
# dtype: float64
# print(df3.describe())
#         c1   c2        c3
# count  3.0  3.0  2.000000
# mean   4.0  5.0  6.000000
# std    3.0  3.0  4.242641
# min    1.0  2.0  3.000000
# 25%    2.5  3.5  4.500000
# 50%    4.0  5.0  6.000000
# 75%    5.5  6.5  7.500000
# max    7.0  8.0  9.000000


#-----------------------------
#Series和DataFrame的排序
# s1 = Series(np.random.randn(10))
# print(s1)
# 0   -1.745069
# 1   -3.339463
# 2    2.245615
# 3    0.201136
# 4   -0.115314
# 5   -0.425709
# 6   -1.037263
# 7    0.015670
# 8   -0.514211
# 9   -0.122862
# dtype: float64
# print(s1.values)
# [-0.46066427 -0.01673619 -0.79758999 -0.99447067 -1.2554336   0.95775716
#  -0.98716949  0.81775325 -0.95819146 -0.38062781]
#print(s1.index)#RangeIndex(start=0, stop=10, step=1)
# s2 = s1.sort_values()
# print(s2)
# 3   -1.533961
# 1   -0.777431
# 5   -0.587565
# 2   -0.463069
# 7   -0.257701
# 0   -0.037266
# 6    0.062657
# 9    0.149767
# 8    0.245388
# 4    2.024740
# dtype: float64
# s2 = s1.sort_values(ascending=False)
# print(s2)
# 1    1.905997
# 6    0.369854
# 0    0.346478
# 2    0.283084
# 3    0.152866
# 4    0.145149
# 5   -0.362064
# 8   -0.627749
# 7   -0.738645
# 9   -0.905832
# dtype: float64
# print(s2.sort_index())
# 0    0.250688
# 1   -0.005753
# 2    0.818747
# 3    1.074309
# 4    0.057101
# 5   -1.576862
# 6   -1.358057
# 7   -0.774541
# 8    1.260600
# 9    0.028084
# dtype: float64


#DataFrame的排序
df1 = DataFrame(np.random.randn(40).reshape(8,5),columns=["A","B","C","D","E"])
print(df1)
#           A         B         C         D         E
# 0  1.301407  0.079596 -0.324598 -0.489004 -0.319954
# 1  1.627349 -1.848241 -1.535149  0.616749 -0.581343
# 2 -1.599599  0.177486  0.413103 -0.121707 -0.771692
# 3 -0.346563  2.376872 -0.299881 -0.038205 -1.101628
# 4  2.000585 -0.087473  1.679934 -1.520698 -0.037990
# 5 -0.622608  0.178647  0.511137  0.001924  1.104219
# 6  0.680216  0.616194  0.492893 -1.495716 -2.129312
# 7  0.769310 -0.425242  0.270568 -1.340633 -0.507089

print(df1["A"].sort_values())
# 0   -0.781176
# 5   -0.699767
# 4   -0.257146
# 6   -0.168928
# 2   -0.160794
# 1    0.348743
# 3    1.015523
# 7    1.750817
# Name: A, dtype: float64

print(df1.sort_values("A"))
#           A         B         C         D         E
# 7 -1.667484  1.052349 -0.786262  1.515977 -1.663600
# 1 -0.755957 -0.748133 -0.078783  1.221847  1.087867
# 0 -0.624164 -0.225844  0.146987  0.209596 -1.327463
# 5 -0.362764  0.958340  0.580041 -1.062712  0.233652
# 4 -0.184361  0.924434  0.304635  1.863528  0.775122
# 6  0.406105  0.030612 -1.115804  2.543703 -0.234756
# 3  0.657304  1.464882  0.091570 -1.226326 -1.272059
# 2  2.092520 -0.210072 -0.693642  0.152570  0.659520

df2 = df1.sort_values("A")
print(df2.sort_index())#跟df1一样的
#           A         B         C         D         E
# 0 -0.612644 -0.795620  1.621510 -1.316650  1.504513
# 1 -1.770057 -1.740721  2.078625 -1.738596  0.345799
# 2  0.697535  1.126456  0.591017  0.272984  1.004823
# 3  1.323213  0.630537  1.063169 -0.682980  0.630861
# 4  0.292257 -0.683437 -2.204945 -0.997271  0.535046
# 5  1.441142  0.637664  0.801728 -0.249832  2.079914
# 6 -0.647377  0.078151 -0.649099 -0.360512  0.692393
# 7  0.333072  1.713874  0.672938  0.130204 -1.050239

转载于:https://www.cnblogs.com/nikecode/p/11130907.html