python数据分析-04Nan的类型处理

#NaN --means Not a Number
import pandas as pd
import numpy as np
from pandas import Series,DataFrame
# n = np.nan
# print(type(n)) #<class 'float'>
# print(1+n) #nan
#nan in Series
#s1 = Series([1,2,np.nan,3,4],index=['A','B','C','D','E'])
# print(s1)
# A    1.0
# B    2.0
# C    NaN
# D    3.0
# E    4.0
# dtype: float64
# print(s1.isnull())
# A    False
# B    False
# C     True
# D    False
# E    False
# dtype: bool
#print(s1.dropna())#去掉值为nan的行
# A    1.0
# B    2.0
# D    3.0
# E    4.0
# dtype: float64
#NaN in DataFrame
#dframe = DataFrame([[1,2,3],[np.nan,5,6],[7,np.nan,9],[np.nan,np.nan,np.nan]])
#print(dframe)
#      0    1    2
# 0  1.0  2.0  3.0
# 1  NaN  5.0  6.0
# 2  7.0  NaN  9.0
# 3  NaN  NaN  NaN
#print(dframe.isnull())
#        0      1      2
# 0  False  False  False
# 1   True  False  False
# 2  False   True  False
# 3   True   True   True
# df1 = dframe.dropna(axis=0)
# print(df1)
#      0    1    2
# 0  1.0  2.0  3.0
# df2 = dframe.dropna(axis=1)
# print(df2)
# Empty DataFrame
# Columns: []
# Index: [0, 1, 2, 3]
# df3= dframe.dropna(axis=0,how='any')#默认为any
# print(df3)
#      0    1    2
# 0  1.0  2.0  3.0
# df4= dframe.dropna(axis=0,how='all')#全部为nan才会被删除
# print(df4)
#      0    1    2
# 0  1.0  2.0  3.0
# 1  NaN  5.0  6.0
# 2  7.0  NaN  9.0
# dframe2 = DataFrame([[1,2,3,np.nan],[2,np.nan,5,6],[np.nan,7,np.nan,9],[1,np.nan,np.nan,np.nan]])
# print(dframe2)
#      0    1    2    3
# 0  1.0  2.0  3.0  NaN
# 1  2.0  NaN  5.0  6.0
# 2  NaN  7.0  NaN  9.0
# 3  1.0  NaN  NaN  NaN
# df2 = dframe2.dropna(thresh=None)#包含nan都会被删掉
# print(df2)
# Empty DataFrame
# Columns: [0, 1, 2, 3]
# Index: []
# df2 = dframe2.dropna(thresh=2)#2个以上nan的值会被删掉
# print(df2)
#      0    1    2    3
# 0  1.0  2.0  3.0  NaN
# 1  2.0  NaN  5.0  6.0
# 2  NaN  7.0  NaN  9.0
#print(dframe2.fillna(value=1))#用1填充所有的nan值
#      0    1    2    3
# 0  1.0  2.0  3.0  1.0
# 1  2.0  1.0  5.0  6.0
# 2  1.0  7.0  1.0  9.0
# 3  1.0  1.0  1.0  1.0
#print(dframe2.fillna(value={0:0,1:1,2:2,3:3}))#第一列用0，第二列用1，第三列用2，第四列用3填充
#      0    1    2    3
# 0  1.0  2.0  3.0  3.0
# 1  2.0  1.0  5.0  6.0
# 2  0.0  7.0  2.0  9.0
# 3  1.0  1.0  2.0  3.0
#----------------------------------
#多级index
# s1 = Series(np.random.randn(6),index=[['1','1','1','2','2','2'],['a','b','c','a','b','c']])
# print(s1)
# 1  a    0.450512
#    b   -0.432511
#    c   -0.280125
# 2  a    0.333269
#    b    0.123369
#    c   -2.000533
# dtype: float64
# print(s1['1'])
# a    0.870953
# b    0.128729
# c    0.958637
# dtype: float64
# print(type(s1["1"]))#<class 'pandas.core.series.Series'>
# print(s1['1']['a']) #-1.6023742345246375
# print(s1[:,'a'])
# 1    0.891888
# 2   -1.087930
# dtype: float64
# df1 = s1.unstack()
# print(df1)
#           a         b         c
# 1 -0.300567  0.124230 -0.488987
# 2  1.618275 -0.155234 -0.284849
# df2 = DataFrame([s1['1'],s1['2']])
# print(df2)
#           a         b         c
# 0 -0.757713  0.801604  1.975145
# 1 -0.112589  0.083369 -1.174583
# s2 = df1.unstack()
# print(s2)
# a  1   -0.037449
#    2   -1.364984
# b  1   -1.748248
#    2    0.581338
# c  1    1.758856
#    2   -0.244383
# dtype: float64
# s2 = df1.T.unstack()
# print(s2)
# 1  a    0.343976
#    b    1.664177
#    c   -0.039674
# 2  a    0.357644
#    b    0.357658
#    c   -0.308326
# dtype: float64
# df = DataFrame(np.arange(16).reshape(4,4))
# print(df)
#     0   1   2   3
# 0   0   1   2   3
# 1   4   5   6   7
# 2   8   9  10  11
# 3  12  13  14  15
# df = DataFrame(np.arange(16).reshape(4,4),index=[['a','a','b','b'],[1,2,1,2]])
# print(df)
#       0   1   2   3
# a 1   0   1   2   3
#   2   4   5   6   7
# b 1   8   9  10  11
#   2  12  13  14  15
# df = DataFrame(np.arange(16).reshape(4,4),index=[['a','a','b','b'],[1,2,1,2]],columns=[['BJ','BJ','SH','GZ'],[8,9,8,8]])
# print(df)
#      BJ      SH  GZ
#       8   9   8   8
# a 1   0   1   2   3
#   2   4   5   6   7
# b 1   8   9  10  11
#   2  12  13  14  15
# print(df['BJ'][8])
# a  1     0
#    2     4
# b  1     8
#    2    12
# Name: 8, dtype: int32