pandas：重新指定索引reindex函数，删除行/列drop函数，索引、选取和过滤

基本功能

对列/行索引重新指定索引（删除/增加：行/列）：reindex函数

reindex的method选项：

#重新指定索引及NaN填充值
x= Series([4,7,5],index= ['a','b','c'])
y= x.reindex(['a','b','c','d'])
print(y)
"""
a    4.0
b    7.0
c    5.0
d    NaN
dtype: float64
"""

## fill_value 指定不存在元素NaN的默认值
print(x.reindex(['a','b','c','d']), fill_value = 0)
"""
a    4
b    7
c    5
d    0
dtype: int64
"""

#新指定索引并指定填充NaN的方法
x=Series('blue','purple', index= [0,2])
print(x.reindex(range(4)),method='ffill')
'''
0      blue
1      blue
2    purple
3    purple
dtype: object
'''


#对DataFrame重新指定行/列索引
x= DataFrame(np.arange(9).reshape(3,3),
             index= ['a','c','d'],
             columns=['A','B','C'])

print(x)
'''
   A  B  C
a  0  1  2
c  3  4  5
d  6  7  8
'''

x= x.reindex(['a', 'b', 'c', 'd'],method='bfill')
print(x)
'''
   A  B  C
a  0  1  2
b  3  4  5
c  3  4  5
d  6  7  8
'''

#重新指定column
states=['A', 'B', 'C', 'D']
x.reindex(columns = states, fill_value= 0)
print(x)
'''
   A  B  C  D
a  0  1  2  0
b  3  4  5  0
d  6  7  8  0
c  3  4  5  0
'''

#????
print(x.ix[['a', 'b', 'd', 'c'], states])
'''
   A  B  C  D
a  0  1  2  0
b  3  4  5  0
d  6  7  8  0
c  3  4  5  0
'''

删除（丢弃）整一行/列的元素：drop函数

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

#Series根据行索引删除行
x= Series(np.arange(4),index= ['a','b','c','d'])
print(x.drop('c'))
'''
a    0
b    1
d    3
dtype: int32
'''

#  花式删除
print(x.drop(['a','b']))
'''
c    2
d    3
dtype: int32
'''

#DataFrame根据索引行/列删除行/列
x = DataFrame(np.arange(16).reshape((4, 4)),
                  index = ['a', 'b', 'c', 'd'],
                  columns = ['A', 'B', 'C', 'D'])

print(x)
'''
    A   B   C   D
a   0   1   2   3
b   4   5   6   7
c   8   9  10  11
d  12  13  14  15
'''

print(x.drop(['A','B'],axis= 1))    # 在列的维度上删除AB两行
'''
    C   D
a   2   3
b   6   7
c  10  11
d  14  15
'''

print(x.drop('a',axis= 0))          # 在行的维度上删除行
'''
    A   B   C   D
b   4   5   6   7
c   8   9  10  11
d  12  13  14  15
'''

print(x.drop(['a','b'],axis= 0))
'''
    A   B   C   D
c   8   9  10  11
d  12  13  14  15
'''

索引、选取和过滤

DataFrame的索引选项：

Series的数组索引/字典索引

#Series的数组索引/字典索引
x= Series(np.arange(4),index= ['a','b', 'c', 'd'])
print(x['b'])       # 1 像字典一样索引
print(x[1])         # 1  像数组一样索引
print(x[[1,3]])     # 花式索引
'''
b    1
d    3
dtype: int32
'''

print(x[x < 2])     # 布尔索引
'''
a    0
b    1
dtype: int32
'''

#Series的数组切片
print(x['a':'c'])       # 闭区间，索引顺序须为前后
'''
a    0
b    1
c    2
dtype: int32
'''

x['a':'c']= 5
print(x)
'''
a    5
b    5
c    5
d    3
dtype: int32
'''

DataFrame的索引

#DataFrame的索引
data = DataFrame(np.arange(16).reshape((4, 4)),
                  index = ['a', 'b', 'c', 'd'],
                  columns = ['A', 'B', 'C', 'D'])
print(data)
'''
    A   B   C   D
a   0   1   2   3
b   4   5   6   7
c   8   9  10  11
d  12  13  14  15
'''

print(data['A'])        #打印列
'''
a     0
b     4
c     8
d    12
Name: A, dtype: int32
'''

print( data[['A','B']])     # 花式索引
'''
    A   B
a   0   1
b   4   5
c   8   9
d  12  13
'''

#按行号  进行索引
print(data.ix[1])
'''
A    4
B    5
C    6
D    7
Name: b, dtype: int32
'''

print(data[:2])         # 切片索引,选择行
'''
   A  B  C  D
a  0  1  2  3
b  4  5  6  7
'''

print(data.ix[:2,['A','B']])     # 指定行和列索引
'''
   A  B
a  0  1
b  4  5
'''

print(data.ix[['a','b'],[3,0,1]])       #行:字典索引，列:数组索引
'''
   D  A  B
a  3  0  1
b  7  4  5
'''

print(data.ix[:'b','A'])    # 行从开始到b，第A列。
'''
a    0
b    4
Name: A, dtype: int32
'''


#根据条件选择
print(data)
'''
    A   B   C   D
a   0   1   2   3
b   4   5   6   7
c   8   9  10  11
d  12  13  14  15
'''

print(data[data.A > 5])     # 根据条件选择行,A列大于5的行
'''
    A   B   C   D
c   8   9  10  11
d  12  13  14  15

'''

print(data < 5)     # 打印True或者False
'''
       A      B      C      D
a   True   True   True   True
b   True  False  False  False
c  False  False  False  False
d  False  False  False  False
'''

data[data < 5] = 0 # 条件索引
print(data)
'''
    A   B   C   D
a   0   0   0   0
b   0   5   6   7
c   8   9  10  11
d  12  13  14  15
'''