python-pandas的基本用法05

pandas的基本用法05-索引

# -*- coding: utf-8 -*-
import numpy as np
from pandas import Series, DataFrame
from numpy.core.defchararray import index

print 'Series的索引，默认数字索引可以工作。'

s = Series(np.arange(4.), index=['a','b','c','d'])
print s[['a','b']]
# a    0
# b    1
# dtype: float64
print s[[0,1,2]]
# a    0
# b    1
# c    2
# dtype: float64
print s[s>1]
# c    2
# d    3
# dtype: float64

print 'Series的数组切片'
print s['a':'c']
# a    0
# b    1
# c    2
# dtype: float64

print 'DataFrame的索引'
df = DataFrame(np.arange(16).reshape(4,4),
index = ['a', 'b','c','d'],
columns=[1,2,3,4]
)

print df
#     1   2   3   4
# a   0   1   2   3
# b   4   5   6   7
# c   8   9  10  11
# d  12  13  14  15

print '打印列'
print df[[1,2]]
#     1   2
# a   0   1
# b   4   5
# c   8   9
# d  12  13
print '打印行'
print df[:2]
#    1  2  3  4
# a  0  1  2  3
# b  4  5  6  7
print df.ix[:2]
#    1  2  3  4
# a  0  1  2  3
# b  4  5  6  7
print '指定索引和列'
print df.ix[['a','b'], [1,2,3]]
#    1  2  3
# a  0  1  2
# b  4  5  6
print df.ix[:'c', :3]
#    1  2   3
# a  0  1   2
# b  4  5   6
# c  8  9  10

print '根据条件选择'
print df>3
#        1      2      3      4
# a  False  False  False  False
# b   True   True   True   True
# c   True   True   True   True
# d   True   True   True   True
print df[[1,2]]>3
#        1      2
# a  False  False
# b   True   True
# c   True   True
# d   True   True
df[df<3]=0
print df
#     1   2   3   4
# a   0   0   0   3
# b   4   5   6   7
# c   8   9  10  11
# d  12  13  14  15
print df.T
#    a  b   c   d
# 1  0  4   8  12
# 2  0  5   9  13
# 3  0  6  10  14
# 4  3  7  11  15