数据分析之路——第一天

初始numpy、pandas：

#!/usr/bin/python27
#coding=utf8
__author__ = 'Jeremy'

import numpy as np
import pandas as pd
#迭代建立字典，用DataFrame方法建立二维数组数据框
dic_1 = {}
dic_str = 'asdqwezxcr'
for i in xrange(10):
    dic_1[dic_str[i]] = [i,i+1,i+2,i+3,i+4]
print dic_1,type(dic_1)
df_1 = pd.DataFrame(dic_1)
print df_1,'\n',type(df_1)
#通过字典创建三维数组，用DataFrame方法展示
dic3 = {'one':{'a':1,'b':2,'c':3,'d':4},
'two':{'a':5,'b':6,'c':7,'d':8},
'three':{'a':9,'b':10,'c':11,'d':12}}

df_2 = pd.DataFrame(dic3)
print df_2
#手工建立二维数组样式展示
ls_1 = [[3,4,5,6]]
df_3 = pd.DataFrame(ls_1)
print df_3
#建立索引，然后使用数据运算功能
arr_1 = pd.Series(np.array([5,4,3,2,1,0]))
arr_1.index = ['a','b','c','d','e','f']
arr_2 = pd.Series(np.array([12,13,14,15,16,17]))
arr_2.index = ['a','b','c','d','e','f']
print arr_1*arr_2

#numpy数组和list用DataFrame方法展示的区别

ls_1 = np.array([[2,3,4,5]])
ls_2 = [[2,3,4,5]]
pd_1 = pd.DataFrame(ls_1)
pd_2 = pd.DataFrame(ls_2)
print ls_1,'\n',ls_2,'\n',pd_1,'\n',pd_2
结果：  

[[2 3 4 5]] 
[[2, 3, 4, 5]] 
   0  1  2  3
0  2  3  4  5 
   0  1  2  3
0  2  3  4  5