python学习笔记-pandas

#-*- coding:utf-8 -*-
#author : zhangwei

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

#pandas创建序列
# s = pd.Series([1,2,3,np.nan,44,1])
# print s
#
# dates = pd.date_range('20180603',periods=6)
# # print dates
# df = pd.DataFrame(np.random.rand(6,4),index=dates , columns=['a','b','c','d']) #定义DataFrame，行和列
# # df1 = pd.DataFrame(np.arange(12).reshape([3,4]))
# # print df1.dtypes                             #打印类型
# # print df1.index                              #打印标签
# # print df1.values                             #打印列表中的内容
# # print df1.describe()                         #打印数字形式的均值等操作
# # print df1.T
# print df.sort_index(axis=0 , ascending=False)  #index排序ascending：False代表是否为倒序,axis=0代表的行，1代表的是列操作；
# print df.sort_values(by='b',ascending=False)                   #对data中values进行排序

# dates = pd.date_range('20180603' , periods=6)
# df = pd.DataFrame(np.arange(24).reshape(6,4),index=dates,columns=['A','B','C','D'])
# print df
# print df['A'] , df.A                     #导入第一列,两种方法
# print df[0:3]                            #查找第0到第三行数据，右开
# print df['20180603':'20180605']          #进行行号索引
# print df.loc['20180604']                 #筛选值loc
# # print df.loc[:,['A','B']]              #打印AB列的所有值
# print df.loc['20180604',['A','B']]       #行和列进行打开
# print df.iloc[3:5,1:3]                   #打印第三行到第五行，第一列到第三列
# print df.iloc[[1,3,4],1:3]               #间断打开行
# print df.ix[:3 , 'A':'C']                #ix进行筛选，标签核行号索引
# print(df.A > 8)                          #帅选A列中大于8的值

# dates = pd.date_range('20180603' , periods=6)
# df = pd.DataFrame(np.arange(24).reshape(6,4),index=dates,columns=['A','B','C','D'])
# print df
# # df.iloc[2,2] = 111      #改变第二行第二列的数据为111
# # df.loc['20180604' , 'B'] = 7    #用loc方法进行该表数据内部元素
# # df[df.A > 4] = 0                  #A列中values>4的值全部替换为0
# # df.A[df.A>4] = 0                  #只针对A这一列进行操作
# df['F'] = np.nan                    #加入一列
# df['E'] = pd.Series([1,2,3,4,5,6] , index=pd.date_range('20180603' , periods=6)) #加入新的一列，并进行赋值
# print(df)


# dates = pd.date_range('20180603' , periods=6)
# df = pd.DataFrame(np.arange(24).reshape(6,4),index=dates,columns=['A','B','C','D'])
# df.iloc[0,1] = np.nan
# df.iloc[1,2] = np.nan
# print df
# print df.dropna()                           #丢弃含有nan的值及其对应的行
# print(df.dropna(axis=1,how='any'))          #how={any，all}，all：只有所有是nan才进行丢弃，any：只有含有一个nan就进行丢弃；axis=0,1分别对应行核列;
# print df.fillna(value=1)                    #对nan进行填充value
# print df.isnull() , df.isna()               #查找是否存在缺失值，返回bool值

#read文件以及保存文件csv,pickle
# data = pd.read_csv('/home/zhangwei/student.csv')    #read_csv格式的文件
# print data
# data.to_pickle('/home/zhangwei/student.pickle')     #保存文件格式为Python的格式pickle

#数据合并多个data ,concatenating
# df1 = pd.DataFrame(np.ones((3,4))*0 , columns=['a','b','c','d'])
# df2 = pd.DataFrame(np.ones((3,4))*1 , columns=['a','b','c','d'])
# df3 = pd.DataFrame(np.ones((3,4))*2 , columns=['a','b','c','d'])
# df4 = pd.DataFrame(np.ones((3,4))*0 , columns=['a','b','c','d'] , index= [1,2,3])
# df5 = pd.DataFrame(np.ones((3,4))*1 , columns=['b','c','d','e'] , index= [2,3,4])
# #print df1 , df2 , df3
# # res = pd.concat([df1 , df2 , df3] , axis=0 , ignore_index=True)                #合并数据，axis=0代表的是行合并；ignore_index对信号进行重新排序;
# # print df4 , df5
# # res = pd.concat([df4 , df5] , axis=0 , join='inner' , ignore_index=True)       #join{'inner','outer'},outer进行部nan操作；inner进行裁剪掉，寻找相同的部分进行合;
# # res = pd.concat([df4 , df5] , axis=1 , join_axes=[df4.index])                  #join_axes数据按照【】里面的数据进行排序;
# # res = df4.append([df3 , df5] , ignore_index=True)                              #append进行添加数据
# s1 = pd.Series([1,2,3,4] , index=['a','b','c','d'])
# res = df4.append(s1 , ignore_index=True)                                         #用series进行添加行
# print(res)

#采用merge进行合并dataframe
# left = pd.DataFrame({'key1':['k0','k1','k0','k1'],
#                      'key2':['k0','k0','k1','k1'],
#                      'A' : ['A0','A1','A2','A3'],
#                      'B':['B0','B1','B2','B3']})
# right = pd.DataFrame({'key1':['k0','k1','k1','k0'],
#                       'key2':['k0','k1','k1','k1'],
#                       'C':['C0','C1','C2','C3'],
#                       'D':['D0','D1','D2','D3']})
#print left , right
# res = pd.merge(left , right , on='key')                                                              #对key进行合并
# print left , right
# res = pd.merge(left , right , on=['key1' , 'key2'] , how='outer' , indicator='indicator_column')     #how:{inner , outer , left , right} , left则是以左边的key1进行考虑,indicator显示是那边数据进行合并
# print res

#handle overlapping
# boys = pd.DataFrame({'k':['K0','K1','K2'],
#                      'ages':[1,2,3]})
# girls = pd.DataFrame({'k':['K0','K1','K2'],
#                      'ages':[4,5,6]})
# print boys , girls
# res = pd.merge(boys , girls , on='k' , how='outer' , suffixes=['_boys' , '_girls'])     #suffixes输出boys and girls
# print res

#plot data
# data = pd.Series(np.random.randn(1000) , index=np.arange(1000))
# data = data.cumsum()                                                #对数据进行累加
# data.plot()                                                         #线性的plot,当采用pandas时，无需定义xy洲，plot内部有很多参数，包括线的颜色以及线的宽度、等等；
# plt.show()
data = pd.DataFrame(np.random.randn(1000,4),
                    index=np.arange(1000) ,
                    columns=['A','B','C','D'])  #数据四个一组,注意list列表必须是括号形式，而不是中括号形式；
data = data.cumsum()
# print data.head(8)                            #显示数据的前8行
# data.plot()
# plt.show()
#plot methods:bar , hist , box , kde , area , scatter , hexbin.......
ax = data.plot.scatter(x='A' , y='B' , color='DarkBlue' , label='Class1')
data.plot.scatter(x='A' , y='C' , color='Darkgreen' , label='Class2',ax=ax)  #使用ax=ax代表的是在同一张图上画两张图；
plt.show()