pandas笔记

#!/usr/bin/env python # -*- coding: UTF-8 -*- """ @author: XiangguoSun @contact: sunxiangguodut@qq.com @file: learn_pandas.py @time: 2017/3/8 8:18 @software: PyCharm """ import numpy as np from pandas import Series, DataFrame import pandas as pd ''' 1,基本数据结构 ''' ''' 1.1 Series: dic+array ''' obj_dic={'a':1,'b':2,'c':3} objd=Series(obj_dic) obj = Series([4,7,-5,3],index=['a','b','c','d']) print obj.index,obj.values print obj[['a','c']] print 'b' in obj obj_na = Series(obj,index=['a','b','c','d','add']) print obj_na print obj_na.isnull() # also pd.isnull(obj_na) print obj_na.notnull() # also pd.notnull(obj_na) print obj_na.name print obj_na.index.name obj_na.index=['x','y','z','o','p'] obj_na.name='my_table' obj_na.index.name='my_index' print obj_na ''' 1.2 DataFrame ''' data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'], 'year': [2000, 2001, 2002, 2001, 2002], 'pop': [1.5, 1.7, 3.6, 2.4, 2.9] } df = DataFrame(data, columns=['year', 'state', 'pop', 'debt'], index=['one', 'two', 'three', 'four', 'five']) print df print df.ix['three'] df['five']=np.arange(5) print df #增加和删除列 df['new_column']=df.state == 'Ohio' print df del df['new_column'] print df.columns #嵌套字典 pop = {'Nevada':{2001:2.4,2002:2.9}, 'Ohio':{2000:1.5,2001:1.7,2002:3.6} } data = DataFrame(pop) print data print data.T print DataFrame(pop,index=[2001,2002,2003]) data.index.name='sunxiangguo' data.columns.name = 'state' print data print data.values#返回二维ndarray #索引对象index：不常用，略 '''index对象不可修改''' ''' 2,基本功能 ''' #重新索引 obj = Series([4.5,7,-2,4],index=['b','a','c','d']) print obj obj2 = obj.reindex(['a','b','c','d','e']) print obj2 obj3 = obj.reindex(['a','b','c','d','e'], fill_value=0) print obj3 #插值处理 obj = Series(['blue','perple','yellow'],index=[0,2,4]) print obj obj2 = obj.reindex(range(8),method='ffill') # 前向插值 print obj2 print obj.reindex(range(7),method='pad') # equal to ffill print obj.reindex(range(7),method='bfill') # 后向插值 print obj.reindex(range(7),method='backfill') # equal to bfill

# 丢弃指定轴上的项 obj = Series(np.arange(5), index=['a', 'b', 'c', 'd', 'e']) new_obj = obj.drop('c') print obj print new_obj print obj.drop(['c', 'd']) data = DataFrame(np.arange(16).reshape((4, 4)), index=['Ohio', 'Colorado', 'Utah', 'New York'], columns=['one', 'two', 'three', 'four'] ) print data print data.drop(['Colorado', 'Ohio']) print data.drop('two', axis=1) print data.drop(['two', 'four'], axis=1) # 索引、选取和过滤 data = Series(np.arange(4), index=['a', 'b', 'c', 'd']) print data print data['b'] print data[1] print data[2:4] print data[['b','a','d']] print data[[1,3]] print data[data<2] print data['a':'c'] data = DataFrame(np.arange(16).reshape((4, 4)), index=['Ohio', 'Colorado', 'Utah', 'New York'], columns=['one', 'two', 'three', 'four']) print data print data['two'] # 选取列 print data[['three', 'one']] # 选取列 print data[:2] # 注意[]里面是切片或者布尔型数组时，选取的不再是列，而是行 print data[data['three'] > 5] # 注意[]里面是切片或者布尔型数组时，选取的不再是列，而是行 print data.ix[:2, :2] # 同时选取行和列 print data.ix[1:3] # 选取一组行 print data.xs('Ohio') # 根据标签选取若干行 print data.xs(range(1, 4), axis=1) # 根据标签选取若干列 ''' print data.icol(2) print data.irow(0) 这两个已经被下面两行代码取代 ''' print data.iloc[:, 2] print data.iloc[0]