pandas操作

• pandas知识回顾
• iloc/ix切片
• 列条件与与列的筛选
• 读取csv、xlsx文件
• 行的增加与删除
• 列的增加与删除
• 排序
• 数据分组描述
• 统计描述
• 作图
• 数据框合并

#-*-encoding:utf-8-*-'''created by zwg in 2016-12-03'''import pandasimport numpyfrom pylab import mplfrom matplotlib import pyplotmpl.rcParams['font.sans-serif']=['SimHei']mpl.rcParams['axes.unicode_minus']=Falsedef practise_one():    #pandas知识回顾    numpy.random.seed()    Data = pandas.DataFrame(data=numpy.random.randn(5, 3), columns=list('ABC'))    # print Data    # print Data.values    # print Data.columns    # print Data.index    # print Data.tail(5)    # print Data.head(5)    #iloc/ix切片    print Data.iloc[0:2, [0, 2]]    print Data.ix[0:2, [0, 2]]    print Data.ix[0:2, ['A', 'C']]    print Data.iat[0, 0]    # 列条件与与列的筛选    print Data[Data.A > 0.5]    print Data[(Data.A > 0.5) & (Data.C < 0.7)]    print Data[['B']]    print Data[Data.A > 0.5].ix[:, 'B']    print Data[Data.A > 0.5][['B']]    print Data[['B']][Data.A > 0.5]    #读取csv、xlsx文件    # pandas.read_csv(filepath_or_buffer=file_name,header=0/None,index_col=Fasle/row_name,encoding='utf-8')    # pandas.read_table(filepath_or_buffer=file_name,header=0/None,index_col=Fasle/row_name,encoding='utf-8')    # pandas.read_excel(io=file_name,sheetname=0/sheetname,header=0/None,index_col=Fasle/row_name,encoding='utf-8')def practise_two():    Data=pandas.read_excel('test.xlsx',encoding='utf-8',header=0)    # 行的增加与删除    # Data1 = Data.drop([1,2,3], axis=0)    # Data2=Data1.copy()    # Data1=Data1.append(Data2,ignore_index=True)    # print Data1    # 列的增加与删除    # Data1=Data.drop(['name', 'class'],axis=1)    # print Data1.columns    # Data1=Data.reindex(columns=['class','name','grade','add'])    # print Data1.columns    #排序    # print Data.sort_values(by=['grade'],ascending=False)    # print Data.sort_index(axis=0,ascending=False)    # 数据分组描述    # Data1=Data.groupby('sex')    # print Data1['sex'].count()    # print Data1['grade'].mean()    # print Data1['sex'].unique()    # 数据分组    # Data2=Data.groupby(['class','sex'])    # print Data2['grade'].describe()    # 统计描述    # print Data.describe(include='all')    # Data3=Data[['grade','sex']]    # figure=pyplot.figure()    # Data3.plot(kind='box',by='sex')    # pyplot.show()    #分组计数    # print Data['sex'].value_counts()    # 作图    # Data.boxplot(column='grade',by=['class','sex'])    # Data.hist(column='grade')    # Data['sex'].value_counts().plot(kind='bar')    Data.groupby(['class'])['grade'].mean().plot(kind='barh',colormap='cool')    Data.plot(x='grade',y='age',kind='scatter',title='grade-age change',logx=True,logy=True)    Data.plot(kind='kde')    pyplot.show()def practise_three():    #数据框合并    Data1=pandas.DataFrame(data=numpy.random.rand(5,3),columns=list('ABC'))    Data1['D'] = [1, 2, 3, 4, 5]    print Data1    Data2 = pandas.DataFrame(data=numpy.random.rand(5, 3), columns=list('ABC'))    Data2['D'] = [1, 2, 2, 4, 5]    print Data2    # join数据框合并和merge数据框合并    # Data1=Data1.set_index('D')    # Data2=Data2.set_index('D')    # Data3=Data1.join(Data2,lsuffix='_left',rsuffix='_right',how='left')    # print Data3    Data4=Data1.merge(Data2,on='D',how='inner',suffixes=('_1','_2'))    print Data4if __name__=='__main__':    # practise_one()    practise_two()    # practise_three()