Pandas_数据透视表与交叉表

数据透视表   pivot_table()

pivot_table(self, values=None, index=None, columns=None,aggfunc='mean',
 fill_value=None, margins=False,dropna=True, margins_name='All'):

'''
values:需要聚合的列名，默认所有数值的列
index:在结果透视表的行上进行分组的列名分组键
columns:在结果透视表的列上进行分组的列名分组键
aggfunc:聚合函数或函数列表，默认为mean
fill_value:在结果表中替换缺失值的值
margins:添加行列总计(与aggfunc对应)
dropna:是否除去均为nan的列
margins_name:与margins对应
'''

tips=pd.read_csv('tips.csv')
#下列两组效果一样
result1=tips.pivot_table(index=['day','smoker'])
tips.groupby(by=['day','smoker']).agg('mean')
print(result1)
'''
                 size       tip  total_bill
day  smoker                                
Fri  No      2.250000  2.812500   18.420000
     Yes     2.066667  2.714000   16.813333
Sat  No      2.555556  3.102889   19.661778
     Yes     2.476190  2.875476   21.276667
Sun  No      2.929825  3.167895   20.506667
     Yes     2.578947  3.516842   24.120000
Thur No      2.488889  2.673778   17.113111
     Yes     2.352941  3.030000   19.190588
'''

result1=tips.pivot_table(values=['tip','size'],index=['day','time'],
columns='smoker',margins=True,margins_name='all_mean')
'''
                     size                           tip                    
smoker                 No       Yes  all_mean        No       Yes  all_mean
day      time                                                              
Fri      Dinner  2.000000  2.222222  2.166667  2.750000  3.003333  2.940000
         Lunch   3.000000  1.833333  2.000000  3.000000  2.280000  2.382857
Sat      Dinner  2.555556  2.476190  2.517241  3.102889  2.875476  2.993103
Sun      Dinner  2.929825  2.578947  2.842105  3.167895  3.516842  3.255132
Thur     Dinner  2.000000       NaN  2.000000  3.000000       NaN  3.000000
         Lunch   2.500000  2.352941  2.459016  2.666364  3.030000  2.767705
all_mean         2.668874  2.408602  2.569672  2.991854  3.008710  2.998279
'''

交叉表

交叉表是数据透视表的特殊情况，计算的是分组的频率

def crosstab(index, columns, values=None, rownames=None, colnames=None,aggfunc=None, 
margins=False, margins_name='All', dropna=True,normalize=False):

'''
index:在结果透视表的行上进行分组的列名分组键
columns:在结果透视表的列上进行分组的列名分组键
values:需要聚合的列名，默认所有数值的列
rownames:给index起名
colnames：给columns起名
aggfunc:聚合函数或函数列表,默认计算频率表
margins:添加行列总计(与aggfunc对应)
margins_name:与margins对应
dropna:是否除去均为nan的列
'''

result=pd.crosstab(index=[tips['time'],tips['day']],columns=tips['smoker'],margins=True)
'''
smoker        No  Yes  All
time   day                
Dinner Fri     3    9   12
       Sat    45   42   87
       Sun    57   19   76
       Thur    1    0    1
Lunch  Fri     1    6    7
       Thur   44   17   61
All          151   93  244
'''