pandas 사용

1
2
3
4
5
6

ser_1 = pd.Series([2, 5, 3, 4, 6, 2, 3])
ser_2 = pd.Series([7, 3, 6, 5, 2, 6, 7])
ser_3 = pd.Series([9, 11, 4, 8, 2, 15, 3])

df_aov = pd.DataFrame([ser_1, ser_2, ser_3]).transpose().melt()
df_aov

1

pd.cut([5, 20, 29, 33, 41], bins = 5, right = False)

1

pd.qcut([5, 20, 29, 33, 41], [0,0.2,0.4,0.6,0.8,1])

1
2
3
4
5
6
7
8

import numpy as np
import pandas as pd

data = pd.DataFrame({'cust_id': ['c1', 'c1', 'c1', 'c2', 'c2', 'c2', 'c3', 'c3', 'c3'],
'prod_cd': ['p1', 'p2', 'p3', 'p1', 'p2', 'p3', 'p1', 'p2', 'p3'],
'grade' : ['A', 'A', 'A', 'A', 'A', 'A', 'B', 'B', 'B'],
 'pch_amt': [30, 10, 0, 40, 15, 30, 0, 0, 10]})
data

1

data.pivot(index='cust_id', columns='prod_cd', values='pch_amt')

1

pd.pivot_table(data, index='grade', columns='prod_cd', values='pch_amt', aggfunc=np.mean)

1

pd.pivot_table(data, index='grade', columns='prod_cd', values='pch_amt', aggfunc=np.sum, margins=True)

1
2
3
4

mul_index = pd.MultiIndex.from_tuples([('cust_1', '2015'), ('cust_1', '2016'),('cust_2', '2015'), ('cust_2', '2016')])
data = pd.DataFrame(data=np.arange(16).reshape(4, 4),
        index=mul_index,columns=['prd_1', 'prd_2', 'prd_3', 'prd_4'], dtype='int')
data

1

data.stack(level = -1, dropna=False)

1

data.unstack(level=-1)

1

data.unstack(level=0)

1

data.unstack(level=1)