计算指标/哑变量

from pandas import DataFrame,Series
import pandas as pd
import numpy as np

# 如果一个DataFrame的某一列中含有K个不同值，则可以派生出一个K列矩阵
df = DataFrame({'key':['b','b','a','c','a','b'],
                'data':range(6)})
print(df)
'''
  key  data
0   b     0
1   b     1
2   a     2
3   c     3
4   a     4
5   b     5
'''
dummies = pd.get_dummies(df['key'],prefix='key')
print(dummies)
'''
   key_a  key_b  key_c
0      0      1      0
1      0      1      0
2      1      0      0
3      0      0      1
4      1      0      0
5      0      1      0
'''
df_with_dummies = df[['data']].join(dummies)
print(df_with_dummies)
'''
   data  key_a  key_b  key_c
0     0      0      1      0
1     1      0      1      0
2     2      1      0      0
3     3      0      0      1
4     4      1      0      0
5     5      0      1      0
'''

from pandas import DataFrame,Series
import pandas as pd
import numpy as np

mnames = ['movie_id','title','genres']
movies = pd.read_table('movies.dat', sep='::', header=None, names=mnames, encoding='ISO-8859-1',engine='python')
#print(movies[:10])

genre_iter = (set(x.split('|')) for x in movies.genres)
genres = sorted(set.union(*genre_iter)) # set.union选取并集，重复元素只会出现一次
#print(genres[:10])

# 创建一个多行多列全0的DataFrame
dummies = DataFrame(np.zeros((len(movies),len(genres))),columns=genres)

for i,gen in enumerate(movies.genres):
    indices = dummies.columns.get_indexer(gen.split('|')) # 返回拆分结果在dummies中的排行
    dummies.iloc[i,indices] = 1
movies_windic = movies.join(dummies.add_prefix('Genre_'))
print(movies_windic.iloc[0].head(10)) # 取第1行的前10列

 

import pandas as pd
import numpy as np

values = np.random.rand(10)
print(values)
'''
[0.07858525 0.87300262 0.35604229 0.93110966 0.79934318 0.08215684
 0.96897297 0.3661382  0.22688337 0.50674505]
'''
bins = [0,0.2,0.4,0.6,0.8,1]
print(pd.get_dummies(pd.cut(values,bins)))
'''
   (0.0, 0.2]  (0.2, 0.4]  (0.4, 0.6]  (0.6, 0.8]  (0.8, 1.0]
0           1           0           0           0           0
1           0           0           0           0           1
2           0           1           0           0           0
3           0           0           0           0           1
4           0           0           0           1           0
5           1           0           0           0           0
6           0           0           0           0           1
7           0           1           0           0           0
8           0           1           0           0           0
9           0           0           1           0           0
'''