二值化与分段

sklearn.preprocessing.Binarizer

from sklearn.preprocessing import Binarizer
import pandas as pd

data = pd.read_csv("./data_full", index_col=0)
data
Age Survived Sex_female Sex_male Embarked_C Embarked_Q Embarked_S
0 22.000000 0.0 0.0 1.0 0.0 0.0 1.0
1 38.000000 2.0 1.0 0.0 1.0 0.0 0.0
2 26.000000 2.0 1.0 0.0 0.0 0.0 1.0
3 35.000000 2.0 1.0 0.0 0.0 0.0 1.0
4 35.000000 0.0 0.0 1.0 0.0 0.0 1.0
... ... ... ... ... ... ... ...
884 25.000000 0.0 0.0 1.0 0.0 0.0 1.0
885 39.000000 0.0 1.0 0.0 0.0 0.0 1.0
886 27.000000 0.0 1.0 0.0 0.0 0.0 1.0
887 19.000000 2.0 0.0 1.0 1.0 0.0 0.0
888 29.699118 0.0 0.0 1.0 0.0 1.0 0.0

887 rows × 7 columns

data1 = data.copy()
age = data1.iloc[:,0].values.reshape(-1,1)
result = Binarizer(threshold=30).fit_transform(age)
data1.iloc[:,0] = result

data1
Age Survived Sex_female Sex_male Embarked_C Embarked_Q Embarked_S
0 0.0 0.0 0.0 1.0 0.0 0.0 1.0
1 1.0 2.0 1.0 0.0 1.0 0.0 0.0
2 0.0 2.0 1.0 0.0 0.0 0.0 1.0
3 1.0 2.0 1.0 0.0 0.0 0.0 1.0
4 1.0 0.0 0.0 1.0 0.0 0.0 1.0
... ... ... ... ... ... ... ...
884 0.0 0.0 0.0 1.0 0.0 0.0 1.0
885 1.0 0.0 1.0 0.0 0.0 0.0 1.0
886 0.0 0.0 1.0 0.0 0.0 0.0 1.0
887 0.0 2.0 0.0 1.0 1.0 0.0 0.0
888 0.0 0.0 0.0 1.0 0.0 1.0 0.0

887 rows × 7 columns

preprocessing.KBinsDiscretizer

from sklearn.preprocessing import KBinsDiscretizer
data2 = data.copy()
age = data2.iloc[:,0].values.reshape(-1,1)
result2 = KBinsDiscretizer(n_bins=5,encode="ordinal",strategy="uniform").fit_transform(age)

set(result2.ravel())

{0.0, 1.0, 2.0, 3.0, 4.0}

result3 = KBinsDiscretizer(n_bins=5, encode="onehot",strategy="quantile").fit_transform(age)
result3.toarray()

array([[0., 1., 0., 0., 0.],
       [0., 0., 0., 0., 1.],
       [0., 1., 0., 0., 0.],
       ...,
       [0., 1., 0., 0., 0.],
       [1., 0., 0., 0., 0.],
       [0., 0., 0., 1., 0.]])