sklearnのカテゴリフィーチャー回転数値タイプ
2760 ワード
------------------------- -------------------------------------------------------------------------------
import numpy as np
import pandas as pd
df = pd.DataFrame([['green', 'M', 10.1, 'class1'],
['red', 'L', 13.5, 'class2'],
['blue', 'XL', 15.3, 'class1']],columns=['color', 'size', 'price', 'classlabel'])
print(df)
color size price classlabel
0 green M 10.1 class1
1 red L 13.5 class2
2 blue XL 15.3 class1
size_mapping = {'XL':3, 'L':2, 'M':1}
df['size'] = df['size'].map(size_mapping)
print(df)
color size price classlabel
0 green 1 10.1 class1
1 red 2 13.5 class2
2 blue 3 15.3 class1
Series
## Series
for idx, label in enumerate(df['classlabel']):
print(idx, label)
0 class1
1 class2
2 class1
1 LabelEncoder
from sklearn.preprocessing import LabelEncoder
class_le = LabelEncoder()
color_le = LabelEncoder()
df['classlabel'] = class_le.fit_transform(df['classlabel'].values)
df['color'] = color_le.fit_transform(df['color'].values)
print(df)
color size price classlabel
0 0 1 10.1 0
1 1 2 13.5 1
2 0 3 15.3 0
2.
class_mapping = {label: idx for idx, label in enumerate(np.unique(df['classlabel']))}
df['classlabel'] = df['classlabel'].map(class_mapping)
print('2,', df)
2, color size price classlabel
0 green M 10.1 0
1 red L 13.5 1
2 green XL 15.3 0
3.one-hot
pf = pd.get_dummies(df[['color']])
df = pd.concat([df, pf], axis=1)
df.drop(['color'], axis=1, inplace=True)
print(df)
size price classlabel color_green color_red
0 M 10.1 class1 1 0
1 L 13.5 class2 0 1
2 XL 15.3 class1 1 0