ML - 전처리 단계

Preprocessing (Label_encoder, min_max scaler, Standard scaler, Robust scaler)

import pandas as pd
df = pd.DataFrame({
    'A' : ['a','b','c','a','b'],
    'B' : [1, 2, 3, 1, 0 ]
})
df

⏹Label_encoder

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
df['le_A']= le.fit_transform(df['A'])
df

# 다시 원래대로 하는 경우
le.inverse_transform(df['le_A'])

array(['a', 'b', 'c', 'a', 'b'], dtype=object)

⏹Min_Max Scaler

df = pd.DataFrame({
    'A' : [10, 20, -10, 0, 25],
    'B' : [1, 2, 3, 1, 0 ]
})
df

from sklearn.preprocessing import MinMaxScaler

mms = MinMaxScaler()
mms.fit(df)

mms.data_max_, mms.data_min_, mms.data_range_

(array([25.,  3.]), array([-10.,   0.]), array([35.,  3.]))

df_mms = mms.transform(df)
df_mms

array([[0.57142857, 0.33333333],
       [0.85714286, 0.66666667],
       [0.        , 1.        ],
       [0.28571429, 0.33333333],
       [1.        , 0.        ]])

mms.inverse_transform(df_mms)

array([[ 10.,   1.],
       [ 20.,   2.],
       [-10.,   3.],
       [  0.,   1.],
       [ 25.,   0.]])

⏹Standard Scaler

from sklearn.preprocessing import StandardScaler

ss = StandardScaler()
ss.fit(df)

#평균, 표준편차
ss.mean_, ss.scale_

(array([9. , 1.4]), array([12.80624847,  1.0198039 ]))

# 평균 0 표준편차 1 인 데이터로 변환 
df_ss = ss.transform(df)
df_ss

array([[ 0.07808688, -0.39223227],
       [ 0.85895569,  0.58834841],
       [-1.48365074,  1.56892908],
       [-0.70278193, -0.39223227],
       [ 1.2493901 , -1.37281295]])

⏹Robust Scaler

df = pd.DataFrame({
    'A' : [-0.1,0.,0.1,0.2,0.3,0.4,1.0,1.1,5.0]
})
df

from sklearn.preprocessing import RobustScaler

rs = RobustScaler()
df_scaler = df.copy()

df_scaler['Min_Max'] = mms.fit_transform(df)
df_scaler['Standard'] = ss.fit_transform(df)
df_scaler['Robust'] = rs.fit_transform(df)

df_scaler

# 각 스케일러의 차이와 특징 그래프로 확인
# 특히 MinMax Scaler 이상치에 대해 민감 

import seaborn as sns
import matplotlib.pyplot as plt

sns.set_theme(style='whitegrid')

plt.figure(figsize=(16,6))
sns.boxplot(data=df_scaler,orient = 'h');