특성 선택 방법

특성을 선택하는 이유

세 가지 방법군

VarianceThreshold

from sklearn.feature_selection import VarianceThreshold

sel = VarianceThreshold(threshold=0.01)
X_reduced = sel.fit_transform(X)
print("Kept:", X_reduced.shape[1], "of", X.shape[1])

f_classif를 사용하는 SelectKBest

from sklearn.feature_selection import SelectKBest, f_classif

sel = SelectKBest(score_func=f_classif, k=10)
X_best = sel.fit_transform(X, y)
print(sel.get_support(indices=True))

상호 정보량

from sklearn.feature_selection import SelectKBest, mutual_info_classif

sel = SelectKBest(score_func=mutual_info_classif, k=10)
X_mi = sel.fit_transform(X, y)

f_classif와 상호 정보량 비교

import numpy as np
from sklearn.feature_selection import f_classif, mutual_info_classif

f_scores, _ = f_classif(X, y)
mi_scores = mutual_info_classif(X, y)
print("F-test top:", np.argsort(f_scores)[::-1][:5])
print("MI top:", np.argsort(mi_scores)[::-1][:5])

재귀적 특성 제거

from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression

rfe = RFE(estimator=LogisticRegression(max_iter=1000), n_features_to_select=10)
rfe.fit(X, y)
print(rfe.support_)

RFECV: 특성 개수 자동 선택

from sklearn.feature_selection import RFECV
from sklearn.ensemble import RandomForestClassifier

rfecv = RFECV(
    estimator=RandomForestClassifier(),
    cv=5,
    scoring="accuracy",
)
rfecv.fit(X, y)
print("Optimal features:", rfecv.n_features_)

Lasso를 사용하는 SelectFromModel

from sklearn.feature_selection import SelectFromModel
from sklearn.linear_model import Lasso

sel = SelectFromModel(Lasso(alpha=0.01))
sel.fit(X, y)
X_lasso = sel.transform(X)
print("Kept:", X_lasso.shape[1])

트리 중요도를 사용하는 SelectFromModel

from sklearn.feature_selection import SelectFromModel
from sklearn.ensemble import RandomForestClassifier

sel = SelectFromModel(
    RandomForestClassifier(n_estimators=200),
    threshold="median",
)
sel.fit(X, y)

방법 선택하기

빠른 확인

요약