4-2. Ensemble Classifier

Voting Classifier

위스콘신 유방암 데이터 로드

import pandas as pd

from sklearn.ensemble import VotingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

cancer = load_breast_cancer()

data_df = pd.DataFrame(cancer.data, columns=cancer.feature_names)
data_df.head(3)

	mean radius	mean texture	mean perimeter	mean area	mean smoothness	mean compactness	mean concavity	mean concave points	mean symmetry	mean fractal dimension	...	worst radius	worst texture	worst perimeter	worst area	worst smoothness	worst compactness	worst concavity	worst concave points	worst symmetry	worst fractal dimension
0	17.99	10.38	122.8	1001.0	0.11840	0.27760	0.3001	0.14710	0.2419	0.07871	...	25.38	17.33	184.6	2019.0	0.1622	0.6656	0.7119	0.2654	0.4601	0.11890
1	20.57	17.77	132.9	1326.0	0.08474	0.07864	0.0869	0.07017	0.1812	0.05667	...	24.99	23.41	158.8	1956.0	0.1238	0.1866	0.2416	0.1860	0.2750	0.08902
2	19.69	21.25	130.0	1203.0	0.10960	0.15990	0.1974	0.12790	0.2069	0.05999	...	23.57	25.53	152.5	1709.0	0.1444	0.4245	0.4504	0.2430	0.3613	0.08758
3 rows × 30 columns

 

VotingClassifier로 개별모델은 로지스틱 회귀와 KNN을 보팅방식으로 결합하고 성능 비교

# 개별 모델은 로지스틱 회귀와 KNN 임. 
lr_clf = LogisticRegression()
knn_clf = KNeighborsClassifier(n_neighbors=8)

# 개별 모델을 소프트 보팅 기반의 앙상블 모델로 구현한 분류기 
vo_clf = VotingClassifier( estimators=[('LR',lr_clf),('KNN',knn_clf)] , voting='soft' )

X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, 
                                                    test_size=0.2 , random_state= 156)

# VotingClassifier 학습/예측/평가. 
vo_clf.fit(X_train , y_train)
pred = vo_clf.predict(X_test)
print('Voting 분류기 정확도: {0:.4f}'.format(accuracy_score(y_test , pred)))

# 개별 모델의 학습/예측/평가.
classifiers = [lr_clf, knn_clf]
for classifier in classifiers:
    classifier.fit(X_train , y_train)
    pred = classifier.predict(X_test)
    class_name= classifier.__class__.__name__
    print('{0} 정확도: {1:.4f}'.format(class_name, accuracy_score(y_test , pred)))
    
    
    
Voting 분류기 정확도: 0.9474
LogisticRegression 정확도: 0.9386
KNeighborsClassifier 정확도: 0.9386