[Machine Learning] 분류 알고리즘 - 앙상블(Ensemble) 기법의 부스팅(Boosting) / LightGBM

import xgboost   

print(xgboost._version_) # 버전 확인  

# LightGBM의 파이썬 패키지인 lightgbm에서 LGBMClassifier 임포트
from lightgbm import LGBMClassifier

import pandas as pd
import numpy as np
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
import warnings
warnings.filterwarnings('ignore')

dataset = load_breast_cancer()

cancer_df = pd.DataFrame(data=dataset.data, columns=dataset.feature_names)
cancer_df['target']= dataset.target

cancer_df.head()

X_features = cancer_df.iloc[:, :-1]
y_label = cancer_df.iloc[:, -1]

# 전체 데이터 중 80%는 학습용 데이터, 20%는 테스트용 데이터 추출
X_train, X_test, y_train, y_test=train_test_split(X_features, y_label,
                                         test_size=0.2, random_state=156 )

# 위에서 만든 X_train, y_train을 다시 쪼개서 90%는 학습과 10%는 검증용 데이터로 분리  
X_tr, X_val, y_tr, y_val= train_test_split(X_train, y_train,
                                         test_size=0.1, random_state=156 )

# 앞서 XGBoost와 동일하게 n_estimators는 400 설정. 
lgbm_wrapper = LGBMClassifier(n_estimators=400, learning_rate=0.05)

# LightGBM도 XGBoost와 동일하게 조기 중단 수행 가능. 
evals = [(X_tr, y_tr), (X_val, y_val)]
lgbm_wrapper.fit(X_tr, y_tr, early_stopping_rounds=50, eval_metric="logloss", 
                 eval_set=evals, verbose=True)
preds = lgbm_wrapper.predict(X_test)
pred_proba = lgbm_wrapper.predict_proba(X_test)[:, 1]

from sklearn.metrics import confusion_matrix, accuracy_score
from sklearn.metrics import precision_score, recall_score
from sklearn.metrics import f1_score, roc_auc_score

def get_clf_eval(y_test, pred=None, pred_proba=None):
    confusion = confusion_matrix( y_test, pred)
    accuracy = accuracy_score(y_test , pred)
    precision = precision_score(y_test , pred)
    recall = recall_score(y_test , pred)
    f1 = f1_score(y_test,pred)
    # ROC-AUC 추가 
    roc_auc = roc_auc_score(y_test, pred_proba)
    print('오차 행렬')
    print(confusion)
    # ROC-AUC print 추가
    print('정확도: {0:.4f}, 정밀도: {1:.4f}, 재현율: {2:.4f},\
    F1: {3:.4f}, AUC:{4:.4f}'.format(accuracy, precision, recall, f1, roc_auc))

get_clf_eval(y_test, preds, pred_proba)

# plot_importance( )를 이용하여 feature 중요도 시각화
from lightgbm import plot_importance
import matplotlib.pyplot as plt
%matplotlib inline

fig, ax = plt.subplots(figsize=(10, 12))
plot_importance(lgbm_wrapper, ax=ax)
plt.show()