lightgbm_분류

 

 

 

LightGBM¶

 

 

위스콘신 유방암 예측¶

 

In [1]:

# lightgbm에서 early_stopping_rounds를 사용하기 위해서는 버전을 '3.3.1', '3.3.2'로 변경

# !pip install lightgbm==3.3.2  

import lightgbm
lightgbm.__version__

 

Out[1]:

'3.3.2'

 

In [28]:

# 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() # 데이터 불러오기
dataset.keys()

df = pd.DataFrame(data = dataset.data, columns = dataset.feature_names) # dataframe로 변경
df['target'] = dataset.target # 타겟 값 추가

X_features = df.iloc[:, :-1]
y_label = 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 쪼개서90%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 XGB와 동일하게 n_estimators는 400 설정
lgbm_wrapper = LGBMClassifier(n_estimators = 400, learning_rate = 0.05) # 모델 생성

# lgbm도 동일하게 조기 중단
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) # 학습
preds = lgbm_wrapper.predict(X_test) # 예측
pred_proba = lgbm_wrapper.predict_proba(X_test)[:, 1] # 확률값 예측

 

Out[28]:

dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename', 'data_module'])

 

[1]	training's binary_logloss: 0.625671	valid_1's binary_logloss: 0.628248
[2]	training's binary_logloss: 0.588173	valid_1's binary_logloss: 0.601106
[3]	training's binary_logloss: 0.554518	valid_1's binary_logloss: 0.577587
[4]	training's binary_logloss: 0.523972	valid_1's binary_logloss: 0.556324
[5]	training's binary_logloss: 0.49615	valid_1's binary_logloss: 0.537407
[6]	training's binary_logloss: 0.470108	valid_1's binary_logloss: 0.519401
[7]	training's binary_logloss: 0.446647	valid_1's binary_logloss: 0.502637
[8]	training's binary_logloss: 0.425055	valid_1's binary_logloss: 0.488311
[9]	training's binary_logloss: 0.405125	valid_1's binary_logloss: 0.474664
[10]	training's binary_logloss: 0.386526	valid_1's binary_logloss: 0.461267
[11]	training's binary_logloss: 0.367027	valid_1's binary_logloss: 0.444274
[12]	training's binary_logloss: 0.350713	valid_1's binary_logloss: 0.432755
[13]	training's binary_logloss: 0.334601	valid_1's binary_logloss: 0.421371
[14]	training's binary_logloss: 0.319854	valid_1's binary_logloss: 0.411418
[15]	training's binary_logloss: 0.306374	valid_1's binary_logloss: 0.402989
[16]	training's binary_logloss: 0.293116	valid_1's binary_logloss: 0.393973
[17]	training's binary_logloss: 0.280812	valid_1's binary_logloss: 0.384801
[18]	training's binary_logloss: 0.268352	valid_1's binary_logloss: 0.376191
[19]	training's binary_logloss: 0.256942	valid_1's binary_logloss: 0.368378
[20]	training's binary_logloss: 0.246443	valid_1's binary_logloss: 0.362062
[21]	training's binary_logloss: 0.236874	valid_1's binary_logloss: 0.355162
[22]	training's binary_logloss: 0.227501	valid_1's binary_logloss: 0.348933
[23]	training's binary_logloss: 0.218988	valid_1's binary_logloss: 0.342819
[24]	training's binary_logloss: 0.210621	valid_1's binary_logloss: 0.337386
[25]	training's binary_logloss: 0.202076	valid_1's binary_logloss: 0.331523
[26]	training's binary_logloss: 0.194199	valid_1's binary_logloss: 0.326349
[27]	training's binary_logloss: 0.187107	valid_1's binary_logloss: 0.322785
[28]	training's binary_logloss: 0.180535	valid_1's binary_logloss: 0.317877
[29]	training's binary_logloss: 0.173834	valid_1's binary_logloss: 0.313928
[30]	training's binary_logloss: 0.167198	valid_1's binary_logloss: 0.310105
[31]	training's binary_logloss: 0.161229	valid_1's binary_logloss: 0.307107
[32]	training's binary_logloss: 0.155494	valid_1's binary_logloss: 0.303837
[33]	training's binary_logloss: 0.149125	valid_1's binary_logloss: 0.300315
[34]	training's binary_logloss: 0.144045	valid_1's binary_logloss: 0.297816
[35]	training's binary_logloss: 0.139341	valid_1's binary_logloss: 0.295387
[36]	training's binary_logloss: 0.134625	valid_1's binary_logloss: 0.293063
[37]	training's binary_logloss: 0.129167	valid_1's binary_logloss: 0.289127
[38]	training's binary_logloss: 0.12472	valid_1's binary_logloss: 0.288697
[39]	training's binary_logloss: 0.11974	valid_1's binary_logloss: 0.28576
[40]	training's binary_logloss: 0.115054	valid_1's binary_logloss: 0.282853
[41]	training's binary_logloss: 0.110662	valid_1's binary_logloss: 0.279441
[42]	training's binary_logloss: 0.106358	valid_1's binary_logloss: 0.28113
[43]	training's binary_logloss: 0.102324	valid_1's binary_logloss: 0.279139
[44]	training's binary_logloss: 0.0985699	valid_1's binary_logloss: 0.276465
[45]	training's binary_logloss: 0.094858	valid_1's binary_logloss: 0.275946
[46]	training's binary_logloss: 0.0912486	valid_1's binary_logloss: 0.272819
[47]	training's binary_logloss: 0.0883115	valid_1's binary_logloss: 0.272306
[48]	training's binary_logloss: 0.0849963	valid_1's binary_logloss: 0.270452
[49]	training's binary_logloss: 0.0821742	valid_1's binary_logloss: 0.268671
[50]	training's binary_logloss: 0.0789991	valid_1's binary_logloss: 0.267587
[51]	training's binary_logloss: 0.0761072	valid_1's binary_logloss: 0.26626
[52]	training's binary_logloss: 0.0732567	valid_1's binary_logloss: 0.265542
[53]	training's binary_logloss: 0.0706388	valid_1's binary_logloss: 0.264547
[54]	training's binary_logloss: 0.0683911	valid_1's binary_logloss: 0.26502
[55]	training's binary_logloss: 0.0659347	valid_1's binary_logloss: 0.264388
[56]	training's binary_logloss: 0.0636873	valid_1's binary_logloss: 0.263128
[57]	training's binary_logloss: 0.0613354	valid_1's binary_logloss: 0.26231
[58]	training's binary_logloss: 0.0591944	valid_1's binary_logloss: 0.262011
[59]	training's binary_logloss: 0.057033	valid_1's binary_logloss: 0.261454
[60]	training's binary_logloss: 0.0550801	valid_1's binary_logloss: 0.260746
[61]	training's binary_logloss: 0.0532381	valid_1's binary_logloss: 0.260236
[62]	training's binary_logloss: 0.0514074	valid_1's binary_logloss: 0.261586
[63]	training's binary_logloss: 0.0494837	valid_1's binary_logloss: 0.261797
[64]	training's binary_logloss: 0.0477826	valid_1's binary_logloss: 0.262533
[65]	training's binary_logloss: 0.0460364	valid_1's binary_logloss: 0.263305
[66]	training's binary_logloss: 0.0444552	valid_1's binary_logloss: 0.264072
[67]	training's binary_logloss: 0.0427638	valid_1's binary_logloss: 0.266223
[68]	training's binary_logloss: 0.0412449	valid_1's binary_logloss: 0.266817
[69]	training's binary_logloss: 0.0398589	valid_1's binary_logloss: 0.267819
[70]	training's binary_logloss: 0.0383095	valid_1's binary_logloss: 0.267484
[71]	training's binary_logloss: 0.0368803	valid_1's binary_logloss: 0.270233
[72]	training's binary_logloss: 0.0355637	valid_1's binary_logloss: 0.268442
[73]	training's binary_logloss: 0.0341747	valid_1's binary_logloss: 0.26895
[74]	training's binary_logloss: 0.0328302	valid_1's binary_logloss: 0.266958
[75]	training's binary_logloss: 0.0317853	valid_1's binary_logloss: 0.268091
[76]	training's binary_logloss: 0.0305626	valid_1's binary_logloss: 0.266419
[77]	training's binary_logloss: 0.0295001	valid_1's binary_logloss: 0.268588
[78]	training's binary_logloss: 0.0284699	valid_1's binary_logloss: 0.270964
[79]	training's binary_logloss: 0.0273953	valid_1's binary_logloss: 0.270293
[80]	training's binary_logloss: 0.0264668	valid_1's binary_logloss: 0.270523
[81]	training's binary_logloss: 0.0254636	valid_1's binary_logloss: 0.270683
[82]	training's binary_logloss: 0.0245911	valid_1's binary_logloss: 0.273187
[83]	training's binary_logloss: 0.0236486	valid_1's binary_logloss: 0.275994
[84]	training's binary_logloss: 0.0228047	valid_1's binary_logloss: 0.274053
[85]	training's binary_logloss: 0.0221693	valid_1's binary_logloss: 0.273211
[86]	training's binary_logloss: 0.0213043	valid_1's binary_logloss: 0.272626
[87]	training's binary_logloss: 0.0203934	valid_1's binary_logloss: 0.27534
[88]	training's binary_logloss: 0.0195552	valid_1's binary_logloss: 0.276228
[89]	training's binary_logloss: 0.0188623	valid_1's binary_logloss: 0.27525
[90]	training's binary_logloss: 0.0183664	valid_1's binary_logloss: 0.276485
[91]	training's binary_logloss: 0.0176788	valid_1's binary_logloss: 0.277052
[92]	training's binary_logloss: 0.0170059	valid_1's binary_logloss: 0.277686
[93]	training's binary_logloss: 0.0164317	valid_1's binary_logloss: 0.275332
[94]	training's binary_logloss: 0.015878	valid_1's binary_logloss: 0.276236
[95]	training's binary_logloss: 0.0152959	valid_1's binary_logloss: 0.274538
[96]	training's binary_logloss: 0.0147216	valid_1's binary_logloss: 0.275244
[97]	training's binary_logloss: 0.0141758	valid_1's binary_logloss: 0.275829
[98]	training's binary_logloss: 0.0136551	valid_1's binary_logloss: 0.276654
[99]	training's binary_logloss: 0.0131585	valid_1's binary_logloss: 0.277859
[100]	training's binary_logloss: 0.0126961	valid_1's binary_logloss: 0.279265
[101]	training's binary_logloss: 0.0122421	valid_1's binary_logloss: 0.276695
[102]	training's binary_logloss: 0.0118067	valid_1's binary_logloss: 0.278488
[103]	training's binary_logloss: 0.0113994	valid_1's binary_logloss: 0.278932
[104]	training's binary_logloss: 0.0109799	valid_1's binary_logloss: 0.280997
[105]	training's binary_logloss: 0.0105953	valid_1's binary_logloss: 0.281454
[106]	training's binary_logloss: 0.0102381	valid_1's binary_logloss: 0.282058
[107]	training's binary_logloss: 0.00986714	valid_1's binary_logloss: 0.279275
[108]	training's binary_logloss: 0.00950998	valid_1's binary_logloss: 0.281427
[109]	training's binary_logloss: 0.00915965	valid_1's binary_logloss: 0.280752
[110]	training's binary_logloss: 0.00882581	valid_1's binary_logloss: 0.282152
[111]	training's binary_logloss: 0.00850714	valid_1's binary_logloss: 0.280894

Out[28]:

LGBMClassifier(learning_rate=0.05, n_estimators=400)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

 

In [ ]:

from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score, precision_score, recall_score, 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('오차행렬')
    print(confusion)
    
    # ROC-AUC 출력
    print('정확도 : {0:.4f}, 정밀도 : {1:.4f}, 재현율 : {2:.4f}, F1 : {3:.4f}, AUC : {4:.4f}'.format(accuracy, precision, recall, f1, roc_auc))

 

In [29]:

get_clf_eval(y_test, preds, pred_proba) # 평가

 

 

오차행렬
[[34  3]
 [ 2 75]]
정확도 : 0.9561, 정밀도 : 0.9615, 재현율 : 0.9740, F1 : 0.9677, AUC : 0.9877

 

In [36]:

# 피처 중요도 시각화

from lightgbm import plot_importance
import matplotlib.pyplot as plt

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