[ML] 3-5. 평가 - 최종 평가 지표 함수

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import load_breast_cancer

cancer = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, test_size = 0.2, random_state=120)

lr_clf = LogisticRegression()

lr_clf.fit(X_train, y_train)
pred = lr_clf.predict(X_test)

from sklearn.metrics import accuracy_score, precision_score, recall_score, confusion_matrix, 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 = roc_auc_score(y_test, pred_proba)
    
    print('오차 행렬')
    print(confusion)
    print('정확도: {0:.4f}, 정밀도: {1:.4f}, 재현율: {2:.4f}, F1: {3:.4f}, AUC:{4:.4f}'.format(accuracy, precision, recall, f1, roc_auc))

pred_proba = lr_clf.predict_proba(X_test)[:, 1]

get_clf_eval(y_test, pred=pred, pred_proba=pred_proba)

오차 행렬
[[39  4]
 [ 2 69]]
정확도: 0.9474, 정밀도: 0.9452, 재현율: 0.9718, F1: 0.9583, AUC:0.9869