from sklearn.metrics import (confusion_matrix, classification_report,
                             accuracy_score, precision_score, recall_score,
                             f1_score, roc_auc_score, roc_curve)
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
import seaborn as sns

# 이진 분류 데이터
X, y = make_classification(n_samples=1000, n_features=20,
                           weights=[0.7, 0.3], random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
                                                     random_state=42)

model = LogisticRegression(max_iter=1000)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

# 혼동 행렬
cm = confusion_matrix(y_test, y_pred)
sns.heatmap(cm, annot=True, fmt="d", cmap="Blues",
            xticklabels=["음성", "양성"], yticklabels=["음성", "양성"])
plt.xlabel("예측")
plt.ylabel("실제")
plt.title("혼동 행렬")
plt.show()

# 종합 리포트
print(classification_report(y_test, y_pred))

# 개별 지표
print(f"Accuracy:  {accuracy_score(y_test, y_pred):.4f}")
print(f"Precision: {precision_score(y_test, y_pred):.4f}")
print(f"Recall:    {recall_score(y_test, y_pred):.4f}")
print(f"F1:        {f1_score(y_test, y_pred):.4f}")

# ROC 곡선 그리기
y_prob = model.predict_proba(X_test)[:, 1]
fpr, tpr, thresholds = roc_curve(y_test, y_prob)
auc = roc_auc_score(y_test, y_prob)

plt.plot(fpr, tpr, label=f"ROC (AUC = {auc:.3f})")
plt.plot([0, 1], [0, 1], "k--", label="랜덤 분류기")
plt.xlabel("거짓 양성률 (FPR)")
plt.ylabel("진양성률 (TPR)")
plt.title("ROC 곡선")
plt.legend()
plt.show()