from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, roc_auc_score, roc_curve
import matplotlib.pyplot as plt

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y, random_state=42)

pipe = Pipeline([
    ('scaler', StandardScaler()),
    ('clf', RandomForestClassifier(n_estimators=100, random_state=42, n_jobs=-1))
])
pipe.fit(X_train, y_train)

y_pred = pipe.predict(X_test)
y_prob = pipe.predict_proba(X_test)[:, 1]
print(classification_report(y_test, y_pred))
print(f'ROC-AUC: {roc_auc_score(y_test, y_prob):.3f}')

from xgboost import XGBClassifier

# Use sklearn-compatible API with proper parameters (avoid deprecated seed, nthread)
xgb = XGBClassifier(
    n_estimators=100,
    max_depth=6,
    learning_rate=0.1,
    random_state=42,  # NOT seed
    n_jobs=-1,        # NOT nthread
    eval_metric='logloss'
)

pipe = Pipeline([('scaler', StandardScaler()), ('clf', xgb)])
pipe.fit(X_train, y_train)

from sklearn.linear_model import LogisticRegressionCV

# L1 for sparse biomarkers, L2 for correlated features, elasticnet for mixed
logit = LogisticRegressionCV(
    Cs=10,
    cv=5,
    penalty='l1',
    solver='saga',
    max_iter=1000,
    random_state=42
)
pipe = Pipeline([('scaler', StandardScaler()), ('clf', logit)])
pipe.fit(X_train, y_train)

# Get selected features (nonzero coefficients)
feature_mask = logit.coef_[0] != 0
selected = X.columns[feature_mask]

fpr, tpr, _ = roc_curve(y_test, y_prob)
auc = roc_auc_score(y_test, y_prob)

plt.figure(figsize=(6, 6))
plt.plot(fpr, tpr, label=f'ROC (AUC = {auc:.3f})')
plt.plot([0, 1], [0, 1], 'k--')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.legend()
plt.savefig('roc_curve.png', dpi=150)

from sklearn.metrics import classification_report
from sklearn.preprocessing import LabelEncoder

le = LabelEncoder()
y_encoded = le.fit_transform(y)

# Use class_weight for imbalanced data
rf = RandomForestClassifier(n_estimators=100, class_weight='balanced', random_state=42)

import pandas as pd

importances = pipe.named_steps['clf'].feature_importances_
feature_imp = pd.DataFrame({'feature': X.columns, 'importance': importances})
feature_imp = feature_imp.sort_values('importance', ascending=False).head(20)