classifier/train_xgboost.py

import numpy as np
import xgboost as xgb
from sklearn.metrics import accuracy_score, classification_report
import joblib
import os

PROJECT_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))

FEATURE_DIR = os.path.join(
    PROJECT_ROOT,
    "featureextraction",
    "final_features"
)

X_train = np.load(
    os.path.join(FEATURE_DIR, "train_X.npy"),
    allow_pickle=True
)
y_train = np.load(
    os.path.join(FEATURE_DIR, "train_y.npy"),
    allow_pickle=True
)

X_val = np.load(
    os.path.join(FEATURE_DIR, "val_X.npy"),
    allow_pickle=True
)
y_val = np.load(
    os.path.join(FEATURE_DIR, "val_y.npy"),
    allow_pickle=True
)

print("Train shape:", X_train.shape)
print("Validation shape:", X_val.shape)
print("Feature dtype:", X_train.dtype)

model = xgb.XGBClassifier(
    n_estimators=300,
    max_depth=6,
    learning_rate=0.05,
    subsample=0.8,
    colsample_bytree=0.8,
    objective="binary:logistic",
    eval_metric="logloss",
    random_state=42
)

model.fit(X_train, y_train)

val_preds = model.predict(X_val)

print("\nVALIDATION RESULTS\n")
print("Accuracy:", accuracy_score(y_val, val_preds))
print(
    classification_report(
        y_val,
        val_preds,
        target_names=["Human", "AI"]
    )
)

MODEL_DIR = os.path.join(PROJECT_ROOT, "models")
os.makedirs(MODEL_DIR, exist_ok=True)

model.save_model(os.path.join(MODEL_DIR, "xgboost_final_model.json"))
joblib.dump(model, os.path.join(MODEL_DIR, "xgboost_final_model.pkl"))

print("\n XGBoost model saved successfully")