Spaces:
Runtime error
Runtime error
File size: 1,525 Bytes
b144cb7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | 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")
|