X_train = pipeline.fit_transform(train)
X_val = pipeline.transform(val)
X_test = pipeline.transform(test)
eval_set = [(X_train, y_train), (X_val, y_val)]
model = XGBRFClassifier(n_jobs=-1,
n_estimators=5000,
early_stopping_rounds=100,
random_state=42,
scale_pos_weight=15,
learning_rate=.005,
reg_lambda=.01,
verbosity=1)
print('fitting...')
model.fit(X_train, y_train, eval_set=eval_set, eval_metric='auc', verbose=True)
y_pred_proba = model.predict_proba(X_val)[:, 1]
print(f'Validation ROC AUC score: {roc_auc_score(y_val, y_pred_proba)}')
print('permuting...')
permuter = PermutationImportance(model,
cv='prefit',
n_iter=5,
scoring='roc_auc',
random_state=42)
permuter.fit(X_val, y_val)
features_of_import = pd.Series(permuter.feature_importances_,
val.columns).sort_values(ascending=True)
print('importance', features_of_import)
'colsample_bytree': 0.07,
'gamma': 0.005,
'max_depth': 3,
'min_child_weight': 3,
'n_estimators': 500,
'objective': 'binary:logistic',
'random_state': 10,
'reg_alpha': 9,
'reg_lambda': 0,
'subsample': 0.6,
'verbosity': 0
}
model_L = XGBRFClassifier(**model_L_params)
model_L.fit(X_train_scl_L,
y_train_L,
eval_set=eval_set,
eval_metric='auc',
early_stopping_rounds=20,
verbose=False)
pred_L = model_L.predict(X_clouds_scl_L)
clouds_R, _ = get_clouds(roiR)
X_clouds_R = clouds_R.reshape((clouds_R.shape[0], -1))
X_clouds_scl_R = X_clouds_R / scale_rnd_R
model_R_params = {
'colsample_bytree': 0.07,
'gamma': 0.005,
'max_depth': 3,
'min_child_weight': 3,
'n_estimators': 500,
'objective': 'binary:logistic',
'random_state': 10,
xgbrf_classifier = XGBRFClassifier(
learning_rate=0.1,
n_estimators=1000,
max_depth=7,
min_child_weight=5
)
else:
xgbrf_classifier = XGBRFClassifier(
learning_rate=0.1,
n_estimators=1000,
max_depth=7,
min_child_weight=3
)
print('[LOG] Fitting model...')
xgbrf_classifier.fit(trainDataset.X, trainDataset.Y[:,0])
print('[LOG] Fitting done!')
print('-- Model Report --')
print('XGBoost train Accuracy: '+str(accuracy_score(xgbrf_classifier.predict(trainDataset.X), trainDataset.Y[:,0])))
print('XGBoost valid Accuracy: '+str(accuracy_score(xgbrf_classifier.predict(validDataset.X), validDataset.Y[:,0])))
if not os.path.isdir(arg.img):
os.mkdir(arg.img)
f, ax = plt.subplots(figsize=(10,5))
plot = sns.barplot(x=features, y=xgbrf_classifier.feature_importances_)
ax.set_title('Feature Importance')
plot.set_xticklabels(plot.get_xticklabels(),rotation='vertical')
plt.savefig(os.path.join(arg.img, modelName))
# save model
pickl = {'model': xgbrf_classifier}