def modelfit(train,
labels,
test,
features,
useTrainCV=True,
cv_folds=5,
early_stopping_rounds=50):
param_test1 = {
'max_depth': range(3, 10, 2),
'min_child_weight': range(1, 6, 2)
}
model = GridSearchCV(estimator=XGBClassifier(learning_rate=0.1,
n_estimators=140,
max_depth=5,
min_child_weight=1,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
objective='binary:logistic',
nthread=4,
scale_pos_weight=1,
seed=27),
param_grid=param_test1,
scoring='roc_auc',
n_jobs=4,
iid=False,
cv=5)
test_percent = 0.2
X_train, X_test, y_train, y_test = train_test_split(train,
labels,
test_size=test_percent,
random_state=23)
xgb_param = model.get_xgb_params()
#Fit the algorithm on the data
model.fit(X_train, y_train)
print(model.grid_scores_)
print(model.best_params_)
print(model.best_score_)
##training predictions
proba = model.predict_proba(X_test)
preds = proba[:, 1]
score = roc_auc_score(y_test, preds)
print("Area under ROC {0}".format(score))
#Print model report:
# print "\nModel Report"
# print "Accuracy : %.4g" % accuracy_score(y_train, preds)
# print "AUC Score (Train): %f" % roc_auc_score(y_train, preds)
feat_imp = pd.Series(
model.booster().get_fscore()).sort_values(ascending=False)
feat_imp.plot(kind='bar', title='Feature Importances')
plt.ylabel('Feature Importance Score')
# plt.show()
##test predictions
test_proba = model.predict_proba(test)
test_preds = test_proba[:, 1]
return test_preds
