# n_jobs = 3)
# cv_rf.fit(training_set, class_set)
# print('Best Parameters using grid search: \n',
# cv_rf.best_params_)
# end = time.time()
# print('Time taken in grid search: {0: .2f}'\
#.format(end - start))
# Test Set Calculations -------------------------------------
# Test error rate
test_error_rate_rf = 1 - accuracy_rf
# Confusion Matrix
test_crosstb = hf.create_conf_mat(test_class_set, predictions_rf)
# Print Variable Importance
hf.variable_importance(importances_rf, indices_rf)
# Cross validation
print('Cross Validation:')
hf.cross_val_metrics(fit_rf, training_set, class_set, print_results=True)
print('Confusion Matrix:')
print(test_crosstb, '\n')
print("Here is our mean accuracy on the test set:\n {0: 0.3f}"\
.format(accuracy_rf))
print("The test error rate for our model is:\n {0: .3f}"\
.format(test_error_rate_rf))
test_error_rate_RF = 1 - accuracy_RF
# ROC Curve stuff
fpr2, tpr2, _ = roc_curve(predictions_RF,
test_class_set)
auc_rf = auc(fpr2, tpr2)
# Uncomment to save your model as a pickle object!
# joblib.dump(fit_RF, 'pickle_models/model_rf.pkl')
if __name__=='__main__':
# Print model parameters
print(fit_RF)
hf.variable_importance(import_rf, ind_rf)
hf.variable_importance_plot(import_rf_desc, ind_rf)
print('''
############################################
## HYPERPARAMETER OPTIMIZATION ##
############################################
'''
)
print("Note: Remove commented code to see this section")
print("chosen parameters: {'bootstrap': True, 'criterion': 'entropy', \
'max_depth': 4}\
\nElapsed time of optimization: 189.949 seconds")
# Set the random state for reproducibility
fit_rf = RandomForestClassifier(random_state=42)
## Set best parameters given by grid search
fit_rf.set_params(criterion='gini',
max_features='log2',
max_depth=3,
n_estimators=400)
# Fit model on training data
fit_rf.fit(training_set, class_set)
# Tree Specific -------------------------------------------------
# Extracting feature importance
var_imp_rf = hf.variable_importance(fit_rf)
importances_rf = var_imp_rf['importance']
indices_rf = var_imp_rf['index']
if __name__ == '__main__':
# Print model parameters ------------------------------------
print(fit_rf, '\n')
# Initialize function for metrics ---------------------------
fit_dict_rf = produce_model_metrics(fit_rf, test_set, test_class_set, 'rf')
# Extract each piece from dictionary
predictions_rf = fit_dict_rf['predictions']
accuracy_rf = fit_dict_rf['accuracy']