###############################
'''
)
print(pd.crosstab(predictions_nn,
test_class_set['diagnosis'],
rownames=['Predicted Values'],
colnames=['Actual Values']))
print("Here is our mean accuracy on the test set:\n {0: .3f}"\
.format(accuracy_nn))
print("The test error rate for our model is:\n {0: .3f}"\
.format(test_error_rate_nn))
# ROC Curve
hf.plot_roc_curve(fpr3, tpr3, auc_nn, 'nn')
# Zoomed in ROC Curve
hf.plot_roc_curve(fpr3, tpr3, auc_nn, 'nn',
(-0.001, 0.2), (0.7, 1.05))
else:
def return_nn():
'''
Function to output values created in script
'''
return fpr3, tpr3, auc_nn, predictions_nn, test_error_rate_nn
# Keep Cross validation metrics
mean_cv_nn, std_error_nn = hf.cross_val_metrics(fit_nn,
training_set_scaled,
class_set['diagnosis'],
###############################
'''
)
print(pd.crosstab(predictions_RF,
test_class_set['diagnosis'],
rownames=['Predicted Values'],
colnames=['Actual Values']))
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))
# ROC Curve
hf.plot_roc_curve(fpr2, tpr2, auc_rf, 'rf')
# Zoomed in ROC Curve
hf.plot_roc_curve(fpr2, tpr2, auc_rf, 'rf',
(-0.001, 0.2), (0.7, 1.05))
else:
def return_rf():
'''
Function to output values created in script
'''
return fpr2, tpr2, auc_rf, predictions_RF, test_error_rate_RF
mean_cv_rf, std_error_rf = hf.cross_val_metrics(fit_RF,
training_set,
class_set['diagnosis'],
print_results = False)
rownames=['Predicted Values'],
colnames=['Actual Values']))
# TEST ERROR RATE!!
print("Here is our accuracy for our test set:\n {0: .3f}"\
.format(accuracy))
# Here we calculate the test error rate!
print("The test error rate for our model is:\n {0: .3f}"\
.format(test_error_rate))
# ROC Curve
# NOTE: These functions were created in the helperFunctions.py
# script to reduce lines of code
# refer to helper.py for additional information
hf.plot_roc_curve(fpr, tpr, auc_knn, 'knn')
# Zoomed in ROC Curve
hf.plot_roc_curve(fpr, tpr, auc_knn, 'knn', (-0.001, 0.2), (0.7, 1.05))
else:
def return_knn():
'''
Function to output values created in script
'''
return fpr, tpr, auc_knn, predictions, test_error_rate
mean_cv_knn, std_error_knn = hf.cross_val_metrics(fit_knn,
training_set,
class_set['diagnosis'],
print_results=False)