# use the trained model to make predictions againts the validation
# feature matrix X_validation
predictions = lr.predict(X_validation)
# determine the accuracy of the model by scoring against the validation
# results vector Y_validation
print('accuracy_score:', a_s(Y_validation, predictions))
print('\n')
print('confusion_matrix')
print('\n')
# generate confusion matrix
print(c_m(Y_validation, predictions))
print('\n')
print('classification_report')
print('\n')
# generate classification report
print(c_r(Y_validation, predictions))
# load test dataset
testfile = './woe-test.csv'
dataset = pandas.read_csv(testfile, header=0)
# Dimensions: dataset.shape -> tells us how many rows and cols
# i.e. how many instances (rows) & attributes (cols)
print('\n dataset.shape:')
print(dataset.shape)
print('\ndataset.head(5)')
print(dataset.head(5))
# drop 'fil' and 'status_log' cols
scoring=scoring)
results.append(cv_results)
names.append(name)
# the data output is: name, mean & std
model_res = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
print(model_res)
# LDA performed best
print('\n')
print('running LDA model i.e. best performing model on validation data....')
print('\n')
lda = LDA()
# first fit the lda instance against the entire training dataset
lda.fit(X_train, Y_train)
# use the trained model to make predictions againts the validation
# feature matrix X_validation
predictions = lda.predict(X_validation)
# determine the accuracy of the model by scoring against the validation
# results vector Y_validation
print('accuracy_score:', a_s(Y_validation, predictions))
print('\n')
print('confusion_matrix')
print('\n')
# generate confusion matrix
print(c_m(Y_validation, predictions))
print('\n')
print('classification_report')
print('\n')
# generate classification report
print(c_r(Y_validation, predictions))
test_size=test_set_size,
random_state=seed,
shuffle=False)
# instantiate XGBC class using defaults
model = XGBC()
# fit model to training datasets
print('\n training d model...')
model.fit(X_train, Y_train)
# view trained model
print('\n model...')
print(model)
# make predictions for test data
print('\n making predictions...')
y_pred = model.predict(X_test)
predictions = [round(value) for value in y_pred]
train_predictions = model.score(X_train, Y_train)
# determine the accuracy of the model by scoring against the test
# results vector Y_test
print('\n xgb_test_standardized_accuracy_score:', a_s(Y_test, predictions))
print('\n xgb_train_standardized_accuracy_score:', train_predictions)
# determine the classification report of the model
print('\n xg_classification report:')
print('\n')
print(c_r(Y_test, predictions, digits=3))