def nearest_neighbours_classifier_prediction(nearest_neighbours_data_model,test_data):
print('Predicting the class label using the nearest neighbours classifier model . . .')
X = util.drop_target_variable(test_data)
y = util.retrieve_target_variable(test_data)
meval.plot_ROC_curve(nearest_neighbours_data_model, X, y,'Nearest Neighbours Classifier')
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.9999, random_state=1)
Y_predict = nearest_neighbours_data_model.predict(X_test)
util.display_all_metrics(y_test, Y_predict)
util.save_data_model(nearest_neighbours_data_model,'predicted_nearest_neighbours_classifier')
return;
def linear_support_vector_classifier_prediction(
linear_support_vector_data_model, test_data):
X, y = make_classification(n_features=11, random_state=0)
print(
'Predicting the class label using the linear support vector classifier model . . .',
linear_support_vector_data_model.predict(
[[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]))
# meval.plot_ROC_curve(linear_support_vector_data_model, X, y,'Linear Support Vector Classifier')
util.save_data_model(linear_support_vector_data_model,
'predicted_linear_support_vector_classifier')
return
def nearest_neighbours_classifier(training_data):
print('Generating the data model for a nearest neighbours classifier . . .\n')
X = util.drop_target_variable(training_data)
y = util.retrieve_target_variable(training_data)
X_train, X_test, y_train, y_test = train_test_split(X, y,stratify=y, test_size=0.1, random_state=1)
nca = NeighborhoodComponentsAnalysis(random_state=42)
knn = KNeighborsClassifier(n_neighbors=3)
knn=knn.fit(X_train, y_train)
nca_pipe = Pipeline([('nca', nca), ('knn', knn)])
nca_pipe.fit(X_train, y_train)
print('The data model for nearest neighbours classifier has been generated successfully!\n')
util.save_data_model(knn,'nearest_neighbours_classifier')
return knn;
def adaboost_classifier_prediction(adaboost_data_model, test_data):
print(
'Predicting the class label using the adaboost classifier model . . .')
X = util.drop_target_variable(test_data)
y = util.retrieve_target_variable(test_data)
meval.plot_ROC_curve(adaboost_data_model, X, y, 'Ada Boost Classifier')
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.9999,
random_state=1)
Y_predict = adaboost_data_model.predict(X_test)
util.display_all_metrics(y_test, Y_predict)
util.save_data_model(adaboost_data_model, 'predicted_adaboost_classifier')
return
def rule_based_classifier_prediction(rule_based_data_model, test_data):
print(
'Predicting the class label using the rule based classifier model . . .'
)
X = util.drop_target_variable(test_data)
y = util.retrieve_target_variable(test_data)
meval.plot_ROC_curve(rule_based_data_model, X, y, 'Rule Based Classifier')
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.9999,
random_state=1)
Y_predict = rule_based_data_model.predict(X_test)
util.display_all_metrics(y_test, Y_predict)
util.save_data_model(rule_based_data_model,
'predicted_rule_based_classifier')
return
def rule_based_classifier(training_data):
print('Generating the data model for a rule based classifier . . .\n')
X = util.drop_target_variable(training_data)
y = util.retrieve_target_variable(training_data)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.7,
random_state=1)
rule_based_classifier = lw.RIPPER()
rule_based_classifier.fit(X_train, y_train)
print(rule_based_classifier.ruleset_.out_pretty())
print(
'The data model for rule based classifier has been generated successfully!\n'
)
util.save_data_model(rule_based_classifier, 'rule_based_classifier')
return
def adaboost_classifier(training_data):
print('Generating the data model for adaboost classifier . . .\n')
adaboost_classifier = AdaBoostClassifier(n_estimators=100, random_state=7)
X = util.drop_target_variable(training_data)
y = util.retrieve_target_variable(training_data)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
stratify=y,
test_size=0.1,
random_state=1)
adaboost_classifier = adaboost_classifier.fit(X_train, y_train)
print(
'The data model for adaboost classifier has been generated successfully!\n'
)
util.save_data_model(adaboost_classifier, 'adaboost_classifier')
return
def decision_tree_classifier(training_data):
print('Generating the data model for a decision tree classifier . . .\n')
X = util.drop_target_variable(training_data)
y = util.retrieve_target_variable(training_data)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.1,
random_state=1)
decision_tree_classifier = DecisionTreeClassifier()
decision_tree_classifier = decision_tree_classifier.fit(X_train, y_train)
print(
'The data model for decision tree classifier has been generated successfully!\n'
)
visualizing_decision_tree(decision_tree_classifier, X,
'visualizing_decision_tree')
util.save_data_model(decision_tree_classifier, 'decision_tree_classifier')
return
def linear_support_vector_classifier(training_data):
print(
'Generating the data model for a linear support vector classifier . . .\n'
)
X, y = make_classification(n_features=11, random_state=0)
linear_support_vector_classifier = LinearSVC(random_state=0, tol=1e-5)
linear_support_vector_classifier.fit(X, y)
print('The intercept of linear support vector classifier is : ',
linear_support_vector_classifier.intercept_)
print('\nThe slope of linear support vector classifier is : ',
linear_support_vector_classifier.coef_)
print(
'\nThe data model for linear support vector classifier has been generated successfully!\n'
)
util.save_data_model(linear_support_vector_classifier,
'linear_support_vector_classifier')
# meval.plot_ROC_curve(linear_support_vector_classifier, X, y,'Linear Support Vector Classifier')
return
def stochastic_gradient_boosting_classifier_prediction(
stochastic_gradient_boosting_data_model, test_data):
print(
'Predicting the class label using the stochastic gradient boosting classifier model . . .'
)
X = util.drop_target_variable(test_data)
y = util.retrieve_target_variable(test_data)
meval.plot_ROC_curve(stochastic_gradient_boosting_data_model, X, y,
'Stochastic Gradient Boosting Classifier')
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.9999,
random_state=1)
Y_predict = stochastic_gradient_boosting_data_model.predict(X_test)
util.display_all_metrics(y_test, Y_predict)
util.save_data_model(stochastic_gradient_boosting_data_model,
'predicted_stochastic_gradient_boosting_classifier')
return
def decision_tree_classifier_prediction(decision_tree_data_model, test_data):
print(
'Predicting the class label using the decision tree classifier model . . .'
)
X = util.drop_target_variable(test_data)
y = util.retrieve_target_variable(test_data)
meval.plot_ROC_curve(decision_tree_data_model, X, y,
'Decision Tree Classifier')
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.9999,
random_state=1)
Y_predict = decision_tree_data_model.predict(X_test)
util.display_all_metrics(y_test, Y_predict)
visualizing_decision_tree(decision_tree_data_model, X,
'visualizing_predicted_decision_tree')
util.save_data_model(decision_tree_data_model,
'predicted_decision_tree_classifier')
return
def random_forest_classifier_prediction(random_forest_data_model, test_data):
print(
'Predicting the class label using the random forest classifier model . . .'
)
X = util.drop_target_variable(test_data)
y = util.retrieve_target_variable(test_data)
meval.plot_ROC_curve(random_forest_data_model, X, y,
'Random Forest Classifier')
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.9999,
random_state=1)
Y_predict = random_forest_data_model.predict(X_test)
util.display_all_metrics(y_test, Y_predict)
single_predicted_decision_tree = random_forest_data_model.estimators_[5]
tree.visualizing_decision_tree(single_predicted_decision_tree, X,
'visualizing_predicted_random_forest')
util.save_data_model(random_forest_data_model,
'predicted_random_forest_classifier')
return
def random_forest_classifier(training_data):
print('Generating the data model for random forest classifier . . .\n')
random_forest_classifier = RandomForestClassifier(n_estimators=100,
random_state=7)
X = util.drop_target_variable(training_data)
y = util.retrieve_target_variable(training_data)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
stratify=y,
test_size=0.1,
random_state=1)
random_forest_classifier = random_forest_classifier.fit(X_train, y_train)
print(
'The data model for random forest classifier has been generated successfully!\n'
)
single_decision_tree = random_forest_classifier.estimators_[5]
tree.visualizing_decision_tree(single_decision_tree, X,
'visualizing_random_forest')
util.save_data_model(random_forest_classifier, 'random_forest_classifier')
return
def stochastic_gradient_boosting_classifier(training_data):
print(
'Generating the data model for stochastic gradient boosting classifier . . .\n'
)
stochastic_gradient_boosting_classifier = GradientBoostingClassifier(
n_estimators=100, random_state=7)
X = util.drop_target_variable(training_data)
y = util.retrieve_target_variable(training_data)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
stratify=y,
test_size=0.1,
random_state=1)
stochastic_gradient_boosting_classifier = stochastic_gradient_boosting_classifier.fit(
X_train, y_train)
print(
'The data model for stochastic gradient boosting classifier has been generated successfully!\n'
)
util.save_data_model(stochastic_gradient_boosting_classifier,
'stochastic_gradient_boosting_classifier')
return
def bagging_method_classifier(training_data, nearest_neighbours_classifier):
print('Generating the data model for a bagging method classifier . . .\n')
bagging_method_classifier = BaggingClassifier(
base_estimator=nearest_neighbours_classifier,
n_estimators=100,
random_state=7,
max_samples=0.5,
max_features=0.5)
X = util.drop_target_variable(training_data)
y = util.retrieve_target_variable(training_data)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
stratify=y,
test_size=0.1,
random_state=1)
bagging_method_classifier = bagging_method_classifier.fit(X_train, y_train)
print(
'The data model for bagging method classifier has been generated successfully!\n'
)
util.save_data_model(bagging_method_classifier,
'bagging_method_classifier')
return
