def evalute_model(path):
df = pd.read_csv(path)
x, y = df.iloc[:, :-1].values, df.iloc[:, -1].values
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.3,
random_state=1337)
rf = RandomForestClassifier(n_estimators=100, random_state=1337)
print_result("Without NaiveBayes:", rf, x_train, x_test, y_train, y_test)
rf_nb = RandomForestClassifier(n_estimators=100, random_state=1337)
rf_nb.base_estimator = NBDecisionTreeClassifier()
print_result("With NaiveBayes:", rf_nb, x_train, x_test, y_train, y_test)
ensembles_results['train_score'].append(knn_bagging_ensemble.score(X_train, y_train))
ensembles_results['validation_score'].append(knn_bagging_ensemble.score(X_validation,y_validation))
# In[157]:
# As DecisionTreeclassifier was the most cussessful in previous ensembles,
# now I will try out RandomForestClassifier
# In[158]:
rfc_ensemble = RandomForestClassifier(n_estimators=100, random_state=0)
rfc_ensemble.base_estimator = dtc_estimator
# In[159]:
rfc_ensemble.fit(X_train, y_train)
ensembles_results['ensemble'].append('RandomForestClassifier')
ensembles_results['train_score'].append(rfc_ensemble.score(X_train, y_train))
ensembles_results['validation_score'].append(rfc_ensemble.score(X_validation,y_validation))
# In[160]:
