def chooseClassification(name):
print "Choosen classfier:", name
return {
'NB': GaussianNB(),
'ADA': adaBoost(n_estimators=2),
'RF': rf(n_estimators=7),
'KNN': knn(n_neighbors=15, p=1),
'SVM': svm.SVC(C=0.01, kernel='rbf', probability=True),
'BAG': BaggingClassifier(n_estimators=7) #base_estimator=knn(),
#bootstrap=True,
#bootstrap_features=True,
#oob_score=True,
#max_features = 10,
#max_samples = 100),
}.get(name, GaussianNB()) # default Gaussian Naive Bayes
def chooseClassification(name):
print "Choosen classfier:",name
return {
'NB': GaussianNB(),
'ADA': adaBoost(n_estimators=50),
'RF': rf(n_estimators = 100),
'KNN': knn(n_neighbors=15, p=1),
'SVM': svm.SVC(kernel='rbf', probability=True),
'BAG':BaggingClassifier(n_estimators = 30)#base_estimator=knn(),
#bootstrap=True,
#bootstrap_features=True,
#oob_score=True,
#max_features = 10,
#max_samples = 100),
}.get(name, GaussianNB()) # default Gaussian Naive Bayes
random_state=0)
print(X_train.shape)
print(y_train.shape)
print(X_test.shape)
print(y_test.shape)
#############################################
#ADABOOST
#############################################
#cross validation and grid search for hyperparameter estimation
param_dist = {'algorithm': ["SAMME", "SAMME.R"]}
cv = StratifiedShuffleSplit(n_splits=5, test_size=0.2, random_state=0)
clf = GridSearchCV(adaBoost(), param_grid=param_dist, cv=cv)
clf = clf.fit(X_train, y_train.values.ravel())
print("Best estimator found by grid search:")
print(clf.best_estimator_)
#apply the classifier on the test data and show the accuracy of the model
print('the acuracy of Adaboost is:')
print(clf.score(X_test, y_test.values.ravel()))
prediction = clf.predict(X_test)
#use the metrics.classification to report.
print("Confusion matrix:\n%s" % metrics.confusion_matrix(y_test, prediction))
print("Classification report:\n %s\n" %
metrics.classification_report(y_test, prediction))
y_pred = model.predict(X_test) confusion_matrix(y_test, y_pred) # In[11]: accuracy_score(y_test, y_pred) # In[12]: f1_score(y_test, y_pred, average='macro') # <h2> <b> Ada-Boost with decision Tree as base-estimator ( An ensemble Approach) # In[13]: Model = adaBoost(n_estimators=100, base_estimator=dtclf(), learning_rate=0.98) Model.fit(X_train, y_train) y_pred = model.predict(X_test) # In[14]: confusion_matrix(y_test, y_pred) # In[15]: accuracy_score(y_test, y_pred) # In[16]: f1_score(y_test, y_pred, average='macro')