#X_train, X_test, y_train, y_test = train_test_split(X1, y1, test_size=0.4, random_state=1)##balancear datos con SMOTE
#Arbol de decisión
#model = DecisionTreeClassifier(criterion='entropy')
#Forest
#model=RandomForestClassifier(n_estimators=100)
#Maquina de soporte vectorial
#model=svm.SVC(kernel='linear', C=1, probability=True)
#K vecino más cercano
model = KNeighborsClassifier(n_neighbors=10)
model.fitted = model.fit(X_train, y_train)
model.predictions = model.fitted.predict(X_test)
y_probas = model.fitted.predict_proba(X_test)
print(confusion_matrix(y_test, model.predictions))
print(accuracy_score(y_test, model.predictions))
predicted = cross_validation.cross_val_predict(model, X_normalized, Yn, cv=10)
print(accuracy_score(Yn, predicted))
skplt.metrics.plot_confusion_matrix(y_test,
model.predictions,
title='Matriz de confusión',
figsize=(13, 13),
cmap='Blues')
pyplot.show()
