seed = 7
DTC = DecisionTreeClassifier
parameters = {'max_depth':range(3,10), 'max_leaf_nodes':range(10, 30), 'criterion': ['gini'], "splitter" :   ["best"]}#, 'max_features':range(10,100)}
dt = RandomizedSearchCV(DTC(random_state=seed), parameters, n_jobs=10, cv=kfold) #min_samples_leaf=10
fit_dt= dt.fit(X_train, Y_train)
print(dir(fit_dt))
tree_model = dt.best_estimator_
print (dt.best_score_, dt.best_params_, dt.error_score) #, dt.cv_results_)
print('best estimators')
print(fit_dt.best_estimator_)

features = tree_model.feature_importances_
print(features)

rank = np.argsort(features)[::-1]
print(rank[:12])
print(sorted(list(zip(features))))
#for items in fit_dt.feature_importances_:
 #   print (items)

# Print best scores and best parameters

means = dt.cv_results_['mean_test_score']
stds = dt.cv_results_['std_test_score']
for mean, std, params in zip(means, stds, dt.cv_results_['params']):
    print("%0.3f (+/-%0.03f) for %r"
            % (mean, std * 2, params))

print('Best Score: {}'
      .format(dt.best_score_))
print('Best params: {}'
      .format(dt.best_params_))

print('Accuracy of DT classifier on training set: {:.2f}'
     .format(dt.score(X_train, Y_train)))
print('Accuracy of DT classifier on test set: {:.2f}'
     .format(dt.score(X_test, Y_test)))

predictions = dt.predict(X_test)
print(np.column_stack((Y_test, np.round(predictions))))