net_pretrain = pkl.load(f)
#================#
## VALIDATION ##
#================#
y_pred = net.predict(x_valid)
acc = accuracy_score(y_valid,y_pred)
print('Total Accuracy: {0:2.4}%'.format(acc*100))
# cm = confusion_matrix(y_valid, y_pred)
# cm_norm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
# print(cm_norm)
## Fit to validation
# print('fitting to validation data ...')
# net.fit(x_valid,y_valid,epochs=50)
# with gzip.open('./cuisine_net2.pkl', 'wb') as file:
# pkl.dump(net, file, -1)
#==========================#
## TESTING & SUBMISSION ##
#==========================#
predictions = net.predict(x_test)
outfile=netfile[:-7] + '_submission.csv'
dface.make_submission(predictions, filename=outfile)
## Train some classifiers
#KNN
start = time()
knn = KNeighborsClassifier(n_neighbors=15)
knn.fit(x_train,y_train)
y_pred= knn.predict(x_valid)
end = time()
m, s = divmod(end-start, 60)
# h, m = divmod(m, 60)
print 'Training runtime: {0}mins, {1}s'.format(m,s)
acc = accuracy_score(y_valid,y_pred)
print(classification_report(y_valid,y_pred, labels=np.unique(y_valid), target_names=labels ))
print 'Total Accuracy: {0:2.4}%'.format(acc*100)
#plot_confusion_matrix(y_valid, y_pred)
## Create Submission file
clf = knn
start = time()
predictions = clf.predict(x_test)
end = time()
m, s = divmod(end-start, 60)
print 'Test runtime: {0}mins, {1}s'.format(m,s)
dface.make_submission(predictions)
