'''
oversampled_path = "resources/oversampled_normalized_data_ratio_2.bin"
homesite = Data()
homesite.load_sliptted_data(oversampled_path)
del homesite.test_x # Deleted to save memory.
print homesite.train_x.shape
# Creating classifier.
# clf = DecisionTreeClassifier()
clf = RandomForestClassifier(max_features=100)
# clf = AdaBoostClassifier(n_estimators = 10)
# clf = svm.SVC(gamma = 0.00005)
# clf = RandomForestClassifier()
# clf = MultiplePLS(n_classifiers = 10, n_samples = 5000, n_positive_samples = 2500, threshold = 0.9, acc = 0.999)
# clf = svm.LinearSVC()
# Train classifier.
print "Training classifier."
clf.fit(homesite.train_x, homesite.train_y)
# Test classifier.
print 'Testing classifier.'
predicted_labels = clf.predict_proba(homesite.validation_x)[:, 1]
# Show final results.
results = confusion_matrix(homesite.validation_y,
np.round(predicted_labels))
accuracy, precision, recall = compute_performance_metrics(results)
auc = compute_auc(homesite.validation_y, predicted_labels)
cvs = StratifiedKFold(homesite.train_y, n_folds = 5)
clf = RandomForestClassifier(n_estimators = c, max_features = 100, n_jobs = 4)
# Train classifier.
print "\nTraining classifier param %d" % c
for i, (train, test) in enumerate(cvs):
sm = OverSampler(verbose = False, ratio = 2.5)
train_oversampled_x, train_oversampled_train_y = sm.fit_transform(homesite.train_x[train], homesite.train_y[train])
probas_ = clf.fit(train_oversampled_x, train_oversampled_train_y).predict_proba(homesite.train_x[test])
fpr, tpr, thresholds = roc_curve(homesite.train_y[test], probas_[:, 1])
mean_tpr += interp(mean_fpr, fpr, tpr)
mean_tpr[0] = 0.0
roc_auc = compute_auc(homesite.train_y[test], probas_[:, 1])
fold_cm = confusion_matrix(homesite.train_y[test], np.round(probas_)[:, 1])
confusion_matrix_history = np.dstack((confusion_matrix_history, fold_cm))
accuracy, precision, recall = compute_performance_metrics(fold_cm)
mean_acc += accuracy
mean_recall += recall
mean_precision += precision
accuracy_history.append(accuracy)
precision_history.append(precision)
recall_history.append(recall)
auc_history.append(roc_auc)
save_np_array("../../results/random_forests/rf_accuracy_" + str(c) + ".bin", np.array(accuracy_history))
save_np_array("../../results/random_forests/rf_precision_" + str(c) + ".bin", np.array(precision_history))
save_np_array("../../results/random_forests/rf_recall_" + str(c) + ".bin", np.array(recall_history))
if __name__ == '__main__':
'''
Train neural network.
'''
# oversampled_path = "../../homesite_data/resources/oversampled_normalized_data_ratio_2.5.bin"
oversampled_path = "../../homesite_data/resources/oversampled_normalized_data_ratio_2.bin"
homesite_data = Data()
homesite_data.load_sliptted_data(oversampled_path, one_hot = True)
# Train neural network.
clf = NeuralNetwork(input_units = 644, hidden_units = 50, output_units = 2, \
lr = 0.00005, lamb = 0.)
# clf.fit(homesite_data, batch_size = 128,
# max_iterations = 100, save_interval = 10,
# path = "../homesite_data/ann_weights.bin")
# Test neural network.
# clf = NeuralNetwork(path = "../../homesite_data/ann_weights.bin", lr = 0.05, lamb = 0.000005)
# Test classifier.
print 'Testing classifier.'
predicted_labels = clf.predict_proba(homesite_data.validation_x)[:, 1]
# Show final results.
results = confusion_matrix(np.argmax(homesite_data.validation_y, axis = 1), np.round(predicted_labels))
accuracy, precision, recall = compute_performance_metrics(results)
auc = compute_auc(np.argmax(homesite_data.validation_y, axis = 1), predicted_labels)