def tune_svm_using_10_fold():
dh = DataHandler('data/train-set-feature-engineered.csv', 'prediction_label')
headers, train_features, train_prediction_labels = dh.get_numeric_data_set()
#train_features = dh.get_k_best_features(500, train_features, train_prediction_labels)
data_sets = dh.get_cross_validation_data_sets(10, train_features, train_prediction_labels)
accuracy = []
for data_set_number in data_sets:
data_set = data_sets.get(data_set_number)
training_set = data_set[0]
tuning_set = data_set[1]
train_features = training_set["data_points"]
train_prediction_labels = training_set["labels"]
# Feature selection
train_features, selected_features = dh.get_k_best_features(len(train_features[0]), train_features, train_prediction_labels)
test_features = tuning_set["data_points"]
test_prediction_labels = tuning_set["labels"]
# Feature selection
test_features = dh.get_new_feature_vec(test_features, selected_features)
svm = Svm(train_features, train_prediction_labels, 200, 1, 2)
svm.train()
eval_metrics = EvaluationMetrics(svm, test_features, test_prediction_labels)
eval = eval_metrics.evaluate()
accuracy.append(eval['accuracy'])
average_accuracy = sum(accuracy) / len(accuracy)
print average_accuracy
def evaluate_svm():
dh = DataHandler('data/train-set-feature-engineered.csv', 'prediction_label')
headers, train_features, train_prediction_labels = dh.get_numeric_data_set()
# Feature selection
train_features, selected_features = dh.get_k_best_features(len(train_features[0]), train_features, train_prediction_labels)
svm = Svm(train_features, train_prediction_labels, 20, 0)
svm.train()
dh_test = DataHandler('data/test-set-feature-engineered.csv', 'prediction_label')
headers, test_features, test_prediction_labels = dh_test.get_numeric_data_set()
# Feature selection
test_features = dh_test.get_new_feature_vec(test_features, selected_features)
eval_metrics = EvaluationMetrics(svm, test_features, test_prediction_labels)
eval = eval_metrics.evaluate()
eval_metrics.compute_and_plot_auc(eval['predicted'], test_prediction_labels)
eval_metrics.compute_au_roc(eval['predicted'], test_prediction_labels)
def main(argv):
train_x = read_from_file(sys.argv[1])
train_x = one_hot_encode(train_x).astype(float)
train_y = read_from_file(sys.argv[2])
train_y = train_y.astype(float).astype(int)
num_of_labels = len(Counter(train_y).keys())
# np.random.seed(5)
# mapIndexPosition = list(zip(train_x, train_y))
# np.random.shuffle(mapIndexPosition)
# train_x, train_y = zip(*mapIndexPosition)
# train_y = np.asarray(train_y)
# train_x = np.asarray(train_x)
############## prediction:################
test_x = read_from_file(sys.argv[3])
test_x = one_hot_encode(test_x).astype(float)
#
# test_y = read_from_file("test_y.txt").astype(float).astype(int).tolist()
# ###### cross validation #######
# trains_x = [all_train_x[:657],all_train_x[657:1314],all_train_x[1314:1971],all_train_x[1971:2628],all_train_x[2628:]]
# trains_y = [all_train_y[:657], all_train_y[657:1314], all_train_y[1314:1971], all_train_y[1971:2628],all_train_y[2628:]]
# for K in range(5):
# test_x = trains_x[K]
# test_y = trains_y[K]
# train_x = []
# train_y = []
# for i in range(5):
# if i is not K:
# for example, lable in zip(trains_x[i],trains_y[i]):
# train_x.append(example)
# train_y.append(lable)
#
# train_x = np.asarray(train_x)
# train_y = np.asarray(train_y)
# d = {"I": 0, "M": 1, "F": 2}
# temp = train_x
# temp = scipy.stats.zscore(temp)
train_x_Z_score, mean, std_dev = z_score_norm(train_x)
train_x_min_max, min_train, max_train = min_max_norm(train_x)
test_x_z_score = z_score_norm_by_mean_std(test_x, mean, std_dev)
test_x_min_max = min_max_norm_by_min_max(test_x, min_train, max_train)
# perceptron_z_score = Perceptron(train_x_Z_score, train_y, num_of_feature, num_of_labels)
# svm_z_score = Svm(train_x_Z_score, train_y, num_of_feature, num_of_labels)
# pa_z_score = Pa(train_x_Z_score, train_y, num_of_feature, num_of_labels)
#
# perceptron_min_max = Perceptron(train_x_min_max, train_y, num_of_feature, num_of_labels)
# svm_min_max = Svm(train_x_min_max, train_y, num_of_feature, num_of_labels)
# pa_min_max = Pa(train_x_min_max, train_y, num_of_feature, num_of_labels)
############# training:#################
perceptron = Perceptron(train_x_min_max, train_y, num_of_labels)
svm = Svm(train_x_min_max, train_y, num_of_labels)
pa = Pa(train_x_Z_score, train_y, num_of_labels)
perceptron.train()
svm.train()
pa.train()
predict_pereceptron = []
predict_svm = []
predict_pa = []
for test_min_max, test_z_score in zip(test_x_min_max, test_x_z_score):
predict_pereceptron.append(perceptron.predict(test_min_max))
predict_svm.append(svm.predict(test_min_max))
predict_pa.append(pa.predict(test_z_score))
# for test in test_x_z_score:
# predict_pa.append(pa.predict(test))
print_predict(predict_pereceptron, predict_svm, predict_pa)
