start = time.time()
with open(results_file, 'w') as fout:
csv_writer = csv.writer(fout,
delimiter=';',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
csv_writer.writerow([
"dataset", "cls", "params", "nr_events", "nr_events_predy",
"metric", "score"
])
correct_all_train = 0
correct_all_val = 0
correct_all_test = 0
for i in range(max_len):
X_test, y_test = dataset_manager.generate_3d_data_for_prefix_length(
dt_test, max_len, i + 1)
y_pred_test = model.predict(X_test)
correct_train = np.sum(
[0 if res < 0.5 else 1
for res in np.ravel(y_pred[:, i, 0])] == np.ravel(y[:, i, 0]))
correct_val = np.sum([
0 if res < 0.5 else 1 for res in np.ravel(y_pred_val[:, i, 0])
] == np.ravel(y_val[:, i, 0]))
correct_test = np.sum([
0 if res < 0.5 else 1 for res in np.ravel(y_pred_test[:, i, 0])
] == np.ravel(y_test[:, i, 0]))
print(i, correct_train, correct_val, correct_test)
csv_writer.writerow([
dataset_name, cls_method, params, i, -1, "tp_train",
correct_train
print("Done: %s" % (time.time() - start))
print('Evaluating...')
start = time.time()
with open(results_file, 'w') as fout:
csv_writer = csv.writer(fout,
delimiter=';',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
csv_writer.writerow(
["dataset", "cls", "params", "nr_events", "metric", "score"])
correct_all_train = 0
correct_all_test = 0
for nr_events in range(1, max_len + 1):
X, y = dataset_manager.generate_3d_data_for_prefix_length(
dt_train, nr_events, nr_events)
X_test, y_test = dataset_manager.generate_3d_data_for_prefix_length(
dt_test, nr_events, nr_events)
y = y[:, 0, 0].reshape(y.shape[0])
y_test = y_test[:, 0, 0].reshape(y_test.shape[0])
X_reshaped = X.reshape((X.shape[0], X.shape[1] * X.shape[2]))
X_reshaped_test = X_test.reshape(
(X_test.shape[0], X.shape[1] * X.shape[2]))
cls = RandomForestClassifier(n_estimators=n_estimators,
max_features=max_features)
cls.fit(X_reshaped, y)
y_pred = cls.predict(X_reshaped)
y_pred_test = cls.predict(X_reshaped_test)
correct_train = np.sum(y == y_pred)
print("Done: %s"%(time.time() - start))
print('Evaluating...')
start = time.time()
with open(results_file, 'w') as fout:
csv_writer = csv.writer(fout, delimiter=';', quotechar='"', quoting=csv.QUOTE_MINIMAL)
csv_writer.writerow(["dataset", "cls", "params", "nr_events", "metric", "score"])
total = 0
total_acc = 0
total_mae = 0
for nr_events in range(2, max_len-1):
# encode only prefixes of this length
X, y_a, y_t = dataset_manager.generate_3d_data_for_prefix_length(dt_test, max_len, nr_events)
if X.shape[0] == 0:
break
y_t = y_t * dataset_manager.divisors["timesincelastevent"]
pred_y = model.predict(X, verbose=0)
pred_y_a = pred_y[0]
pred_y_t = pred_y[1]
pred_y_t = pred_y_t.flatten()
pred_y_t[pred_y_t < 0] = 0
pred_y_t = pred_y_t * dataset_manager.divisors["timesincelastevent"]
acc = accuracy_score(np.argmax(y_a, axis=1), np.argmax(pred_y_a, axis=1))
mae = mean_absolute_error(y_t, pred_y_t)
total += X.shape[0]
total_acc += acc * X.shape[0]
