# Standardise training and testing data scaler_train = StandardScaler() scaler_test = StandardScaler() scaler_train.fit(training_data) scaler_test.fit(testing_data) testing_data = scaler_test.transform(testing_data) # Convert training data to pd dataframe columns = "BC NC LP LI".split() training_data = pd.DataFrame(data=training_data, index=None, columns=columns) # Replicate the training data replicated_data1 = replicate_data(training_data, 10, 0.03) replicated_data2 = replicate_data(training_data, 10, 0.05) training_data = training_data.append(replicated_data1, ignore_index=True, sort=False) training_data = training_data.append(replicated_data2, ignore_index=True, sort=False) training_data = scaler_train.transform(training_data) training_data = np.array(training_data) # Calculate training and testing labels try: a = []
index +=1 # Standardise Test Data for subset in subset_test_list: subset.value = scaler_train.transform(subset.value) # Replicate and Standardise the training data in each subset. columns = "BC NC LP LI NIC".split() for index, subset in enumerate(subset_train_list): df = pd.DataFrame(data=subset.value, index=None, columns=columns) ref = df df = scaler_train.transform(df) replicated_data1 = replicate_data(ref, 50, 0.03) replicated_data1 = scaler_train.transform(replicated_data1) df = np.append(df, replicated_data1, axis=0) replicated_data2 = replicate_data(ref, 50, 0.05) replicated_data2 = scaler_train.transform(replicated_data2) df = np.append(df, replicated_data2, axis=0) subset.value = df # Calculate training and test labels for index1, subset in enumerate(subset_train_list): a = [] try: