mlalgorithm.py 文件源码

def preprocess_data(train_data_matrix, valid_data_matrix, test_data_matrix):
    """
    Function to preprocess the data with the standard scaler from sci-kit learn.
    It takes in the training, validation, and testing matrices and returns the
    standardized versions of them.

    Input:      train_data_matrix               The data matrix with the training set data
                valid_data_matrix               The data matrix with the validation set data
                test_data_matrix                The data matrix with the testing set data
.
    Output:     transform_train_data_matrix     The data matrix with the standardized training set data
                transform_valid_data_matrix     The data matrix with the standardized validation set data
                transform_test_data_matrix      The data matrix with the standardized testing set data
    Usage:      analyze_ml_data(actual_bg_test_array, test_prediction, True, False, True, False, "00000001", "Linear Regression", "Pred30Data5")
    """

    reg_scaler = prep.StandardScaler().fit(train_data_matrix)
    transform_train_data_matrix = reg_scaler.transform(train_data_matrix)
    transform_valid_data_matrix = reg_scaler.transform(valid_data_matrix)
    transform_test_data_matrix = reg_scaler.transform(test_data_matrix)

    return transform_train_data_matrix, transform_valid_data_matrix, transform_test_data_matrix