DATA_UTILS

data_utils.to_categorical(y[, num_classes])	Converts a class vector (integers) to binary class matrix. E.g. for use with categorical_crossentropy. :param y: class vector to be converted into a matrix (integers from 0 to num_classes). :type y: numpy array :param num_classes: total number of classes. :type num_classes: int.
data_utils.convert_to_class(y_one_hot[, dtype])	Converts a one-hot class encoding (array with as many positions as total classes, with 1 in the corresponding class position, 0 in the other positions), or soft-max class encoding (array with as many positions as total classes, whose largest valued position is used as class membership) to an integer class encoding.
data_utils.scale_array(mat[, scaling])	Scale data included in numpy array.
data_utils.impute_and_scale_array(mat[, scaling])	Impute missing values with mean and scale data included in numpy array.
data_utils.drop_impute_and_scale_dataframe(df)	Impute missing values with mean and scale data included in pandas dataframe.
data_utils.discretize_dataframe(df, col[, ...])	Discretize values of given column in pandas dataframe.
data_utils.discretize_array(y[, bins])	Discretize values of given array.
data_utils.lookup(df, query, ret, keys[, match])	Dataframe lookup.
data_utils.load_X_data(train_file, test_file)	Load training and testing unlabeleled data from the files specified and construct corresponding training and testing pandas DataFrames.
data_utils.load_X_data2(train_file, test_file)	Load training and testing unlabeleled data from the files specified.
data_utils.load_Xy_one_hot_data(train_file, ...)	Load training and testing data from the files specified, with a column indicated to use as label.
data_utils.load_Xy_one_hot_data2(train_file, ...)	Load training and testing data from the files specified, with a column indicated to use as label.
data_utils.load_Xy_data2(train_file, test_file)	Load training and testing data from the files specified, with a column indicated to use as label.
data_utils.load_Xy_data_noheader(train_file, ...)	Load training and testing data from the files specified, with the first column to use as label.
data_utils.load_csv_data(train_path[, ...])	Load data from the files specified.