DATA_UTILS#
|
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. |
|
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. |
|
Scale data included in numpy array. |
|
Impute missing values with mean and scale data included in numpy array. |
Impute missing values with mean and scale data included in pandas dataframe. |
|
|
Discretize values of given column in pandas dataframe. |
|
Discretize values of given array. |
|
Dataframe lookup. |
|
Load training and testing unlabeleled data from the files specified and construct corresponding training and testing pandas DataFrames. |
|
Load training and testing unlabeleled data from the files specified. |
|
Load training and testing data from the files specified, with a column indicated to use as label. |
|
Load training and testing data from the files specified, with a column indicated to use as label. |
|
Load training and testing data from the files specified, with a column indicated to use as label. |
|
Load training and testing data from the files specified, with the first column to use as label. |
|
Load data from the files specified. |