Graphical user interface based feature extraction application for machine learning and cognitive models

A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to implement a feature extraction tool for graphical user interface based feature extraction, wherein the computer readable program causes the computing device to:

• receive, by the feature extraction tool, selection by a user of a dataset from which features are to be extracted for a machine learning model;
• load, by the feature extraction tool, a feature template associated with the selected dataset, wherein the feature template includes a plurality of feature definitions, wherein each feature definition comprises a data structure that defines a name, a type, at least one parameter, and a description for a corresponding feature that may be extracted;
• generate, by the feature extraction tool, a graphical user interface that allows the user to add features from the plurality of features to a feature file;
• present the graphical user interface to the user and receive user selection of at least one feature to be added to the feature file;
• generate, by the feature extraction tool, the feature file based on the user selection of the at least one feature, wherein the feature file comprises a data structure that lists and defines the selected at least one feature to be extracted for the machine learning model;
• perform, by the feature extraction tool, feature extraction against the selected dataset in accordance with the feature file;
• and
• generate, by the feature extraction tool, a feature matrix for the machine learning model containing results of the feature extraction, wherein the feature matrix comprises a data structure that contains values for the selected at least one feature in the feature file that were extracted from the selected dataset.

An apparatus comprising:

• a processor;
• and
• a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to implement a feature extraction tool for graphical user interface based feature extraction, wherein the instructions cause the processor to:
• receive, by the feature extraction tool, selection by a user of a dataset from which features are to be extracted for a machine learning model;
• load, by the feature extraction tool, a feature template associated with the selected dataset, wherein the feature template includes a plurality of feature definitions, wherein each feature definition comprises a data structure that defines a name, a type, at least one parameter, and a description for a corresponding feature that may be extracted;
• generate, by the feature extraction tool, a graphical user interface that allows the user to add features from the plurality of features to a feature file;
• present the graphical user interface to the user and receive user selection of at least one feature to be added to the feature file;
• generate, by the feature extraction tool, the feature file based on the user selection of the at least one feature, wherein the feature file comprises a data structure that lists and defines the selected at least one feature to be extracted for the machine learning model;
• perform, by the feature extraction tool, feature extraction against the selected dataset in accordance with the feature file;
• and
• generate, by the feature extraction tool, a feature matrix for the machine learning model containing results of the feature extraction, wherein the feature matrix comprises a data structure that contains values for the selected at least one feature in the feature file that were extracted from the selected dataset.