Generation of a dataset in the format of a machine learning framework

A system, comprising:

• a memory;
• and
• a processor coupled to the memory, wherein the processor performs operations, the operations performed by the processor comprising:
• storing, in a capacity storage tier, a dataset formatted in a first format, wherein the dataset formatted in the first format includes at least a plurality of data elements that comprise data;
• selecting, via a computational device, a machine learning framework, wherein the machine learning framework operates on datasets formatted in a second format that is different from the first format;
• and
• converting, via the computational device, the dataset from the first format to the second format and generating symbolic links or hard links from the converted dataset formatted in the second format to the plurality of data elements of the dataset formatted in the first format to avoid creating additional copies of the plurality of data elements, wherein the dataset formatted in the first format is generated from search results, wherein a directory structure for the machine learning framework is automatically created in a performance storage tier and the symbolic links or the hard links to the plurality of data elements of the dataset formatted in the first format and generated from the search results are created in one or more directories, wherein files or objects of the dataset are copied from the capacity storage tier into the performance storage tier, and wherein as the files or the objects of the dataset are copied into the performance storage tier, the dataset is registered with a workflow support application based on the selected machine language framework and a workflow to train a machine learning model is automatically invoked while the dataset is being prefetched from the capacity storage tier to the performance storage tier.

A computer program product comprising a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code configured to perform operations, the operations comprising:

• storing, in a capacity storage tier, a dataset formatted in a first format, wherein the dataset formatted in the first format includes at least a plurality of data elements that comprise data;
• selecting, via a computational device, a machine learning framework, wherein the machine learning framework operates on datasets formatted in a second format that is different from the first format;
• and
• converting, via the computational device, the dataset from the first format to the second format and generating symbolic links or hard links from the converted dataset formatted in the second format to the plurality of data elements of the dataset formatted in the first format to avoid creating additional copies of the plurality of data elements, wherein the dataset formatted in the first format is generated from search results, wherein a directory structure for the machine learning framework is automatically created in a performance storage tier and the symbolic links or the hard links to the plurality of data elements of the dataset formatted in the first format and generated from the search results are created in one or more directories, wherein files or objects of the dataset are copied from the capacity storage tier into the performance storage tier, and wherein as the files or the objects of the dataset are copied into the performance storage tier, the dataset is registered with a workflow support application based on the selected machine language framework and a workflow to train a machine learning model is automatically invoked while the dataset is being prefetched from the capacity storage tier to the performance storage tier.