Each data set (containing one or more files) is uploadable through the project page.
Training files are to be uploaded first.
The central table is to be explicitly pointed out by the user selecting the file containing the outcome column.
N.B.: Files have to be encoded in UTF-8 or ASCII.
In a project, the settings are the same in all files.
A format is automatically detected, the user then update the settings according to its file format.
The field separator can be chosen among pipe (|), coma (,), semicolon (;), or tabulation (\t).
Each entity of the training data set has to be identified by a unique key. The name of this key field has to be specified as PredicSis.ai, and chosen among the list of the central file columns.
In the central files, the outcome feature, for each entity, has to be present and selected from the list the list of the central file columns.
N.B.: As the key and outcome features have to be present in the central files, each file should containat least 2 columns.
The report, and later the scoring, will be dependent on the user’s choice of the main modality. This main modality has, of course, to be present in the outcome column.
N.B.: At least 2 modalities have to be present in the outcome field. This means that each file should contain at least 3 lines, one for the header, and two for two distinct modalities.
Adding a test set.
A click on the button ADD TEST SETS sends to the test sets upload page.
Test files, formatted the same way train files are, can be uploaded by browsing the file system.
- Headers are compulsory in all files, to identify the features.
- Fields can be quoted by double quote (") as long as they do not contain a carriage return.
- Files should not contain back ticks (`).