ANTAVIRA FAQ

Where to begin?

After logging into your Personal Account, you need to create a dataset file with variables and a dataset file with targets. Click on the “Create Project” button, fill out the “New Project” form by uploading your dataset file with variables and your dataset file with targets. Don’t forget to specify the column delimiter symbol, decimal separator, and language encoding. Click the “Save” button.

Next, click on your project in the project list to open the list of project counts, where the project formation status will be displayed. This indicates the process of data uploading to the server. This process will take some time. The project creation process is considered complete when the number of observations, variables, targets, and the “New Count” button appear. The displayed numbers of observations, variables, and targets should match the numbers in the uploaded dataset files.

To start the count, click on the “New Count” button, fill out the form, specifying all the necessary settings, and click the “Create” button. The created count will appear in your project account. To view the modeling results, click on the “Count Results” button next to the name of count.

What file type is suitable?

To be uploaded to the platform, a dataset file with variables and a dataset file with targets must be created in the cvs format with column separators convenient for you, but it is better to use a comma “,” or a semicolon “;”.

If the datasets files are large, zip them.

How many columns can my dataset have?

There are NO restrictions on the number of columns in the variable dataset file and the target dataset file. The first column of both files contains a unique index or observation number. Duplicating indexes is NOT allowed. All other columns represent variables or targets in the case of the target dataset file.

Is there a character limit for columns in my dataset?

There are NO restrictions on the number of characters in columns in the variable dataset file and the target dataset file.

Is there a limit on the number of rows?

There are NO restrictions on the number of rows in the variable dataset file and the target dataset file.

What date and time formats does machine learning support?

Currently, the platform does not support variables with date or time format values.

Are there any restrictions on the types of characters that my data can include?

Variable values can only be numeric or string. Target values can be binary (0 or 1) or from 0 to 1 (numeric, separated by dot “.”).

Is there a limit on the size of my dataset?

There are NO restrictions on the size of the variable dataset file or the target dataset file. ANTAVIRA can handle heavy workloads, even when processing datasets over 20 GB.

If the datasets files are large, zip them.