The train.csv contains the comment id, comment and a column positive, which highlights whether the statement is positive (1) or not (0).
test.csv follows the same structure.

## Files

*   **Dataset_Kaggle.csv** - the training set
*   **Test_upload.csv** - the test set
*   **Sample Submission.csv** - a sample submission file in the correct format

## Columns

*   `Id` - comment id.
*   `Comment` - The comment to be analysed.
*   `Positive` - The comment is positive or not.