## What am I predicting?  

You are predicting the binary `target` associated with each row, without overfitting to the minimal set of training examples provided.

## Files

*   **train.csv** - the training set. 250 rows.
*   **test.csv** - the test set. 19,750 rows.
*   **sample_submission.csv** - a sample submission file in the correct format

## Columns

*   `id`- sample id
*   `target`- a binary target of mysterious origin.
*   `0-299`- continuous variables.