The evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using precision and recall. 

Precision is the ratio of true positives TP to all predicted positives TP + FP. Recall is the ratio of true positives TP to all actual positives TP + FN. The F1 score is given by:

F1 = 2 p r / (p + r), where p = TP / (TP + FP), r = TP / (TP + FN).

The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.

## Submission Format

**For every paper excerpt in the dataset**, submission files should contain two columns: `id` and `fake`. `id` is a list of test set excerpt IDs and can be copied from the provided **sample_submission.csv**. `fake` is a binary vector, accepted values are 0 and 1. 

The file should contain a header and have the following format:
```
id,fake
0,1
3,0
```

The submission file can be prepared the following way
```
import pandas as df
subm_df = pd.read_csv(PATH_TO_SAMPLE_SUB.csv, index_col='id')
subm_df['fake'] = 1 # change to an array with your model predictions
subm_df.to_csv('subm.csv')
```