# 🕵️ Introduction

![](https://storage.googleapis.com/kaggle-competitions/kaggle/4104/media/retina.jpg)

Test your vision of ML by this vision problem of Diabetes. Diabetic retinopathy is the leading cause of blindness in the working-age population of the developed world. 
Here is a problem for you to classify the patient retina as being diabetic or not diabetic taking into consideration the available features of dataset. To know more about diabetic retinopathy click [here](https://www.aao.org/eye-health/diseases/what-is-diabetic-retinopathy).
Understand with code! Here is [getting started code](https://discourse.aicrowd.com/t/baseline-mnist/2757) for you.😄


# 💾 Dataset

This dataset contains features extracted from the Messidor image set to predict whether an image contains signs of diabetic retinopathy or not. There are total of `20` attributes to this dataset, out of which first `19` attributes represents a descriptive features extracted from the image set. Last attribute `label` is `1` if image contains signs of Diabetic Retinopathy and `0` if no signs of Diabetic Retinopathy.
For details about attributes visit [here!](https://gitlab.aicrowd.com/aicrowd/practice-challenges/aicrowd_DIBRD_challenge/blob/master/dataset_info.txt).


## 📁 Files

  - `./data/train.csv` - (`920` samples) File that should be used for training and validation purpose by the user.
  - `./data/test.csv` - (`230` samples) File that will be used for actual evaluation for the leaderboard score.

# 🚀 Submission

- Prepare a csv containing header as `label` and predicted value as digit `0` or `1` with name as `submission.csv`.
- Sample submission format available at `./data/sample_submission.csv`.   

**Make your first submission [here](https://www.aicrowd.com/challenges/dibrd-predict-diabetic-retinopathy/submissions/new)  🚀 !!**

# 🖊 Evaluation Criteria

During evaluation [F1 score](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.f1_score.html) and [Log Loss](http://wiki.fast.ai/index.php/Log_Loss) will be used to test the efficiency of the model where,

<img src="https://latex.codecogs.com/gif.latex?%24%24F1%20%3D%20%7Bprecision%20*%20recall%20%5Cover%20precision%20&plus;%20recall%7D%24%24"/> </br>

<img src="http://latex.codecogs.com/gif.latex?%24%24%20Log%20Loss%20%3D%20-log%20P%28yt%7Cyp%29%20%3D%20-%28yt%20log%28yp%29%20&plus;%20%281%20-%20yt%29%20log%281%20-%20yp%29%29%20%24%24"/>


# 🔗 Links
* 💪 Challenge Page : https://www.aicrowd.com/challenges/dibrd-predict-diabetic-retinopathy
* 🗣️ Discussion Forum : https://www.aicrowd.com/challenges/dibrd-predict-diabetic-retinopathy/discussion
* 🏆 leaderboard : https://www.aicrowd.com/challenges/dibrd-predict-diabetic-retinopathy/leaderboards

# 📱 Contact
- [Shubham Sharma](shubham@ext.aicrowd.com)

# 📚 References

* References:
  - Dr. Balint Antal, Department of Computer Graphics and Image Processing
    Faculty of Informatics, University of Debrecen, 4010, Debrecen, POB 12, Hungary, antal.balint@inf.unideb.hu

  - Dr. Andras Hajdu, Department of Computer Graphics and Image Processing
    Faculty of Informatics, University of Debrecen, 4010, Debrecen, POB 12, Hungary, hajdu.andras@inf.unideb.hu
     
  - Dua, D. and Graff, C. (2019). UCI Machine Learning  Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of   Information and Computer Science.
  - [Image source](https://www.kaggle.com/c/diabetic-retinopathy-detection)