Commit 1b61cbb2 authored by sanjay_pokkali's avatar sanjay_pokkali
Browse files

First commit

parents
# To be filled in later with an consistent contribution guide
- Q : Who writes that ?
\ No newline at end of file
>**🛠 Contribute:** Found a typo? Or any other change in the description that you would like to see? Please consider sending us a pull request in the [public repo of the challenge here](https://gitlab.aicrowd.com/aicrowd/practice-challenges/aicrowd_ADCLK_challenge).
# 🕵️ Introduction
**Instructions**
* Introduce the challenge here. Include :
- A picture ( Save the picture in the images folder)
- A catchy one-liner introducing the problem
- a link to the getting started code
- Do not remove the contribution line.
__For example, this is how we write this section for the MNIST challenge__
![](https://upload.wikimedia.org/wikipedia/commons/2/27/MnistExamples.png)
Get back to Kindergarten. Remember how learning numbers was fun? We give you handwritten digits and ask to identify the number.
</br>Understand with code! Here is [`getting started code`](https://discourse.aicrowd.com/t/baseline-mnist/2757) for you.`😄`
# 💾 Dataset
**Instructions**
* Write something about the dataset here :
- The following question should be answered from the dataset description
- What the dataset is about?
- What are the attributes of the dataset?
- How many attributes are there in the dataset?
- What is the data type of the attributes?
- What are the classes that need to be predicted?
- Formatting Instructions
- All the numbers and keywords should be highlighted.
- The words used in the description should be simple to understand. Do not use terms specific of any domain. If it cannot be avoided add a link to the meaning or Wikipedia link for the term.
- If the number of attributes is too large put it in a separate file named "dataset_info.txt" in the same directory.
__For example, this is how we write this section for the MNIST challenge__
The MNIST database (Modified National Institute of Standards and Technology database) is a large database of handwritten digits that is commonly used for training various image processing systems. The database is also widely used for training and testing in the field of machine learning. Each image is `28` pixels in height and `28` pixels in width, for a total of `784` pixels in total. Each pixel has a single pixel-value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel-value is an integer between `0` and `255`, inclusive.
For simplification, images have been stored in the CSV file. The `train.csv` has `785` columns, the first column is the label and the rest `784` contain the pixel value of the associated image pixel.
# 📁 Files
**Instructions**
* Describe the file structure for this challenge :
- All the dataset files should go inside the data folder in this repo.
- Change the number of samples according to your dataset files.
__For example, this is how we write this section for the MNIST challenge__
Following files are available in the `resources` section:
- `./data/train.csv` - (`60000` samples) File that should be used for training and validation purposes by the user.
- `./data/test.csv` - (`10000` samples) File that will be used for actual evaluation for the leaderboard score.
# 🚀 Submission
**Instructions**
* Submission instructions :
- Replace the header and the range of predicted value below according to the dataset.
__For example, this is how we write this section for the MNIST challenge__
- Prepare a CSV containing header as `label` and predicted value as digit `[0-9]` with name as `submission.csv`.
- Sample submission format available at `./data/sample_submission.csv`.
**Make your first submission [here](https://www.aicrowd.com/challenges/adclk-predict-if-an-ad-will-be-clicked/submissions/new) 🚀 !!**
# 🖊 Evaluation Criteria
**Instructions**
* Description of the evaluation criteria :
- There should be 2 evaluation criteria.
- Include links to Evaluation metric page on Scikit Learn, if it exists.
- Add an image of the mathematical formula of the evaluation criteria. You can use [this link](https://www.mathjax.org/#demo) to generate the image.
__For example, this is how we write this section for the MNIST challenge__
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?F1%20%3D%202%20*%20%5Cfrac%7Bprecision*recall%7D%7Bprecision&plus;recall%7D"/> </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"/>
<img src="https://latex.codecogs.com/gif.latex?%24%24%20MAE%28y%2C%5Chat%7By%7D%29%20%3D%20%5Cfrac%7B1%7D%7Bm%7D%5Csum_%7Bi%3D1%7D%5E%7Bn%7D%7Cy_i%20-%20%5Chat%7By_i%7D%7C%20%24%24">
<img src="https://latex.codecogs.com/gif.latex?%24%24%20RMSE%20%3D%20%5Csqrt%7B%20%5Cfrac%7B1%7D%7BN%7D%5Csum_%7Bi%3D1%7D%5E%7BN%7D%20%28x_%7Bi%7D%29%5E2%7D%20%24%24">
# 🔗 Links
* 💪 Challenge Page: [https://www.aicrowd.com/challenges/adclk-predict-if-an-ad-will-be-clicked](https://www.aicrowd.com/challenges/adclk-predict-if-an-ad-will-be-clicked)
* 🗣️ Discussion Forum: [https://www.aicrowd.com/challenges/adclk-predict-if-an-ad-will-be-clicked/discussion](https://www.aicrowd.com/challenges/adclk-predict-if-an-ad-will-be-clicked/discussion)
* 🏆 Leaderboard: [https://www.aicrowd.com/challenges/adclk-predict-if-an-ad-will-be-clicked/leaderboards](https://www.aicrowd.com/challenges/adclk-predict-if-an-ad-will-be-clicked/leaderboards)
# 📱 Contact
- Sanjay Pokkali
# 📚 References
**Instructions**
* References:
- Add the source from where the dataset was taken.
- Add the UCI citation policy if the dataset is from UCI.
- Add the source of the image used in the introduction.
- Any additional acknowledgments asked by the source.
\ No newline at end of file
---
challenge_name: aicrowd_ADCLK_challenge
evaluation_repo: git@gitlab.aicrowd.com:aicrowd/practice-challenges/aicrowd_ADCLK_challenge_evaluator.git
data_url: https://s3.wasabisys.com/aicrowd-practice-challenges/public/ADCLK/v0.1/
official_baseline: ADCLK_baseline.ipynb
authors:
- name: Sanjay Pokkali
email: sanjay@ext.aicrowd.com
version: '0.1'
This diff is collapsed.
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment