🚨 Final Leaderboard (for real) + Community Contribution Prize

Congratulations to all the winners!! Hope to see you all in the next competition!!

View post 5

Final leaderboard not visible

After waiting for the whole day:

View post 4

Final leaderboard not visible

View post 7

Final leaderboard not visible

Thanks for the info, can’t wait to see the final leaderboard and winners’ solutions!!

View post 4

Random variable(s)

Hello @demarsylvain,
TLDR: My experiments were somewhat different than yours but the conclusion is similar that data contains some noise/random variables which plays a big role in predictions.
I first tried with raw features and minimal pre-processing, then with heavy feature engineering (around 8-10 features were added), and finally experimented with removing unnecessary features. The results were shockingly similar and unintuitive to me. My raw features model performs almost similar to the heavy feature engineered model and minimal features model. The same data with slight changes leads to a drastic difference in log loss (kinda butterfly effect), therefore I think it’s the case of random variable majorly impacting the results. I hope this helps.

View post 2

That golden feature... were we supposed to have it?

Hello @michael_bordeleau,
I think the feature is used to extract training labels, for example, it might be possible that the 0-5 scale feature is then scaled accordingly to 0-2 ( Normal, Pre-Alzheimers, post-Alzheimers) with some other data to get labels. It may be one of the reasons, i.e, fear of data leak in this competition. This is still my guess, I am not sure. Also thanks for your contributions, I learned a lot from your posts.
Jyot

View post 2

Submission time

Hello @HarryDing, To install any browser, you have to upload the corresponding installer (in Windows VM.exe) from your local computer. I installed firefox this way, also make sure that you upload the complete installer .exe which works offline not the installer that downloads the files from the internet while executing. I spent a lot of time trying to install Firefox, hope this helps.

View post 2

Submission time

Hello @HarryDing, this has happened to me once in Windows VM, I found that simply rerun all the cells after reconnecting to that notebook kernel will resolve this issue. Alternatively, you can restart the jupyter-lab instance.

View post 1

Couldn't decode response from AIcrowd servers

This thread is funny! I think we need a dedicated meme thread for the competition! All the best!!

View post 1

Common issues for Windows users

Hello @jyotish, actually I tried that earlier, and it doesn’t work for me. I have to open new prompt and set up proxies. Then after I can install using pip install x . I found that it is setting temporary proxies for one session I guess.

View post 1

Common issues for Windows users

Thanks, @jyotish and @nrad for helping me. It worked and I was able to successfully run the magic command. I am curious that I need to set all 3 proxies every time I open a new Anaconda Prompt. Any suggestion on how I can set universal or global proxies for that?

View post 1

Common issues for Windows users

Hello @nrad, first of all, thank you for all your efforts and hard work. I have completed the windows VM setup and got the starter notebook. However I am stuck on the %load_ext aicrowd.magic cell when tried to run, it generates error like this:
Import Error: failed to initialize: Bad git executable.
To check the issue, I tried running the pip command on the Anaconda prompt and there I saw that the pip was working there too. I have checked my proxy internet which is working fine as I was able to open pypi.python.org but in jupyter-notebook or anaconda prompt, I couldn’t make the second command work. Also, I tried restarting VM and ensuring that the starter script completes execution. It would be helpful if you can guide me on the issue.
Thanks!

View post 1