Datathons Solutions

Datathon – Sofia Air 2.0 – Solution – Predikt (Sofia Air 2.0) Github: scopyro

GitHub Accounts: KarimEid1, Marcel344, scopyro , @boudy87

Air pollution is quite a topic today. The municipality is investing a lot of effort and resources in order to measure the exact values of the gases and particulate matter in the air in order to identify its quality.

This is the next step towards the completion of a story and holistic view over the data-driven and explained the social topic of unveiling the secrets behind the information about Sofia Air Quality.

This research differentiates the main sources of pollution in Sofia and tries to predict what are the growing rate of this pollution in order to rise awareness against this danger and visualize, in numbers, its growth rate.

5
votes

3 thoughts on “Datathon – Sofia Air 2.0 – Solution – Predikt (Sofia Air 2.0) Github: scopyro

  1. 0
    votes

    Please, upload your .ipynb file here. Also write in the abstract of the article your github usernames. How can you evaluate with “randomly generated test set”? Give more details about this.
    Be more specific on the modeling part: why did you choose LSTM, what was the NN architecture and why … etc.

    1. 0
      votes

      Hello i uploaded the code in a zip file Archive however the code is in python language with .py extension since we used our own ide instead of colab. The Archive contains the data you provided both train and test and our results with the program

  2. 0
    votes

    Please use some visual aids to communicate state and process of building and evaluating models. Also, I need to agree with comments from Pepe for describing process and why you choosed some algorithms over others (which other algorithms you tried before selecting LTSM). As general comment, clearer visual communication can only help with your future work.

Leave a Reply