Add a notebook explaining the models you used, explain the math behind it and compare them

Data Engineers will handle this task

Create documentation for back-end

Add the plots of EDA to notebooks

Where it gives a 403 Error when trying to make a GET request.

Potential solution:

• Including Headers

Setup the deployment and CI/CD on Microsoft Azure portal and Azure DevOps, waiting on finalisation of front end for testing and to link w/ git repo. Deployment failed as of right now.

I worked on a workflow that automates the preprocessing of the data everytime new data is added however I could not achieve that due to the user items dataset being too big to upload on github.

• Model selector in frontend
• Chatbot (making api call to the openai gpt model)
• Use a database to store our data (MongoDB).

• Do a release with release notes following Recommenders or PyTorch.
• Create a MLOps procedure with tests and GitHub actions. Every time a PR is raised, all the tests need to pass. Follow https://github.com/miguelgfierro/project_template
• Create a library with the python files that are called by the notebooks, following https://github.com/miguelgfierro/project_template
• Add the plots of EDA to notebooks
• Add a notebook explaining the models you used, explain the math behind it and compare them
• Use a PR per feature instead of a massive PR. See #4 (comment)
• If you want multiple people to work on the same branch, do it via PRs. See #4 (comment)
• For each of these pieces of feedback, you can create an issue, then a branch, fix it, do a PR, let other person in the team review, and then merge.
• Some of the commits are not linked to the GitHub account, like the work of Tomas. Make sure you configure your git client. You can follow this guide: https://github.com/Microsoft/Recommenders/wiki/How-to-add-your-name-as-a-contributor-to-the-repo#make-sure-that-your-github-user-is-setup-correctly

When trying to model with the Singular Value Decomposition, I seem to always get a precision score of 0.

Here's the code;

`import numpy as np

Number of latent factors

k = 100

Perform SVD

U, sigma, Vt = svds(train_sparse, k=k)

Convert sigma into a diagonal matrix

sigma = np.diag(sigma)

Reconstruct the interaction matrix

predicted_interactions = np.dot(np.dot(U, sigma), Vt)

Create an inverse mapping from game indices to game IDs

idx_to_game_id = {idx: game_id for idx, game_id in enumerate(games_dict.keys())}
game_id_to_idx = {game_id: idx for idx, game_id in enumerate(games_dict.keys())}

Create a mapping from user IDs to user indices

user_id_to_idx = {user_id: idx for idx, user_id in enumerate(user_dict.keys())}`

`

Evaluation function (Precision@K)

def precision_at_k(predicted_interactions, test_interactions, k):
precisions = []
for user_id in user_dict.keys():
# Get the user index for the current user ID
user_idx = user_id_to_idx[user_id]

    # Get the top K predicted game indices for each user
    top_k_indices = np.argsort(predicted_interactions[user_idx])[-k:]
    
    # Get the game IDs for the top K predicted games using the inverse mapping
    top_k_games = [idx_to_game_id[i] for i in top_k_indices]
    
    # Count how many of these games are in the test set
    relevant_games = 0
    for game_id in top_k_games:
        game_idx = game_id_to_idx[game_id]
        if test_interactions[user_idx, game_idx] > 0:
            relevant_games += 1
            
    # Calculate the precision for the current user and store it
    precision = relevant_games / k
    precisions.append(precision)

# Calculate the average precision across all users
avg_precision = np.mean(precisions)
return avg_precision

Evaluate the model using Precision@K

for k in range(1, 21):
precision_at_k_value = precision_at_k(predicted_interactions, test_sparse, k)
print(f"Precision@{k}: {precision_at_k_value}")
`

I see contributions from @HenningGC @JPBP22 and @AEscF, however, where are the github of the others and where are their contributions?

Create a library with the python files that are called by the notebooks

ML-Ops, Data Scientists, and ML engineer will handle this task