Giter VIP home page Giter VIP logo

recommendation-system's Introduction

Recommendation-System

Contributions welcome Slack Contributor Covenant

Why this repo

This repo acts as a base for building the recommendation system for the auto generation of the layers as well as a hub to gather/scrape the data for the same. The models generated over here are used to better the model building system in the main repo of AutoDL.
The goal of this repo is to create a system that can automatically recommend a SOTA deep learning model catered to the personalized needs of the user.

How to run

  1. Fork and clone the repository to your local machine.
  2. Install the required dependencies.
  3. cd into the working directory and run the script.

HOW TO USE

Open a terminal in the working directory and run the following command

run startDate endDate absolutePathToDataFolder
  • startDate: start date of the data, format: yyyy-mm
  • endDate: end date of the data, format: yyyy-mm
  • absolutePathToDataFolder: The absolute path to the folder where you want the model files to be saved.

Contributing

Please take a look at our contributing guidelines if you're interested in helping!

recommendation-system's People

Contributors

adi10hero avatar aniket-508 avatar bamblebam avatar dependabot[bot] avatar vedantmahadik avatar

Stargazers

 avatar  avatar  avatar  avatar

Watchers

 avatar

Forkers

bamblebam

recommendation-system's Issues

The directory name in run.bat is wrong

Bug Report

The directory name in run.bat is wrong.

Current Behavior

Will give no such directory error.

Expected behavior/code

Should start the script.

⚙️ Environment

  • Python version(s):
    • good: [e.g. 3.8]
    • better: [3.8.6 - Clang 12.0.0 (clang-1200.0.32.27)]
  • OS: [e.g. Ubuntu 18.04, OSX 10.13.4, Windows 10]

Release drafter failing

Bug Report

Current Behavior

Expected behavior/code

⚙️ Environment

  • Python version(s):
    • good: [e.g. 3.8]
    • better: [3.8.6 - Clang 12.0.0 (clang-1200.0.32.27)]
  • OS: [e.g. Ubuntu 18.04, OSX 10.13.4, Windows 10]

Possible Solution

Additional context/Screenshots

Serve the API.

Feature Request

Is your feature request related to an existing Issue or a new implementation?

No.

Feature Description

Serve the API to call it in the main app.

Possible Solution

Additional context

Model API Creation

Feature Request

Is your feature request related to an existing Issue or a new implementation?

No

Feature Description

To create a backend using either Flask or FastAPI to host the model for use in the main app.

Add tests for scraping feature

Feature Request

Is your feature request related to an existing Issue or a new implementation?

No

Feature Description

Tests are important, let's have it now itself :)

Possible Solution

Writing test

Support for scraping .ipynb files

Feature Request

Is your feature request related to an existing Issue or a new implementation?

No

Feature Description

Add support for scraping sequential models from .ipynb files along side .py files to get even more models.

Possible Solution

Will need to check if github tags .ipynb files as tensorflow as well or could cause problems for getting the repository URL's through the github API. Needs to be tested

Github Actions for pytest

Feature Request

Is your feature request related to an existing Issue or a new implementation?

No.

Feature Description

Add github actions workflow to run the tests and generate a coverage report.

Add Multiprocessing for the scraping code.

Feature Request

Is your feature request related to an existing Issue or a new implementation?

No

Feature Description

Add multiprocessing in the scraping part to try and speed up the computation.

Possible Solution

Update the code mainly in the BFS part or separate the BFS and multiprocessing part into 2 separate code blocks. Will need to check if the BFS task can be split across multiple cores without premature termination for the former suggestion.

Basic data scraping pipeline

Feature Request

Basic data scraping pipeline for getting tensorflow sequential models.

Possible Solution

Use the github SDK to get the urls for the repositories tagged with the tensorflow label. The repositories may or may not have other labels which could give errors. Then parse the repositories through selenium to get the sequential model pickle files.

Additional context

Used as a data scraping script for collecting data for the layer recommendation model.

Basic Recommendation System model

Feature Request

Is your feature request related to an existing Issue or a new implementation?

No

Feature Description

A basic Linear Classification model which will act as a V1 until it is replaced with a better one, trained on more data. Will be used to create the backend Model API and integration with the main app.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.