Snack-Recommendation-System
Team Information
Name | NEU ID |
---|---|
Shubham Mahajan | 001314273 |
Gauri Verma | 001306996 |
Anurag Rachcha | 001375637 |
Getting Started
To setup on your local machine:
-
Install Anaconda with Python >= 3.6. Miniconda is a quick way to get started.
-
Clone the repository
git clone https://github.com/shubham414/Snack-Recommendation-System.git
- Run the generate conda file script to create a conda environment: (This is for a basic python environment)
cd Snack-Recommendation-System
python tools/generate_conda_file.py
conda env create -f reco_base.yaml
- Activate the conda environment and register it with Jupyter:
conda activate reco_base
python -m ipykernel install --user --name reco_base --display-name "Python (reco)"
- Start the Jupyter notebook server
jupyter notebook
- Run the Fastai Snack Recommendation and xDeepFM Snack Recommendation notebook under the
00_quick_start
folder. Make sure to change the kernel to "Python (reco)".
To run the Fast API :
1.Execute following command on terminal and run :
pip install fastapi
Go to path - 00_quick_start from git repository and run :
uvicorn FastAIfastapi:app --reload
Note - FastAIfastapi is the .py file for FastAI algorithm's FastAPI. To run FastAPI for xDeepFM put xdeepfmfastapi befor :app in above command and run
The API will be running on localhost port mentioned on the terminal.
To run the Streamlit app :
1.Execute following command on terminal and run :
pip install streamlit
Go to path - 00_quick_start from git repository and run :
streamlit run Streamlitapp.py
The app will be running on localhost port mentioned on the terminal.