This repository contains the code for an end-to-end machine learning project. Below are the steps to set up and run the project.
conda create -p venv python==3.8
conda activate venv/
Create the file by right-clicking and include the venv directory in it.
pip install -r requirements.txt
This file is used to install the entire project as a package. Additionally, it contains a function to read the packages from requirements.txt.
Include exception.py, logger.py, and utils.py files in this folder. Make this folder a package by including an init.py file. The src folder will also include another folder named components.
Include data_ingestion.py, data_transformation.py, model_trainer.py, and an init.py file. These components are interconnected.
Create two Python files, training_pipeline.py and prediction_pipeline.py, with an init.py file.
Create a folder named data and include the dataset. Additionally, create an EDA.ipynb file to perform exploratory data analysis and model training.ipynb.
This file will contain the Flask application for serving the machine learning model.
Create a folder named templates to store HTML templates for the Flask application.