krishnaik06krishnaik06
300

Deployment Flask

screenshot of Deployment Flask

Github

Overview

Deploying machine learning models has become a crucial aspect of data science and software development. The ML-Model-Flask-Deployment project serves as a straightforward demonstration of how to deploy a machine learning model using Flask API. This setup allows users to input data through a friendly graphical user interface (GUI) or directly via API calls, resulting in accurate salary predictions based on employee details.

This project utilizes popular libraries such as Scikit-learn for model training and Flask for creating the API infrastructure. Users can easily navigate the deployment process and interact with the application, making it an excellent choice for those looking to enhance their understanding of machine learning model deployment in a production environment.

Features

  • Model Training: The project includes a model.py file that trains a machine learning model to predict employee salaries based on the provided training data from a 'hiring.csv' file.

  • Flask API Integration: The app.py file houses the Flask APIs, allowing seamless reception of employee details and computing of predicted salaries based on user input.

  • User-Friendly Interface: A dedicated templates folder includes HTML files that offer an intuitive form for users to enter employee details and view predicted salary results easily.

  • Serialized Model Storage: The trained model is serialized and saved as a model.pkl file, facilitating easy access and reusability without needing to retrain the model each time.

  • Direct API Interaction: The project supports sending POST requests directly to the Flask API through a dedicated request.py file, enabling straightforward API testing and interaction from any Python environment.

  • Local Development Environment: By running the Flask app on a local server, users can develop and test their applications effectively on their local machines before production deployment.

  • Dynamic Predictions: Users can input valid numerical values in the interface and click "Predict" to instantly view the predicted salary, showcasing the model's practical application.