Machine Learning Models Created in Kaggle using Jupyter Notebooks and Gradio Interfaces.
Welcome to the ML-Kaggle repository. This project serves as a portfolio of various Machine Learning models developed, trained, and tested using Kaggle datasets. The repository includes exploratory data analysis (EDA), predictive modeling, and interactive web interfaces built with Gradio.
This repository contains several independent machine learning projects, each housed in its own directory:
Future Career Prediction/- Predictive modeling to forecast potential career paths based on user input and historical data.
House Price Prediction/- Regression models designed to estimate real estate prices using various property features.
Telco Customer Churn Classification/- A classification model that analyzes customer data to predict the likelihood of a user leaving the telecommunications service.
Video Games Sales with Rating/- Data analysis and prediction models focusing on global video game sales and their correlation with critic/user ratings.
Add-Ons-To-Workflow/- Supplementary scripts, utilities, and modular code blocks used to streamline the data preprocessing and model training pipelines.
- Programming Language: Python
- Environment: Jupyter Notebook / Kaggle Notebooks
- Data Manipulation: Pandas, NumPy
- Machine Learning: Scikit-Learn (and/or TensorFlow/PyTorch depending on the specific notebook)
- Data Visualization: Matplotlib, Seaborn
- Interactive UI: Gradio
Mohammed Faisal, GitHub: @mohamfaisal
Kaggle Profile Link: https://www.kaggle.com/mohammedfaisalferoz
LinkedIn Profile Link: www.linkedin.com/in/mohamfaisal
To run these notebooks and Gradio interfaces on your local machine, follow these steps:
git clone [https://github.com/mohamfaisal/ML-Kaggle.git](https://github.com/mohamfaisal/ML-Kaggle.git)
cd ML-Kaggle