Taxi Tip Prediction using Scikit-Learn and Snap ML

Introduction

This project focuses on predicting taxi tip amounts using machine learning models, specifically Decision Tree Regressors, implemented with Scikit-Learn and Snap ML. The dataset comprises information about taxi trips in New York City, and the goal is to create an accurate model to predict tip amounts.

💻 Tech Stack:

Tools

• Python
• Jupyter Notebooks

Libraries

• NumPy
• Pandas
• Matplotlib
• Scikit-Learn
• Snap ML

Key Contributions

• Data analysis and cleaning to prepare the dataset for machine learning.
• Implementation of Decision Tree Regressors with both Scikit-Learn and Snap ML.
• Comparison of training speed and model performance between Scikit-Learn and Snap ML.

Key Skills Demonstrated

• Data preprocessing techniques.
• Implementation of machine learning models for regression tasks.
• Evaluation and comparison of model performance.
• Efficient utilization of Snap ML for accelerated model training.

Achievements

• Successfully built and trained regression models to predict taxi tip amounts.
• Demonstrated the speedup achieved using Snap ML compared to Scikit-Learn.

Why this Repository

This repository serves as a practical example of implementing machine learning models for regression tasks in predicting taxi tip amounts. It showcases the use of both traditional machine learning libraries (Scikit-Learn) and accelerated libraries (Snap ML) to achieve efficient model training. The comparison provides insights into the advantages of utilizing high-performance libraries for machine learning tasks.

Feel free to explore, contribute, and use this project as a reference for similar regression problems!

Connect with me: