This repository contains all the necessary code and resources for analyzing, visualizing, and building machine learning models to predict ride prices for Uber and Lyft. The project focuses on extracting insights from the data, performing exploratory data analysis (EDA), and developing predictive models.
This work is based on the ipykernel
To successfully run the code in this repository, you need to set up your environment with the required dependencies. The dependencies are listed in the requirements.txt
file.
This dataset contains Boston Lyft & Uber prices from November to December 2018 and various columns including weather, vehicle type, distance traveled, pickup location and destination, etc.
Dataset: https://www.kaggle.com/brllrb/uber-and-lyft-dataset-boston-ma
git clone https://github.com/gyb357/Uber-Lyft.git
cd 'your repository directory'
pip install -r requirements.txt
Once you've installed all the libraries, you can run main.py sequentially. Some commented code can be uncommented and run.
The trained model can be tested in test.py.
This project was a collaborative effort among university teammates. Contributions included data preprocessing, feature engineering, model building, and presentation of results.