Predictive Analysis of Taxi Cab Prices and Route Times
------------------------------------------------------


Introduction

Welcome to our project on predicting taxi cab prices and route times. Designed to provide quick and accurate estimates for cab fares and journey durations, our tool leverages a dataset obtained through web scraping. It's user-friendly and compatible with both Jupyter Notebook and Google Colab, hosted using Streamlit.

Features of our project:
* Price Prediction: Accurately estimate taxi fares using data-driven algorithms.
* Route Time Estimation: Calculate expected journey durations.
* Custom Dataset Utilization: Harness the power of a specially curated dataset for precise predictions.
* User-Friendly Design: Straightforward and easy-to-follow code blocks.


Installation and Setup

1. Clone the Repository: Start by cloning the project to your local machine.
2. Install Dependencies: Install necessary libraries as listed in requirements.txt.
3. Launch Jupyter/Colab: Ensure you have Jupyter Notebook or Google Colab for executing the notebook.


How to Use

1. Open the Notebook: Access "Cab Dataset 2.0.ipynb" in your preferred environment.
2. Execute the Cells: Run the cells sequentially, beginning with imports and proceeding through data processing to predictions.
3. Enter Journey Details: Input your specific journey details in designated cells to receive tailored predictions.


Data Source

We used a custom web-scraped dataset. An alternative dataset can also be used, ensuring compatibility with our preprocessing steps.


Contributing

Interested in contributing? We welcome your insights and improvements.
Reach out to us on our LinkedIn!


Contact Information

For queries or collaboration requests, please reach out to us on LinkedIn.
(Provided with our course descriptions on the class website - https://ai3011.plaksha.edu.in/projects.html)

--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------


Streamlit Application for Taxi Cab Price and Route Time Prediction
------------------------------------------------------------------


Overview

Our project now includes an interactive web application built with Streamlit, enhancing the user experience in predicting taxi cab prices and route times. This app, named "CabAlytics", provides a dynamic interface where users can select cab types, input journey details, and receive instant predictions backed by our data-driven models.


Setting Up and Running the Application

1. Prerequisites: Ensure all dependencies listed in requirements.txt are installed. Streamlit should be among these dependencies.
2. Starting the Application: Navigate to the project directory in your terminal and run the command streamlit run app.py. This will launch the application in your default web browser.
3. Required Files: Ensure that the files pipe.pkl, df.pkl, and pipe_route.pkl are in the same directory as app.py for the app to function correctly.


User Interface and Interaction

- Cab Type Selection: At the start, choose the type of cab for which you want predictions.
- Input Parameters: Enter relevant journey details like origin, destination, time of day, etc.
- Visualization: The app uses Plotly to visualize the route and estimated times and costs.
- Prediction Results: Upon submission, the app provides an estimated cab fare and route time based on your inputs.


Additional Notes

The application is best viewed on a desktop browser for optimal layout and visualization experience.
If you encounter any issues while running the application, ensure that all dependencies are correctly installed and that the Streamlit version is compatible with the project.
For advanced users, the app's code can be modified to customize predictions or visualizations as per specific requirements.


Contributing

Interested in contributing? We welcome your insights and improvements.
Reach out to us on our LinkedIn!


Contact Information

For queries or collaboration requests, please reach out to us on LinkedIn.
(Provided with our course descriptions on the class website - https://ai3011.plaksha.edu.in/projects.html)

--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
