The Driver Acceptance Prediction App is a web application that utilizes machine learning models to predict whether the driver will accept or not accept the ride request given different data. The model is trained on ride-sharing record data and it has preprocessed to ensure better predictions. The app has been deployed on Streamlite.
Note: Deployed version of the web pages Here
-
Data input: Users can input the data for prediction as there fields on the page indicates.
-
Prediction: After input all necessary data, users can click the "Predict" button to get the model's prediction regarding the acceptance status.
This project has used the some packages such as numpy, tensorflow, which have to be installed to run this web app locally present in requirements.txt file.
To run the project locally, there is a need to have Visual Studio Code (vs code) installed on your PC:
- VS Code: It is a source-code editor made by Microsoft with the Electron Framework, for Windows, Linux, and macOS.
- Clone the project
git clone https://github.com/UmuhireJessie/acceptance-prediction.git
- Open the project with vs code
cd acceptance-prediction
code .- Install the required dependencies
pip install -r requirements.txt- Run the project
streamlit run app.py- Use the link printed in the terminal to visualise the app. (Usually
http://127.0.0.1:8501/)
- driver_acceptance_model.h5: The main driver acceptance prediction model trained on ride-sharing records data.
- scaler.pkl: The scaler used for standardizing features during inference.
- Jessie Umuhire Umutesi