文件列表:

dataset/
models/
notebooks/
src/
streamlit_app/
app.py
requirements.txt

# Integrated Car Care Platform The Integrated Car Care Platform is a comprehensive repository that provides a suite of tools and functionalities for effective car maintenance, analysis, and prediction. This platform encompasses various modules designed to address specific aspects of vehicle care and management. ## Purpose The primary goal of this project is to offer an all-in-one solution for car owners, mechanics, and enthusiasts to handle car maintenance effectively. From predictive analysis to image-based brand classification and cost prediction, this platform aims to simplify car management tasks. ## Repository Structure The repository structure is organized into several directories: ``` Integrated_Car_Care_Platform/ │ ├── data/ │ ├── car_acceptability/ # Dataset for Car Acceptability Testing │ ├── car_engine/ # Dataset for Car Engine Predictive Maintenance │ ├── car_maintenance/ # Dataset for Car Maintenance Cost Prediction │ ├── models/ │ ├── car_accept.joblib # Saved models for Car Acceptability Testing │ ├── car_engine.joblib # Saved models for Car Engine Predictive Maintenance │ └── car_maintenance.joblib # Saved models for Car Maintenance Cost Prediction │ ├── notebooks/ │ ├── car_accept.ipynb # Jupyter notebook for Car Acceptability Testing │ ├── car_brand_classification.ipynb # Jupyter notebook for Car Brand Image Classification │ ├── car_engine.ipynb # Jupyter notebook for Car Engine Predictive Maintenance │ └── car_maintenance.ipynb # Jupyter notebook for Car Maintenance Cost Prediction │ ├── src/ │ ├── car_acceptability_testing/ # Scripts for Car Acceptability Testing │ ├── car_engine_maintenance/ # Scripts for Car Engine Predictive Maintenance │ └── car_maintenance_cost/ # Scripts for Car Maintenance Cost Prediction │ ├── streamlit_apps/ │ ├── car_brand_classification_app.py # Streamlit app for Car Brand Image Classification │ ├── car_acceptability_testing_app.py # Streamlit app for Car Acceptability Testing │ ├── car_engine_app.py # Streamlit app for Car Engine Predictive Maintenance │ ├── car_maintenance_app.py # Streamlit app for Car Maintenance Cost Prediction │ ├── app.py # Main application script ├── README.md # Documentation file └── requirements.txt # File containing required libraries ``` ## Kaggle References Datasets used in this project: 1. [100 Images of Top 50 Car Brands](https://www.kaggle.com/datasets/yamaerenay/100-images-of-top-50-car-brands) 2. [Car Acceptability Classification Dataset](https://www.kaggle.com/datasets/subhajeetdas/car-acceptability-classification-dataset) 3. [Vehicle Maintenance Record Dataset](https://www.kaggle.com/datasets/navins7/vehicle-maintenance-record) 4. [Automotive Vehicles Engine Health Dataset](https://www.kaggle.com/datasets/parvmodi/automotive-vehicles-engine-health-dataset) Pre-trained model used in this project: 1. [Car brand image detection ViT](https://www.kaggle.com/code/dima806/car-brand-image-detection-vit) ## Getting Started 1. **Data Preparation**: - Ensure datasets are in the `data/` directory. - Run notebooks in `notebooks/` for exploration, preprocessing, and model training. 2. **Model Usage**: - Access models in the `models/` directory for predictions or further analysis. - Use respective modules in `src/` for interacting with models. 3. **Installation of Requirements**: - Download required libraries by running: `pip install -r requirements.txt` in your terminal. ``` pip install -r requirements.txt ``` 4. **Launching the Streamlit App**: - Open your terminal and run: `streamlit run app.py` to start the application. ``` streamlit run app.py ``` These additional steps guide users on installing necessary dependencies and running the Streamlit app directly from the terminal. ## Demonstration  *Caption: Module 1 demonstration* ## Contribution Contributions, issues, and feature requests are welcome! Kindly follow the guidelines provided in the respective module directories in `src/` for contributing.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：