This repository contains a data analysis and machine learning project that focuses on predicting various characteristics of used Audi cars. The project performs exploratory data analysis (EDA) and applies machine learning models, particularly linear regression, to the Audi used car dataset.
- Data Visualization: Utilize different plots (e.g., barplot, piechart, scatter plot, regression plot, pair plot, box plot, violin plot, and histogram) to visualize the dataset.
- Exploratory Data Analysis (EDA): Extract insights about each variable from the dataset using visualizations.
- Machine Learning: Apply linear regression and other models to predict the target variable.
- Model Evaluation: Compute Key Performance Indicators (KPIs) of the machine learning model and visualize prediction errors.
- Source: Audi Used Car Dataset on Kaggle
- File: audi.csv
- audi_used_car_EDA.ipynb: Jupyter notebook that covers the exploratory data analysis and data visualization.
- audi_used_car_ML.ipynb: Jupyter notebook for applying machine learning models to the dataset.
- audi_used_car_ML_Linear_Regresion_with_feature_encoding.ipynb: Jupyter notebook for applying linear regression with feature encoding and computing KPIs.
- Clone the repository:
git clone https://github.com/AudityGhosh/audi_used_car_analysis.git
- Navigate to the folder:
cd audi_used_car_analysis - Open the Jupyter notebooks:
jupyter notebook
- Start with
audi_used_car_EDA.ipynbfor exploratory data analysis and visualization. - Run
audi_used_car_ML.ipynbandaudi_used_car_ML_Linear_Regresion_with_feature_encoding.ipynbfor machine learning tasks.
Feel free to fork the repository, contribute to the analysis, or add improvements to the machine learning models. Pull requests are welcome!
This project is developed by Audity Ghosh to explore the application of machine learning and data visualization on car sales data, specifically Audi used cars.