Predicting the Sale Price of Bulldozers Using Machine Learning 🚜💰 This project uses machine learning to predict bulldozer sale prices based on historical data from the Kaggle Bluebook for Bulldozers competition. The goal is to minimize the RMSLE between actual and predicted prices.
MIT License
In this project, we aim to predict the sale price of bulldozers using machine learning techniques. The data used for this project is from the Kaggle Bluebook for Bulldozers competition.
Built with:
How well can we predict the future sale price of a bulldozer given its characteristics and previous examples of how much similar bulldozers have been sold for?
The data is downloaded from the Kaggle Bluebook for Bulldozers competition. There are three main datasets:
Train.csv
is the training set, which contains data through the end of 2011.Valid.csv
is the validation set, which contains data from January 1, 2012 - April 30, 2012. Your score on this set is used to create the public leaderboard.Test.csv
is the test set, which contains data from May 1, 2012 - November 2012. Your score on the test set determines your final rank for the competition.The evaluation metric for this project is the RMSLE (root mean squared log error) between the actual and predicted auction prices.
For more details on the evaluation of this project, check: https://www.kaggle.com/c/bluebook-for-bulldozers/overview/evaluation
Kaggle provides a data dictionary detailing all the features of the dataset. You can view this data dictionary in data/bluebook-for-bulldozers/Data Dictionary.xlsx
.
The main steps we go through in this project are:
Clone the repository:
git clone https://github.com/AdrianTomin/bulldozer-price-prediction.git
cd bulldozer-price-prediction
Create and activate the Conda environment:
conda env create -f environment.yml
conda activate bulldozer-price-prediction
Clone the repository:
git clone https://github.com/AdrianTomin/bulldozer-price-prediction.git
cd bulldozer-price-prediction
Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate`
Install the dependencies:
pip install -r requirements.txt
Choose one of these options to set up the environment, depending on your preference. `
Install Jupyter Notebook or JupyterLab:
conda install -c conda-forge notebook
# or for JupyterLab
conda install -c conda-forge jupyterlab
Start Jupyter Notebook or JupyterLab:
jupyter notebook
# or for JupyterLab
jupyter lab
Navigate to the project directory:
cd bulldozer-price-prediction
Start the Jupyter Notebook server:
jupyter notebook
Open the notebook:
In the Jupyter Notebook interface, open the bulldozer-price-prediction.ipynb
notebook.
Run the notebook cells:
Execute the cells in the notebook to train the model and make predictions. Ensure you have downloaded the dataset and placed it in the appropriate directory as mentioned in the notebook.
This README provides a comprehensive guide for setting up the environment, installing dependencies, and running the project locally. Adjust paths and repository links as needed to match your specific setup.