House Prices: Advanced Regression Techniques Competition on Kaggle
This project requires Python 2.7 and the following Python libraries installed:
You will also need to have software installed to run and execute an iPython Notebook
All ipython notebook are used for data preprocessing, feature transforming and outlier detecting.
All core scripts are in code
folder, in which the ensemble learning script is in ensemble
folder and
base model script is in sing_model
folder. All input data are in input
folder and the detailed description
of the data can be found in Kaggle.
For a single model run, navigate to the /code/single_model/
and run the following commands: python base_model.py
For a ensemble run, navigate to the /code/ensemble/
and run the following commands: python ensemble.py
Make sure to change the data directory and the parameters accordingly before the model run.
Submission score on Kaggle leaderboard with different approaches.
Flow chart of the code.
See ./doc/capstone_doc.pdf
for detailed project documentation.