AlphaShoe

Machine learning algorithm for SD210 Data Challenge.

team

• Ali (@AliHarouchi)
• François (@Fran-cois)
• Reda (@rslaoui)
• Yohan (@ychalier)

usage

I placed data file (.csv) in a data/ folder at the root of the repository. CSV files are in .gitignore to avoid poluting the repository. The data folder contains the following files:

• customers.csv
• products.csv
• X_train.csv
• X_test.csv
• y_train.csv

Then start Jupyter and open base.ipynb with a Python 2 kernel.

The best score has been achieved on TPT servers using deep.py.

report

• Detailed methods and results
• Code