Project for my submission of the DataDriven.org Pump It Up competition - http://www.drivendata.org/competitions/7/
I made use of scikit-learn's RandomForestClassifier model.
Please sign up for the competition and download necessary .csv data files from http://www.drivendata.org/competitions/7/data/ and place the files under the following names in the data directory.
./data/test_test_values.csv
./data/training_set_values.csv
./data/training_set_labels.csv
You will also need the following python modules which can be installed via pip.
- pandas
- numpy
- scikit-learn
- matplotlib (optional for graphs)
Usage :
python predict.py
77.9