My first attempt at prediction on a big data set.

Uses the Kaggle Hearst Challenge data set

Summary

Name		Name	Last commit message	Last commit date
Latest commit History 20 Commits
README.markdown		README.markdown
csv.py		csv.py
do_knn.bat		do_knn.bat
explore.py		explore.py
kd_tree.py		kd_tree.py
knn.py		knn.py
misc.py		misc.py
parse_weka_results.py		parse_weka_results.py
sqlite_history.py		sqlite_history.py