In [ ]:
In [ ]:
# TODO: move all the merge code from data-analysis-html.ipynb
In [ ]:
# VS251 feature set
# Merge the feature sets.
#
phtml = pd.read_csv('data/sorted-html-features-vs251.csv')
pentropy = pd.read_csv('data/sorted-entropy-features-vs251.csv')
pfileid = pd.read_csv('data/sorted-file-id-features-vs251.csv')
ptridid = pd.read_csv('data/sorted-trid-id-features-vs251.csv')
plabels = pd.read_csv('data/sorted-train-labels-vs251.csv')
phtml.head()
In [ ]:
In [ ]: