def main():
markdown = PagedownToHtml()
print("Reading in the training data")
train = data_io.get_train_df()
for i in train.index:
train["BodyMarkdown"][i] = markdown.convert(train["BodyMarkdown"][i])
print("Extracting features and training")
classifier = get_pipeline()
classifier.fit(train, train["OpenStatus"])
print("Saving the classifier")
data_io.save_model(classifier, "model.pickle")
model = data_io.load_model("model.pickle")
def main():
markdown = PagedownToHtml()
print("Reading the private leaderboard file")
test = data_io.get_test_df()
for i in test.index:
test["BodyMarkdown"][i] = markdown.convert(test["BodyMarkdown"][i])
print("Loading the trained model")
classifier = data_io.load_model("model.pickle")
print("Making predictions")
probs = classifier.predict_proba(test)
solution = data_io.get_private_leaderboard_solution_df()
print("Open AUC: %0.6f" % metrics.auc(solution["open"], probs[:,1]))