train, labels, test, _, _ = utils.load_data()
# transform counts to TFIDF features
tfidf = feature_extraction.text.TfidfTransformer(smooth_idf=False)
train = tfidf.fit_transform(train).toarray()
test = tfidf.transform(test).toarray()
# encode labels
lbl_enc = preprocessing.LabelEncoder()
labels = lbl_enc.fit_transform(labels)
# train classifier
clf = ensemble.ExtraTreesClassifier(n_jobs=4, n_estimators=2000, max_features=20, min_samples_split=3,
bootstrap=False, verbose=3, random_state=23)
if MODE == 'cv':
scores, predictions = utils.make_blender_cv(clf, train, labels, calibrate=False)
print('CV:', scores, 'Mean log loss:', np.mean(scores))
utils.write_blender_data(consts.BLEND_PATH, MODEL_NAME + '.csv', predictions)
elif MODE == 'submission':
clf.fit(train, labels)
predictions = clf.predict_proba(test)
utils.save_submission(consts.DATA_SAMPLE_SUBMISSION_PATH,
os.path.join(consts.ENSEMBLE_PATH, MODEL_NAME + '.csv'),
predictions)
elif MODE == 'holdout':
score = utils.hold_out_evaluation(clf, train, labels, calibrate=False)
print('Log loss:', score)
else:
print('Unknown mode')
p = p.sort('id')
del p['id']
preds_array = np.array(p.to_dataframe(), dtype=float)
return preds_array
if __name__ == '__main__':
train, labels, test, _, _ = utils.load_data()
clf = XGBoost(max_iterations=4800, max_depth=12, min_child_weight=4.9208250938262745,
row_subsample=.9134478530382129, min_loss_reduction=.5132278416508804,
column_subsample=.730128689911957, step_size=.009)
if MODE == 'cv':
scores, predictions = utils.make_blender_cv(clf, train, labels, calibrate=False)
print ('CV:', scores, 'Mean log loss:', np.mean(scores))
utils.write_blender_data(consts.BLEND_PATH, MODEL_NAME + '.csv', predictions)
elif MODE == 'submission':
clf.fit(train, labels)
predictions = clf.predict_proba(test)
utils.save_submission(consts.DATA_SAMPLE_SUBMISSION_PATH,
os.path.join(consts.ENSEMBLE_PATH, MODEL_NAME + '.csv'),
predictions)
elif MODE == 'holdout':
train, labels, _, _ = utils.stratified_split(train, labels, test_size=.7)
score = utils.hold_out_evaluation(clf, train, labels, calibrate=False)
print ('Log loss:', score)
elif MODE == 'tune':
# Objective function
def objective(args):
print (train.shape)
# encode labels
lbl_enc = preprocessing.LabelEncoder()
labels = lbl_enc.fit_transform(labels)
# train classifier
linear_clf = linear_model.LogisticRegression(C=1, penalty='l1',
fit_intercept=True, random_state=23)
clf = ensemble.BaggingClassifier(base_estimator=linear_clf, n_estimators=40,
max_samples=1., max_features=1., bootstrap=True,
n_jobs=5, verbose=True, random_state=23)
if MODE == 'cv':
scores, predictions = utils.make_blender_cv(clf, train, labels)
print ('CV:', scores, 'Mean log loss:', np.mean(scores))
utils.write_blender_data(consts.BLEND_PATH, MODEL_NAME + '.csv', predictions)
elif MODE == 'submission':
clf.fit(train, labels)
predictions = clf.predict_proba(test)
utils.save_submission(consts.DATA_SAMPLE_SUBMISSION_PATH,
os.path.join(consts.ENSEMBLE_PATH, MODEL_NAME + '.csv'),
predictions)
elif MODE == 'holdout':
score = utils.hold_out_evaluation(clf, train, labels)
print ('Log loss:', score)
else:
print ('Unknown mode')
