def spring_brother(training_file, test_file, submission_file):
""" Running on the test file. """
y, meta_data = utilities.read_training_file(training_file)
ids, meta_data_test = utilities.read_test_file(test_file)
x_train, x_test = feature_selection.generate_features(meta_data,
y, meta_data_test)
clf = classification.random_forest(x_train, y, None, None)
p = classification.get_prob(clf, x_test)
utilities.write_submission_file(submission_file, ids, p)
def spring_brother(training_file, test_file, submission_file):
""" Running on the test file. """
y, meta_data = utilities.read_training_file(training_file)
ids, meta_data_test = utilities.read_test_file(test_file)
x_train, x_test = feature_selection.generate_features(
meta_data, y, meta_data_test)
clf = classification.random_forest(x_train, y, None, None)
p = classification.get_prob(clf, x_test)
utilities.write_submission_file(submission_file, ids, p)
def all_feature_classify(training_file, num):
""" Classifier using all features. """
y, meta_data = utilities.read_training_file(training_file)
y, meta_data = utilities.sample(y, meta_data, num)
meta_data_train, y_train, meta_data_cv, y_cv = \
classification.prepare_data(meta_data, y)
x_train, x_cv = feature_selection.generate_features(meta_data_train,
y_train, meta_data_cv)
clf = classification.random_forest(x_train, y_train, x_cv, y_cv)
print utilities.binomial_deviance(y_train,
classification.get_prob(clf, x_train))
print utilities.binomial_deviance(y_cv, classification.get_prob(clf, x_cv))
def all_feature_classify(training_file, num):
""" Classifier using all features. """
y, meta_data = utilities.read_training_file(training_file)
y, meta_data = utilities.sample(y, meta_data, num)
meta_data_train, y_train, meta_data_cv, y_cv = \
classification.prepare_data(meta_data, y)
x_train, x_cv = feature_selection.generate_features(
meta_data_train, y_train, meta_data_cv)
clf = classification.random_forest(x_train, y_train, x_cv, y_cv)
print utilities.binomial_deviance(y_train,
classification.get_prob(clf, x_train))
print utilities.binomial_deviance(y_cv, classification.get_prob(clf, x_cv))