def get_model_root(self, data_type):
method_name = None
if data_type == DataType.Test:
method_name = self.model_name
if data_type == DataType.Train:
method_name = u'{}_train'.format(self.model_name)
return io_utils.get_method_root(method_name)
# MAIN
#
synonyms_filepath = io_utils.get_synonyms_filepath()
print "Preparing Train Collection"
X_train, y_train = create_train_data(io_utils.get_train_vectors_list())
print "Preparing Test Collection"
X_test, test_collections = create_test_data(io_utils.get_test_vectors_list())
BASELINES = {
'baseline_pos': estimators.baseline_pos,
'baseline_neg': estimators.baseline_neg,
'baseline_rand': estimators.baseline_rand,
'baseline_strat': estimators.baseline_strat,
}
# baseline estimators
for method_name in BASELINES:
print "Evaluate for baseline estimator: {}".format(method_name)
test_opinions = fit_and_predict(method_name, BASELINES[method_name],
X_train, y_train, X_test, test_collections,
synonyms_filepath)
io_utils.save_test_opinions(test_opinions, method_name)
edf = evaluate(BASELINES[method_name], method_name,
io_utils.create_files_to_compare_list(method_name),
io_utils.get_method_root(method_name), synonyms_filepath)
edf.to_csv("{}/test_{}.csv".format(io_utils.eval_baseline_root(),
method_name))
print "Preparing Train Collection"
X_train, y_train = create_train_data(io_utils.get_train_vectors_list())
print "Preparing Test Collection"
X_test, test_collections = create_test_data(io_utils.get_train_vectors_list())
# Univariate
for univariate_model_name in UNIVARIATE:
model = UNIVARIATE[univariate_model_name]
model.fit(X_train, y_train)
X_train_new = model.transform(X_train)
X_test_new = model.transform(X_test)
for method_name in CLASSIFIERS:
name = "{}_{}".format(method_name, univariate_model_name)
print "Evaluate for univariate estimator: {}".format(name)
test_opinions = fit_and_predict(name, CLASSIFIERS[method_name],
X_train_new, y_train, X_test_new,
test_collections, synonyms_filepath)
io_utils.save_test_opinions(test_opinions, name)
idf = create_model_feature_importances(None, name, model.get_support(),
io_utils.read_feature_names())
edf = evaluate(CLASSIFIERS[method_name], name,
io_utils.create_files_to_compare_list(method_name),
io_utils.get_method_root(method_name),
synonyms_filepath)
edf.to_csv("{}/test_{}.csv".format(io_utils.eval_univariate_root(),
method_name))
idf.to_csv("{}/test_{}.features.csv".format(
io_utils.eval_features_filepath(), method_name))