def measure_random_performance():
outfile = get_out_file("random_classifier")
write_result(outfile, "smell,auc,precision,recall,f1,average_precision\n")
for smell in smell_list:
data_path = os.path.join(os.path.join(TOKENIZER_OUT_PATH, smell), DIM)
input_data = get_all_data(data_path, smell)
y_pred = np.random.randint(2, size=len(input_data.eval_labels))
auc, precision, recall, f1, average_precision, fpr, tpr = \
metrics_util.get_all_metrics_(input_data.eval_labels, y_pred)
write_result(
outfile, smell + "," + str(auc) + "," + str(precision) + "," +
str(recall) + "," + str(f1) + "," + str(average_precision) + "\n")
def measure_performance_dummy_classifier():
outfile = get_out_file("dummy_classifier")
write_result(outfile, "smell,auc,precision,recall,f1,average_precision\n")
for smell in smell_list:
data_path = os.path.join(os.path.join(TOKENIZER_OUT_PATH, smell), DIM)
input_data = get_all_data(data_path, smell)
# clf = DummyClassifier(strategy='stratified', random_state=0)
clf = DummyClassifier(strategy='most_frequent', random_state=0)
inverted_train_labels = inputs.invert_labels(input_data.train_labels)
clf.fit(input_data.train_data, inverted_train_labels)
y_pred = clf.predict(input_data.eval_data)
auc, precision, recall, f1, average_precision, fpr, tpr = \
metrics_util.get_all_metrics_(input_data.eval_labels, y_pred)
write_result(
outfile, smell + "," + str(auc) + "," + str(precision) + "," +
str(recall) + "," + str(f1) + "," + str(average_precision) + "\n")