def test1():
""" Test to find F1 score by manually selecting product id(s) from original data to test """
script_dir = os.path.dirname(__file__)
file_to_learn = os.path.join(script_dir,
'../autofunc/assets/consumer_systems.csv')
train_data = make_df(file_to_learn)
# Use a threshold to get the top XX% of frequency values
threshold = 0.7
## Choose ID(s) from learning file to separate into the testing set
test_ids = [691, 169]
test_df, train_df = split_learning_verification(train_data, test_ids)
test_list = df_to_list(test_df)
comb_sort = counter_pandas(train_df)
thresh_results = get_top_results(comb_sort, threshold)
# Find the F1 score
learned_dict, matched, overmatched, unmatched, recall, precision, f1 = precision_recall(
thresh_results, test_list)
assert len(learned_dict) != 0
assert f1 > 0
# Dataset used for data mining
script_dir = os.path.dirname(__file__)
file_to_learn = os.path.join(script_dir, '../autofunc/assets/consumer_systems.csv')
train_data = pd.read_csv(file_to_learn)
combos_sorted = counter_pandas(train_data)
# Use a threshold to get the top XX% of confidence values
threshold = 0.5
thresh_results = get_top_results(combos_sorted, threshold)
# Use a known product for verification
test_file = os.path.join(script_dir, '../autofunc/assets/jigsawQuery_headers.csv')
test_data = pd.read_csv(test_file)
test_list = df_to_list(test_data)
learned_dict, matched, overmatched, unmatched, recall, precision, f1 = precision_recall(thresh_results,
test_list)
# Optional write to file - uncomment and rename to write file
# write_results_from_dict(learned_dict, 'test1.csv')
print('Recall = {0:.5f}'.format(recall))
print('Precision = {0:.5f}'.format(precision))
print('F1 = {0:.5f}'.format(f1))