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))
for i in range(iters):
random.shuffle(test_ids)
# Split into folds
n = floor(len(test_ids) / k)
# Making folds using list comprehension
folds = [
test_ids[i * n:(i + 1) * n]
for i in range((len(test_ids) + n - 1) // n)
]
for e in folds:
verification_ids = e
ver_df, learn_df = split_learning_verification(df, verification_ids)
ver_list = df_to_list(ver_df)
if not bd:
comb_sort, counts, combos = counter_pandas_with_counts(learn_df)
thresh_results = get_top_results(comb_sort, threshold)
# Find the F1 score of the verification test by comparing the learned results with the known function/flows
learned_dict, matched, overmatched, unmatched, recall, precision, f1 = precision_recall(
thresh_results, ver_list)
if bd:
bd_comb_sort = counter_pandas(bd_df)
bd_thresh_results = get_top_results(bd_comb_sort, threshold)
learned_dict, matched, overmatched, unmatched, recall, precision, f1 = precision_recall(
bd_thresh_results, ver_list)
## End 1
## 2. Reading in dataframe as computed above
# similarity_df = pd.read_csv('consumer_similarity.csv')
# reading = True
## End 2
all_comps = list(train_df_whole.comp.unique())
num_all_comps = len(all_comps)
## Main loop, comment if not reading in all_data
for test_id in all_train_ids:
# print(test_id)
#
test_df, train_df = split_learning_verification(train_df_whole, [test_id])
test_list = df_to_list(test_df)
train_ids = list(map(int, train_df.id.unique()))
id_comp_ratios.append(
(test_id, len(list(test_df.comp.unique())) / num_all_comps))
#
# Outer loop through percent similar
for i in range(0, 100, 10):
ps_start = time.time()
f1_plot = []
thresh_plot = []
ps_plot = []
keep_ids = []