def test_1():
"""
Tests that the match factor for a known learning set and test case is close to the known value
"""
script_dir = os.path.dirname(__file__)
file1 = os.path.join(script_dir, '../assets/bladeCombined.csv')
store_data, records = get_data(file1)
conf_results, results = find_associations(store_data,
records,
support=0.0003,
confidence=0.01,
lift=0.1)
thresh_results = get_top_results(conf_results, 0.7)
test_file = os.path.join(script_dir, '../assets/jigsawQuery.csv')
test_data, test_records = get_data(test_file)
learned_dict, matched, overmatched, unmatched, match_factor = match(
thresh_results, test_records)
assert np.allclose(0.82051, match_factor)
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
def test_1():
"""
Tests that the top function-flow combination for the component "screw" is "couple solid"
"""
script_dir = os.path.dirname(__file__)
file1 = os.path.join(script_dir, '../assets/bladeCombined.csv')
store_data, records = get_data(file1)
conf_results, results = find_associations(store_data, records)
thresh_results = get_top_results(conf_results, 0.7)
assert thresh_results['screw'][0][0] == 'couple solid'
def test_2():
"""
Tests that the top 70% of function-flow combinations for the component "screw" only has one result
"""
script_dir = os.path.dirname(__file__)
file1 = os.path.join(script_dir, '../assets/bladeCombined.csv')
store_data, records = get_data(file1)
conf_results, results = find_associations(store_data, records)
thresh_results = get_top_results(conf_results, 0.7)
assert len(thresh_results['screw']) == 1
def test_get_top_results():
"""
Tests that the top 70% of function-flow combinations for the component "screw" only has one result
"""
script_dir = os.path.dirname(__file__)
file2 = os.path.join(script_dir, '../assets/bladeCombined.csv')
comb_sort = count_stuff(file2)
threshold = 0.7
thresh_results = get_top_results(comb_sort, threshold)
assert len(thresh_results['screw']) == 1
def test_1():
""" Example showing how to automate result finding with probability values """
# Dataset used for data mining
script_dir = os.path.dirname(__file__)
file1 = os.path.join(script_dir, '../assets/bladeCombined.csv')
comb_sort = count_stuff(file1)
# Use a threshold to get the top XX% of confidence values
threshold = 0.5
thresh_results = get_top_results(comb_sort, threshold)
# Use a known product for verification
input_file = os.path.join(script_dir, '../assets/InputExample.csv')
# Get dictionary of functions and flows for each component based on data mining
results, unmatched = get_func_rep(thresh_results, input_file, True)
assert results['screw'][0][0] == 'couple solid'
assert 'cheese' in unmatched
def test_1():
""" Example showing how to automate functional representation with frequency values"""
# Dataset used for data mining
script_dir = os.path.dirname(__file__)
file_to_test = os.path.join(script_dir,
'../autofunc/assets/consumer_systems.csv')
test_data = pd.read_csv(file_to_test)
combos_sorted = counter_pandas(test_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
input_file = os.path.join(script_dir,
'../autofunc/assets/InputExample.csv')
# Get dictionary of functions and flows for each component based on data mining
results, unmatched = get_func_rep(thresh_results, input_file, True)
assert results['screw'][0][0] == 'couple solid'
assert 'cheese' in unmatched
import os.path
import pandas as pd
""" Example showing how to find F1 score using separate file of input components """
# 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')
# 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)
precisions.append(precision)
recalls.append(recall)
print(e)
train_comps = list(keep_df.comp.unique())
if train_comps:
comp_ratio = len(train_comps) / num_all_comps
comp_ratios.append((len(keep_ids), i, comp_ratio))
if comp_ratio > 0.7 and len(keep_ids) < 40:
keepers.append(keep_ids)
scatter_keep.append((comp_ratio, len(keep_ids)))
for t in range(10, 100, 5):
threshold = t / 100
print(test_id, ' ', ps_thresh, ' ', threshold)
thresh_results = get_top_results(comb_sort, threshold)
if not keep_ids:
f1 = 0
num_train_comps = 0
else:
# 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, test_list)
num_train_comps = len(train_comps)
save_data.append((test_id, ps_thresh, threshold, len(keep_ids), f1,
num_train_comps / num_all_comps))
points.append((ps_thresh, threshold, f1))
from autofunc.get_match_factor import match
from autofunc.get_top_results import get_top_results
from autofunc.find_associations import find_associations
from autofunc.get_data import get_data
import os.path
""" Example showing how to find the match factor using association rules """
# Dataset used for data mining
script_dir = os.path.dirname(__file__)
file1 = os.path.join(script_dir, '../assets/bladeCombined.csv')
# Convert file to data frame and list
store_data, records = get_data(file1)
# Use Association Rules to sort the functions/flows of components by confidence
conf_results, results = find_associations(store_data, records)
# Use a threshold to get the top XX% of confidence values
thresh_results = get_top_results(conf_results, 0.7)
# Use a known product for verification
test_file = os.path.join(script_dir, '../assets/jigsawQuery.csv')
test_data, test_records = get_data(test_file)
# Find the match factor of the verification test by comparing the learned results with the known function/flows
learned_dict, matched, overmatched, unmatched, match_factor = match(
thresh_results, test_records)
print('Match factor = {0:.5f}'.format(match_factor))
