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 test_1():
"""
For this particular .csv file, check to make sure the first component is ic motor
"""
script_dir = os.path.dirname(__file__)
file = os.path.join(script_dir, '../assets/bladeQueryClean.csv')
assert get_data(file)[0][0][0] == 'ic motor'
def test_3():
"""
For this particular .csv file, check to make sure the last component is positioner
"""
script_dir = os.path.dirname(__file__)
file = os.path.join(script_dir, '../assets/bladeQueryClean.csv')
assert get_data(file)[0][0][89] == 'positioner'
def test_2():
"""
For this particular .csv file, check to make sure the first function-flow is convert chemical
"""
script_dir = os.path.dirname(__file__)
file = os.path.join(script_dir, '../assets/bladeQueryClean.csv')
assert get_data(file)[0][1][0] == 'convert chemical'
def test_2():
"""
Testing that the results for the component screw have all three factors: support, confidence, lift
"""
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)
assert len(results['screw']) == 3
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_1():
"""
Testing that the highest confidence result for the screw component is couple solid, which is what
a screw does almost exclusively
"""
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)
assert conf_results['screw'][0][0] == 'couple solid'
from autofunc.get_match_factor import match
from autofunc.simple_counter import count_stuff
from autofunc.get_top_results import get_top_results
from autofunc.get_data import get_data
import os.path
""" Example showing how to find the match factor using the simple counting file """
# 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 = 0.69
thresh_results = get_top_results(comb_sort, threshold)
# 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))
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))