def runApriori(file):
minSupport = float(input("Enter the minimum support value :: "))
minConfidence = float(input("Enter the minimum confidence value :: "))
data = apriori.dataFromFile(file)
items, rules = apriori.runApriori(data, minSupport, minConfidence)
apriori.printResults(items, rules)
def main():
import sys
from optparse import OptionParser
from apriori import runApriori, dataFromFile, printResults
optparser = OptionParser()
optparser.add_option('-f', '--inputFile',
dest='input',
help='filename containing csv',
default=None)
optparser.add_option('-s', '--minSupport',
dest='minS',
help='minimum support value',
default=0.4,
type='float')
(options, args) = optparser.parse_args()
inFile = None
if options.input is None:
inFile = sys.stdin
elif options.input is not None:
inFile = dataFromFile(options.input)
else:
print ('No dataset filename specified, system with exit\n')
sys.exit('System will exit')
minSupport = options.minS
items, PBoarder, NBoarder = runApriori(inFile, minSupport)
printResults(items, minSupport, options.input.split("/")[2], PBoarder, NBoarder)
def test_print_results_should_have_results_in_defined_format(self):
with patch('sys.stdout', new=StringIO()) as fake_output:
items = [(('milk', ), 0.5), (('apple', ), 0.5), (('beer', ), 0.75),
(('rice', ), 0.5), (('beer', 'rice'), 0.5)]
rules = [((('beer', ), ('rice', )), 0.6666666666666666),
((('rice', ), ('beer', )), 1.0)]
printResults(items, rules)
expected = "item: ('milk',) , 0.500\nitem: ('apple',) , "
expected += "0.500\nitem: ('rice',) , 0.500\nitem: ('beer', "
expected += "'rice') , 0.500\nitem: ('beer',) , 0.750\n\n"
expected += "------------------------ RULES:\nRule: ('beer',) "
expected += "==> ('rice',) , 0.667\nRule: ('rice',) ==> "
expected += "('beer',) , 1.000\n"
self.assertEqual(fake_output.getvalue(), expected)
def sd_apri_main(inFile,buckets_cls,minSupport, minConfidence,result_name):
'''
'''
apri_logger.info("start sd_apri")
#cfg_file_name = get_cfg_filename(BASE_DIR)
get_cfg_filename(BASE_DIR)
apri_indi_set = indicator_classify(inFile,buckets_cls)
rows_file = apriori.dataFromList(apri_indi_set)
items, rules = apriori.runApriori(rows_file, minSupport, minConfidence)
result_dict = apriori.printResults(items, rules,result_name)
return result_dict
def test_print_results_should_have_results_in_defined_format(self):
with patch('sys.stdout', new=StringIO()) as fake_output:
items = [
(('milk',), 0.5),
(('apple',), 0.5),
(('beer',), 0.75),
(('rice',), 0.5),
(('beer', 'rice'), 0.5)
]
rules = [
((('beer',), ('rice',)), 0.6666666666666666),
((('rice',), ('beer',)), 1.0)
]
printResults(items, rules)
expected = "item: ('milk',) , 0.500\nitem: ('apple',) , "
expected += "0.500\nitem: ('rice',) , 0.500\nitem: ('beer', "
expected += "'rice') , 0.500\nitem: ('beer',) , 0.750\n\n"
expected += "------------------------ RULES:\nRule: ('beer',) "
expected += "==> ('rice',) , 0.667\nRule: ('rice',) ==> "
expected += "('beer',) , 1.000\n"
self.assertEqual(fake_output.getvalue(), expected)
additives_stats = json.load(open(DATASET_FILENAME, "r"))
except:
print("Building dataset")
additives_stats = openfood.inline_map_reduce(mapper, reducer)
json.dump(additives_stats, open(DATASET_FILENAME, "w"))
#add_clean = [(x['_id'], x['value'].split("_")) for x in additives_stats]
#add_clean.sort()
#for add in add_clean:
# print("{}: {}".format(add[0], add[1]))
ordered_ids = [x['_id'] for x in additives_stats]
ordered_additives = [x['value'] for x in additives_stats]
vectorizer = CountVectorizer(tokenizer=lambda x: x.split("_"), binary=True)
X = vectorizer.fit_transform(ordered_additives)
Xarray = X.toarray()
print("Feature names: ", vectorizer.get_feature_names())
#print(dir(Xarray))
print("Feature vector size: ", Xarray.size)
print("Feature vector shape: ", Xarray.shape)
print("Number of samples: ", len(ordered_additives))
#print(type(Xarray))
ordered_additives_split = [x['value'].split("_") for x in additives_stats]
minSupport = 0.1
minConfidence = 0.5
items, rules = runApriori(ordered_additives_split, minSupport, minConfidence)
printResults(items, rules)
# items, rules = apriori.runApriori(inFile, minSupport, minConfidence)
# apriori.printResults(items, rules)
# except Exception,e:
# logging.error("apriori api error",e)
# else:
# logging.info("apriori api has execute successfully ")
full_name = os.path.realpath(inFile)
cfg_file_name = get_cfg_filename(full_name)
pos = full_name.find(".txt")
result_name = full_name[:pos] + "_result.txt"
logging.info("start apriori!")
try:
#logging.info("in try!")
#logging.info("inFile",str(inFile))
apri_indi_set = indicator_classify(inFile,buckets_cls)
print "excute apriori algorithm"
logging.info("excuting apriori!")
rows_file = apriori.dataFromList(apri_indi_set)
items, rules = apriori.runApriori(rows_file, minSupport, minConfidence)
apriori.printResults(items, rules,result_name)
except Exception,e:
logging.error("apriori api error",str(e))
else:
logging.info("apriori api has execute successfully ")
print "End!!"
# '''
# try:
# apri_indi_set = indicator_classify(inFile,buckets_cls)
# inFile = apriori.dataFromList(apri_indi_set)
# items, rules = apriori.runApriori(inFile, minSupport, minConfidence)
# apriori.printResults(items, rules)
# except Exception,e:
# logging.error("apriori api error",e)
# else:
# logging.info("apriori api has execute successfully ")
full_name = os.path.realpath(inFile)
cfg_file_name = get_cfg_filename(full_name)
pos = full_name.find(".txt")
result_name = full_name[:pos] + "_result.txt"
logging.info("start apriori!")
try:
#logging.info("in try!")
#logging.info("inFile",str(inFile))
apri_indi_set = indicator_classify(inFile, buckets_cls)
print "excute apriori algorithm"
logging.info("excuting apriori!")
rows_file = apriori.dataFromList(apri_indi_set)
items, rules = apriori.runApriori(rows_file, minSupport, minConfidence)
apriori.printResults(items, rules, result_name)
except Exception, e:
logging.error("apriori api error", str(e))
else:
logging.info("apriori api has execute successfully ")
print "End!!"
import json
from apriori import runApriori, printResults
def generateItemsets(items):
for item in items:
if ('ingredient_ids' in item):
yield item['ingredient_ids']
data = json.load(open('../bbc_ingredients/bbc_crawl.json', 'r'));
ingredients = generateItemsets(data)
print 'Computing apriori'
items, rules = runApriori(ingredients, 0.00, 0.80)
printResults(items, rules)