class GraphHandlerTestCase(unittest.TestCase):
def setUp(self):
self.dl = DataLoader()
self.dl.load_dataset_from('./data/tests/issuu_test_graph_handler.json')
self.gh = GraphHandler(self.dl.dicts)
def test_file_created(self):
self.gh.create_graph(base_visitor_uuid="0000",
base_document_uuid="aaaa",
render=False)
import os.path
self.assertTrue(os.path.exists('graphs/alaaaa.dot'))
self.assertTrue(os.path.exists('graphs/alaaaa.dot.pdf'))
def main():
# COMPONENTS CREATION
# ===================
dl = DataLoader()
# ARGUMENTS PARSING
# =================
parser = argparse.ArgumentParser(description='ISSUU Tracker')
parser.add_argument("-u","--user_uuid", help = "UUID of the user")
parser.add_argument("-d","--doc_uuid", help = "UUID of the document")
parser.add_argument("-t","--task_id", help = "ID of the task (2a,2b,3a,3b,4d,5,6)")
parser.add_argument("-f","--file_name", help = "JSON file of the dataset")
args = parser.parse_args()
if args.task_id == "2a":
dl.complete_load(args.file_name)
dv = DataVisualiser(dl.dicts)
dv.plot_countries()
elif args.task_id == "2b":
dl.complete_load(args.file_name)
dv = DataVisualiser(dl.dicts)
dv.plot_continents()
elif args.task_id == "3a":
dl.complete_load(args.file_name)
dv = DataVisualiser(dl.dicts)
dv.plot_browsers_verbose()
elif args.task_id == "3b":
dl.complete_load(args.file_name)
dv = DataVisualiser(dl.dicts)
dv.plot_browsers()
elif args.task_id == "4d":
dl.load_dataset_from(args.file_name)
af = AffinityFinder(dl.dicts)
print(af.also_likes(args.doc_uuid))
elif args.task_id == "5":
dl.load_dataset_from(args.file_name)
gh = GraphHandler(dicts=dl.dicts)
graph = gh.create_graph(base_document_uuid=args.doc_uuid,base_visitor_uuid=args.user_uuid)
elif args.task_id == "6":
gui = GUI()
gui.mainloop()
class AffinityFinderTestCase(unittest.TestCase):
def setUp(self):
self.dl = DataLoader()
self.dl.load_dataset_from('./data/tests/issuu_test_affinity_finder.json')
self.af = AffinityFinder(self.dl.dicts)
def list_equal(self,l1,l2):
print(l1)
print(l2)
return len(l1)==len(l2) and sorted(l1)==sorted(l2)
def test_readers_of(self):
list_result = ["0000","1111"]
readers_of = self.af.readers_of("aaaa")
self.assertTrue(self.list_equal(list_result,readers_of))
def test_has_read(self):
list_result = ["aaaa","bbbb"]
has_read = self.af.has_read("1111")
self.assertTrue(self.list_equal(list_result,has_read))
def test_also_likes_no_user(self):
list_result = ["aaaa","bbbb"]
also_likes = self.af.also_likes("aaaa")
self.assertTrue(self.list_equal(list_result,also_likes))
def test_also_likes_user0(self):
list_result = ["aaaa","bbbb"]
also_likes = self.af.also_likes("aaaa","0000")
self.assertTrue(self.list_equal(list_result,also_likes))
def test_also_likes_user1(self):
list_result = ["bbbb"]
also_likes = self.af.also_likes("bbbb","1111")
self.assertTrue(self.list_equal(list_result,also_likes))
class DataLoaderTestCase(unittest.TestCase):
def setUp(self):
self.dl = DataLoader()
self.dl.load_dataset_from('./data/tests/issuu_test_data_loader.json')
def test_load_dataset(self):
dict_result1 = {
"visitor_useragent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.117 Safari/537.36",
"visitor_country": "MX"
}
dict_result2 = {
"visitor_useragent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/540.36 (KHTML, like Gecko) Chrome/34.0.1750.112 Safari/538.36",
"visitor_country": "MX"
}
dict_result3 = {
"visitor_useragent": "P3P Validator",
"visitor_country": "FR"
}
self.assertEqual(self.dl.dicts[0], dict_result1)
self.assertEqual(self.dl.dicts[1], dict_result2)
self.assertEqual(self.dl.dicts[2], dict_result3)
def test_trimmed_browser_regex_match(self):
test_dict = self.dl.dicts[0]
self.dl.add_trimmed_browser(test_dict)
self.assertEqual(test_dict['visitor_useragent_trimmed'],
'Mozilla Safari')
def test_trimmed_browser_no_regex_match(self):
test_dict = self.dl.dicts[2]
self.dl.add_trimmed_browser(test_dict)
self.assertEqual(test_dict['visitor_useragent_trimmed'],
'P3P Validator')
def test_map_trim_browser(self):
self.dl.map_trim()
dict_result1 = {
"visitor_useragent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.117 Safari/537.36",
"visitor_country": "MX",
"visitor_useragent_trimmed": "Mozilla Safari"
}
dict_result2 = {
"visitor_useragent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/540.36 (KHTML, like Gecko) Chrome/34.0.1750.112 Safari/538.36",
"visitor_country": "MX",
"visitor_useragent_trimmed": "Mozilla Safari"
}
dict_result3 = {
"visitor_useragent": "P3P Validator",
"visitor_country": "FR",
"visitor_useragent_trimmed": "P3P Validator"
}
self.assertEqual(self.dl.dicts[0], dict_result1)
self.assertEqual(self.dl.dicts[1], dict_result2)
self.assertEqual(self.dl.dicts[2], dict_result3)
def test_continent(self):
test_dict1 = self.dl.dicts[0]
test_dict2 = self.dl.dicts[2]
self.dl.add_continent(test_dict1)
self.dl.add_continent(test_dict2)
self.assertEqual(test_dict1['visitor_continent'], 'North America')
self.assertEqual(test_dict2['visitor_continent'], 'Europe')
def test_map_add_continent(self):
self.dl.map_continents()
dict_result1 = {
"visitor_useragent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.117 Safari/537.36",
"visitor_country": "MX",
"visitor_continent": "North America"
}
dict_result2 = {
"visitor_useragent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/540.36 (KHTML, like Gecko) Chrome/34.0.1750.112 Safari/538.36",
"visitor_country": "MX",
"visitor_continent": "North America"
}
dict_result3 = {
"visitor_useragent": "P3P Validator",
"visitor_country": "FR",
"visitor_continent": "Europe"
}
self.assertEqual(self.dl.dicts[0], dict_result1)
self.assertEqual(self.dl.dicts[1], dict_result2)
self.assertEqual(self.dl.dicts[2], dict_result3)
def test_complete_load(self):
dl = DataLoader()
dl.complete_load('./data/tests/issuu_test_data_loader.json')
dict_result1 = {
"visitor_useragent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.117 Safari/537.36",
"visitor_country": "MX",
"visitor_useragent_trimmed": "Mozilla Safari",
"visitor_continent": "North America"
}
dict_result2 = {
"visitor_useragent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/540.36 (KHTML, like Gecko) Chrome/34.0.1750.112 Safari/538.36",
"visitor_country": "MX",
"visitor_useragent_trimmed": "Mozilla Safari",
"visitor_continent": "North America"
}
dict_result3 = {
"visitor_useragent": "P3P Validator",
"visitor_country": "FR",
"visitor_useragent_trimmed": "P3P Validator",
"visitor_continent": "Europe"
}
self.assertEqual(dl.dicts[0], dict_result1)
self.assertEqual(dl.dicts[1], dict_result2)
self.assertEqual(dl.dicts[2], dict_result3)
sort_list = sorted(docs_list, key=counts.get, reverse=True)
# Removing duplicates
sort_list = list(set(sort_list))
if doc_uuid in sort_list:
sort_list.remove(doc_uuid)
return [doc_uuid] + sort_list[:9]
def id(self, docs_list, doc_uuid):
return docs_list
if __name__ == "__main__":
# IMPORTS TO TEST
from IssuuTracker.data_loader import DataLoader, path_base_dataset, path_100k_dataset
dl_full = DataLoader()
dl_full.load_dataset_from(path_base_dataset)
af = AffinityFinder(dl_full.dicts)
# Test 1
# print(af.readers_of_list('130228184234-6fd07690237d48aaa7be4e20cb767b13'))
# print(af.has_read_list('bd378ce6df7cb9cd'))
# print(af.also_likes_list('120928161916-bbf9b86bb865460a8e674d5338115a18'))
# Test 2
print(af.has_read('2f63e0cca690da91'))
print(af.also_likes('140219141540-c900b41f845c67cc08b58911155c681c'))
# dl_100k = DataLoader()
# dl_100k.load_dataset_from(path_100k_dataset)
# af100k = AffinityFinder(dl_100k.dicts)
if not(document_uuid in graph.node_attr):
graph.node(document_uuid[-4:])
graph.edge(visitor_uuid[-4:],document_uuid[-4:])
else:
graph.edge(visitor_uuid[-4:],document_uuid[-4:])
graph.attr('node',style='solid',color='black')
if __name__ == "__main__":
# IMPORT TESTS
from IssuuTracker.data_loader import DataLoader,path_base_dataset,path_100k_dataset,path_400k_dataset,path_600k_dataset,path_3m_dataset
# BASE DATASET TESTS
# ==================
dl_base = DataLoader()
dl_base.load_dataset_from(path_base_dataset)
gh = GraphHandler(dl_base.dicts)
# gh.create_graph(dl_base.df,'bd378ce6df7cb9cd','130228184234-6fd07690237d48aaa7be4e20cb767b13')
# gh.create_graph(dl_base.dicts,'2f63e0cca690da91','140219141540-c900b41f845c67cc08b58911155c681c')
# # 100K DATASET TESTS
# # ==================
dl_100k = DataLoader()
dl_100k.load_dataset_from(path_100k_dataset)
gh = GraphHandler(dicts=dl_100k.dicts)
# gh.create_graph(base_visitor_uuid='00000000deadbeef',base_document_uuid='100806162735-00000000115598650cb8b514246272b5')
gh.create_graph(base_visitor_uuid='00000000deadbeef',base_document_uuid='aaaaaaaaaaaa-00000000df1ad06a86c40000000feadbe')
# # 400K DATASET TESTS
# # ==================