def test_large(self):
d = Dict()
for x in range(60000):
d[str(x)] = x
# Test key and value
self.assertEqual(hash27("".join(d)), -35326655653467556)
self.assertEqual(hash27("".join([str(x) for x in d.values()])),
-35326655653467556)
def test_small(self):
d = Dict()
for x in range(15):
d[str(x)] = x
# Test key and value
self.assertEqual(hash27("".join(d)), 6636034109572507556)
self.assertEqual(hash27("".join([str(x) for x in d.values()])),
6636034109572507556)
def to_hash(in_str):
feas = in_str.split(":")[0]
arr = in_str.split(":")[1]
out_str = "%s:%s" % (feas, (arr + arr[::-1] + arr[::-2] + arr[::-3]))
hash_id = hash27(out_str) % dict_size
if hash_id in hash_dict and hash_dict[hash_id] != out_str:
print(hash_id, out_str, hash27(out_str))
print("conflict")
exit(-1)
return "%s:%s" % (feas, hash_id)
def test_large(self):
d = Set()
for x in range(60000):
d.add(str(x))
self.assertEqual(hash27("".join(d)), -35326655653467556)
def test_small(self):
d = Set()
for x in range(15):
d.add(str(x))
self.assertEqual(hash27("".join(d)), 6636034109572507556)
def test_merge(self):
# Build list of (key, value) pairs to preserve insertion ordering
d = []
e = []
for x in range(200):
d.append((str(x), x))
for x in range(200):
e.append((str(x), x))
m = Dict(d)
m.update(e)
self.assertEqual(hash27("".join(m)), -5846033856052761336)
self.assertEqual(hash27("".join([str(x) for x in m.values()])),
-5846033856052761336)
def test_keys(self):
d = Dict()
d[("abc", 1)] = 1
d[3.3] = 2
d[30] = 3
d["test1234"] = 4
self.assertEqual(hash27("".join([str(k) for k in d])),
7766555225202364718)
def test_values(self):
d = Set()
d.add(("abc", 1))
d.add(3.3)
d.add(30)
d.add("test1234")
self.assertEqual(hash27("".join([str(k) for k in d])),
7766555225202364718)
def test_popitem(self):
d = Dict()
for x in range(500):
d[str(x)] = x
d.popitem()
self.assertEqual(hash27("".join(d)), -434207861779954688)
def test_copy(self):
d = Set()
for x in range(500):
d.add(str(x))
d = d.copy()
self.assertEqual(hash27("".join(d)), 1141231293364439680)
def test_fromkeys(self):
s = []
for x in range(500):
s.append(str(x))
d = Dict.fromkeys(s)
self.assertEqual(hash27("".join(d)), -7925872281736336380)
def test_copy(self):
d = Dict()
for x in range(500):
d[str(x)] = x
d = d.copy()
self.assertEqual(hash27("".join(d)), 1141231293364439680)
def test_pop(self):
d = Set()
for x in range(500):
d.add(str(x))
d.pop()
self.assertEqual(hash27("".join(d)), -434207861779954688)
def to_hash(feas, arr):
out_str = "%s:%s" % (feas, (arr + arr[::-1] + arr[::-2] + arr[::-3]))
hash_id = hash27(out_str) % dict_size
if hash_id in hash_dict and hash_dict[hash_id] != out_str:
print(hash_id, out_str, hash(out_str), hash_dict[hash_id])
print("conflict")
exit(-1)
hash_dict[hash_id] = out_str
return hash_id
def test_delete(self):
d = Set()
for x in range(500):
d.add(str(x))
d.remove("53")
d.discard("155")
self.assertEqual(hash27("".join(d)), -8652364590473687932)
def test_update(self):
d = Dict()
for x in range(500):
d[str(x)] = x
d["255"] = "abc"
d["100"] = "123"
self.assertEqual(hash27("".join(d)), -7925872281736336380)
def test_delete(self):
d = Dict()
for x in range(500):
d[str(x)] = x
del d["53"]
d.pop("155")
self.assertEqual(hash27("".join(d)), -8652364590473687932)
def test_clear(self):
d = Set()
for x in range(500):
d.add(str(x))
d.clear()
for x in range(1000, 1500):
d.add(str(x))
self.assertEqual(hash27("".join(d)), -1473514505880218088)
def test_clear(self):
d = Dict()
for x in range(500):
d[str(x)] = x
d.clear()
for x in range(1000, 1500):
d[str(x)] = x
self.assertEqual(hash27("".join(d)), -1473514505880218088)
def test_pickle(self):
d = Set()
for x in range(500):
d.add(str(x))
d.remove("300")
# Pickle and reload object
data = pickle.dumps(d)
d = pickle.loads(data)
self.assertEqual(hash27("".join(d)), 6818550152093286356)
def process(path):
user_dict = parse_data(data_path + "/users.dat", user_fea)
movie_dict = parse_movie_data(data_path + "/movies.dat", movie_fea)
for line in open(path, encoding='ISO-8859-1'):
line = line.strip()
arr = line.split("::")
userid = arr[0]
movieid = arr[1]
out_str = "time:%s\t%s\t%s\tlabel:%s" % (arr[3], user_dict[userid],
movie_dict[movieid], arr[2])
log_id = hash27(out_str) % 1000000000
print("%s\t%s" % (log_id, out_str))
def test_pickle(self):
d = Dict()
for x in range(500):
d[str(x)] = x
del d["300"]
# Pickle and reload object
data = pickle.dumps(d)
d = pickle.loads(data)
self.assertEqual(hash27("".join(d)), 6818550152093286356)
def generate_online_data(path):
user_dict = parse_data(data_path + "/users.dat", user_fea)
movie_dict = parse_movie_data(data_path + "/movies.dat", movie_fea)
for line in open(path, encoding='ISO-8859-1'):
line = line.strip()
arr = line.split("::")
userid = arr[0]
movieid = arr[1]
label = arr[2]
out_str = "time:%s\t%s\t%s\tlabel:%s" % ("1", user_dict[userid],
movie_dict[movieid], label)
log_id = hash27(out_str) % 1000000000
res = "%s\t%s" % (log_id, out_str)
arr = res.strip().split("\t")
out_str = "logid:%s %s %s %s %s %s %s %s %s %s" % \
(arr[0], arr[1], to_hash(arr[2]), to_hash(arr[3]), to_hash(arr[4]), to_hash(arr[5]), \
to_hash(arr[6]), to_hash_list(arr[7]), to_hash_list(arr[8]), arr[9])
print(out_str)
def test_thash1(self):
self.assertEqual(hash27(("abc", 1)), -6007909421085996277)
def test_bhash(self):
self.assertEqual(hash27("test1234".encode("utf-8")),
1724133767363937712)
def test_shash(self):
self.assertEqual(hash27("test1234"), 1724133767363937712)
def test_ihash(self):
self.assertEqual(hash27(15344), 15344)
def test_fhash(self):
self.assertEqual(hash27(1235.333333), 3408413012)
def test_thash2(self):
self.assertEqual(hash27((3.5, 5.83)), 8767369050595774471)
