def test_no_fit(self):
"""Test that the Zipf fit function correctly identifies a non-Zipfian
distribution"""
p_max = 0.02
freqs = np.asarray([random.randint(0, 20) for _ in range(100)])
_, p = traces.zipf_fit(freqs)
self.assertLessEqual(p, p_max)
def test_no_fit(self):
"""Test that the Zipf fit function correctly identifies a non-Zipfian
distribution"""
p_max = 0.02
freqs = np.asarray([random.randint(0, 20) for _ in range(100)])
_, p = traces.zipf_fit(freqs)
self.assertLessEqual(p, p_max)
def zipf_estimation(trace_path, min_interval_size=2000):
print('estimating zipfian alpha parameter for all intervals of the trace')
data = []
with open('resources/' + trace_path, 'r') as trace:
csv_reader = csv.reader(trace)
requests = 0
occurrence_aggregate = defaultdict(int)
for index, line in enumerate(csv_reader):
time, receiver, object = line[0], line[1], line[2]
requests += 1
occurrence_aggregate[object] += 1
if requests % min_interval_size == 0:
zipf_alpha, zipf_fit_prob = zipf_fit(list(
occurrence_aggregate.values()),
need_sorting=True)
if zipf_fit_prob > 0.95:
data.append(zipf_alpha)
else:
data.append(None)
occurrence_aggregate.clear()
return data
def test_expected_fit(self):
"""Test that the Zipf fit function correctly estimates the alpha
parameter of a known Zipf distribution"""
alpha_tolerance = 0.02 # Tolerated alpha estimation error
p_min = 0.99 # Min p
n = 1000 # Number of Zipf distribution items
alpha = np.arange(0.2, 5.0, 0.1) # Tested range of Zipf's alpha
for a in alpha:
z = TruncatedZipfDist(a, n)
est_a, p = traces.zipf_fit(z.pdf)
self.assertLessEqual(np.abs(a - est_a), alpha_tolerance)
self.assertGreaterEqual(p, p_min)
def test_expected_fit(self):
"""Test that the Zipf fit function correctly estimates the alpha
parameter of a known Zipf distribution"""
alpha_tolerance = 0.02 # Tolerated alpha estimation error
p_min = 0.99 # Min p
n = 1000 # Number of Zipf distribution items
alpha = np.arange(0.2, 5.0, 0.1) # Tested range of Zipf's alpha
for a in alpha:
z = TruncatedZipfDist(a, n)
est_a, p = traces.zipf_fit(z.pdf)
self.assertLessEqual(np.abs(a - est_a), alpha_tolerance)
self.assertGreaterEqual(p, p_min)
def test_expected_fit_not_sorted(self):
"""Test that the Zipf fit function correctly estimates the alpha
parameter of a known Zipf distribution"""
alpha_tolerance = 0.02 # Tolerated alpha estimation error
p_min = 0.99 # Min p
n = 1000 # Number of Zipf distribution items
alpha = np.arange(0.2, 5.0, 0.1) # Tested range of Zipf's alpha
for a in alpha:
pdf = TruncatedZipfDist(a, n).pdf
np.random.shuffle(pdf)
est_a, p = traces.zipf_fit(pdf, need_sorting=True)
assert np.abs(a - est_a) <= alpha_tolerance
assert p >= p_min
