def test_hash_chars(self):
"For one table, all chars map to different chars"
results = set()
for c in range(256):
random.seed(1)
h = distinct.hash(chr(c))
results.add(h)
self.assertEquals(len(results), 256)
def test_hash_chars(self):
"For one table, all chars map to different chars"
results = set()
for c in range(256):
random.seed(1)
h = distinct.hash(chr(c))
results.add(h)
self.assertEquals(len(results), 256)
def test_chi_square(self):
try:
from scipy.stats import chi2
except ImportError:
raise SkipTest("Missing chi2, skipping")
N = 10000
for (bits, buckets) in [(-1, 1024), (24, 256), (16, 256), (8, 256),
(0, 256)]:
bins = [0] * buckets
for i in range(N):
v = distinct.hash(str(i))
if bits < 0:
bin = v / (0xFFFFFFFF / buckets)
else:
bin = (v >> bits) & 0xFF
bins[bin] += 1
value = sum(((x - N / buckets)**2) / (N / buckets) for x in bins)
pval = chi2.cdf(value, N)
if pval > 0.5:
print(bins, pval)
self.assertTrue(pval < 0.5, "bits %s, pval == %s" % (bits, pval))
def test_chi_square(self):
try:
from scipy.stats import chi2
except ImportError:
raise SkipTest("Missing chi2, skipping")
N = 10000
for (bits, buckets) in [(-1, 1024), (24, 256),
(16, 256), (8, 256), (0, 256)]:
bins = [0] * buckets
for i in range(N):
v = distinct.hash(str(i))
if bits < 0:
bin = v / (0xFFFFFFFF / buckets)
else:
bin = (v >> bits) & 0xFF
bins[bin] += 1
value = sum(((x - N / buckets) ** 2) / (N / buckets) for x in bins)
pval = chi2.cdf(value, N)
if pval > 0.5:
print(bins, pval)
self.assertTrue(pval < 0.5, "bits %s, pval == %s" % (bits, pval))
