def zip_cdf(x_arr, a, max_obs): #print x_arr result = [] for x in x_arr: if x <= max_obs: result.append( zipf.cdf(x, a) / zipf.cdf(max_obs, a)) #print result return result
def _generate_zipf_queries(self):
a = 1.5
queries = []
for i in range(QUERY_SIZE):
query = []
for j in range(DIM):
start = np.random.zipf(a)
while (zipf.cdf(start, a=a) + self.perColSelectivity >= 1):
start = np.random.zipf(a)
end = zipf.ppf(zipf.cdf(start, a=a) + self.perColSelectivity, a=a)
query.append(start)
query.append(end)
queries.append(query)
return queries
def test_zipfian_asymptotic(self):
# test limiting case that zipfian(a, n) -> zipf(a) as n-> oo
a = 6.5
N = 10000000
k = np.arange(1, 21)
assert_allclose(zipfian.pmf(k, a, N), zipf.pmf(k, a))
assert_allclose(zipfian.cdf(k, a, N), zipf.cdf(k, a))
assert_allclose(zipfian.sf(k, a, N), zipf.sf(k, a))
assert_allclose(zipfian.stats(a, N, moments='msvk'),
zipf.stats(a, moments='msvk'))
x = np.arange(zipf.ppf(0.01, a), zipf.ppf(0.99, a))
ax.plot(x, zipf.pmf(x, a), 'bo', ms=8, label='zipf pmf')
ax.vlines(x, 0, zipf.pmf(x, a), colors='b', lw=5, alpha=0.5)
# Alternatively, the distribution object can be called (as a function)
# to fix the shape and location. This returns a "frozen" RV object holding
# the given parameters fixed.
# Freeze the distribution and display the frozen ``pmf``:
rv = zipf(a)
ax.vlines(x,
0,
rv.pmf(x),
colors='k',
linestyles='-',
lw=1,
label='frozen pmf')
ax.legend(loc='best', frameon=False)
plt.show()
# Check accuracy of ``cdf`` and ``ppf``:
prob = zipf.cdf(x, a)
np.allclose(x, zipf.ppf(prob, a))
# True
# Generate random numbers:
r = zipf.rvs(a, size=1000)
