def subset_pps5(self, nsamp):
"""
Return a sample of nsamp distinct items from the population, sampled
without replacement with probability proportional to size (PPS)
according to Sampford's sampling scheme.
5-table lookup samplers are used within Sampford's algorithm to
accelerate the sampling for large populations.
"""
# Copy the whole population if nsamp = npopn.
if nsamp == self.npopn:
return [item for item in self.items]
set_rng_state(*random.get_state())
if self.equiprob:
pool = arange(self.npopn)
indices = equalprob(nsamp, pool)
else:
# This part of setup has to be done before any sampling.
if not self.did_init:
print('Initing ppssampler...')
self.sampler = _ppssampler(self.weights)
self.did_init = True
# This part has to be done before any sampling w/o replacement.
if not self.did_Sampford_init:
print('Initing wts...')
self.sort_indices, self.sort_wts, self.tot_wt = \
self.sampler.prepwts(self.weights)
self.max_wt = self.sort_wts[0] / self.tot_wt # Max wt, normed
self.nsamp = 0
self.did_Sampford_init = True
# This part has to be done when sample size changes.
if self.nsamp != nsamp:
print('Initing ratios...')
if nsamp > self.npopn:
raise ValueError('nsamp larger than population size!')
if nsamp * self.max_wt > 1:
raise ValueError('Sample size too large for PPS sampling!')
self.sampler.prepratios(nsamp, self.sort_wts, self.tot_wt)
self.sampler.prepratiotables()
self.did_Sampford_tables = True
self.nsamp = nsamp
# This may happen if subset_pps is called before subset_pps5.
if not self.did_Sampford_tables:
print('Initing ratio tables...')
self.sampler.prepratiotables()
self.did_Sampford_tables = True
self.ntry, indices = self.sampler.samplenr5()
# Note the 5-table version returns unsorted indices.
# indices = [self.sort_indices[i] for i in sindices]
result = [self.items[i] for i in indices]
random.set_state(get_rng_state())
return result
def subset_pps5(self, nsamp):
"""
Return a sample of nsamp distinct items from the population, sampled
without replacement with probability proportional to size (PPS)
according to Sampford's sampling scheme.
5-table lookup samplers are used within Sampford's algorithm to
accelerate the sampling for large populations.
"""
# Copy the whole population if nsamp = npopn.
if nsamp == self.npopn:
return [item for item in self.items]
set_rng_state(*random.get_state())
if self.equiprob:
pool = arange(self.npopn)
indices = equalprob(nsamp, pool)
else:
# This part of setup has to be done before any sampling.
if not self.did_init:
print 'Initing ppssampler...'
self.sampler = _ppssampler(self.weights)
self.did_init = True
# This part has to be done before any sampling w/o replacement.
if not self.did_Sampford_init:
print 'Initing wts...'
self.sort_indices, self.sort_wts, self.tot_wt = \
self.sampler.prepwts(self.weights)
self.max_wt = self.sort_wts[0]/self.tot_wt # Max wt, normed
self.nsamp = 0
self.did_Sampford_init = True
# This part has to be done when sample size changes.
if self.nsamp != nsamp:
print 'Initing ratios...'
if nsamp > self.npopn:
raise ValueError, 'nsamp larger than population size!'
if nsamp*self.max_wt > 1:
raise ValueError, 'Sample size too large for PPS sampling!'
self.sampler.prepratios(nsamp, self.sort_wts, self.tot_wt)
self.sampler.prepratiotables()
self.did_Sampford_tables = True
self.nsamp = nsamp
# This may happen if subset_pps is called before subset_pps5.
if not self.did_Sampford_tables:
print 'Initing ratio tables...'
self.sampler.prepratiotables()
self.did_Sampford_tables = True
self.ntry, indices = self.sampler.samplenr5()
# Note the 5-table version returns unsorted indices.
# indices = [self.sort_indices[i] for i in sindices]
result = [self.items[i] for i in indices]
random.set_state(get_rng_state())
return result
for i in range(100):
local_rand()
print 'Should be dif: ', rand(), local_rand()
random.set_state(get_rng_state())
print 'Should be same:', rand(), local_rand()
print
# Check equal-weight samplers.
print '*** Checking equiprobability samplers ***'
pool = zeros(10) # Workspace
samp = equalprobi(5,10,pool)
print 'equalprobi:', samp
# Check equalprob with a list input.
pool = range(10,20)
samp = equalprob(5,pool)
print 'equalprob:', samp
# Check the original pool is unchanged.
print pool
# Check it again with an array.
pool = array(pool)
samp = equalprob(5,pool)
print 'equalprob:', samp
print pool
print
# Check PPS.
print '*** Checking Population samplers ***'
p5 = Population(['a', 'b', 'c', 'd', 'e'])
wts = array([1., .5, .2, 2.5, 1., .5, .7, .8, .7])
