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
def sample(self, nsamp):
"""
Return a set of nsamp samples from the population, sampled with
replacement.
"""
# *** Implement equiprob case.
if self.equiprob:
raise NotImplementedError('Awaiting code...')
if not self.did_init:
self.sampler = _ppssampler(self.weights)
self.did_init = True
# Track the RNG state within the sampler, to update NumPy's RNG state.
# Internally we only use the MT state; any extra state for cached
# normal or other samples can just be copied.
rng_state = random.get_state()
mt_state, extra_state = rng_state[:3], rng_state[3:]
set_rng_state(*mt_state) # *** modify to handle full rng state
indices = self.sampler.sample(nsamp)
new_state = list(get_rng_state())
new_state.extend(extra_state)
random.set_state(new_state)
return [self.items[i] for i in indices]
def sample(self, nsamp):
"""
Return a set of nsamp samples from the population, sampled with
replacement.
"""
# *** Implement equiprob case.
if self.equiprob:
raise NotImplementedError, 'Awaiting code...'
if not self.did_init:
self.sampler = _ppssampler(self.weights)
self.did_init = True
# Track the RNG state within the sampler, to update NumPy's RNG state.
# Internally we only use the MT state; any extra state for cached
# normal or other samples can just be copied.
rng_state = random.get_state()
mt_state, extra_state = rng_state[:3], rng_state[3:]
set_rng_state(*mt_state) # *** modify to handle full rng state
indices = self.sampler.sample(nsamp)
new_state = list(get_rng_state())
new_state.extend(extra_state)
random.set_state(new_state)
return [self.items[i] for i in indices]