def test_correctness(X=None,
R=None,
nnzPerRow=2,
N=100,
K=3,
D=2,
funcList=None,
prefix='calcRXX_'):
if funcList is None:
funcList = make_funcList(prefix=prefix)
kwargs = _make_kwarg_dict(X=X, R=R, nnzPerRow=nnzPerRow, N=N, K=K, D=D)
for i in range(len(funcList)):
for j in range(i + 1, len(funcList)):
func_i = funcList[i]
func_j = funcList[j]
ans_i = func_i(**kwargs)
ans_j = func_j(**kwargs)
if prefix.count('calcRlogR') and kwargs['nnzPerRow'] == 1:
# SPARSE routine gives scalar 0.0
# but DENSE routine gives vector of all zeros
ans_i = as1D(toCArray(ans_i))
ans_j = as1D(toCArray(ans_j))
if ans_i.size < K:
ans_j = np.sum(ans_j)
elif ans_j.size < K:
ans_i = np.sum(ans_i)
assert np.allclose(ans_i, ans_j)
print(' all pairs of funcs give same answer')
def eta2pi(eta_Km1):
eta_Km1 = as1D(np.asarray(eta_Km1))
pi_K = np.ones(eta_Km1.size + 1)
pi_K[:-1] = np.exp(eta_Km1)
pi_K[:-1] += 1e-100
pi_K /= (1.0 + np.sum(pi_K[:-1]))
return pi_K
def pi2eta(pi_K):
''' Transform vector on simplex to unconstrained real vector
Returns
-------
eta_Km1 : 1D array, size K-1
Examples
--------
# py2 vs py3 round error without format str
>>> print("%.5f" % float(pi2eta(eta2pi(0.42))))
0.42000
>>> print(float(pi2eta(eta2pi(-1.337))))
-1.337
>>> print(pi2eta(eta2pi([-1, 0, 1])))
[-1. 0. 1.]
'''
pi_K = as1D(np.asarray(pi_K))
eta_Km1 = pi_K[:-1] / pi_K[-1]
np.log(eta_Km1, out=eta_Km1)
return eta_Km1
def calcSummaryStats(Data,
LP,
doPrecompEntropy=False,
doPrecompMergeEntropy=False,
mPairIDs=None,
mergePairSelection=None,
trackDocUsage=False,
**kwargs):
""" Calculate sufficient statistics for global updates.
Parameters
-------
Data : bnpy data object
LP : local param dict with fields
resp : Data.nObs x K array,
where resp[n,k] = posterior resp of comp k
doPrecompEntropy : boolean flag
indicates whether to precompute ELBO terms in advance
used for memoized learning algorithms (moVB)
doPrecompMergeEntropy : boolean flag
indicates whether to precompute ELBO terms in advance
for certain merge candidates.
Returns
-------
SS : SuffStatBag with K components
Summarizes for this mixture model, with fields
* N : 1D array, size K
N[k] = expected number of items assigned to comp k
Also has optional ELBO field when precompELBO is True
* ElogqZ : 1D array, size K
Vector of entropy contributions from each comp.
ElogqZ[k] = \sum_{n=1}^N resp[n,k] log resp[n,k]
Also has optional Merge field when precompMergeELBO is True
* ElogqZ : 2D array, size K x K
Each term is scalar entropy of merge candidate
"""
if mPairIDs is not None and len(mPairIDs) > 0:
M = len(mPairIDs)
else:
M = 0
if 'resp' in LP:
Nvec = np.sum(LP['resp'], axis=0)
K = Nvec.size
else:
# Sparse assignment case
Nvec = as1D(toCArray(LP['spR'].sum(axis=0)))
K = LP['spR'].shape[1]
if hasattr(Data, 'dim'):
SS = SuffStatBag(K=K, D=Data.dim, M=M)
else:
SS = SuffStatBag(K=K, D=Data.vocab_size, M=M)
SS.setField('N', Nvec, dims=('K'))
if doPrecompEntropy:
Mdict = calcELBO_NonlinearTerms(LP=LP, returnMemoizedDict=1)
if type(Mdict['Hresp']) == float:
# SPARSE HARD ASSIGNMENTS
SS.setELBOTerm('Hresp', Mdict['Hresp'], dims=None)
else:
SS.setELBOTerm('Hresp', Mdict['Hresp'], dims=('K', ))
if doPrecompMergeEntropy:
m_Hresp = None
if 'resp' in LP:
m_Hresp = -1 * NumericUtil.calcRlogR_specificpairs(
LP['resp'], mPairIDs)
elif 'spR' in LP:
if LP['nnzPerRow'] > 1:
m_Hresp = calcSparseMergeRlogR(spR_csr=LP['spR'],
nnzPerRow=LP['nnzPerRow'],
mPairIDs=mPairIDs)
else:
raise ValueError("Need resp or spR in LP")
if m_Hresp is not None:
assert m_Hresp.size == len(mPairIDs)
SS.setMergeTerm('Hresp', m_Hresp, dims=('M'))
if trackDocUsage:
Usage = np.sum(LP['resp'] > 0.01, axis=0)
SS.setSelectionTerm('DocUsageCount', Usage, dims='K')
return SS