def _get_statistics(self,data):
n = getdatasize(data)
if n > 0:
if isinstance(data, np.ndarray):
xss = (data**2).sum()
else:
xss = np.sum([(d**2).sum() for d in data])
else:
xss = 0
return n, xss
def _get_statistics(self, data):
n = getdatasize(data)
if n > 0:
if isinstance(data, np.ndarray):
xss = (data**2).sum()
else:
xss = np.sum([(d**2).sum() for d in data])
else:
xss = 0
return n, xss
def resample(self,data=[],niter=None):
niter = niter if niter else self.niter
if getdatasize(data) == 0:
self.A = sample_gaussian(J=self.J_0,h=self.h_0.ravel())\
.reshape(self.h_0.shape)
self.sigma = sample_invwishart(self.S_0,self.nu_0)
else:
yyT, yxT, xxT, n = self._get_statistics(data)
for itr in range(niter):
self._resample_A(xxT, yxT, self.sigma)
self._resample_sigma(xxT, yxT, yyT, n, self.A)
def max_likelihood(self,data,weights=None):
if weights is not None:
raise NotImplementedError
assert isinstance(data,list) or isinstance(data,np.ndarray)
if isinstance(data,list):
data = np.concatenate(data)
if getdatasize(data) > 0:
self.add_data(data)
self.EM_fit()
self.labels_list = []
def resample(self, data=[], niter=None):
niter = niter if niter else self.niter
if getdatasize(data) == 0:
self.A = sample_gaussian(J=self.J_0,h=self.h_0.ravel())\
.reshape(self.h_0.shape)
self.sigma = sample_invwishart(self.S_0, self.nu_0)
else:
yyT, yxT, xxT, n = self._get_statistics(data)
for itr in range(niter):
self._resample_A(xxT, yxT, self.sigma)
self._resample_sigma(xxT, yxT, yyT, n, self.A)
def max_likelihood(self, data, weights=None):
if weights is not None:
raise NotImplementedError
assert isinstance(data, list) or isinstance(data, np.ndarray)
if isinstance(data, list):
data = np.concatenate(data)
if getdatasize(data) > 0:
self.add_data(data)
self.EM_fit()
self.labels_list = []
def _get_statistics(self,data):
n = getdatasize(data)
if n > 0:
data = flattendata(data)
feasible = self.r_support <= data.min()
assert np.any(feasible)
r_support = self.r_support[feasible]
normalizers = (special.gammaln(data[:,na]) - special.gammaln(data[:,na]-r_support+1)
- special.gammaln(r_support)).sum(0)
return n, data.sum(), normalizers, feasible
else:
return n, None, None, None
def _get_statistics(self,data):
n = getdatasize(data)
if n > 0:
data = flattendata(data)
feasible = self.r_support <= data.min()
assert np.any(feasible)
r_support = self.r_support[feasible]
normalizers = (special.gammaln(data[:,na]) - special.gammaln(data[:,na]-r_support+1)
- special.gammaln(r_support)).sum(0)
return n, data.sum(), normalizers, feasible
else:
return n, None, None, None
def resample(self,data=[],niter=20):
if getdatasize(data) == 0:
self.p = np.random.beta(self.alpha_0,self.beta_0)
self.r = np.random.gamma(self.k_0,self.theta_0)
else:
data = atleast_2d(flattendata(data))
N = len(data)
for itr in range(niter):
### resample r
msum = sample_crp_tablecounts(self.r,data).sum()
self.r = np.random.gamma(self.k_0 + msum, 1/(1/self.theta_0 - N*np.log(1-self.p)))
### resample p
self.p = np.random.beta(self.alpha_0 + data.sum(), self.beta_0 + N*self.r)
return self
def resample(self,data=[],niter=20):
if getdatasize(data) == 0:
self.p = np.random.beta(self.alpha_0,self.beta_0)
self.r = np.random.gamma(self.k_0,self.theta_0)
else:
data = np.atleast_2d(flattendata(data))
ones = np.ones(data.shape[1],dtype=float)
for itr in range(niter):
### resample r
msum = sample_crp_tablecounts(float(self.r),data,ones).sum()
self.r = np.random.gamma(self.k_0 + msum, 1/(1/self.theta_0 - N*np.log(1-self.p)))
### resample p
self.p = np.random.beta(self.alpha_0 + data.sum(), self.beta_0 + N*self.r)
return self
def resample(self,data):
# doesn't keep a reference to the data like a model would
assert isinstance(data,list) or isinstance(data,np.ndarray)
if getdatasize(data) > 0:
if not isinstance(data,np.ndarray):
data = np.concatenate(data)
self.add_data(data,initialize_from_prior=False)
for itr in range(self.niter):
self.resample_model()
self.labels_list.pop()
else:
self.resample_model()
def resample_python(self,data=[],niter=20):
if getdatasize(data) == 0:
self.p = np.random.beta(self.alpha_0,self.beta_0)
self.r = np.random.gamma(self.k_0,self.theta_0)
else:
data = flattendata(data)
N = len(data)
for itr in range(niter):
### resample r
msum = 0.
for n in data:
msum += (np.random.rand(n) < self.r/(np.arange(n)+self.r)).sum()
self.r = np.random.gamma(self.k_0 + msum, 1/(1/self.theta_0 - N*np.log(1-self.p)))
### resample p
self.p = np.random.beta(self.alpha_0 + data.sum(), self.beta_0 + N*self.r)
return self
def resample_python(self,data=[],niter=20):
if getdatasize(data) == 0:
self.p = np.random.beta(self.alpha_0,self.beta_0)
self.r = np.random.gamma(self.k_0,self.theta_0)
else:
data = flattendata(data)
N = len(data)
for itr in range(niter):
### resample r
msum = 0.
for n in data:
msum += (np.random.rand(n) < self.r/(np.arange(n)+self.r)).sum()
self.r = np.random.gamma(self.k_0 + msum, 1/(1/self.theta_0 - N*np.log(1-self.p)))
### resample p
self.p = np.random.beta(self.alpha_0 + data.sum(), self.beta_0 + N*self.r)
return self
def resample(self, data):
# doesn't keep a reference to the data like a model would
assert isinstance(data, list) or isinstance(data, np.ndarray)
if getdatasize(data) > 0:
if not isinstance(data, np.ndarray):
data = np.concatenate(data)
self.add_data(data, initialize_from_prior=False)
for itr in range(self.niter):
self.resample_model()
self.labels_list.pop()
else:
self.resample_model()
def _get_statistics(self,data):
if getdatasize(data) == 0:
n, tot = 0, 0
elif isinstance(data,np.ndarray):
assert np.all(data >= 0)
data = np.atleast_1d(data)
n, tot = data.shape[0], data.sum()
elif isinstance(data,list):
assert all(np.all(d >= 0) for d in data)
n = sum(d.shape[0] for d in data)
tot = sum(d.sum() for d in data)
else:
assert np.isscalar(data)
n = 1
tot = data
return np.array([n, tot])
def resample_logseriesaug(self,data=[],niter=20):
# an alternative algorithm, kind of opaque and no advantages...
if getdatasize(data) == 0:
self.p = np.random.beta(self.alpha_0,self.beta_0)
self.r = np.random.gamma(self.k_0,self.theta_0)
else:
data = flattendata(data)
N = data.shape[0]
logF = self.logF
L_i = np.zeros(N)
data_nz = data[data > 0]
for itr in range(niter):
logR = np.arange(1,logF.shape[1]+1)*np.log(self.r) + logF
L_i[data > 0] = sample_discrete_from_log(logR[data_nz-1,:data_nz.max()],axis=1)+1
self.r = np.random.gamma(self.k_0 + L_i.sum(), 1/(1/self.theta_0 - np.log(1-self.p)*N))
self.p = np.random.beta(self.alpha_0 + data.sum(), self.beta_0 + N*self.r)
return self
def resample_logseriesaug(self,data=[],niter=20):
# an alternative algorithm, kind of opaque and no advantages...
if getdatasize(data) == 0:
self.p = np.random.beta(self.alpha_0,self.beta_0)
self.r = np.random.gamma(self.k_0,self.theta_0)
else:
data = flattendata(data)
N = data.shape[0]
logF = self.logF
L_i = np.zeros(N)
data_nz = data[data > 0]
for itr in range(niter):
logR = np.arange(1,logF.shape[1]+1)*np.log(self.r) + logF
L_i[data > 0] = sample_discrete_from_log(logR[data_nz-1,:data_nz.max()],axis=1)+1
self.r = np.random.gamma(self.k_0 + L_i.sum(), 1/(1/self.theta_0 - np.log(1-self.p)*N))
self.p = np.random.beta(self.alpha_0 + data.sum(), self.beta_0 + N*self.r)
return self
def _get_statistics(self,data):
if getdatasize(data) == 0:
n, tot = 0, 0
elif isinstance(data,np.ndarray):
assert np.all(data >= 0)
data = np.atleast_1d(data)
n, tot = data.shape[0], data.sum()
elif isinstance(data,list):
assert all(np.all(d >= 0) for d in data)
n = sum(d.shape[0] for d in data)
tot = sum(d.sum() for d in data)
else:
assert np.isscalar(data)
n = 1
tot = data
return np.array([n, tot])
