def possible_mana_combinations(land_list, deck=None):
"""
CommandLine:
python -m mtgmonte.mtgutils --test-possible_mana_combinations
Example:
>>> # ENABLE_DOCTEST
>>> from mtgmonte.mtgutils import * # NOQA
>>> from mtgmonte import mtgobjs
>>> deck = mtgobjs.Deck(mtgobjs.load_cards(['Tropical Island', 'Sunken Hollow', 'Island']))
>>> land_list = mtgobjs.load_cards(['Ancient Tomb', 'Island', 'Flooded Strand', 'Flooded Strand', 'Shivan Reef'])
>>> card = land_list[-1]
>>> mana_combos = possible_mana_combinations(land_list, deck)
>>> result = (ut.repr2(mana_combos, nl=1, strvals=True, nobraces=True))
>>> print(result)
({CC}, {U}, {G}, {U}, {C}),
({CC}, {U}, {G}, {B}, {C}),
({CC}, {U}, {U}, {U}, {C}),
({CC}, {U}, {U}, {B}, {C}),
({CC}, {U}, {G}, {U}, {R}),
({CC}, {U}, {G}, {B}, {R}),
({CC}, {U}, {U}, {U}, {R}),
({CC}, {U}, {U}, {B}, {R}),
"""
from mtgmonte import mtgobjs
avail_mana = [land.mana_potential2(deck=deck, recurse=False) for land in land_list]
avail_mana = filter(len, avail_mana)
mana_combos1 = list(ut.iprod(*avail_mana))
# Encode the idea that two fetches cant fetch the same land
non_class1 = [[c for c in co if not isinstance(c, six.string_types)] for co in mana_combos1]
flags = [len(co) == 0 or len(set(co)) == len(co) for co in non_class1]
mana_combos2 = ut.compress(mana_combos1, flags)
mana_combos3 = [
[[c] if isinstance(c, mtgobjs.ManaSet) else c.mana_potential2(deck=deck) for c in co] for co in mana_combos2
]
unflat_combos3 = [list(ut.iprod(*co)) for co in mana_combos3]
mana_combos4 = ut.flatten(unflat_combos3)
# mana_combos4 = [reduce(operator.add, m) for m in mana_combos4]
# z = reduce(operator.add, m)
# import utool
# utool.embed()
# avail_mana = [land.mana_potential(deck=deck) for land in land_list]
# avail_mana = filter(len, avail_mana)
# mana_combos4 = list(ut.iprod(*avail_mana))
combo_ids = [tuple(sorted(x)) for x in mana_combos4]
flags = ut.flag_unique_items(combo_ids)
mana_combos = ut.compress(mana_combos4, flags)
# mana_combos = list(map(tuple, [''.join(c) for c in mana_combos]))
return mana_combos
def get_subbin_xy_neighbors(subbin_index00, grid_steps, num_cols, num_rows):
""" Generate all neighbor of a bin
subbin_index00 = left and up subbin index
"""
subbin_index00 = np.floor(subbin_index00).astype(np.int32)
subbin_x0, subbin_y0 = subbin_index00
step_list = np.arange(1 - grid_steps, grid_steps + 1)
offset_list = [
# broadcast to the shape we will add too
np.array([xoff, yoff])[:, None]
for xoff, yoff in list(ut.iprod(step_list, step_list))]
neighbor_subbin_index_list = [
np.add(subbin_index00, offset)
for offset in offset_list
]
# Concatenate all subbin indexes into one array for faster vectorized op
neighbor_bin_indices = np.dstack(neighbor_subbin_index_list).T
# Clip with no wrapparound
min_val = np.array([0, 0])
max_val = np.array([num_cols - 1, num_rows - 1])
np.clip(neighbor_bin_indices,
min_val[None, None, :],
max_val[None, None, :],
out=neighbor_bin_indices)
return neighbor_bin_indices
def apply_hard_soft_evidence(cpd_list, evidence_list):
for cpd, ev in zip(cpd_list, evidence_list):
if isinstance(ev, int):
# hard internal evidence
evidence[cpd.variable] = ev
if isinstance(ev, six.string_types):
# hard external evidence
evidence[cpd.variable] = cpd._internal_varindex(
cpd.variable, ev)
if isinstance(ev, dict):
# soft external evidence
# HACK THAT MODIFIES CPD IN PLACE
def rectify_evidence_val(_v, card=cpd.variable_card):
# rectify hacky string structures
tmp = 1 / (2 * card**2)
return (1 + tmp) / (card + tmp) if _v == '+eps' else _v
ev_ = ut.map_dict_vals(rectify_evidence_val, ev)
fill = (1.0 - sum(ev_.values())) / (cpd.variable_card -
len(ev_))
# HACK fix for float problems
if len(ev_) == cpd.variable_card - 1:
fill = 0
assert fill > -1e7, 'fill=%r' % (fill, )
row_labels = list(ut.iprod(*cpd.statenames))
for i, lbl in enumerate(row_labels):
if lbl in ev_:
# external case1
cpd.values[i] = ev_[lbl]
elif len(lbl) == 1 and lbl[0] in ev_:
# external case2
cpd.values[i] = ev_[lbl[0]]
elif i in ev_:
# internal case
cpd.values[i] = ev_[i]
else:
cpd.values[i] = fill
cpd.normalize()
soft_evidence[cpd.variable] = True
def alternatives(self):
r"""
Args:
types (None): (default = None)
Returns:
list: list of alternative mana costs
CommandLine:
python -m mtgmonte.mtgobjs --exec-get_tokens --show
Example:
>>> # ENABLE_DOCTEST
>>> from mtgmonte.mtgobjs import * # NOQA
>>> self = ManaCost(tokenize_manacost('12WWUBRG(W/B)(2/G)(U/P)(U/P)'))
>>> alt_costs = self.alternatives
>>> alt = alt_costs[0]
"""
alt_sets = [ManaSet(combos) for combos in ut.iprod(*[m.alternatives() for m in self._to_manas()])]
alt_costs = [ManaCost(ut.flatten([m.to_tokens() for m in mset._manas])) for mset in alt_sets]
return alt_costs
def apply_hard_soft_evidence(cpd_list, evidence_list):
for cpd, ev in zip(cpd_list, evidence_list):
if isinstance(ev, int):
# hard internal evidence
evidence[cpd.variable] = ev
if isinstance(ev, six.string_types):
# hard external evidence
evidence[cpd.variable] = cpd._internal_varindex(
cpd.variable, ev)
if isinstance(ev, dict):
# soft external evidence
# HACK THAT MODIFIES CPD IN PLACE
def rectify_evidence_val(_v, card=cpd.variable_card):
# rectify hacky string structures
tmp = (1 / (2 * card ** 2))
return (1 + tmp) / (card + tmp) if _v == '+eps' else _v
ev_ = ut.map_dict_vals(rectify_evidence_val, ev)
fill = (1.0 - sum(ev_.values())) / (cpd.variable_card - len(ev_))
# HACK fix for float problems
if len(ev_) == cpd.variable_card - 1:
fill = 0
assert fill > -1E7, 'fill=%r' % (fill,)
row_labels = list(ut.iprod(*cpd.statenames))
for i, lbl in enumerate(row_labels):
if lbl in ev_:
# external case1
cpd.values[i] = ev_[lbl]
elif len(lbl) == 1 and lbl[0] in ev_:
# external case2
cpd.values[i] = ev_[lbl[0]]
elif i in ev_:
# internal case
cpd.values[i] = ev_[i]
else:
cpd.values[i] = fill
cpd.normalize()
soft_evidence[cpd.variable] = True
def try_query(model, infr, evidence, interest_ttypes=[], verbose=True):
r"""
CommandLine:
python -m wbia.algo.hots.bayes --exec-try_query --show
Example:
>>> # DISABLE_DOCTEST
>>> from wbia.algo.hots.bayes import * # NOQA
>>> verbose = True
>>> other_evidence = {}
>>> name_evidence = [1, None, 0, None]
>>> score_evidence = ['high', 'low', 'low']
>>> query_vars = None
>>> model = make_name_model(num_annots=4, num_names=4, verbose=True, mode=1)
>>> model, evidence, soft_evidence = update_model_evidence(model, name_evidence, score_evidence, other_evidence)
>>> interest_ttypes = ['name']
>>> infr = pgmpy.inference.BeliefPropagation(model)
>>> evidence = infr._ensure_internal_evidence(evidence, model)
>>> query_results = try_query(model, infr, evidence, interest_ttypes, verbose)
>>> result = ('query_results = %s' % (str(query_results),))
>>> ut.quit_if_noshow()
>>> show_model(model, show_prior=True, **query_results)
>>> ut.show_if_requested()
Ignore:
query_vars = ut.setdiff_ordered(model.nodes(), list(evidence.keys()))
probs = infr.query(query_vars, evidence)
map_assignment = infr.map_query(query_vars, evidence)
"""
infr = pgmpy.inference.VariableElimination(model)
# infr = pgmpy.inference.BeliefPropagation(model)
if True:
return bruteforce(model, query_vars=None, evidence=evidence)
else:
import vtool as vt
query_vars = ut.setdiff_ordered(model.nodes(), list(evidence.keys()))
# hack
query_vars = ut.setdiff_ordered(
query_vars, ut.list_getattr(model.ttype2_cpds['score'],
'variable'))
if verbose:
evidence_str = ', '.join(model.pretty_evidence(evidence))
logger.info('P(' + ', '.join(query_vars) + ' | ' + evidence_str +
') = ')
# Compute MAP joints
# There is a bug here.
# map_assign = infr.map_query(query_vars, evidence)
# (probably an invalid thing to do)
# joint_factor = pgmpy.factors.factor_product(*factor_list)
# Brute force MAP
name_vars = ut.list_getattr(model.ttype2_cpds['name'], 'variable')
query_name_vars = ut.setdiff_ordered(name_vars, list(evidence.keys()))
# TODO: incorporate case where Na is assigned to Fred
# evidence_h = ut.delete_keys(evidence.copy(), ['Na'])
joint = model.joint_distribution()
joint.evidence_based_reduction(query_name_vars, evidence, inplace=True)
# Find static row labels in the evidence
given_name_vars = [var for var in name_vars if var in evidence]
given_name_idx = ut.dict_take(evidence, given_name_vars)
given_name_val = [
joint.statename_dict[var][idx]
for var, idx in zip(given_name_vars, given_name_idx)
]
new_vals = joint.values.ravel()
# Add static evidence variables to the relabeled name states
new_vars = given_name_vars + joint.variables
new_rows = [tuple(given_name_val) + row for row in joint._row_labels()]
# Relabel rows based on the knowledge that
# everything is the same, only the names have changed.
temp_basis = [i for i in range(model.num_names)]
def relabel_names(names, temp_basis=temp_basis):
names = list(map(six.text_type, names))
mapping = {}
for n in names:
if n not in mapping:
mapping[n] = len(mapping)
new_names = tuple([temp_basis[mapping[n]] for n in names])
return new_names
relabeled_rows = list(map(relabel_names, new_rows))
# Combine probability of rows with the same (new) label
data_ids = np.array(vt.other.compute_unique_data_ids_(relabeled_rows))
unique_ids, groupxs = vt.group_indices(data_ids)
reduced_row_lbls = ut.take(relabeled_rows,
ut.get_list_column(groupxs, 0))
reduced_row_lbls = list(map(list, reduced_row_lbls))
reduced_values = np.array(
[g.sum() for g in vt.apply_grouping(new_vals, groupxs)])
# Relabel the rows one more time to agree with initial constraints
used_ = []
replaced = []
for colx, (var, val) in enumerate(zip(given_name_vars,
given_name_val)):
# All columns must be the same for this labeling
alias = reduced_row_lbls[0][colx]
reduced_row_lbls = ut.list_replace(reduced_row_lbls, alias, val)
replaced.append(alias)
used_.append(val)
basis = model.ttype2_cpds['name'][0]._template_.basis
find_remain_ = ut.setdiff_ordered(temp_basis, replaced)
repl_remain_ = ut.setdiff_ordered(basis, used_)
for find, repl in zip(find_remain_, repl_remain_):
reduced_row_lbls = ut.list_replace(reduced_row_lbls, find, repl)
# Now find the most likely state
sortx = reduced_values.argsort()[::-1]
sort_reduced_row_lbls = ut.take(reduced_row_lbls, sortx.tolist())
sort_reduced_values = reduced_values[sortx]
# Remove evidence based labels
new_vars_ = new_vars[len(given_name_vars):]
sort_reduced_row_lbls_ = ut.get_list_column(
sort_reduced_row_lbls, slice(len(given_name_vars), None))
sort_reduced_row_lbls_[0]
# hack into a new joint factor
var_states = ut.lmap(ut.unique_ordered, zip(*sort_reduced_row_lbls_))
statename_dict = dict(zip(new_vars, var_states))
cardinality = ut.lmap(len, var_states)
val_lookup = dict(
zip(ut.lmap(tuple, sort_reduced_row_lbls_), sort_reduced_values))
values = np.zeros(np.prod(cardinality))
for idx, state in enumerate(ut.iprod(*var_states)):
if state in val_lookup:
values[idx] = val_lookup[state]
joint2 = pgmpy.factors.Factor(new_vars_,
cardinality,
values,
statename_dict=statename_dict)
logger.info(joint2)
max_marginals = {}
for i, var in enumerate(query_name_vars):
one_out = query_name_vars[:i] + query_name_vars[i + 1:]
max_marginals[var] = joint2.marginalize(one_out, inplace=False)
# max_marginals[var] = joint2.maximize(one_out, inplace=False)
logger.info(joint2.marginalize(['Nb', 'Nc'], inplace=False))
factor_list = max_marginals.values()
# Better map assignment based on knowledge of labels
map_assign = dict(zip(new_vars_, sort_reduced_row_lbls_[0]))
sort_reduced_rowstr_lbls = [
ut.repr2(dict(zip(new_vars, lbls)),
explicit=True,
nobraces=True,
strvals=True) for lbls in sort_reduced_row_lbls_
]
top_assignments = list(
zip(sort_reduced_rowstr_lbls[:3], sort_reduced_values))
if len(sort_reduced_values) > 3:
top_assignments += [('other', 1 - sum(sort_reduced_values[:3]))]
# import utool
# utool.embed()
# Compute all marginals
# probs = infr.query(query_vars, evidence)
# probs = infr.query(query_vars, evidence)
# factor_list = probs.values()
## Marginalize over non-query, non-evidence
# irrelevant_vars = ut.setdiff_ordered(joint.variables, list(evidence.keys()) + query_vars)
# joint.marginalize(irrelevant_vars)
# joint.normalize()
# new_rows = joint._row_labels()
# new_vals = joint.values.ravel()
# map_vals = new_rows[new_vals.argmax()]
# map_assign = dict(zip(joint.variables, map_vals))
# Compute Marginalized MAP joints
# marginalized_joints = {}
# for ttype in interest_ttypes:
# other_vars = [v for v in joint_factor.scope()
# if model.var2_cpd[v].ttype != ttype]
# marginal = joint_factor.marginalize(other_vars, inplace=False)
# marginalized_joints[ttype] = marginal
query_results = {
'factor_list': factor_list,
'top_assignments': top_assignments,
'map_assign': map_assign,
'marginalized_joints': None,
}
return query_results
def flow():
"""
http://pmneila.github.io/PyMaxflow/maxflow.html#maxflow-fastmin
pip install PyMaxFlow
pip install pystruct
pip install hdbscan
"""
# Toy problem representing attempting to discover names via annotation
# scores
import pystruct # NOQA
import pystruct.models # NOQA
import networkx as netx # NOQA
import vtool as vt
num_annots = 10
num_names = num_annots
hidden_nids = np.random.randint(0, num_names, num_annots)
unique_nids, groupxs = vt.group_indices(hidden_nids)
toy_params = {
True: {
'mu': 1.0,
'sigma': 2.2
},
False: {
'mu': 7.0,
'sigma': 0.9
}
}
if True:
import vtool as vt
import wbia.plottool as pt
xdata = np.linspace(0, 100, 1000)
tp_pdf = vt.gauss_func1d(xdata, **toy_params[True])
fp_pdf = vt.gauss_func1d(xdata, **toy_params[False])
pt.plot_probabilities([tp_pdf, fp_pdf], ['TP', 'TF'], xdata=xdata)
def metric(aidx1, aidx2, hidden_nids=hidden_nids, toy_params=toy_params):
if aidx1 == aidx2:
return 0
rng = np.random.RandomState(int(aidx1 + aidx2))
same = hidden_nids[int(aidx1)] == hidden_nids[int(aidx2)]
mu, sigma = ut.dict_take(toy_params[same], ['mu', 'sigma'])
return np.clip(rng.normal(mu, sigma), 0, np.inf)
pairwise_aidxs = list(ut.iprod(range(num_annots), range(num_annots)))
pairwise_labels = np.array(
[hidden_nids[a1] == hidden_nids[a2] for a1, a2 in pairwise_aidxs])
pairwise_scores = np.array([metric(*zz) for zz in pairwise_aidxs])
pairwise_scores_mat = pairwise_scores.reshape(num_annots, num_annots)
if num_annots <= 10:
logger.info(ut.repr2(pairwise_scores_mat, precision=1))
# aids = list(range(num_annots))
# g = netx.DiGraph()
# g.add_nodes_from(aids)
# g.add_edges_from([(tup[0], tup[1], {'weight': score}) for tup, score in zip(pairwise_aidxs, pairwise_scores) if tup[0] != tup[1]])
# netx.draw_graphviz(g)
# pr = netx.pagerank(g)
X = pairwise_scores
Y = pairwise_labels
encoder = vt.ScoreNormalizer()
encoder.fit(X, Y)
encoder.visualize()
# meanshift clustering
import sklearn
bandwidth = sklearn.cluster.estimate_bandwidth(
X[:, None]) # , quantile=quantile, n_samples=500)
assert bandwidth != 0, '[] bandwidth is 0. Cannot cluster'
# bandwidth is with respect to the RBF used in clustering
# ms = sklearn.cluster.MeanShift(bandwidth=bandwidth, bin_seeding=True, cluster_all=True)
ms = sklearn.cluster.MeanShift(bandwidth=bandwidth,
bin_seeding=True,
cluster_all=False)
ms.fit(X[:, None])
label_arr = ms.labels_
unique_labels = np.unique(label_arr)
max_label = max(0, unique_labels.max())
num_orphans = (label_arr == -1).sum()
label_arr[label_arr == -1] = np.arange(max_label + 1,
max_label + 1 + num_orphans)
X_data = np.arange(num_annots)[:, None].astype(np.int64)
# graph = pystruct.models.GraphCRF(
# n_states=None,
# n_features=None,
# inference_method='lp',
# class_weight=None,
# directed=False,
# )
import scipy
import scipy.cluster
import scipy.cluster.hierarchy
thresh = 2.0
labels = scipy.cluster.hierarchy.fclusterdata(X_data,
thresh,
metric=metric)
unique_lbls, lblgroupxs = vt.group_indices(labels)
logger.info(groupxs)
logger.info(lblgroupxs)
logger.info('groupdiff = %r' %
(ut.compare_groupings(groupxs, lblgroupxs), ))
logger.info('common groups = %r' %
(ut.find_grouping_consistencies(groupxs, lblgroupxs), ))
# X_data, seconds_thresh, criterion='distance')
# help(hdbscan.HDBSCAN)
import hdbscan
alg = hdbscan.HDBSCAN(metric=metric,
min_cluster_size=1,
p=1,
gen_min_span_tree=1,
min_samples=2)
labels = alg.fit_predict(X_data)
labels[labels == -1] = np.arange(np.sum(labels == -1)) + labels.max() + 1
unique_lbls, lblgroupxs = vt.group_indices(labels)
logger.info(groupxs)
logger.info(lblgroupxs)
logger.info('groupdiff = %r' %
(ut.compare_groupings(groupxs, lblgroupxs), ))
logger.info('common groups = %r' %
(ut.find_grouping_consistencies(groupxs, lblgroupxs), ))
# import ddbscan
# help(ddbscan.DDBSCAN)
# alg = ddbscan.DDBSCAN(2, 2)
# D = np.zeros((len(aids), len(aids) + 1))
# D.T[-1] = np.arange(len(aids))
## Can alpha-expansion be used when the pairwise potentials are not in a grid?
# hidden_ut.group_items(aids, hidden_nids)
if False:
import maxflow
# from maxflow import fastmin
# Create a graph with integer capacities.
g = maxflow.Graph[int](2, 2)
# Add two (non-terminal) nodes. Get the index to the first one.
nodes = g.add_nodes(2)
# Create two edges (forwards and backwards) with the given capacities.
# The indices of the nodes are always consecutive.
g.add_edge(nodes[0], nodes[1], 1, 2)
# Set the capacities of the terminal edges...
# ...for the first node.
g.add_tedge(nodes[0], 2, 5)
# ...for the second node.
g.add_tedge(nodes[1], 9, 4)
g = maxflow.Graph[float](2, 2)
g.maxflow()
g.get_nx_graph()
g.get_segment(nodes[0])
def crftest():
"""
pip install pyqpbo
pip install pystruct
http://taku910.github.io/crfpp/#install
cd ~/tmp
#wget https://drive.google.com/folderview?id=0B4y35FiV1wh7fngteFhHQUN2Y1B5eUJBNHZUemJYQV9VWlBUb3JlX0xBdWVZTWtSbVBneU0&usp=drive_web#list
7z x CRF++-0.58.tar.gz
7z x CRF++-0.58.tar
cd CRF++-0.58
chmod +x configure
./configure
make
"""
import pystruct
import pystruct.models
inference_method_options = ['lp', 'max-product']
inference_method = inference_method_options[1]
# graph = pystruct.models.GraphCRF(
# n_states=None,
# n_features=None,
# inference_method=inference_method,
# class_weight=None,
# directed=False,
# )
num_annots = 5
num_names = num_annots
aids = np.arange(5)
rng = np.random.RandomState(0)
hidden_nids = rng.randint(0, num_names, num_annots)
unique_nids, groupxs = ut.group_indices(hidden_nids)
# Indicator vector indicating the name
node_features = np.zeros((num_annots, num_names))
node_features[(aids, hidden_nids)] = 1
toy_params = {True: {'mu': 1.0, 'sigma': 2.2}, False: {'mu': 7.0, 'sigma': 0.9}}
if False:
import vtool as vt
import wbia.plottool as pt
pt.ensureqt()
xdata = np.linspace(0, 100, 1000)
tp_pdf = vt.gauss_func1d(xdata, **toy_params[True])
fp_pdf = vt.gauss_func1d(xdata, **toy_params[False])
pt.plot_probabilities([tp_pdf, fp_pdf], ['TP', 'TF'], xdata=xdata)
def metric(aidx1, aidx2, hidden_nids=hidden_nids, toy_params=toy_params):
if aidx1 == aidx2:
return 0
rng = np.random.RandomState(int(aidx1 + aidx2))
same = hidden_nids[int(aidx1)] == hidden_nids[int(aidx2)]
mu, sigma = ut.dict_take(toy_params[same], ['mu', 'sigma'])
return np.clip(rng.normal(mu, sigma), 0, np.inf)
pairwise_aidxs = list(ut.iprod(range(num_annots), range(num_annots)))
pairwise_labels = np.array( # NOQA
[hidden_nids[a1] == hidden_nids[a2] for a1, a2 in pairwise_aidxs]
)
pairwise_scores = np.array([metric(*zz) for zz in pairwise_aidxs])
pairwise_scores_mat = pairwise_scores.reshape(num_annots, num_annots) # NOQA
graph = pystruct.models.EdgeFeatureGraphCRF( # NOQA
n_states=num_annots,
n_features=num_names,
n_edge_features=1,
inference_method=inference_method,
)
import opengm
numVar = 10
unaries = np.ones([numVar, 3], dtype=opengm.value_type)
gm = opengm.gm(np.ones(numVar, dtype=opengm.label_type) * 3)
unary_fids = gm.addFunctions(unaries)
gm.addFactors(unary_fids, np.arange(numVar))
infParam = opengm.InfParam(workflow=ut.ensure_ascii('(IC)(TTC-I,CC-I)'))
inf = opengm.inference.Multicut(gm, parameter=infParam)
visitor = inf.verboseVisitor(printNth=1, multiline=False)
inf.infer(visitor)
arg = inf.arg()
# gridVariableIndices = opengm.secondOrderGridVis(img.shape[0], img.shape[1])
# fid = gm.addFunction(regularizer)
# gm.addFactors(fid, gridVariableIndices)
# regularizer = opengm.pottsFunction([3, 3], 0.0, beta)
# gridVariableIndices = opengm.secondOrderGridVis(img.shape[0], img.shape[1])
# fid = gm.addFunction(regularizer)
# gm.addFactors(fid, gridVariableIndices)
unaries = np.random.rand(10, 10, 2)
potts = opengm.PottsFunction([2, 2], 0.0, 0.4)
gm = opengm.grid2d2Order(unaries=unaries, regularizer=potts)
inf = opengm.inference.GraphCut(gm)
inf.infer()
arg = inf.arg() # NOQA
def get_toy_data_1v1(num_annots=5, num_names=None, **kwargs):
r"""
CommandLine:
python -m ibeis.algo.hots.demobayes --exec-get_toy_data_1v1 --show
Example:
>>> # ENABLE_DOCTEST
>>> from ibeis.algo.hots.demobayes import * # NOQA
>>> toy_data = get_toy_data_1v1()
>>> ut.quit_if_noshow()
>>> import plottool as pt
>>> show_toy_distributions(toy_data['toy_params'])
>>> ut.show_if_requested()
Example1:
>>> # ENABLE_DOCTEST
>>> from ibeis.algo.hots.demobayes import * # NOQA
>>> toy_data = get_toy_data_1v1()
>>> kwargs = {}
>>> initial_aids = toy_data['aids']
>>> initial_nids = toy_data['nids']
>>> num_annots = 1
>>> num_names = 6
>>> toy_data2 = get_toy_data_1v1(num_annots, num_names, initial_aids=initial_aids, initial_nids=initial_nids)
>>> ut.quit_if_noshow()
>>> import plottool as pt
>>> show_toy_distributions(toy_data['toy_params'])
>>> ut.show_if_requested()
Ignore:
>>> num_annots = 1000
>>> num_names = 400
"""
import vtool as vt
tup_ = get_toy_annots(num_annots, num_names, **kwargs)
aids, nids, aids1, nids1, all_aids, all_nids = tup_
rng = vt.ensure_rng(None)
def pairwise_feature(aidx1,
aidx2,
all_nids=all_nids,
toy_params=toy_params):
if aidx1 == aidx2:
score = -1
else:
#rng = np.random.RandomState(int((aidx1 + 13) * (aidx2 + 13)))
nid1 = all_nids[int(aidx1)]
nid2 = all_nids[int(aidx2)]
params = toy_params[nid1 == nid2]
mu, sigma = ut.dict_take(params, ['mu', 'sigma'])
score_ = rng.normal(mu, sigma)
score = np.clip(score_, 0, np.inf)
return score
pairwise_nids = list([tup[::-1] for tup in ut.iprod(nids, nids1)])
pairwise_matches = np.array([nid1 == nid2 for nid1, nid2 in pairwise_nids])
pairwise_aidxs = list([tup[::-1] for tup in ut.iprod(aids, aids1)])
pairwise_features = np.array(
[pairwise_feature(aidx1, aidx2) for aidx1, aidx2 in pairwise_aidxs])
#pairwise_scores_mat = pairwise_scores.reshape(num_annots, num_annots)
is_diag = [r < c for r, c, in pairwise_aidxs]
diag_scores = pairwise_features.compress(is_diag)
diag_aidxs = ut.compress(pairwise_aidxs, is_diag)
import utool
with utool.embed_on_exception_context:
diag_nids = ut.compress(pairwise_nids, is_diag)
diag_labels = pairwise_matches.compress(is_diag)
#import utool
#utool.embed()
toy_data = {
'aids': aids,
'nids': nids,
'all_nids': all_nids,
'all_aids': all_aids,
#'pairwise_aidxs': pairwise_aidxs,
#'pairwise_scores': pairwise_scores,
#'pairwise_matches': pairwise_matches,
'diag_labels': diag_labels,
'diag_scores': diag_scores,
'diag_nids': diag_nids,
'diag_aidxs': diag_aidxs,
'toy_params': toy_params,
}
return toy_data
def new_cpd(self, parents=None, pmf_func=None):
"""
Makes a new random variable that is an instance of this tempalte
parents : only used to define the name of this node.
"""
if pmf_func is None:
pmf_func = self.pmf_func
# --- MAKE VARIABLE ID
def _getid(obj):
if isinstance(obj, int):
return str(obj)
elif isinstance(obj, six.string_types):
return obj
else:
return obj._template_id
if not ut.isiterable(parents):
parents = [parents]
template_ids = [_getid(cpd) for cpd in parents]
HACK_SAME_IDS = True
# TODO: keep track of parent index inheritence
# then rectify uniqueness based on that
if HACK_SAME_IDS and ut.allsame(template_ids):
_id = template_ids[0]
else:
_id = ''.join(template_ids)
variable = ''.join([self.varpref, _id])
# variable = '_'.join([self.varpref, '{' + _id + '}'])
# variable = '$%s$' % (variable,)
evidence_cpds = [cpd for cpd in parents if hasattr(cpd, 'ttype')]
if len(evidence_cpds) == 0:
evidence_cpds = None
variable_card = len(self.basis)
statename_dict = {
variable: self.basis,
}
if self.evidence_ttypes is not None:
if any(cpd.ttype != tcpd.ttype
for cpd, tcpd in zip(evidence_cpds, evidence_cpds)):
raise ValueError('Evidence is not of appropriate type')
evidence_bases = [cpd.variable_statenames for cpd in evidence_cpds]
evidence_card = list(map(len, evidence_bases))
evidence_states = list(ut.iprod(*evidence_bases))
for cpd in evidence_cpds:
_dict = ut.dict_subset(cpd.statename_dict, [cpd.variable])
statename_dict.update(_dict)
evidence = [cpd.variable for cpd in evidence_cpds]
else:
if evidence_cpds is not None:
raise ValueError('Gave evidence for evidence-less template')
evidence = None
evidence_card = None
# --- MAKE TABLE VALUES
if pmf_func is not None:
if isinstance(pmf_func, list):
values = np.array(pmf_func)
else:
values = np.array([[
pmf_func(vstate, *estates) for estates in evidence_states
] for vstate in self.basis])
ensure_normalized = True
if ensure_normalized:
values = values / values.sum(axis=0)
else:
# assume uniform
fill_value = 1.0 / variable_card
if evidence_card is None:
values = np.full((1, variable_card), fill_value)
else:
values = np.full([variable_card] + list(evidence_card),
fill_value)
try:
cpd = pgmpy.factors.TabularCPD(
variable=variable,
variable_card=variable_card,
values=values,
evidence=evidence,
evidence_card=evidence_card,
# statename_dict=statename_dict,
state_names=statename_dict,
)
except Exception as ex:
ut.printex(
ex,
'Failed to create TabularCPD',
keys=[
'variable',
'variable_card',
'statename_dict',
'evidence_card',
'evidence',
'values.shape',
],
)
ut.embed()
raise
cpd.ttype = self.ttype
cpd._template_ = self
cpd._template_id = _id
return cpd
def get_toy_data_1v1(num_annots=5, num_names=None, **kwargs):
r"""
CommandLine:
python -m ibeis.algo.hots.demobayes --exec-get_toy_data_1v1 --show
Example:
>>> # ENABLE_DOCTEST
>>> from ibeis.algo.hots.demobayes import * # NOQA
>>> toy_data = get_toy_data_1v1()
>>> ut.quit_if_noshow()
>>> import plottool as pt
>>> show_toy_distributions(toy_data['toy_params'])
>>> ut.show_if_requested()
Example1:
>>> # ENABLE_DOCTEST
>>> from ibeis.algo.hots.demobayes import * # NOQA
>>> toy_data = get_toy_data_1v1()
>>> kwargs = {}
>>> initial_aids = toy_data['aids']
>>> initial_nids = toy_data['nids']
>>> num_annots = 1
>>> num_names = 6
>>> toy_data2 = get_toy_data_1v1(num_annots, num_names, initial_aids=initial_aids, initial_nids=initial_nids)
>>> ut.quit_if_noshow()
>>> import plottool as pt
>>> show_toy_distributions(toy_data['toy_params'])
>>> ut.show_if_requested()
Ignore:
>>> num_annots = 1000
>>> num_names = 400
"""
import vtool as vt
tup_ = get_toy_annots(num_annots, num_names, **kwargs)
aids, nids, aids1, nids1, all_aids, all_nids = tup_
rng = vt.ensure_rng(None)
def pairwise_feature(aidx1, aidx2, all_nids=all_nids, toy_params=toy_params):
if aidx1 == aidx2:
score = -1
else:
#rng = np.random.RandomState(int((aidx1 + 13) * (aidx2 + 13)))
nid1 = all_nids[int(aidx1)]
nid2 = all_nids[int(aidx2)]
params = toy_params[nid1 == nid2]
mu, sigma = ut.dict_take(params, ['mu', 'sigma'])
score_ = rng.normal(mu, sigma)
score = np.clip(score_, 0, np.inf)
return score
pairwise_nids = list([tup[::-1] for tup in ut.iprod(nids, nids1)])
pairwise_matches = np.array(
[nid1 == nid2 for nid1, nid2 in pairwise_nids])
pairwise_aidxs = list([tup[::-1] for tup in ut.iprod(aids, aids1)])
pairwise_features = np.array(
[pairwise_feature(aidx1, aidx2) for aidx1, aidx2 in pairwise_aidxs])
#pairwise_scores_mat = pairwise_scores.reshape(num_annots, num_annots)
is_diag = [r < c for r, c, in pairwise_aidxs]
diag_scores = pairwise_features.compress(is_diag)
diag_aidxs = ut.compress(pairwise_aidxs, is_diag)
import utool
with utool.embed_on_exception_context:
diag_nids = ut.compress(pairwise_nids, is_diag)
diag_labels = pairwise_matches.compress(is_diag)
#import utool
#utool.embed()
toy_data = {
'aids': aids,
'nids': nids,
'all_nids': all_nids,
'all_aids': all_aids,
#'pairwise_aidxs': pairwise_aidxs,
#'pairwise_scores': pairwise_scores,
#'pairwise_matches': pairwise_matches,
'diag_labels': diag_labels,
'diag_scores': diag_scores,
'diag_nids': diag_nids,
'diag_aidxs': diag_aidxs,
'toy_params': toy_params,
}
return toy_data
def dummy_cut_example():
r"""
CommandLine:
python -m ibeis.workflow --exec-dummy_cut_example --show
Example:
>>> # DISABLE_DOCTEST
>>> from ibeis.workflow import * # NOQA
>>> result = dummy_cut_example()
>>> print(result)
>>> ut.quit_if_noshow()
>>> import plottool as pt
>>> ut.show_if_requested()
"""
import opengm
import numpy as np
import plottool as pt
pt.ensure_pylab_qt4()
# Matching Graph
cost_matrix = np.array([
[0.5, 0.6, 0.2, 0.4],
[0.0, 0.5, 0.2, 0.9],
[0.0, 0.0, 0.5, 0.1],
[0.0, 0.0, 0.0, 0.5],
])
cost_matrix += cost_matrix.T
number_of_labels = 4
num_annots = 4
#cost_matrix = (cost_matrix * 2) - 1
#gm = opengm.gm(number_of_labels)
gm = opengm.gm(np.ones(num_annots) * number_of_labels)
aids = np.arange(num_annots)
aid_pairs = np.array([(a1, a2) for a1, a2 in ut.iprod(
aids, aids) if a1 != a2], dtype=np.uint32)
aid_pairs.sort(axis=1)
# add a potts function
# penalizes neighbors for having different labels
# beta = 0 # 0.1 # strength of potts regularizer
#beta = 0.1 # 0.1 # strength of potts regularizer
# Places to look for the definition of this stupid class
# ~/code/opengm/src/interfaces/python/opengm/opengmcore/pyFunctionTypes.cxx
# /src/interfaces/python/opengm/opengmcore/function_injector.py
#shape = [number_of_labels] * 2
#regularizer = opengm.PottsGFunction(shape, 0.0, beta)
# __init__( (object)arg1, (object)shape [, (object)values=()]) -> object :
# values = np.arange(1, ut.num_partitions(num_annots) + 1)
#regularizer = opengm.PottsGFunction(shape)
#reg_fid = gm.addFunction(regularizer)
# A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
# http://arxiv.org/pdf/1404.0533.pdf
# regularizer1 = opengm.pottsFunction([number_of_labels] * 2, valueEqual=0.0, valueNotEqual=beta)
# gm.addFactors(reg_fid, aid_pairs)
# 2nd order function
pair_fid = gm.addFunction(cost_matrix)
gm.addFactors(pair_fid, aid_pairs)
if False:
Inf = opengm.inference.BeliefPropagation
parameter = opengm.InfParam(steps=10, damping=0.5, convergenceBound=0.001)
else:
Inf = opengm.inference.Multicut
parameter = opengm.InfParam()
inf = Inf(gm, parameter=parameter)
class PyCallback(object):
def __init__(self,):
self.labels = []
def begin(self, inference):
print("begin of inference")
def end(self, inference):
self.labels.append(inference.arg())
def visit(self, inference):
gm = inference.gm()
labelVector = inference.arg()
print("energy %r" % (gm.evaluate(labelVector),))
self.labels.append(labelVector)
callback = PyCallback()
visitor = inf.pythonVisitor(callback, visitNth=1)
inf.infer(visitor)
print(callback.labels)
print(cost_matrix)
pt.imshow(cost_matrix, cmap='magma')
opengm.visualizeGm(gm=gm)
pass
def crftest():
"""
pip install pyqpbo
pip install pystruct
http://taku910.github.io/crfpp/#install
cd ~/tmp
#wget https://drive.google.com/folderview?id=0B4y35FiV1wh7fngteFhHQUN2Y1B5eUJBNHZUemJYQV9VWlBUb3JlX0xBdWVZTWtSbVBneU0&usp=drive_web#list
7z x CRF++-0.58.tar.gz
7z x CRF++-0.58.tar
cd CRF++-0.58
chmod +x configure
./configure
make
"""
import pystruct
import pystruct.models
inference_method_options = ['lp', 'max-product']
inference_method = inference_method_options[1]
#graph = pystruct.models.GraphCRF(
# n_states=None,
# n_features=None,
# inference_method=inference_method,
# class_weight=None,
# directed=False,
#)
num_annots = 5
num_names = num_annots
aids = np.arange(5)
rng = np.random.RandomState(0)
hidden_nids = rng.randint(0, num_names, num_annots)
unique_nids, groupxs = ut.group_indices(hidden_nids)
# Indicator vector indicating the name
node_features = np.zeros((num_annots, num_names))
node_features[(aids, hidden_nids)] = 1
toy_params = {
True: {'mu': 1.0, 'sigma': 2.2},
False: {'mu': 7.0, 'sigma': .9}
}
if False:
import vtool as vt
import plottool as pt
pt.ensure_pylab_qt4()
xdata = np.linspace(0, 100, 1000)
tp_pdf = vt.gauss_func1d(xdata, **toy_params[True])
fp_pdf = vt.gauss_func1d(xdata, **toy_params[False])
pt.plot_probabilities([tp_pdf, fp_pdf], ['TP', 'TF'], xdata=xdata)
def metric(aidx1, aidx2, hidden_nids=hidden_nids, toy_params=toy_params):
if aidx1 == aidx2:
return 0
rng = np.random.RandomState(int(aidx1 + aidx2))
same = hidden_nids[int(aidx1)] == hidden_nids[int(aidx2)]
mu, sigma = ut.dict_take(toy_params[same], ['mu', 'sigma'])
return np.clip(rng.normal(mu, sigma), 0, np.inf)
pairwise_aidxs = list(ut.iprod(range(num_annots), range(num_annots)))
pairwise_labels = np.array([hidden_nids[a1] == hidden_nids[a2] for a1, a2 in pairwise_aidxs])
pairwise_scores = np.array([metric(*zz) for zz in pairwise_aidxs])
pairwise_scores_mat = pairwise_scores.reshape(num_annots, num_annots)
graph = pystruct.models.EdgeFeatureGraphCRF(
n_states=num_annots,
n_features=num_names,
n_edge_features=1,
inference_method=inference_method,
)
import opengm
numVar = 10
unaries = np.ones([numVar, 3], dtype=opengm.value_type)
gm = opengm.gm(np.ones(numVar, dtype=opengm.label_type) * 3)
unary_fids = gm.addFunctions(unaries)
gm.addFactors(unary_fids, np.arange(numVar))
infParam = opengm.InfParam(
workflow=ut.ensure_ascii('(IC)(TTC-I,CC-I)'),
)
inf = opengm.inference.Multicut(gm, parameter=infParam)
visitor = inf.verboseVisitor(printNth=1, multiline=False)
inf.infer(visitor)
arg = inf.arg()
# gridVariableIndices = opengm.secondOrderGridVis(img.shape[0], img.shape[1])
# fid = gm.addFunction(regularizer)
# gm.addFactors(fid, gridVariableIndices)
# regularizer = opengm.pottsFunction([3, 3], 0.0, beta)
# gridVariableIndices = opengm.secondOrderGridVis(img.shape[0], img.shape[1])
# fid = gm.addFunction(regularizer)
# gm.addFactors(fid, gridVariableIndices)
unaries = np.random.rand(10, 10, 2)
potts = opengm.PottsFunction([2, 2], 0.0, 0.4)
gm = opengm.grid2d2Order(unaries=unaries, regularizer=potts)
inf = opengm.inference.GraphCut(gm)
inf.infer()
arg = inf.arg()
def intra_encounter_matching():
qreq_, cm_list = testdata_workflow()
# qaids = [cm.qaid for cm in cm_list]
# top_aids = [cm.get_top_aids(5) for cm in cm_list]
import numpy as np
from scipy.sparse import coo_matrix, csgraph
aid_pairs = np.array([(cm.qaid, daid) for cm in cm_list for daid in cm.get_top_aids(5)])
top_scores = ut.flatten([cm.get_top_scores(5) for cm in cm_list])
N = aid_pairs.max() + 1
mat = coo_matrix((top_scores, aid_pairs.T), shape=(N, N))
csgraph.connected_components(mat)
tree = csgraph.minimum_spanning_tree(mat) # NOQA
import plottool as pt
dense = mat.todense()
pt.imshow(dense / dense.max() * 255)
pt.show_if_requested()
# load image and convert to LAB
img_fpath = str(ut.grab_test_imgpath(str('lena.png')))
img = vigra.impex.readImage(img_fpath)
imgLab = vigra.colors.transform_RGB2Lab(img)
superpixelDiameter = 15 # super-pixel size
slicWeight = 15.0 # SLIC color - spatial weight
labels, nseg = vigra.analysis.slicSuperpixels(imgLab, slicWeight,
superpixelDiameter)
labels = vigra.analysis.labelImage(labels)-1
# get 2D grid graph and RAG
gridGraph = graphs.gridGraph(img.shape[0:2])
rag = graphs.regionAdjacencyGraph(gridGraph, labels)
nodeFeatures = rag.accumulateNodeFeatures(imgLab)
nodeFeaturesImg = rag.projectNodeFeaturesToGridGraph(nodeFeatures)
nodeFeaturesImg = vigra.taggedView(nodeFeaturesImg, "xyc")
nodeFeaturesImgRgb = vigra.colors.transform_Lab2RGB(nodeFeaturesImg)
#from sklearn.cluster import MiniBatchKMeans, KMeans
from sklearn import mixture
nCluster = 3
g = mixture.GMM(n_components=nCluster)
g.fit(nodeFeatures[:,:])
clusterProb = g.predict_proba(nodeFeatures)
import numpy
#https://github.com/opengm/opengm/blob/master/src/interfaces/python/examples/tutorial/Irregular%20Factor%20Graphs.ipynb
#https://github.com/opengm/opengm/blob/master/src/interfaces/python/examples/tutorial/Hard%20and%20Soft%20Constraints.ipynb
clusterProbImg = rag.projectNodeFeaturesToGridGraph(clusterProb.astype(numpy.float32))
clusterProbImg = vigra.taggedView(clusterProbImg, "xyc")
# strength of potts regularizer
beta = 40.0
# graphical model with as many variables
# as superpixels, each has 3 states
gm = opengm.gm(numpy.ones(rag.nodeNum,dtype=opengm.label_type)*nCluster)
# convert probabilites to energies
probs = numpy.clip(clusterProb, 0.00001, 0.99999)
costs = -1.0*numpy.log(probs)
# add ALL unaries AT ONCE
fids = gm.addFunctions(costs)
gm.addFactors(fids,numpy.arange(rag.nodeNum))
# add a potts function
regularizer = opengm.pottsFunction([nCluster]*2,0.0,beta)
fid = gm.addFunction(regularizer)
# get variable indices of adjacent superpixels
# - or "u" and "v" node id's for edges
uvIds = rag.uvIds()
uvIds = numpy.sort(uvIds,axis=1)
# add all second order factors at once
gm.addFactors(fid,uvIds)
# get super-pixels with slic on LAB image
import opengm
# Matching Graph
cost_matrix = np.array([
[0.5, 0.6, 0.2, 0.4, 0.1],
[0.0, 0.5, 0.2, 0.9, 0.2],
[0.0, 0.0, 0.5, 0.1, 0.1],
[0.0, 0.0, 0.0, 0.5, 0.1],
[0.0, 0.0, 0.0, 0.0, 0.5],
])
cost_matrix += cost_matrix.T
number_of_labels = 5
num_annots = 5
cost_matrix = (cost_matrix * 2) - 1
#gm = opengm.gm(number_of_labels)
gm = opengm.gm(np.ones(num_annots) * number_of_labels)
aids = np.arange(num_annots)
aid_pairs = np.array([(a1, a2) for a1, a2 in ut.iprod(aids, aids) if a1 != a2], dtype=np.uint32)
aid_pairs.sort(axis=1)
# 2nd order function
fid = gm.addFunction(cost_matrix)
gm.addFactors(fid, aid_pairs)
Inf = opengm.inference.BeliefPropagation
#Inf = opengm.inference.Multicut
parameter = opengm.InfParam(steps=10, damping=0.5, convergenceBound=0.001)
parameter = opengm.InfParam()
inf = Inf(gm, parameter=parameter)
class PyCallback(object):
def __init__(self,):
self.labels=[]
pass
def begin(self,inference):
print("begin of inference")
pass
def end(self,inference):
self.labels.append(inference.arg())
pass
def visit(self,inference):
gm=inference.gm()
labelVector=inference.arg()
print("energy %r" % (gm.evaluate(labelVector),))
self.labels.append(labelVector)
pass
callback=PyCallback()
visitor=inf.pythonVisitor(callback,visitNth=1)
inf.infer(visitor)
print(callback.labels)
# baseline jobid
# https://github.com/opengm/opengm/blob/master/src/interfaces/python/examples/tutorial/OpenGM%20tutorial.ipynb
numVar = 10
unaries = np.ones([numVar, 3], dtype=opengm.value_type)
gm = opengm.gm(np.ones(numVar, dtype=opengm.label_type) * 3)
unary_fids = gm.addFunctions(unaries)
gm.addFactors(unary_fids, np.arange(numVar))
infParam = opengm.InfParam(
workflow=ut.ensure_ascii('(IC)(TTC-I,CC-I)'),
)
inf = opengm.inference.Multicut(gm, parameter=infParam)
visitor = inf.verboseVisitor(printNth=1, multiline=False)
inf.infer(visitor)
arg = inf.arg()
# gridVariableIndices = opengm.secondOrderGridVis(img.shape[0], img.shape[1])
# fid = gm.addFunction(regularizer)
# gm.addFactors(fid, gridVariableIndices)
# regularizer = opengm.pottsFunction([3, 3], 0.0, beta)
# gridVariableIndices = opengm.secondOrderGridVis(img.shape[0], img.shape[1])
# fid = gm.addFunction(regularizer)
# gm.addFactors(fid, gridVariableIndices)
unaries = np.random.rand(10, 10, 2)
potts = opengm.PottsFunction([2, 2], 0.0, 0.4)
gm = opengm.grid2d2Order(unaries=unaries, regularizer=potts)
inf = opengm.inference.GraphCut(gm)
inf.infer()
arg = inf.arg() # NOQA
"""
def new_cpd(self, parents=None, pmf_func=None):
"""
Makes a new random variable that is an instance of this tempalte
parents : only used to define the name of this node.
"""
if pmf_func is None:
pmf_func = self.pmf_func
# --- MAKE VARIABLE ID
def _getid(obj):
if isinstance(obj, int):
return str(obj)
elif isinstance(obj, six.string_types):
return obj
else:
return obj._template_id
if not ut.isiterable(parents):
parents = [parents]
template_ids = [_getid(cpd) for cpd in parents]
HACK_SAME_IDS = True
# TODO: keep track of parent index inheritence
# then rectify uniqueness based on that
if HACK_SAME_IDS and ut.list_allsame(template_ids):
_id = template_ids[0]
else:
_id = ''.join(template_ids)
variable = ''.join([self.varpref, _id])
#variable = '_'.join([self.varpref, '{' + _id + '}'])
#variable = '$%s$' % (variable,)
evidence_cpds = [cpd for cpd in parents if hasattr(cpd, 'ttype')]
if len(evidence_cpds) == 0:
evidence_cpds = None
variable_card = len(self.basis)
statename_dict = {
variable: self.basis,
}
if self.evidence_ttypes is not None:
if any(cpd.ttype != tcpd.ttype
for cpd, tcpd in zip(evidence_cpds, evidence_cpds)):
raise ValueError('Evidence is not of appropriate type')
evidence_bases = [cpd.variable_statenames for cpd in evidence_cpds]
evidence_card = list(map(len, evidence_bases))
evidence_states = list(ut.iprod(*evidence_bases))
for cpd in evidence_cpds:
_dict = ut.dict_subset(cpd.statename_dict, [cpd.variable])
statename_dict.update(_dict)
evidence = [cpd.variable for cpd in evidence_cpds]
else:
if evidence_cpds is not None:
raise ValueError('Gave evidence for evidence-less template')
evidence = None
evidence_card = None
# --- MAKE TABLE VALUES
if pmf_func is not None:
if isinstance(pmf_func, list):
values = np.array(pmf_func)
else:
values = np.array([
[pmf_func(vstate, *estates) for estates in evidence_states]
for vstate in self.basis
])
ensure_normalized = True
if ensure_normalized:
values = values / values.sum(axis=0)
else:
# assume uniform
fill_value = 1.0 / variable_card
if evidence_card is None:
values = np.full((1, variable_card), fill_value)
else:
values = np.full([variable_card] + list(evidence_card), fill_value)
try:
cpd = pgmpy.factors.TabularCPD(
variable=variable,
variable_card=variable_card,
values=values,
evidence=evidence,
evidence_card=evidence_card,
statename_dict=statename_dict,
)
except Exception as ex:
ut.printex(ex, 'Failed to create TabularCPD',
keys=[
'variable',
'variable_card',
'statename_dict',
'evidence_card',
'evidence',
'values.shape',
])
raise
cpd.ttype = self.ttype
cpd._template_ = self
cpd._template_id = _id
return cpd
def dummy_cut_example():
r"""
CommandLine:
python -m ibeis.workflow --exec-dummy_cut_example --show
Example:
>>> # DISABLE_DOCTEST
>>> from ibeis.workflow import * # NOQA
>>> result = dummy_cut_example()
>>> print(result)
>>> ut.quit_if_noshow()
>>> import plottool as pt
>>> ut.show_if_requested()
"""
import opengm
import numpy as np
import plottool as pt
pt.ensure_pylab_qt4()
# Matching Graph
cost_matrix = np.array([
[0.5, 0.6, 0.2, 0.4],
[0.0, 0.5, 0.2, 0.9],
[0.0, 0.0, 0.5, 0.1],
[0.0, 0.0, 0.0, 0.5],
])
cost_matrix += cost_matrix.T
number_of_labels = 4
num_annots = 4
#cost_matrix = (cost_matrix * 2) - 1
#gm = opengm.gm(number_of_labels)
gm = opengm.gm(np.ones(num_annots) * number_of_labels)
aids = np.arange(num_annots)
aid_pairs = np.array([(a1, a2)
for a1, a2 in ut.iprod(aids, aids) if a1 != a2],
dtype=np.uint32)
aid_pairs.sort(axis=1)
# add a potts function
# penalizes neighbors for having different labels
# beta = 0 # 0.1 # strength of potts regularizer
#beta = 0.1 # 0.1 # strength of potts regularizer
# Places to look for the definition of this stupid class
# ~/code/opengm/src/interfaces/python/opengm/opengmcore/pyFunctionTypes.cxx
# /src/interfaces/python/opengm/opengmcore/function_injector.py
#shape = [number_of_labels] * 2
#regularizer = opengm.PottsGFunction(shape, 0.0, beta)
# __init__( (object)arg1, (object)shape [, (object)values=()]) -> object :
# values = np.arange(1, ut.num_partitions(num_annots) + 1)
#regularizer = opengm.PottsGFunction(shape)
#reg_fid = gm.addFunction(regularizer)
# A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
# http://arxiv.org/pdf/1404.0533.pdf
# regularizer1 = opengm.pottsFunction([number_of_labels] * 2, valueEqual=0.0, valueNotEqual=beta)
# gm.addFactors(reg_fid, aid_pairs)
# 2nd order function
pair_fid = gm.addFunction(cost_matrix)
gm.addFactors(pair_fid, aid_pairs)
if False:
Inf = opengm.inference.BeliefPropagation
parameter = opengm.InfParam(steps=10,
damping=0.5,
convergenceBound=0.001)
else:
Inf = opengm.inference.Multicut
parameter = opengm.InfParam()
inf = Inf(gm, parameter=parameter)
class PyCallback(object):
def __init__(self, ):
self.labels = []
def begin(self, inference):
print("begin of inference")
def end(self, inference):
self.labels.append(inference.arg())
def visit(self, inference):
gm = inference.gm()
labelVector = inference.arg()
print("energy %r" % (gm.evaluate(labelVector), ))
self.labels.append(labelVector)
callback = PyCallback()
visitor = inf.pythonVisitor(callback, visitNth=1)
inf.infer(visitor)
print(callback.labels)
print(cost_matrix)
pt.imshow(cost_matrix, cmap='magma')
opengm.visualizeGm(gm=gm)
pass
