def create_aggretriever(aggregation_info):
"""This function works to aggregate a retriever following the instructions
input in the aggregation_info variable. It returns an instance of a
retriever object to be appended in the collection manager list of
retrievers.
Parameters
----------
aggregation_info: tuple
the information to create a retriever aggregation.
Returns
-------
ret_out: pst.BaseRetriever
the retriever instance.
"""
## 0. Preparing inputs
assert type(aggregation_info) == tuple
disc_info, _, retriever_out, agg_info = aggregation_info
assert type(agg_info) == tuple
assert len(agg_info) == 2
aggregating_ret, _ = agg_info
## 1. Computing retriever_out
locs, regs, disc = _discretization_parsing_creation(disc_info)
ret_out = aggregating_ret(retriever_out, locs, regs, disc)
assert isinstance(ret_out, BaseRetriever)
return ret_out
def create_m_in_direct_discretization(discretization_info):
"""Create in_map for direct discretization.
Parameters
----------
discretization_info: tuple or pst.BaseSpatialDiscretizor
It is defined by a discretization object or a tuple of locations,
regions and discretization object. The standard inputs of that
function parameter are:
* (discretizator, locs)
* (locs, regions)
* disc
* locs, regs, disc
Returns
-------
m_in_direct_discretazation: function
the function which formats the input of the retriever.
"""
## 0. Parsing discretization information input
locs, regions, disc = _discretization_parsing_creation(discretization_info)
## 1. Building map
if disc is not None:
def m_in_direct_discretazation(self, idxs):
"""Direct application of the discretization information."""
return [disc.discretize(locs[i]) for i in idxs]
else:
def m_in_direct_discretazation(self, idxs):
"""Direct application of the discretization information."""
return [np.array(regions[e]) for e in idxs]
return m_in_direct_discretazation
def create_m_in_inverse_discretization(discretization_info):
"""Create in_map for inverse discretization.
Parameters
----------
discretization_info: tuple or pst.BaseSpatialDiscretizor
It is defined by a discretization object or a tuple of locations,
regions and discretization object. The standard inputs of that
function parameter are:
* (discretizator, locs)
* (locs, regions)
* disc
* locs, regs, disc
Returns
-------
m_in_inverse_discretazation: function
the function which formats the input of the retriever.
"""
## 0. Parsing discretization information input
locs, regions, disc = _discretization_parsing_creation(discretization_info)
## 1. Building map
def m_in_inverse_discretazation(self, idxs):
"""Inverse application of the discretization information."""
new_idxs = []
for i in idxs:
new_idxs.append(np.where(regions == i)[0])
return new_idxs
return m_in_inverse_discretazation
def create_m_out_inverse_discretization(discretization_info):
"""Create out_map for inverse discretization.
Parameters
----------
discretization_info: tuple or pst.BaseSpatialDiscretizor
It is defined by a discretization object or a tuple of locations,
regions and discretization object. The standard inputs of that
function parameter are:
* (discretizator, locs)
* (locs, regions)
* disc
* locs, regs, disc
Returns
-------
m_out_inverse_discretization: function
the function which formats the output of the retriever.
"""
## 0. Parsing discretization information input
locs, regions, disc = _discretization_parsing_creation(discretization_info)
## 1. Building map
if type(regions) == np.ndarray:
def m_out_inverse_discretization(self, idxs, neighs_info):
"""This out_map for retrievers change the size of neighbourhood by
substituting the regions_id or groups_id in the neighs_info for the
elements which belong to this groups.
"""
neighs, dists = neighs_info
neighs_o, dists_o = [], []
for iss_i in range(len(neighs)):
neighs_p, dists_p = [], []
for i in range(len(neighs[iss_i])):
neighs_ip = np.where(regions == neighs[iss_i][i])[0]
neighs_p.append(neighs_ip)
if dists[iss_i] is not None:
sh = len(neighs_ip), 1
dists_p.append(np.ones(sh) * dists[iss_i][i])
if neighs_p:
neighs_p = np.concatenate(neighs_p)
if dists_p:
dists_p = np.concatenate(dists_p)
else:
dists_p = np.ones((0, 1))
neighs_o.append(neighs_p)
dists_o.append(dists_p)
return neighs_o, dists_o
return m_out_inverse_discretization
def create_aggfeatures(sp_descriptor, features):
"""Average distance of points of the different regions.
Function to compute the spatial distances between regions.
Parameters
----------
sp_descriptor: tuple (aggregation_info format) or SpatialDescriptorModel
the information to compute aggregation.
features: pst.BaseFeatures
the features we want to aggregate.
Returns
-------
new_exlicit_features: pst.Features object
the features object obtained by aggregating the features.
"""
## 1. Computing
if type(sp_descriptor) == tuple:
## 0. Parsing inputs
disc_info, retriever_in, _, agg_info = sp_descriptor
assert type(agg_info) == tuple
assert len(agg_info) == 2
_, aggregating_feat = agg_info
agg_f_ret, desc_in, pars_feat_in, pars_feats, desc_out = _parse_aggregation_feat(aggregating_feat, features)
## Retrievers
locs, regs, disc = _discretization_parsing_creation(disc_info)
retrievers = agg_f_ret(retriever_in, locs, regs, disc)
## Featurers
# Feature creation
object_feats, core_features, pars_fea_o_in = features.export_features()
pars_fea_o_in["descriptormodel"] = desc_in
new_features = object_feats(core_features, **pars_fea_o_in)
# Feature manager creation
pars_feat_in["maps_vals_i"] = regs
pars_feat_in["selectors"] = (0, 0), (0, 0), (0, 0)
featurers = FeaturesManager(new_features, **pars_feat_in)
## 1. Preparing spdesc object
spdesc = SpatialDescriptorModel(retrievers, featurers)
## 2. Compute
aggfeatures = spdesc.compute()
else:
aggfeatures = sp_descriptor.compute()
pars_feats = {}
desc_out = sp_descriptor.featurers.features[0].descriptormodel
## 3. Creation of the object features aggregations
new_exlicit_features = _featuresobject_parsing_creation((aggfeatures, pars_feats, desc_out))
return new_exlicit_features
def test():
## 0. Artificial data
# Parameters
n = 1000
ngx, ngy = 100, 100
# Artificial distribution in space
fucnts = [lambda locs: locs[:, 0]*np.cos(locs[:, 1]*2*np.pi),
lambda locs: locs[:, 0]*np.sin(locs[:, 1]*np.pi*2)]
locs1 = random_transformed_space_points(n, 2, None)
locs2 = random_transformed_space_points(n, 2, fucnts)
locs3 = random_transformed_space_points(n/100, 2, None)
Locs = [locs1, locs2, locs3]
# Set discretization
elements1 = np.random.randint(0, 50, 200)
elements2 = np.random.randint(0, 2000, 200)
#
# ## Test distributions
# #fig1 = plt.plot(locs[:,0], locs[:, 1], '.')
# #fig2 = plt.plot(locs2[:,0], locs2[:, 1], '.')
#
### Testing utils
# Discretization 2d utils
regions_id = np.arange(10)
indices = np.unique(np.random.randint(0, 10, 5))
indices_assignation(indices, regions_id)
mask_application_grid(np.random.random(), np.random.random(10))
#compute_limital_polygon(limits)
#match_regions(polygons, regionlocs, n_dim=2)
# testing voronoi tesselation
tesselation(np.random.random((10, 2)))
# Checker
try:
boolean = False
check_discretizors(5)
boolean = True
raise Exception("It has to halt here.")
except:
if boolean:
raise Exception("It has to halt here.")
class Prueba:
def __init__(self):
self.n_dim = 9
self.metric = None
self.format_ = None
try:
boolean = False
check_discretizors(Prueba)
boolean = True
raise Exception("It has to halt here.")
except:
if boolean:
raise Exception("It has to halt here.")
class Prueba:
def __init__(self):
self._compute_limits = 9
self._compute_contiguity_geom = None
self._map_loc2regionid = None
self._map_regionid2regionlocs = None
try:
boolean = False
check_discretizors(Prueba)
boolean = True
raise Exception("It has to halt here.")
except:
if boolean:
raise Exception("It has to halt here.")
### Discretization
############################# Grid discretizer ############################
disc1 = GridSpatialDisc((ngx, ngy), xlim=(0, 1), ylim=(0, 1))
disc2 = GridSpatialDisc((ngx, ngy), xlim=(-1, 1), ylim=(-1, 1))
mapping2grid(Locs[0], (ngx, ngy), xlim=(0, 1), ylim=(0, 1))
compute_contiguity_grid(-10, (ngx, ngy))
# Test functions
disc1[0]
disc1[locs1[0]]
len(disc1)
for i in range(len(Locs)):
disc1.discretize(Locs[i])
disc1.map_locs2regionlocs(Locs[i])
disc1.map2agglocs(Locs[i])
disc1._map_regionid2regionlocs(0)
disc1._map_locs2regionlocs(Locs[i])
disc1.retrieve_region(Locs[i][0], {})
disc1.retrieve_neigh(Locs[i][0], Locs[i])
disc1.get_activated_regions(Locs[i])
disc1.belong_region(Locs[i])
disc1.belong_region(Locs[i], disc1[0])
disc1.check_neighbors([disc1[0], disc1[1]], disc1[2])
disc1.get_limits()
disc1.get_limits(disc1[0])
# General functions applyable to this class
disc1.map_locs2regionlocs(Locs[i])
disc1.map2agglocs(Locs[i])
disc1.get_contiguity()
## Special functions (recomendable to elevate in the hierharchy)
disc1.get_nregs()
disc1.get_regions_id()
disc1.get_regionslocs()
## Class functions
disc1._compute_contiguity_geom()
disc1._compute_contiguity_geom(disc1[0])
########################### Bisector discretizer ##########################
try:
boolean = False
disc6 = BisectorSpatialDisc(locs3, np.arange(len(locs3)+1))
boolean = True
raise Exception("It has to halt here.")
except:
if boolean:
raise Exception("It has to halt here.")
disc6 = BisectorSpatialDisc(locs3, np.arange(len(locs3)))
# Test functions
disc6[0]
disc6[locs1[0]]
len(disc6)
for i in range(len(Locs)):
disc6.discretize(Locs[i])
disc6.map_locs2regionlocs(Locs[i])
disc6.map2agglocs(Locs[i])
disc6._map_regionid2regionlocs(0)
disc6._map_locs2regionlocs(Locs[i])
disc6.retrieve_region(Locs[i][0], {})
disc6.retrieve_neigh(Locs[i][0], Locs[i])
disc6.get_activated_regions(Locs[i])
disc6.belong_region(Locs[i])
disc6.belong_region(Locs[i], disc6[0])
disc6.check_neighbors([disc6[0], disc6[1]], disc6[2])
## Not implemented yet
#disc6.get_contiguity()
#disc6.get_contiguity(disc6[0])
#disc6.get_limits()
#disc6.get_limits(disc6[0])
########################### Circular discretizer ##########################
# Parameters
centers = np.random.random((20, 2))
radios = np.random.random(20)/5
jit = np.random.random((100, 2))
locs_r = centers[np.random.randint(0, 20, 100)] + jit/100000.
regions_ids = [np.arange(20), np.arange(10, 30)]
# General tests
disc4 = CircularSpatialDisc(centers, 0.5)
disc4._compute_limits(disc4.regions_id[0])
disc4._map_regionid2regionlocs(0)
try:
boolean = False
disc4._map_regionid2regionlocs(-1)
boolean = True
raise Exception("It has to halt here.")
except:
if boolean:
raise Exception("It has to halt here.")
# Exhaustive tests
for j in range(len(regions_ids)):
disc4 = CircularInclusiveSpatialDisc(centers, radios, regions_ids[j])
disc5 = CircularExcludingSpatialDisc(centers, radios, regions_ids[j])
# Testing functions
for i in range(len(Locs)):
disc4.discretize(Locs[i])
# disc4.map_locs2regionlocs(Locs[i])
# disc4.map2agglocs(Locs[i])
# disc4._map_regionid2regionlocs(0)
# disc4._map_locs2regionlocs(Locs[i])
# disc4.retrieve_region(Locs[i][0], {})
# disc4.retrieve_neigh(Locs[i][0], Locs[i])
# disc4.get_activated_regions(Locs[i])
# disc4.belong_region(Locs[i])
# disc4.belong_region(Locs[i], disc4[0])
# disc4.check_neighbors([disc4[0], disc4[1]], disc4[2])
# ## Not implemented yet
# #disc4.get_contiguity()
# #disc4.get_contiguity(disc6[0])
# #disc4.get_limits(Locs[i])
# #disc4.get_limits(Locs[i], disc6[0])
disc5.discretize(Locs[i])
# #disc5.map_locs2regionlocs(Locs[i])
# disc5.map2agglocs(Locs[i])
# disc5.retrieve_region(Locs[i][0], {})
# disc5.retrieve_neigh(Locs[i][0], Locs[i])
# disc5.get_activated_regions(Locs[i])
# disc5.belong_region(Locs[i])
# disc5.belong_region(Locs[i], disc5[0])
# disc5.check_neighbors([disc5[0], disc5[1]], disc5[2])
# ## Not implemented yet
# #disc5.get_contiguity()
# #disc5.get_contiguity(disc5[0])
# #disc5.get_limits(Locs[i])
# #disc5.get_limits(Locs[i], disc5[0])
disc4.discretize(locs_r)
#disc4.map_locs2regionlocs(locs_r)
disc4.map2agglocs(locs_r)
disc4.get_activated_regions(locs_r)
disc4.belong_region(locs_r)
disc4.belong_region(locs_r, disc4[0])
disc5.discretize(locs_r)
#disc5.map_locs2regionlocs(locs_r)
disc5.map2agglocs(locs_r)
disc5.get_activated_regions(locs_r)
disc5.belong_region(locs_r)
disc5.belong_region(locs_r, disc5[0])
############################## Set discretizer ############################
## Format auxiliar functions
random_membership(10, 20, True)
random_membership(10, 20, False)
memb, out = format_membership(randint_sparse_matrix(0.2, (2000, 100), 1))
# to_sparse(memb, out)
# memb, out = format_membership(np.random.random((20, 10)))
to_sparse(memb, out)
memb, out = format_membership(list_membership(20, 10))
to_sparse(memb, out)
memb0 = list_membership(10, 20)
memb0 = [list(e) for e in memb0]
memb, out = format_membership(memb0)
to_sparse(memb, out)
memb0 = list_membership(10, 20)
memb0[0] = 0
memb, out = format_membership(memb0)
to_sparse(memb, out)
memb0 = [[np.random.randint(0, 20)] for e in range(10)]
memb, out = format_membership(memb0)
to_sparse(memb, out)
memb0 = list_membership(10, 20)
memb0 = [dict(zip(m, len(m)*[{}])) for m in memb0]
memb, out = format_membership(memb0)
to_sparse(memb, out)
find_idx_in_array(10, np.arange(40))
## Format discretizer
disc6 = SetDiscretization(np.random.randint(0, 2000, 50))
# Test functions
disc6[0]
disc6[disc6.regionlocs[0]]
len(disc6)
disc6.borders
disc6.discretize(disc6.regionlocs)
disc6._map_regionid2regionlocs(0)
disc6.retrieve_region(disc6.regionlocs[0], {})
disc6.retrieve_neigh(disc6.regionlocs[0], disc6.regionlocs)
disc6.get_activated_regions(disc6.regionlocs)
disc6.belong_region(disc6.regionlocs)
disc6.belong_region(disc6.regionlocs, disc6[0])
disc6.check_neighbors([disc6[0], disc6[1]], disc6[2])
# disc6.get_limits()
# disc6.get_limits(disc6.regions_id[0])
disc7 = SetDiscretization(randint_sparse_matrix(0.2, (2000, 100), 1))
# Test functions
disc7[0]
disc7.borders
disc7[disc7.regionlocs[0]]
len(disc7)
disc7.discretize(disc7.regionlocs)
disc7._map_regionid2regionlocs(0)
disc7.retrieve_region(disc7.regionlocs[0], {})
disc7.retrieve_neigh(disc7.regionlocs[0], disc7.regionlocs)
disc7.get_activated_regions(disc7.regionlocs)
# disc7.belong_region(disc6.regionlocs)
# disc7.belong_region(disc6.regionlocs, disc7[0])
# disc7.check_neighbors([disc7[0], disc7[1]], disc7[2])
# disc7.get_limits()
# disc7.get_limits(disc6.regions_id[0])
###########################################################################
#### Testing auxiliar parsing
locs = np.random.random((100, 2))
discretization_info = disc1, locs
_discretization_parsing_creation(discretization_info)
discretization_info = locs, np.random.randint(0, 10, 100)
locs, regs, discs = _discretization_parsing_creation(discretization_info)
disc1.discretize(locs)
locs, regs, discs = _discretization_parsing_creation((locs, regs, discs))
regs, locs = _discretization_regionlocs_parsing_creation(disc1)
# assert(len(regs) == len(locs))
regs, locs = _discretization_regionlocs_parsing_creation((disc1, locs))
# assert(len(regs) == len(locs))
regs, locs = _discretization_regionlocs_parsing_creation((disc1, locs),
None, True)
# assert(len(regs) == len(locs))
locs = np.random.random((100, 2))
disc1 = GridSpatialDisc((ngx, ngy), xlim=(0, 1), ylim=(0, 1))
regs, locs = _discretization_regionlocs_parsing_creation((disc1, locs),
np.arange(100),
True)
# assert(len(regs) == len(locs))
regs, locs = _discretization_regionlocs_parsing_creation((disc1, locs),
np.arange(100),
False)
def compute_AvgDistanceRegions(sp_descriptor, store='network', elements=None,
symmetric=False, activated=None):
"""Average distance of points of the different regions.
Function to compute the spatial distances between regions.
Parameters
----------
locs: np.ndarray
the locations of the elements.
discretizor: pst.Discretization object
the discretization information to transform locations into regions.
store: optional, ['network', 'sparse', 'matrix']
the type of object we want to store the relation metric.
elements: array_like, list or None
the regions we want to use for measure the metric distance between
them.
activated: numpy.ndarray or None
the location points we want to know if we use the regions non-empty
or None if we want to use all of them.
Returns
-------
relations: networkx, scipy.sparse, np.ndarray
the relationship information between regions.
_data: np.ndarray
the regions_id.
symmetric: boolean
if the relations are symmetric or not (in order to save memory space).
store: str
how we want to store the relations.
"""
pars_rel = {'distanceorweighs': False, 'symmetric': symmetric}
## 1. Computing
if type(sp_descriptor) == tuple:
disc_info, retriever_info, _ = sp_descriptor
locs, regs, _ = _discretization_parsing_creation(disc_info)
assert(retriever_info is not None)
retriever_info = tuple([retriever_info[0]] + [locs] +
list(retriever_info[1:]))
# Preparing descriptormodel
_data = np.unique(regs)
## WARNING:
#map_idx = lambda reg: reg
map_idx = lambda reg: np.where(_data == reg)[0][0]
descriptormodel =\
NormalizedDistanceDescriptor(regs, len(_data), map_idx=map_idx)
# Preparing spdesc
feats_info = PhantomFeatures((None, len(_data)),
descriptormodel=descriptormodel)
# Map_vals_i setting
pars_feats = {'maps_vals_i': regs}
feats_info = feats_info, pars_feats
sp_descriptor = _spdesc_parsing_creation(retriever_info, feats_info)
# Compute
relations = sp_descriptor.compute()[:, :, 0]
else:
relations = sp_descriptor.compute()[:, :, 0]
_data = np.arange(len(relations))
## 2. Formatting output
if store == 'matrix':
pass
elif store == 'sparse':
relations = coo_matrix(relations)
elif store == 'network':
relations = coo_matrix(relations)
relations = nx.from_scipy_sparse_matrix(relations)
mapping = dict(zip(relations.nodes(), _data.ravel()))
relations = nx.relabel_nodes(relations, mapping)
pars_rel = {'symmetric': symmetric, 'store': store}
return relations, pars_rel, _data
def create_m_out_direct_discretization(discretization_info):
"""Create out_map for inverse discretization.
Parameters
----------
discretization_info: tuple or pst.BaseSpatialDiscretizor
It is defined by a discretization object or a tuple of locations,
regions and discretization object. The standard inputs of that
function parameter are:
* (discretizator, locs)
* (locs, regions)
* disc
* locs, regs, disc
Returns
-------
m_out_direct_discretization: function
the function which formats the output of the retriever.
"""
## 0. Parsing discretization information input
locs, regions, disc = _discretization_parsing_creation(discretization_info)
## 1. Building map
if disc is None:
def m_out_direct_discretization(self, idxs, neighs_info):
"""This out_map for retrievers don't change the size of
neighbourhood, only substitutes the element id for the group or
regions id. It is useful for PhantomFeatures and direct distance
features. Distance don't change.
Parameters
----------
neighs_info: tuple (neighs, dists)
the neighbourhood information.
Returns
-------
neighs_info: tuple (neighs, dists)
the neighbourhood information.
"""
neighs, dists = neighs_info
neighs_o = []
for iss_i in range(len(neighs)):
neighs_p = []
for i in range(len(neighs[iss_i])):
neighs_ip = np.array([regions[neighs[iss_i][i]]]).ravel()
neighs_p.append(neighs_ip)
if neighs_p:
neighs_p = np.concatenate(neighs_p)
neighs_o.append(neighs_p)
return neighs_o, dists
else:
def m_out_direct_discretization(self, idxs, neighs_info):
"""This out_map for retrievers don't change the size of
neighbourhood, only substitutes the element id for the group or
regions id. It is useful for PhantomFeatures and direct distance
features. Distance don't change.
Parameters
----------
neighs_info: tuple (neighs, dists)
the neighbourhood information.
Returns
-------
neighs_info: tuple (neighs, dists)
the neighbourhood information.
"""
neighs, dists = neighs_info
neighs_o = []
for iss_i in range(len(neighs)):
neighs_p = []
for i in range(len(neighs[iss_i])):
neighs_ip = disc.discretize(locs[neighs[iss_i][i]])
neighs_p.append(np.array([neighs_ip]).ravel())
if neighs_p:
neighs_p = np.concatenate(neighs_p)
neighs_o.append(neighs_p)
return neighs_o, dists
return m_out_direct_discretization
