def local_bivariate_stat(self, subquery, attr1, attr2,
permutations, geom_col, id_col,
w_type, num_ngbrs):
"""
Moran's I (local) Bivariate (untested)
"""
params = OrderedDict([("id_col", id_col),
("attr1", attr1),
("attr2", attr2),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
result = self.data_provider.get_moran(w_type, params)
# collect attributes
attr1_vals = pu.get_attributes(result, 1)
attr2_vals = pu.get_attributes(result, 2)
# create weights
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local_BV(attr1_vals, attr2_vals, weight,
permutations=permutations)
# find clustering of significance
lisa_sig = quad_position(lisa.q)
return zip(lisa.Is, lisa_sig, lisa.p_sim, weight.id_order)
def local_rate_stat(self, subquery, numerator, denominator,
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I Local Rate
Andy Eschbacher
"""
# geometries with values that are null are ignored
# resulting in a collection of not as near neighbors
params = OrderedDict([("id_col", id_col),
("numerator", numerator),
("denominator", denominator),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
result = self.data_provider.get_moran(w_type, params)
# collect attributes
numer = pu.get_attributes(result, 1)
denom = pu.get_attributes(result, 2)
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local_Rate(numer, denom, weight,
permutations=permutations)
# find quadrants for each geometry
quads = quad_position(lisa.q)
return zip(lisa.Is, quads, lisa.p_sim, weight.id_order, lisa.y)
def local_stat(self, subquery, attr,
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I implementation for PL/Python
Andy Eschbacher
"""
# geometries with attributes that are null are ignored
# resulting in a collection of not as near neighbors
params = OrderedDict([("id_col", id_col),
("attr1", attr),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
result = self.data_provider.get_moran(w_type, params)
attr_vals = pu.get_attributes(result)
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local(attr_vals, weight,
permutations=permutations)
# find quadrants for each geometry
quads = quad_position(lisa.q)
return zip(lisa.Is, quads, lisa.p_sim, weight.id_order, lisa.y)
def global_stat(self, subquery, attr_name,
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I (global)
Implementation building neighbors with a PostGIS database and Moran's I
core clusters with PySAL.
Andy Eschbacher
"""
params = OrderedDict([("id_col", id_col),
("attr1", attr_name),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
result = self.data_provider.get_moran(w_type, params)
# collect attributes
attr_vals = pu.get_attributes(result)
# calculate weights
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate moran global
moran_global = ps.esda.moran.Moran(attr_vals, weight,
permutations=permutations)
return zip([moran_global.I], [moran_global.EI])
def global_rate_stat(self, subquery, numerator, denominator,
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I Rate (global)
Andy Eschbacher
"""
params = OrderedDict([("id_col", id_col),
("attr1", numerator),
("attr2", denominator)
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
result = self.data_provider.get_moran(w_type, params)
# collect attributes
numer = pu.get_attributes(result, 1)
denom = pu.get_attributes(result, 2)
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate moran global rate
lisa_rate = ps.esda.moran.Moran_Rate(numer, denom, weight,
permutations=permutations)
return zip([lisa_rate.I], [lisa_rate.EI])
def getis_ord(self, subquery, attr, w_type, num_ngbrs, permutations,
geom_col, id_col):
"""
Getis-Ord's G*
Implementation building neighbors with a PostGIS database and PySAL's
Getis-Ord's G* hotspot/coldspot module.
Andy Eschbacher
"""
# geometries with attributes that are null are ignored
# resulting in a collection of not as near neighbors if kNN is chosen
qvals = OrderedDict([("id_col", id_col), ("attr1", attr),
("geom_col", geom_col), ("subquery", subquery),
("num_ngbrs", num_ngbrs)])
result = self.data_provider.get_getis(w_type, qvals)
attr_vals = pu.get_attributes(result)
# build PySAL weight object
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate Getis-Ord's G* z- and p-values
getis = ps.esda.getisord.G_Local(attr_vals,
weight,
star=True,
permutations=permutations)
return zip(getis.z_sim, getis.p_sim, getis.p_z_sim, weight.id_order)
def moran_local_bv(subquery, attr1, attr2, permutations, geom_col, id_col,
w_type, num_ngbrs):
"""
Moran's I (local) Bivariate (untested)
"""
plpy.notice('** Constructing query')
qvals = {
"num_ngbrs": num_ngbrs,
"attr1": attr1,
"attr2": attr2,
"subquery": subquery,
"geom_col": geom_col,
"id_col": id_col
}
query = pu.construct_neighbor_query(w_type, qvals)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(4)
except plpy.SPIError:
plpy.error("Error: areas of interest query failed, " \
"check input parameters")
plpy.notice('** Query failed: "%s"' % query)
return pu.empty_zipped_array(4)
## collect attributes
attr1_vals = pu.get_attributes(result, 1)
attr2_vals = pu.get_attributes(result, 2)
# create weights
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local_BV(attr1_vals,
attr2_vals,
weight,
permutations=permutations)
plpy.notice("len of Is: %d" % len(lisa.Is))
# find clustering of significance
lisa_sig = quad_position(lisa.q)
plpy.notice('** Finished calculations')
return zip(lisa.Is, lisa_sig, lisa.p_sim, weight.id_order)
def moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs,
permutations, geom_col, id_col):
"""
Moran's I Local Rate
Andy Eschbacher
"""
# geometries with values that are null are ignored
# resulting in a collection of not as near neighbors
query = pu.construct_neighbor_query(
w_type, {
"id_col": id_col,
"numerator": numerator,
"denominator": denominator,
"geom_col": geom_col,
"subquery": subquery,
"num_ngbrs": num_ngbrs
})
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(5)
except plpy.SPIError:
plpy.error(
'Error: areas of interest query failed, check input parameters')
plpy.notice('** Query failed: "%s"' % query)
plpy.notice('** Error: %s' % plpy.SPIError)
return pu.empty_zipped_array(5)
## collect attributes
numer = pu.get_attributes(result, 1)
denom = pu.get_attributes(result, 2)
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local_Rate(numer,
denom,
weight,
permutations=permutations)
# find units of significance
quads = quad_position(lisa.q)
return zip(lisa.Is, quads, lisa.p_sim, weight.id_order, lisa.y)
def moran_local_bv(subquery, attr1, attr2,
permutations, geom_col, id_col, w_type, num_ngbrs):
"""
Moran's I (local) Bivariate (untested)
"""
plpy.notice('** Constructing query')
qvals = OrderedDict([("id_col", id_col),
("attr1", attr1),
("attr2", attr2),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(4)
except plpy.SPIError:
plpy.error("Error: areas of interest query failed, " \
"check input parameters")
plpy.notice('** Query failed: "%s"' % query)
return pu.empty_zipped_array(4)
## collect attributes
attr1_vals = pu.get_attributes(result, 1)
attr2_vals = pu.get_attributes(result, 2)
# create weights
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local_BV(attr1_vals, attr2_vals, weight,
permutations=permutations)
plpy.notice("len of Is: %d" % len(lisa.Is))
# find clustering of significance
lisa_sig = quad_position(lisa.q)
plpy.notice('** Finished calculations')
return zip(lisa.Is, lisa_sig, lisa.p_sim, weight.id_order)
def global_stat(self, subquery, attr_name, w_type, num_ngbrs, permutations,
geom_col, id_col):
"""
Moran's I (global)
Implementation building neighbors with a PostGIS database and Moran's I
core clusters with PySAL.
Args:
subquery (str): Query to give access to the data needed. This query
must give access to ``attr_name``, ``geom_col``, and ``id_col``.
attr_name (str): Column name of data to analyze
w_type (str): Type of spatial weight. Must be one of `knn`
or `queen`. See `PySAL documentation
<http://pysal.readthedocs.io/en/latest/users/tutorials/weights.html>`__
for more information.
num_ngbrs (int): If using `knn` for ``w_type``, this
specifies the number of neighbors to be used to define the spatial
neighborhoods.
permutations (int): Number of permutations for performing
conditional randomization to find the p-value. Higher numbers
takes a longer time for getting results.
geom_col (str): Name of the geometry column in the dataset for
finding the spatial neighborhoods.
id_col (str): Row index for each value. Usually the database index.
"""
params = OrderedDict([("id_col", id_col), ("attr1", attr_name),
("geom_col", geom_col), ("subquery", subquery),
("num_ngbrs", num_ngbrs)])
result = self.data_provider.get_moran(w_type, params)
# collect attributes
attr_vals = pu.get_attributes(result)
# calculate weights
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate moran global
moran_global = ps.esda.moran.Moran(attr_vals,
weight,
permutations=permutations)
return zip([moran_global.I], [moran_global.EI])
def moran(subquery, attr_name, w_type, num_ngbrs, permutations, geom_col,
id_col):
"""
Moran's I (global)
Implementation building neighbors with a PostGIS database and Moran's I
core clusters with PySAL.
Andy Eschbacher
"""
qvals = {
"id_col": id_col,
"attr1": attr_name,
"geom_col": geom_col,
"subquery": subquery,
"num_ngbrs": num_ngbrs
}
query = pu.construct_neighbor_query(w_type, qvals)
plpy.notice('** Query: %s' % query)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(2)
plpy.notice('** Query returned with %d rows' % len(result))
except plpy.SPIError:
plpy.error(
'Error: areas of interest query failed, check input parameters')
plpy.notice('** Query failed: "%s"' % query)
plpy.notice('** Error: %s' % plpy.SPIError)
return pu.empty_zipped_array(2)
## collect attributes
attr_vals = pu.get_attributes(result)
## calculate weights
weight = pu.get_weight(result, w_type, num_ngbrs)
## calculate moran global
moran_global = ps.esda.moran.Moran(attr_vals,
weight,
permutations=permutations)
return zip([moran_global.I], [moran_global.EI])
def moran_rate(subquery, numerator, denominator, w_type, num_ngbrs,
permutations, geom_col, id_col):
"""
Moran's I Rate (global)
Andy Eschbacher
"""
qvals = {
"id_col": id_col,
"attr1": numerator,
"attr2": denominator,
"geom_col": geom_col,
"subquery": subquery,
"num_ngbrs": num_ngbrs
}
query = pu.construct_neighbor_query(w_type, qvals)
plpy.notice('** Query: %s' % query)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(2)
plpy.notice('** Query returned with %d rows' % len(result))
except plpy.SPIError:
plpy.error(
'Error: areas of interest query failed, check input parameters')
plpy.notice('** Query failed: "%s"' % query)
plpy.notice('** Error: %s' % plpy.SPIError)
return pu.empty_zipped_array(2)
## collect attributes
numer = pu.get_attributes(result, 1)
denom = pu.get_attributes(result, 2)
weight = pu.get_weight(result, w_type, num_ngbrs)
## calculate moran global rate
lisa_rate = ps.esda.moran.Moran_Rate(numer,
denom,
weight,
permutations=permutations)
return zip([lisa_rate.I], [lisa_rate.EI])
def global_rate_stat(self, subquery, numerator, denominator, w_type,
num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I Rate (global)
Args:
subquery (str): Query to give access to the data needed. This query
must give access to ``attr_name``, ``geom_col``, and ``id_col``.
numerator (str): Column name of numerator to analyze
denominator (str): Column name of the denominator
w_type (str): Type of spatial weight. Must be one of `knn`
or `queen`. See `PySAL documentation
<http://pysal.readthedocs.io/en/latest/users/tutorials/weights.html>`__
for more information.
num_ngbrs (int): If using `knn` for ``w_type``, this
specifies the number of neighbors to be used to define the spatial
neighborhoods.
permutations (int): Number of permutations for performing
conditional randomization to find the p-value. Higher numbers
takes a longer time for getting results.
geom_col (str): Name of the geometry column in the dataset for
finding the spatial neighborhoods.
id_col (str): Row index for each value. Usually the database index.
"""
params = OrderedDict([("id_col", id_col), ("attr1", numerator),
("attr2", denominator), ("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
result = self.data_provider.get_moran(w_type, params)
# collect attributes
numer = pu.get_attributes(result, 1)
denom = pu.get_attributes(result, 2)
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate moran global rate
lisa_rate = ps.esda.moran.Moran_Rate(numer,
denom,
weight,
permutations=permutations)
return list(zip([lisa_rate.I], [lisa_rate.EI]))
def moran_local(subquery, attr, w_type, num_ngbrs, permutations, geom_col,
id_col):
"""
Moran's I implementation for PL/Python
Andy Eschbacher
"""
# geometries with attributes that are null are ignored
# resulting in a collection of not as near neighbors
qvals = {
"id_col": id_col,
"attr1": attr,
"geom_col": geom_col,
"subquery": subquery,
"num_ngbrs": num_ngbrs
}
query = pu.construct_neighbor_query(w_type, qvals)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(5)
except plpy.SPIError:
plpy.error(
'Error: areas of interest query failed, check input parameters')
plpy.notice('** Query failed: "%s"' % query)
return pu.empty_zipped_array(5)
attr_vals = pu.get_attributes(result)
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local(attr_vals,
weight,
permutations=permutations)
# find quadrants for each geometry
quads = quad_position(lisa.q)
return zip(lisa.Is, quads, lisa.p_sim, weight.id_order, lisa.y)
def moran_local_rate(subquery, numerator, denominator,
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I Local Rate
Andy Eschbacher
"""
# geometries with values that are null are ignored
# resulting in a collection of not as near neighbors
qvals = OrderedDict([("id_col", id_col),
("numerator", numerator),
("denominator", denominator),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(5)
except plpy.SPIError:
plpy.error('Error: areas of interest query failed, check input parameters')
plpy.notice('** Query failed: "%s"' % query)
plpy.notice('** Error: %s' % plpy.SPIError)
return pu.empty_zipped_array(5)
## collect attributes
numer = pu.get_attributes(result, 1)
denom = pu.get_attributes(result, 2)
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local_Rate(numer, denom, weight,
permutations=permutations)
# find quadrants for each geometry
quads = quad_position(lisa.q)
return zip(lisa.Is, quads, lisa.p_sim, weight.id_order, lisa.y)
def moran(subquery, attr_name,
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I (global)
Implementation building neighbors with a PostGIS database and Moran's I
core clusters with PySAL.
Andy Eschbacher
"""
qvals = OrderedDict([("id_col", id_col),
("attr1", attr_name),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
plpy.notice('** Query: %s' % query)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(2)
plpy.notice('** Query returned with %d rows' % len(result))
except plpy.SPIError:
plpy.error('Error: areas of interest query failed, check input parameters')
plpy.notice('** Query failed: "%s"' % query)
plpy.notice('** Error: %s' % plpy.SPIError)
return pu.empty_zipped_array(2)
## collect attributes
attr_vals = pu.get_attributes(result)
## calculate weights
weight = pu.get_weight(result, w_type, num_ngbrs)
## calculate moran global
moran_global = ps.esda.moran.Moran(attr_vals, weight,
permutations=permutations)
return zip([moran_global.I], [moran_global.EI])
def moran_rate(subquery, numerator, denominator,
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I Rate (global)
Andy Eschbacher
"""
qvals = OrderedDict([("id_col", id_col),
("attr1", numerator),
("attr2", denominator)
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
plpy.notice('** Query: %s' % query)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(2)
plpy.notice('** Query returned with %d rows' % len(result))
except plpy.SPIError:
plpy.error('Error: areas of interest query failed, check input parameters')
plpy.notice('** Query failed: "%s"' % query)
plpy.notice('** Error: %s' % plpy.SPIError)
return pu.empty_zipped_array(2)
## collect attributes
numer = pu.get_attributes(result, 1)
denom = pu.get_attributes(result, 2)
weight = pu.get_weight(result, w_type, num_ngbrs)
## calculate moran global rate
lisa_rate = ps.esda.moran.Moran_Rate(numer, denom, weight,
permutations=permutations)
return zip([lisa_rate.I], [lisa_rate.EI])
def moran_local_bv(subquery, attr1, attr2,
permutations, geom_col, id_col, w_type, num_ngbrs):
"""
Moran's I (local) Bivariate (untested)
"""
qvals = OrderedDict([("id_col", id_col),
("attr1", attr1),
("attr2", attr2),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(4)
except plpy.SPIError:
plpy.error("Error: areas of interest query failed, "
"check input parameters")
return pu.empty_zipped_array(4)
# collect attributes
attr1_vals = pu.get_attributes(result, 1)
attr2_vals = pu.get_attributes(result, 2)
# create weights
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local_BV(attr1_vals, attr2_vals, weight,
permutations=permutations)
# find clustering of significance
lisa_sig = quad_position(lisa.q)
return zip(lisa.Is, lisa_sig, lisa.p_sim, weight.id_order)
"subquery": subquery,
"num_ngbrs": num_ngbrs}
try:
query_result = plpy.execute(
pu.construct_neighbor_query(w_type, qvals)
)
if len(query_result) == 0:
return zip([None], [None], [None], [None], [None])
except plpy.SPIError, err:
plpy.debug('Query failed with exception %s: %s' % (err, pu.construct_neighbor_query(w_type, qvals)))
plpy.error('Query failed, check the input parameters')
return zip([None], [None], [None], [None], [None])
## build weight
weights = pu.get_weight(query_result, w_type)
weights.transform = 'r'
## prep time data
t_data = get_time_data(query_result, time_cols)
plpy.debug('shape of t_data %d, %d' % t_data.shape)
plpy.debug('number of weight objects: %d, %d' % (weights.sparse).shape)
plpy.debug('first num elements: %f' % t_data[0, 0])
sp_markov_result = ps.Spatial_Markov(t_data,
weights,
k=num_classes,
fixed=False,
permutations=permutations)
query = pu.construct_neighbor_query(w_type, qvals)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(2)
except plpy.SPIError, e:
plpy.error('Analysis failed: %s' % e)
return pu.empty_zipped_array(2)
## collect attributes
attr_vals = pu.get_attributes(result)
## calculate weights
weight = pu.get_weight(result, w_type, num_ngbrs)
## calculate moran global
moran_global = ps.esda.moran.Moran(attr_vals,
weight,
permutations=permutations)
return zip([moran_global.I], [moran_global.EI])
def moran_local(subquery, attr, w_type, num_ngbrs, permutations, geom_col,
id_col):
"""
Moran's I implementation for PL/Python
Andy Eschbacher
"""
query = pu.construct_neighbor_query(w_type, qvals)
try:
result = plpy.execute(query)
# if there are no neighbors, exit
if len(result) == 0:
return pu.empty_zipped_array(2)
except plpy.SPIError, e:
plpy.error('Analysis failed: %s' % e)
return pu.empty_zipped_array(2)
## collect attributes
attr_vals = pu.get_attributes(result)
## calculate weights
weight = pu.get_weight(result, w_type, num_ngbrs)
## calculate moran global
moran_global = ps.esda.moran.Moran(attr_vals, weight,
permutations=permutations)
return zip([moran_global.I], [moran_global.EI])
def moran_local(subquery, attr,
w_type, num_ngbrs, permutations, geom_col, id_col):
"""
Moran's I implementation for PL/Python
Andy Eschbacher
"""
# geometries with attributes that are null are ignored
def spatial_trend(self,
subquery,
time_cols,
num_classes=7,
w_type='knn',
num_ngbrs=5,
permutations=0,
geom_col='the_geom',
id_col='cartodb_id'):
"""
Predict the trends of a unit based on:
1. history of its transitions to different classes (e.g., 1st
quantile -> 2nd quantile)
2. average class of its neighbors
Inputs:
@param subquery string: e.g., SELECT the_geom, cartodb_id,
interesting_time_column FROM table_name
@param time_cols list of strings: list of strings of column names
@param num_classes (optional): number of classes to break
distribution of values into. Currently uses quantile bins.
@param w_type string (optional): weight type ('knn' or 'queen')
@param num_ngbrs int (optional): number of neighbors (if knn type)
@param permutations int (optional): number of permutations for test
stats
@param geom_col string (optional): name of column which contains
the geometries
@param id_col string (optional): name of column which has the ids
of the table
Outputs:
@param trend_up float: probablity that a geom will move to a higher
class
@param trend_down float: probablity that a geom will move to a
lower class
@param trend float: (trend_up - trend_down) / trend_static
@param volatility float: a measure of the volatility based on
probability stddev(prob array)
"""
if len(time_cols) < 2:
plpy.error('More than one time column needs to be passed')
params = {
"id_col": id_col,
"time_cols": time_cols,
"geom_col": geom_col,
"subquery": subquery,
"num_ngbrs": num_ngbrs
}
result = self.data_provider.get_markov(w_type, params)
# build weight
weights = pu.get_weight(result, w_type)
weights.transform = 'r'
# prep time data
t_data = get_time_data(result, time_cols)
sp_markov_result = ps.Spatial_Markov(t_data,
weights,
k=num_classes,
fixed=False,
permutations=permutations)
# get lag classes
lag_classes = ps.Quantiles(ps.lag_spatial(weights, t_data[:, -1]),
k=num_classes).yb
# look up probablity distribution for each unit according to class and
# lag class
prob_dist = get_prob_dist(sp_markov_result.P, lag_classes,
sp_markov_result.classes[:, -1])
# find the ups and down and overall distribution of each cell
trend_up, trend_down, trend, volatility = get_prob_stats(
prob_dist, sp_markov_result.classes[:, -1])
# output the results
return zip(trend, trend_up, trend_down, volatility, weights.id_order)
"subquery": subquery,
"num_ngbrs": num_ngbrs
}
try:
query_result = plpy.execute(pu.construct_neighbor_query(w_type, qvals))
if len(query_result) == 0:
return zip([None], [None], [None], [None], [None])
except plpy.SPIError, e:
plpy.debug('Query failed with exception %s: %s' %
(err, pu.construct_neighbor_query(w_type, qvals)))
plpy.error('Analysis failed: %s' % e)
return zip([None], [None], [None], [None], [None])
## build weight
weights = pu.get_weight(query_result, w_type)
weights.transform = 'r'
## prep time data
t_data = get_time_data(query_result, time_cols)
plpy.debug('shape of t_data %d, %d' % t_data.shape)
plpy.debug('number of weight objects: %d, %d' % (weights.sparse).shape)
plpy.debug('first num elements: %f' % t_data[0, 0])
sp_markov_result = ps.Spatial_Markov(t_data,
weights,
k=num_classes,
fixed=False,
permutations=permutations)
def local_stat(self, subquery, attr, w_type, num_ngbrs, permutations,
geom_col, id_col):
"""
Moran's I (local)
Args:
subquery (str): Query to give access to the data needed. This query
must give access to ``attr_name``, ``geom_col``, and ``id_col``.
attr (str): Column name of data to analyze
w_type (str): Type of spatial weight. Must be one of `knn`
or `queen`. See `PySAL documentation
<http://pysal.readthedocs.io/en/latest/users/tutorials/weights.html>`__
for more information.
num_ngbrs (int): If using `knn` for ``w_type``, this
specifies the number of neighbors to be used to define the spatial
neighborhoods.
permutations (int): Number of permutations for performing
conditional randomization to find the p-value. Higher numbers
takes a longer time for getting results.
geom_col (str): Name of the geometry column in the dataset for
finding the spatial neighborhoods.
id_col (str): Row index for each value. Usually the database index.
Returns:
list of tuples: Where each tuple consists of the following values:
- quadrants classification (one of `HH`, `HL`, `LL`, or `LH`)
- p-value
- spatial lag
- standardized spatial lag (centered on the mean, normalized by the
standard deviation)
- original value
- standardized value
- Moran's I statistic
- original row index
"""
# geometries with attributes that are null are ignored
# resulting in a collection of not as near neighbors
params = OrderedDict([("id_col", id_col), ("attr1", attr),
("geom_col", geom_col), ("subquery", subquery),
("num_ngbrs", num_ngbrs)])
result = self.data_provider.get_moran(w_type, params)
attr_vals = pu.get_attributes(result)
weight = pu.get_weight(result, w_type, num_ngbrs)
# calculate LISA values
lisa = ps.esda.moran.Moran_Local(attr_vals,
weight,
permutations=permutations)
# find quadrants for each geometry
quads = quad_position(lisa.q)
# calculate spatial lag
lag = ps.weights.spatial_lag.lag_spatial(weight, lisa.y)
lag_std = ps.weights.spatial_lag.lag_spatial(weight, lisa.z)
return zip(quads, lisa.p_sim, lag, lag_std, lisa.y, lisa.z, lisa.Is,
weight.id_order)