def spatial_markov_trend(
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")
qvals = {
"id_col": id_col,
"time_cols": time_cols,
"geom_col": geom_col,
"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])
def spatial_markov_trend(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')
qvals = {
"id_col": id_col,
"time_cols": time_cols,
"geom_col": geom_col,
"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])
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 = OrderedDict([("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, e:
plpy.error('Analysis failed: %s' % e)
return pu.empty_zipped_array(5)
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 = OrderedDict([("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, e:
plpy.error('Analysis failed: %s' % e)
return pu.empty_zipped_array(5)
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 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 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_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)
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)
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)
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)
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)
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)
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)
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)
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)
def test_construct_neighbor_query(self):
"""Test construct_neighbor_query"""
# Compare to raw knn query
self.assertEqual(pu.construct_neighbor_query("knn", self.params), pu.knn(self.params))
def test_construct_neighbor_query(self):
"""Test construct_neighbor_query"""
# Compare to raw knn query
self.assertEqual(pu.construct_neighbor_query('knn', self.params),
pu.knn(self.params))
