def test_shiftGeocodesUp():
n = nodes.GeounitNode(geocode='123456789abcdefg',
geocode_dict={
16: 'Block',
12: 'Block_Group',
11: 'Tract',
5: 'County',
2: 'State',
0: 'US'
})
n.shiftGeocodesUp()
assert n.geocode == '123456789abc'
assert n.geolevel == 'Block_Group'
n.shiftGeocodesUp()
assert n.geocode == '123456789ab'
assert n.geolevel == 'Tract'
n.shiftGeocodesUp()
assert n.geocode == '12345'
assert n.geolevel == 'County'
n.shiftGeocodesUp()
assert n.geocode == '12'
assert n.geolevel == 'State'
n.shiftGeocodesUp()
assert n.geocode == ''
assert n.geolevel == 'US'
def n():
geocode_dict = {16: 'Block', 12: 'Block_Group', 11: 'Tract', 5: 'County'}
histogram = sparse.multiSparse(
np.array([[[[5, 0], [0, 4]], [[5, 0], [0, 4]]],
[[[5, 0], [0, 4]], [[5, 0], [0, 4]]]]))
housing_hist = sparse.multiSparse((np.array([0, 1, 1, 0, 0, 0, 7, 2])))
return nodes.GeounitNode(geocode='123456789abcdefg',
geocode_dict=geocode_dict,
raw=histogram,
raw_housing=housing_hist)
def test_wconstraints():
geocode_dict = {
16: 'Block',
12: 'Block_Group',
11: 'Tract',
5: 'County'
}
histogram, housing_hist = table2hists(
np.array(
[ # columns: 'hhgq', 'votingage', 'hispanic', 'cenrace', 'unique unitid' (shape 8,2,2,63 + unitUID)
# each row is a person
[0, 1, 1, 20, 0],
[1, 0, 0, 1, 1],
[3, 1, 0, 10, 2],
[3, 0, 0, 15, 2],
[1, 1, 0, 15, 3]
]),
SchemaMaker.fromName(CC.SCHEMA_PL94),
CC.ATTR_HHGQ)
inv_dict = InvariantsMaker.make(schema=CC.SCHEMA_PL94,
raw=histogram,
raw_housing=housing_hist,
invariant_names=("tot", "gqhh_vect",
"gqhh_tot", "va"))
con_dict = cPL94.ConstraintsCreator(hist_shape=(histogram.shape, housing_hist.shape), invariants=inv_dict, constraint_names=("total",))\
.calculateConstraints().constraints_dict
n1 = nodes.GeounitNode(geocode='123456789abcdefg',
geocode_dict=geocode_dict,
raw=histogram,
raw_housing=housing_hist,
cons=con_dict,
invar=inv_dict)
n2 = nodes.GeounitNode(geocode='123456789abcdefg',
geocode_dict=geocode_dict,
raw=histogram,
raw_housing=housing_hist,
cons=con_dict,
invar=inv_dict)
assert n1 == n2
def test_node_init():
n = nodes.GeounitNode(geocode='123456789abcdefg',
geocode_dict={
16: 'Block',
12: 'Block_Group',
11: 'Tract',
5: 'County'
})
assert n.parentGeocode == '123456789abc'
assert n.geolevel == 'Block'
n = nodes.GeounitNode(geocode='12',
geocode_dict={
16: 'Block',
12: 'Block_Group',
11: 'Tract',
5: 'County',
2: 'State'
})
assert n.parentGeocode == ''
assert n.geolevel == 'State'
def makeBlockNode(self, person_unit_arrays):
"""
This function makes block nodes from person unit arrays for a given geocode.
Inputs:
config: a configuration object
person_unit_arrays: a RDD of (geocode, arrays), where arrays are the tables defined in the config
Output:
block_node: a nodes.GeounitNode object for the given geocode
"""
geocode, arrays = person_unit_arrays
# Assign arrays to table names in a dictionary {name:array} and fill in with zeros if array is non-existent
assert len(arrays) == len(self.data_names)
data_dict = {
n: a if a is not None else np.zeros(self.shape_dict[n]).astype(
int
) # TODO: Wonder if this creation of zeros takes too much time, maybe directly in multisparse?
for n, a in zip(self.data_names, arrays)
}
# geocode is a tuple where the [1] entry is empty. We only want the [0] entry.
geocode = geocode[0]
logging.info(f"creating geocode: {geocode}")
raw = sparse.multiSparse(
data_dict[self.privacy_table_name],
shape=self.shape_dict[self.privacy_table_name])
raw_housing = sparse.multiSparse(
data_dict[self.constraint_table_name],
shape=self.shape_dict[self.constraint_table_name])
# Make Invariants
invariants_dict = self.setup.makeInvariants(
raw=raw, raw_housing=raw_housing, invariant_names=self.invar_names)
# Make Constraints
constraints_dict = self.setup.makeConstraints(
hist_shape=(self.setup.hist_shape, self.setup.unit_hist_shape),
invariants=invariants_dict,
constraint_names=self.cons_names)
block_node = nodes.GeounitNode(geocode=geocode,
geocode_dict=self.modified_geocode_dict,
raw=raw,
raw_housing=raw_housing,
cons=constraints_dict,
invar=invariants_dict)
return block_node