def node2SparkRows(node: GeounitNode):
nodedict = node.toDict((SYN, INVAR, GEOCODE))
persons = makeHistRowsFromMultiSparse(
nodedict,
schema,
row_recoder=self.row_recoder,
geocode_dict=inverted_geodict)
return persons
def node2SparkRows(node: GeounitNode):
nodedict = node.toDict((SYN, INVAR, GEOCODE))
households = makeHistRowsFromMultiSparse(
nodedict, schema, row_recoder=self.row_recoder)
units = addEmptyAndGQ(
nodedict,
schema,
households,
row_recoder=self.row_recoder,
gqtype_recoder=HHGQUnitDemoProductAttr.das2mdf,
geocode_dict=inverted_geodict)
return units
def node2SparkRows(node: GeounitNode):
nodedict = node.toDict((SYN, INVAR, GEOCODE))
households = makeHistRowsFromMultiSparse(
nodedict,
schema,
row_recoder=self.row_recoder,
geocode_dict=inverted_geodict,
microdata_field=None)
units = addGroupQuarters(nodedict,
schema,
households,
row_recoder=self.row_recoder,
geocode_dict=inverted_geodict,
to_microdata=False)
# 'priv' means "protected via the differential privacy routines in this code base" variable to be renamed after P.L.94-171 production
ordered_cols = self.var_list + ['priv']
return [
Row(*ordered_cols)(*[unit[col] for col in ordered_cols])
for unit in units
]
