# The query stream contains only a single query box.
query_streamer = ArrayStreamer(query_schema, [
(query, ),
])
engines.append(query_streamer)
counties_source = Rtree(counties_file, 'counties.the_geom')
counties_accessor = DataAccessor(
query_streamer.output(),
counties_source,
FindRange,
)
engines.append(counties_accessor)
demux = Demux(counties_accessor.output())
def intersection(a, b):
g1 = a.geom()
g2 = b.geom()
try:
if g1.is_valid and g2.is_valid:
i = g1.intersection(g2)
return Geometry(i)
else:
return None
except:
return None
# Data source for the species.
species_source = DBTable(input_file, 'species', species_schema)
# Data accessor for the species data source.
species_accessor = DataAccessor(genus_id_select.output(), species_source,
FindIdentities)
engines.append(species_accessor)
# A join mini-engine to associate families, genera and species.
family_genus_species_joiner = Join(
family_genus_id_grouper.output(),
species_accessor.output(),
)
engines.append(family_genus_species_joiner)
demux = Demux(family_genus_species_joiner.output())
mux_streams = []
for i in range(tracks):
channel = demux.channel()
# Select only the species ID for querying plants.
species_id_select = Select(
channel,
UniversalSelect(
channel.schema(), {
'plants.species_id': {
'type': int,
'args': ['species.id'],
'function': lambda v: v
}
# Group states by OID
states_group = Group(states_select.output(), {
'states.oid': lambda a, b: a == b
})
engines.append(states_group)
# Join counties and states
states_counties_join = Join(
states_group.output(),
counties_oid_select.output(),
)
engines.append(states_counties_join)
# De-multiplex the joined stream across multiple tracks for better CPU core
# utilization.
demux = Demux(states_counties_join.output())
mux_streams = []
for i in range(tracks):
channel = demux.channel()
# To query the locations in the geonames layer, trim the counties to
# the state and query boundary.
counties_select = Select(
channel,
UniversalSelect(
channel.schema(), {
'geonames.location': {
'type': Geometry,
'args': ['states.the_geom', 'counties.the_geom'],
'function': lambda s, c: intersection(s, c),
}
self._c[i] = self._af[i][1](c, r[i])
engines = []
counters = []
# The query stream contains only a single query box.
query_streamer = ArrayStreamer(query_schema, [(query,)])
engines.append(query_streamer)
counties_source = Rtree(counties_file, "counties.the_geom")
counties_accessor = DataAccessor(query_streamer.output(), counties_source, FindRange)
engines.append(counties_accessor)
demux = Demux(counties_accessor.output())
def intersection(a, b):
g1 = a.geom()
g2 = b.geom()
try:
if g1.is_valid and g2.is_valid:
i = g1.intersection(g2)
return Geometry(i)
else:
return None
except:
return None
query_schema = Schema()
query_schema.append(Attribute('age', IntInterval))
# query stream generator from array
query_streamer = ArrayStreamer(query_schema, [
(IntInterval(1, 3), ),
(IntInterval(2, 5), ),
(IntInterval(1, 3), ),
(IntInterval(1, 3), ),
(IntInterval(2, 5), ),
(IntInterval(2, 5), ),
(IntInterval(1, 3), ),
(IntInterval(2, 5), ),
])
demux = Demux(query_streamer.output())
# schema definition of the data stream
data_schema = Schema()
data_schema.append(Attribute('name', str))
data_schema.append(Attribute('age', int))
data_schema.append(Attribute('rowid', int, True))
data_source = DBTable('test.db', 'person', data_schema)
# definition of the data source
#data_source = CSVFile('test.csv', data_schema)
data_accessors = []
selects = []
for i in range(0, 1):
for i, c in enumerate(self._c):
self._c[i] = self._af[i][1](c, r[i])
# The query stream contains only a single query.
query_streamer = ArrayStreamer(query_schema, [
(IntInterval(0, int(1E10)), ),
])
# Create a species data source: a table in the input database.
species_source = DBTable(input_file, 'species', species_schema)
# Data accessor for the species data source.
species_accessor = DataAccessor(query_streamer.output(), species_source,
FindRange)
demux = Demux(species_accessor.output())
engines = []
mux_streams = []
for i in range(tracks):
channel = demux.channel()
# Select only the species ID for querying plants.
species_id_select = Select(
channel,
UniversalSelect(
species_accessor.output().schema(), {
'plants.species_id': {
'type': int,
'args': ['species.id'],
'function': lambda v: v
query_schema = Schema()
query_schema.append(Attribute('age', IntInterval))
# query stream generator from array
query_streamer = ArrayStreamer(query_schema, [
(IntInterval(1, 3),),
(IntInterval(2, 5),),
(IntInterval(1, 3),),
(IntInterval(1, 3),),
(IntInterval(2, 5),),
(IntInterval(2, 5),),
(IntInterval(1, 3),),
(IntInterval(2, 5),),
])
demux = Demux(query_streamer.output())
# schema definition of the data stream
data_schema = Schema()
data_schema.append(Attribute('name', str))
data_schema.append(Attribute('age', int))
data_schema.append(Attribute('rowid', int, True))
data_source = DBTable('test.db', 'person', data_schema)
# definition of the data source
#data_source = CSVFile('test.csv', data_schema)
data_accessors = []
selects = []
for i in range(0, 1):
'type': Geometry,
'args': ['counties.geom', 'zip.geom'],
'function': lambda a, b: intersection(a, b),
}
}))
engines.append(zip_trim)
zip_filter = Filter(
zip_trim.output(),
UniversalFilter(zip_trim.output().schema(), {
'zip.geom':
lambda g: g and g.geom().is_valid and g.geom().area != 0,
}))
engines.append(zip_filter)
demux = Demux(zip_filter.output())
mux_streams = []
for i in range(tracks):
channel = demux.channel()
zip_group = Group(
channel, {
'states.oid': lambda a, b: a == b,
'counties.oid': lambda a, b: a == b,
'zip.oid': lambda a, b: a == b,
})
engines.append(zip_group)
cover_query = Select(
channel,