query_grouper = Group(
query_streamer.output(),
{'age': lambda a, b: a is b}
)
qselect = Select(
query_grouper.output(),
AttributeRename(
query_grouper.output().schema(),
{ 'age': 'age_range' }
)
)
aggregate = Aggregate(
data_accessor.output(),
SumAgeAggregator(data_accessor.output().schema())
)
aselect = Select(
aggregate.output(),
UniversalSelect(
aggregate.output().schema(),
{
'name_age': {
'type': str,
'args': ['name', 'age'],
'function': lambda name, age: '%s --> %d' % (name, age),
}
}
)
# 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
# The query stream contains only a single query.
query_streamer = ArrayStreamer(query_schema, [
(IntInterval(0, int(1E10)), ),
])
engines.append(query_streamer)
# Create a family data source: a table in the input database.
family_source = DBTable(input_file, 'family', family_schema)
# Data accessor for the species data source.
family_accessor = DataAccessor(query_streamer.output(), family_source,
FindRange)
engines.append(family_accessor)
# A group mini-engine to split the family IDs into groups.
family_id_grouper = Group(family_accessor.output(), {
'family.id': lambda a, b: a == b
})
engines.append(family_id_grouper)
# Select only the family ID for querying genera.
family_id_select = Select(
family_accessor.output(),
UniversalSelect(
family_accessor.output().schema(), {
'genus.family_id': {
'type': int,
'args': ['family.id'],
'function': lambda v: v
}
}))
# The query stream contains only a single query box.
query_streamer = ArrayStreamer(query_schema, [
(query, ),
])
engines.append(query_streamer)
# Query the states from the data source.
states_source = Rtree(states_file, 'states.the_geom')
states_accessor = DataAccessor(query_streamer.output(), states_source,
FindRange)
engines.append(states_accessor)
# Trim the states to the query region.
states_select = Select(
states_accessor.output(),
UniversalSelect(
states_accessor.output().schema(),
{
# trim geometry
'states.the_geom': {
'type': Geometry,
'args': ['states.the_geom'],
'function': lambda v: intersection(v, query),
},
# keep OID
'states.oid': {
'type': int,
'args': ['oid'],
'function': lambda v: v,
}
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
# 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)
# create a data accessor
data_accessor = DataAccessor(
query_streamer.output(),
data_source,
FindRange
)
name_age_combiner = NameAgeCombiner(data_accessor.output().schema())
select = Select(data_accessor.output(), name_age_combiner)
query_grouper = Group(
query_streamer.output(),
{'age': lambda a, b: a is b}
)
joiner = Join(query_grouper.output(), select.output())
filter = Filter(joiner.output(), FilterNameAge(joiner.output().schema()))
result_stack = ResultStack(
filter.output(),
# joiner.output(),
# query_streamer.output(),
# query_grouper.output(),
},
}
)
)
engines.append(states_query)
states_source = Rtree(states_file, 'states.geom')
states_accessor = DataAccessor(
states_query.output(),
states_source,
FindRange
)
engines.append(states_accessor)
states_select = Select(
states_accessor.output(),
UniversalSelect(
states_accessor.output().schema(),
{
'states.oid': {
'type': int,
'args': ['oid'],
'function': lambda v: v,
},
'states.geom': {
'type': Geometry,
'args': ['states.geom'],
'function': lambda v: v,
}
}
)
(IntInterval(2, 5), ),
(IntInterval(1, 3), ),
(IntInterval(2, 5), ),
])
# 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)
# create a data accessor
data_accessor = DataAccessor(query_streamer.output(), data_source, FindRange)
name_age_combiner = NameAgeCombiner(data_accessor.output().schema())
select = Select(data_accessor.output(), name_age_combiner)
query_grouper = Group(query_streamer.output(), {'age': lambda a, b: a is b})
joiner = Join(query_grouper.output(), select.output())
filter = Filter(joiner.output(), FilterNameAge(joiner.output().schema()))
result_stack = ResultStack(
filter.output(),
# joiner.output(),
# query_streamer.output(),
# query_grouper.output(),
# select.output(),
)
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):
# create a data accessor
data_accessor = DataAccessor(demux, data_source, FindRange)
name_age_combiner = NameAgeCombiner(data_accessor.output().schema())
selects.append(Select(data_accessor.output(), name_age_combiner))
data_accessors.append(data_accessor)
mux = Mux(*[s.output() for s in selects])
#name_age_combiner_reverse = NameAgeCombinerReverse(demux.schema())
#select2 = Select(demux, name_age_combiner_reverse)
#name_age_combiner = NameAgeCombiner(data_accessor.output().schema())
#select = Select(data_accessor.output(), name_age_combiner)
#name_age_combiner_reverse = NameAgeCombinerReverse(data_accessor.output().schema())
#select2 = Select(data_accessor.output(), name_age_combiner_reverse)
result_stack = ResultStack(
# query_streamer.output(),
])
engines.append(query_streamer)
# Create a family data source: a table in the input database.
family_source = DBTable(input_file, 'family', family_schema)
# Data accessor for the species data source.
family_accessor = DataAccessor(
query_streamer.output(),
family_source,
FindRange
)
engines.append(family_accessor)
# A group mini-engine to split the family IDs into groups.
family_id_grouper = Group(
family_accessor.output(),
{'family.id': lambda a, b: a == b}
)
engines.append(family_id_grouper)
# Select only the family ID for querying genera.
family_id_select = Select(
family_accessor.output(),
UniversalSelect(
family_accessor.output().schema(),
{
'genus.family_id': {
'type': int,
'args': ['family.id'],
'function': lambda v: v
}
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,),
])
engines.append(query_streamer)
# Query the states from the data source.
states_source = Rtree(states_file, 'states.the_geom')
states_accessor = DataAccessor(
query_streamer.output(),
states_source,
FindRange
)
engines.append(states_accessor)
# Trim the states to the query region.
states_select = Select(
states_accessor.output(),
UniversalSelect(
states_accessor.output().schema(),
{
# trim geometry
'states.the_geom': {
'type': Geometry,
'args': ['states.the_geom'],
'function': lambda v: intersection(v, query),
},
# keep OID
'states.oid': {
'type': int,
'args': ['oid'],
'function': lambda v: v,
}
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):
# create a data accessor
data_accessor = DataAccessor(
demux,
data_source,
FindRange
)
name_age_combiner = NameAgeCombiner(data_accessor.output().schema())
selects.append(Select(data_accessor.output(), name_age_combiner))
data_accessors.append(data_accessor)
mux = Mux(*[s.output() for s in selects])
#name_age_combiner_reverse = NameAgeCombinerReverse(demux.schema())
#select2 = Select(demux, name_age_combiner_reverse)
#name_age_combiner = NameAgeCombiner(data_accessor.output().schema())
#select = Select(data_accessor.output(), name_age_combiner)
#name_age_combiner_reverse = NameAgeCombinerReverse(data_accessor.output().schema())
#select2 = Select(data_accessor.output(), name_age_combiner_reverse)
result_stack = ResultStack(
# query_streamer.output(),
UniversalSelect(
query_streamer.output().schema(), {
'states.geom': {
'type': Geometry,
'args': ['queries.geom'],
'function': lambda v: v,
},
}))
engines.append(states_query)
states_source = Rtree(states_file, 'states.geom')
states_accessor = DataAccessor(states_query.output(), states_source, FindRange)
engines.append(states_accessor)
states_select = Select(
states_accessor.output(),
UniversalSelect(
states_accessor.output().schema(), {
'states.oid': {
'type': int,
'args': ['oid'],
'function': lambda v: v,
},
'states.geom': {
'type': Geometry,
'args': ['states.geom'],
'function': lambda v: v,
}
}))
engines.append(states_select)
# 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'],