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),
}
}
)
)
# Send '1' for each retrieved geoname location.
geonames_select = Select(
geonames_accessor.output(),
UniversalSelect(
geonames_accessor.output().schema(), {
'count': {
'type': int,
'args': ['geonames.location'],
'function': lambda v: 1
}
}))
engines.append(geonames_select)
geonames_aggregate = Aggregate(
geonames_select.output(),
SumAggregator(geonames_select.output().schema(), 'count'))
engines.append(geonames_aggregate)
select = Select(
channel,
UniversalSelect(channel.schema(), {
'oid': {
'type': int,
'args': ['oid'],
'function': lambda v: v
},
}))
engines.append(select)
counties_grouper = Group(select.output(), {'oid': lambda a, b: a == b})
# Select only the species ID for querying plants.
plants_height_select = Select(
plants_filter.output(),
UniversalSelect(
plants_filter.output().schema(), {
'plants.height': {
'type': int,
'args': ['plants.height'],
'function': lambda v: v
}
}))
engines.append(plants_height_select)
plants_height_aggregate = Aggregate(
plants_height_select.output(),
MaxHeightAggregator(plants_height_select.output().schema()))
engines.append(plants_height_aggregate)
family_genus_species_id_grouper = Group(
channel, {
'family.id': lambda a, b: a == b,
'genus.id': lambda a, b: a == b,
'species.id': lambda a, b: a == b
})
engines.append(family_genus_species_id_grouper)
# mux_streams.append(family_genus_species_id_grouper.output())
species_plants_joiner = Join(family_genus_species_id_grouper.output(),
plants_height_aggregate.output())
engines.append(species_plants_joiner)
# Send '1' for each retrieved geoname location.
geonames_select = Select(
geonames_accessor.output(),
UniversalSelect(
geonames_accessor.output().schema(), {
'count': {
'type': int,
'args': ['geonames.location'],
'function': lambda v: 1
}
}))
engines.append(geonames_select)
# Aggregate the geonames
geonames_aggregate = Aggregate(
geonames_select.output(),
SumAggregator(geonames_select.output().schema(), 'count'))
engines.append(geonames_aggregate)
# Select only the OIDs from each of the hierarchy levels.
select = Select(
channel,
UniversalSelect(
channel.schema(), {
'states.oid': {
'type': int,
'args': ['states.oid'],
'function': lambda v: v
},
'counties.oid': {
'type': int,
lambda a, b:
intersection(a, b).geom().area / b.geom().area
})
]
)
)
engines.append(cover_area)
#############################################################
#
# 1st level aggregation
#
#############################################################
cover_aggregate = Aggregate(
cover_area.output(),
SumAggregator(cover_area.output().schema(), 'area')
)
engines.append(cover_aggregate)
mux_streams.append(cover_aggregate.output())
mux = Mux(*mux_streams)
engines.append(mux)
#############################################################
#
# 2nd level aggregation
#
#############################################################
counties_level_select = Select(
mux.output(),
engines.append(geonames_accessor)
# XXX At this point no additional filter for the contraining the
# geonames to the query region is required.
# Send '1' for each retrieved geoname location.
geonames_select = Select(
geonames_accessor.output(),
UniversalSelect(
geonames_accessor.output().schema(),
{"count": {"type": int, "args": ["geonames.location"], "function": lambda v: 1}},
),
)
engines.append(geonames_select)
geonames_aggregate = Aggregate(geonames_select.output(), SumAggregator(geonames_select.output().schema(), "count"))
engines.append(geonames_aggregate)
select = Select(
channel, UniversalSelect(channel.schema(), {"oid": {"type": int, "args": ["oid"], "function": lambda v: v}})
)
engines.append(select)
counties_grouper = Group(select.output(), {"oid": lambda a, b: a == b})
engines.append(counties_grouper)
joiner = Join(counties_grouper.output(), geonames_aggregate.output())
engines.append(joiner)
mux_streams.append(joiner.output())
# mux_streams.append(counties_select.output())
plants_filter.output(),
UniversalSelect(
plants_filter.output().schema(),
{
'plants.height': {
'type': int,
'args': ['plants.height'],
'function': lambda v: v
}
}
)
)
engines.append(plants_height_select)
plants_height_aggregate = Aggregate(
plants_height_select.output(),
MaxHeightAggregator(plants_height_select.output().schema())
)
engines.append(plants_height_aggregate)
family_genus_species_id_grouper = Group(
channel,
{
'family.id': lambda a, b: a == b,
'genus.id': lambda a, b: a == b,
'species.id': lambda a, b: a == b
}
)
engines.append(family_genus_species_id_grouper)
# mux_streams.append(family_genus_species_id_grouper.output())
species_plants_joiner = Join(
# Select only the species ID for querying plants.
plants_height_select = Select(
plants_filter.output(),
UniversalSelect(
plants_filter.output().schema(), {
'plants.height': {
'type': int,
'args': ['plants.height'],
'function': lambda v: v
}
}))
engines.append(plants_height_select)
plants_height_aggregate = Aggregate(
plants_height_select.output(),
MaxHeightAggregator(plants_height_select.output().schema()))
engines.append(plants_height_aggregate)
species_id_grouper = Group(channel, {'species.id': lambda a, b: a == b})
engines.append(species_id_grouper)
joiner = Join(species_id_grouper.output(),
plants_height_aggregate.output())
engines.append(joiner)
mux_streams.append(joiner.output())
mux = Mux(*mux_streams)
result_stack = ResultFile(
'results.txt',
UniversalSelect(
geonames_accessor.output().schema(),
{
'count': {
'type': int,
'args': ['geonames.location'],
'function': lambda v: 1
}
}
)
)
engines.append(geonames_select)
# Aggregate the geonames
geonames_aggregate = Aggregate(
geonames_select.output(),
SumAggregator(geonames_select.output().schema(), 'count')
)
engines.append(geonames_aggregate)
# Select only the OIDs from each of the hierarchy levels.
select = Select(
channel,
UniversalSelect(
channel.schema(),
{
'states.oid': {
'type': int,
'args': ['states.oid'],
'function': lambda v: v
},
'counties.oid': {
float,
'args': ['zip.geom', 'cover.geom'],
'function':
lambda a, b: intersection(a, b).geom().area / b.geom().area
})
]))
engines.append(cover_area)
#############################################################
#
# 1st level aggregation
#
#############################################################
cover_aggregate = Aggregate(
cover_area.output(), SumAggregator(cover_area.output().schema(),
'area'))
engines.append(cover_aggregate)
mux_streams.append(cover_aggregate.output())
mux = Mux(*mux_streams)
engines.append(mux)
#############################################################
#
# 2nd level aggregation
#
#############################################################
counties_level_select = Select(
mux.output(),
plants_filter.output(),
UniversalSelect(
plants_filter.output().schema(),
{
'plants.height': {
'type': int,
'args': ['plants.height'],
'function': lambda v: v
}
}
)
)
engines.append(plants_height_select)
plants_height_aggregate = Aggregate(
plants_height_select.output(),
MaxHeightAggregator(plants_height_select.output().schema())
)
engines.append(plants_height_aggregate)
species_id_grouper = Group(
channel,
{'species.id': lambda a, b: a == b}
)
engines.append(species_id_grouper)
joiner = Join(species_id_grouper.output(), plants_height_aggregate.output())
engines.append(joiner)
mux_streams.append(joiner.output())
mux = Mux(*mux_streams)