def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('b402ff2a76968f1e8867f52a876690b6',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('70ec7833a06f2b6989747149874bb74d',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('324fa582528ea3dbc96bd7e94a2d5b61',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('9b69d8fc8b441b43d493d713e5703ada',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('green-rush-daily',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_metafilter_resource_type_all():
filter = f.overlap_filter(field='resource-type', values=['all'], min=1)
candidates = CLIENT.get_candidates("wide-open-spaces",
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=100,
sort_by=SortStrategy.POP_1D)
assert len(candidates) > 0
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('565a3d0d5b838bc0005f81a706afdec2',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('1a1e951c0be6ac5f7a57c617f1160972',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) > 10000
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('3c499a166380645f83154eb95983ed96',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('8bf9fa832a2cf351cf1a19098038459d',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('1154d080d208325324fa2f30fa1c1c64',
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=1000,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_global_filter_and_resource_type(customer_name, site_id):
filter = f.overlap_filter(field='resource-type', values=['nyc'], min=1)
candidates = CLIENT.get_candidates(site_id,
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=100,
sort_by=SortStrategy.POP_1D)
for c in candidates:
print(c)
assert c.event_counts is not None or c.base_score is not None
def test_gazette():
filter_resource_type = ff.overlap_filter(field='resource-type', values={'thegazette_sports'}, min=1, match_type=MatchType.CONTAINS)
filter_meta_global = ff.and_filter(filter_resource_type, schema.named_filters['GLOBAL'])
candidates = client.get_candidates(site_id=site_id, filter=filter_meta_global, limit=100, sort_by=SortStrategy.POP_1D)
assert len(candidates) == 100
resource_ids = [candidate.resource_id for candidate in candidates]
resources = client.get_resources(site_id=site_id, ids=resource_ids).resources
resource_types = [resource.to_jsonobj()['fields']['resource-type'] for resource in resources]
for resource_type in resource_types:
assert 'thegazette_sports' in resource_type
def test_upout_resource_type_nyc():
site_id = "7a0f18a6274829b2e0710f57eea2b6d0"
filter = f.overlap_filter(field='resource-type', values=['nyc'], min=1)
candidates = CLIENT.get_candidates(site_id,
filter=f.and_filter(
f.named_filter('GLOBAL'), filter),
limit=100,
sort_by=SortStrategy.POP_1D)
assert len(candidates) == 100
for c in candidates:
print(c)
assert (c.event_counts is not None or c.base_score is not None)
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('774367e2d0fa1515ca1e3580188b7d03', filter=f.and_filter(f.named_filter('GLOBAL'), filter), limit=1000, sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('e22d241e217d40fe9451573dd9bd319f', filter=f.and_filter(f.named_filter('GLOBAL'), filter), limit=1000, sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
from bt_candidates.client import Client
from bt_candidates.wiring import default_filter_factory as ff
from bt_candidates.filters import MatchType
from bt_candidates.sorting import SortStrategy
client = Client('candidates.magic.boomtrain.com')
schema = client.get_schema('atlanta-black-star')
filt = ff.or_filter(
ff.overlap_filter('title', ['Yohannes', 'IV'], match_type=MatchType.EXACT, min=2, max=2),
ff.overlap_filter('title', ['Search', 'chicago'], match_type=MatchType.EXACT, min=2, max=2),
ff.overlap_filter('title', ['african', 'history', 'month'], match_type=MatchType.EXACT, min=3, max=3)
)
candidates = client.get_candidates('atlanta-black-star', filt, limit=25)
print(len(candidates))
for c in candidates:
print(c)
print('======================================================')
import itertools as it
def split_candidates(candidates, needed=10):
to_score = []
for _, grp in it.groupby(candidates, lambda c: c.sort_weight):
grp = list(grp)
if len(grp) > needed:
to_score.extend(grp)
return to_score
else:
from bt_candidates.client import Client
from bt_candidates.wiring import default_schema_factory as sf
from bt_candidates.wiring import default_filter_factory as ff
from bt_candidates.common import FieldType, AmountType, MatchType
from bt_candidates.resource_schema import SchemaField, ResourceSchema, DataFormat, DataLoader
from datetime import timedelta
client = Client(host='candidates.aws.boomtrain.com', port=7070)
# yellow pages.
site_id = "593964c3c0f76bc59c65b324f9dbf869"
schema = client.get_schema(site_id)
filter_item_type = ff.overlap_filter(field='itemType',
values={'lists_en'},
min=1,
match_type=MatchType.CONTAINS)
filter_city_region = ff.overlap_filter(field='cityRegion',
values={'toronto'},
min=1,
match_type=MatchType.CONTAINS)
filter_meta = ff.and_filter(filter_item_type, filter_city_region)
filter_meta_global = ff.and_filter(filter_item_type, filter_city_region,
schema.named_filters['GLOBAL'])
candidates_meta = client.get_candidates(site_id=site_id,
filter=filter_meta,
limit=100)
candidates_meta_global = client.get_candidates(site_id=site_id,
filter=filter_meta_global,
limit=100)
def test_metafilter_resource_type_article():
filter = f.overlap_filter(field='resource-type', values=['article'], min=1)
candidates = CLIENT.get_candidates('14d221d80a228de0c48ee754c7a4ead7', filter=f.and_filter(f.named_filter('GLOBAL'), filter), limit=1000, sort_by=SortStrategy.POP_1D)
assert len(candidates) == 1000
