def test_asym_min_constraint(self):
corpus = DefaultJsonCorpus(self.get_docs())
ds = TagRecommender(max_s2_size=1.0, min_s2_size=10)
ds.fit(corpus)
res = ds.knn("football", k=1, metric='asym')
self.assertEqual(len(res), 0)
docs = []
for filename in os.listdir("reuters-21578-json/data/full"):
f = open("reuters-21578-json/data/full/" + filename)
js = json.load(f)
for j in js:
if 'topics' in j and 'body' in j:
d = {}
d["id"] = j['id']
d["text"] = j['body'].replace("\n", "")
d["title"] = j['title']
d["tags"] = ",".join(j['topics'])
docs.append(d)
print "loaded ", len(docs), " documents"
from seldon.text import DocumentSimilarity, DefaultJsonCorpus
import logging
logger = logging.getLogger()
logger.setLevel(logging.INFO)
corpus = DefaultJsonCorpus(docs)
ds = DocumentSimilarity(model_type='gensim_lsi')
ds.fit(corpus)
print "built model"
import seldon
rw = seldon.Recommender_wrapper()
rw.save_recommender(ds, "reuters_recommender")
print "saved recommender"
def test_asym(self):
corpus = DefaultJsonCorpus(self.get_docs())
ds = TagRecommender(max_s2_size=1.0, min_s2_size=0)
ds.fit(corpus)
res = ds.knn("football", k=1, metric='asym')
self.assertEqual(res[0], ("soccer", 1.0))
def test_jaccard_max_constraint(self):
corpus = DefaultJsonCorpus(self.get_docs())
ds = Tag_Recommender(max_s2_size=0.1,min_s2_size=0)
ds.fit(corpus)
res = ds.knn("football",k=1,metric='jaccard')
self.assertEqual(len(res),0)
