def test_mean_vectors():
my_list = Datasource("my_list")
my_mean = aggregators.mean(my_list, vector=True)
cache = {my_list: [[1, 2, 3], [4, 5, 6]]}
assert all(a == b
for a, b in zip(solve(my_mean, cache=cache), [2.5, 3.5, 4.5]))
cache = {my_list: [[]]}
assert solve(my_mean, cache=cache) == [0]
cache = {my_list: [None]}
assert solve(my_mean, cache=cache) == [0]
assert pickle.loads(pickle.dumps(my_mean)) == my_mean
def load_vectorizer(self, enwiki_kvs_path):
enwiki_kvs = vectorizers.word2vec.load_gensim_kv(
path=enwiki_kvs_path,
mmap="r"
)
vectorize_words = functools.partial(vectorizers.word2vec.vectorize_words, enwiki_kvs)
revision_text_vectors = vectorizers.word2vec(
mappers.lower_case(wikitext.revision.datasources.words),
vectorize_words,
name="revision.text.en_vectors")
w2v = aggregators.mean(
revision_text_vectors,
vector=True,
name="revision.text.en_vectors_mean"
)
return w2v
from revscoring.datasources.meta import vectorizers, mappers
from revscoring.features import wikitext
from revscoring.features.meta import aggregators
cswiki_kvs = vectorizers.word2vec.load_gensim_kv(
filename="cswiki-20191201-learned_vectors.50_cell.100k.kv", mmap='r')
def vectorize_words(words):
return vectorizers.word2vec.vectorize_words(cswiki_kvs, words)
revision_text_vectors = vectorizers.word2vec(mappers.lower_case(
wikitext.revision.datasources.words),
vectorize_words,
name="revision.text.cs_vectors")
w2v = aggregators.mean(revision_text_vectors,
vector=True,
name="revision.text.cs_vectors_mean")
drafttopic = [w2v]
articletopic = drafttopic
wikidata_kvs = vectorizers.word2vec.load_gensim_kv(
filename="wikidata-20200501-learned_vectors.50_cell.10k.kv", mmap="r")
def process_claims_to_words(claims):
words = []
for pid, value in claims:
words.append(pid)
if QID_RE.match(value) is not None:
words.append(value)
return words
def vectorize_words(words):
return vectorizers.word2vec.vectorize_words(wikidata_kvs, words)
claim_words = Datasource("wikidata.revision.claim_words",
process_claims_to_words,
depends_on=[wikibase.revision.datasources.claims])
revision_claim_words_vectors = vectorizers.word2vec(
claim_words, vectorize_words, name="revision.text.wikidata_vectors")
w2v = aggregators.mean(revision_claim_words_vectors,
vector=True,
name="revision.text.wikidata_vectors_mean")
articletopic = [w2v]
from revscoring.datasources.meta import vectorizers
from revscoring.features.meta import aggregators
from revscoring.languages import english
google_news_kvs = vectorizers.word2vec.load_kv(
filename="GoogleNews-vectors-negative300.bin.gz", limit=150000)
def vectorize_words(words):
return vectorizers.word2vec.vectorize_words(google_news_kvs, words)
revision_text_vectors = vectorizers.word2vec(
english.stopwords.revision.datasources.non_stopwords,
vectorize_words,
name="revision.text.google_news_vectors")
w2v = aggregators.mean(
revision_text_vectors,
vector=True,
name="revision.text.google_news_vector_mean"
)
drafttopic = [w2v]
