def bm25_vectorizer(data):
vectorizer = TfidfVectorizer(
sublinear_tf=True,
max_df=0.5,
preprocessor=stif_classifier_dataset.preprocessor)
vectorizer._tfidf = bm25_tfidf.BM25Transformer(use_idf=True,
k1=1.5,
b=0.75)
X = vectorizer.fit_transform(data)
return vectorizer, X
def from_path(cls, path, **shared):
import numpy as np
import scipy.sparse as sp
from sklearn.feature_extraction.text import (TfidfTransformer,
TfidfVectorizer as
SklearnTfidfVectorizer)
path = Path(path)
model_path = path / "vectorizer.json"
if not model_path.exists():
raise LoadingError("Missing vectorizer model file: %s" %
model_path.name)
with model_path.open("r", encoding="utf-8") as f:
vectorizer_dict = json.load(f)
vectorizer = cls(vectorizer_dict["config"], **shared)
vectorizer._language = vectorizer_dict["language_code"]
builtin_entity_scope = vectorizer_dict["builtin_entity_scope"]
if builtin_entity_scope is not None:
builtin_entity_scope = set(builtin_entity_scope)
vectorizer.builtin_entity_scope = builtin_entity_scope
vectorizer_ = vectorizer_dict["vectorizer"]
if vectorizer_:
vocab = vectorizer_["vocab"]
idf_diag_data = vectorizer_["idf_diag"]
idf_diag_data = np.array(idf_diag_data)
idf_diag_shape = (len(idf_diag_data), len(idf_diag_data))
row = list(range(idf_diag_shape[0]))
col = list(range(idf_diag_shape[0]))
idf_diag = sp.csr_matrix((idf_diag_data, (row, col)),
shape=idf_diag_shape)
tfidf_transformer = TfidfTransformer()
tfidf_transformer._idf_diag = idf_diag
vectorizer_ = SklearnTfidfVectorizer(
tokenizer=lambda x: tokenize_light(x, vectorizer._language))
vectorizer_.vocabulary_ = vocab
vectorizer_._tfidf = tfidf_transformer
vectorizer._tfidf_vectorizer = vectorizer_
return vectorizer
def bm25_vectorizer(data):
vectorizer = TfidfVectorizer(sublinear_tf=True, max_df=0.5, preprocessor=stif_classifier_dataset.preprocessor)
vectorizer._tfidf = bm25_tfidf.BM25Transformer(use_idf=True, k1=1.5, b=0.75)
X = vectorizer.fit_transform(data)
return vectorizer,X
