taghasher.py 文件源码

def new(n_feature=128):
  vectorizer = CountVectorizer(
    encoding='utf-8',
    ngram_range=(1,1), # Unigram only
    max_features=n_feature, 
    binary=True
  )

  # Fill the gap (missing expected tags)
  # ---
  # Hypothesis: Some tags are somehow related so 
  # we smoothen the missing values with matrix factorisation.
  smoother = NMF(n_components=n_feature)

  # Binarise the vector's individual values 
  binariser = Binarizer(copy=True)

  # Count vectoriser => NMF as smoother => Binariser
  print(colored('Taghasher model created','yellow'))
  return [vectorizer,smoother,binariser]