Extracting features from text

run_inference.py

def batch(iterable, n=1):
    l = len(iterable)
    for ndx in range(0, l, n):
        yield iterable[ndx:min(ndx + n, l)]

def build_vectorizer(_estimator, _input_fn_builder, batch_size=128):
  container = DataContainer()
  predict_fn = _estimator.predict(_input_fn_builder(container), yield_single_examples=False)
  
  def vectorize(text, verbose=False):
    x = []
    bar = Progbar(len(text))
    for text_batch in batch(text, batch_size):
      container.set(text_batch)
      x.append(next(predict_fn)['output'])
      if verbose:
        bar.add(len(text_batch))
      
    r = np.vstack(x)
    return r
  
  return vectorize