def test_save_load_with_memmap(self):
p = Path("fse/test/test_data/test_vectors")
p_target = Path("fse/test/test_data/test_vectors.vectors")
p_not_exists = Path("fse/test/test_data/test_vectors.vectors.npy")
sv = SentenceVectors(2, mapfile_path=str(p))
shape = (1000, 1000)
sv.vectors = np.ones(shape, dtype=np.float32)
memvecs = np.memmap(
p_target, dtype=np.float32,
mode='w+', shape=shape)
memvecs[:] = sv.vectors[:]
del memvecs
self.assertTrue(p_target.exists())
sv.save(str(p.absolute()))
self.assertTrue(p.exists())
self.assertFalse(p_not_exists.exists())
sv = SentenceVectors.load(str(p.absolute()))
self.assertEqual(shape, sv.vectors.shape)
for t in [p, p_target]:
t.unlink()
def setUp(self):
self.sv = SentenceVectors(2)
self.sv.vectors = np.arange(10).reshape(5, 2)
def __init__(
self,
model: BaseKeyedVectors,
sv_mapfile_path: str = None,
wv_mapfile_path: str = None,
workers: int = 1,
lang_freq: str = None,
fast_version: int = 0,
batch_words: int = 10000,
batch_ngrams: int = 40,
**kwargs,
):
""" Base class for all Sentence2Vec Models. Provides core functionality, such as
save, load, sanity checking, frequency induction, data checking, scanning, etc.
Parameters
----------
model : :class:`~gensim.models.keyedvectors.BaseKeyedVectors` or :class:`~gensim.models.base_any2vec.BaseWordEmbeddingsModel`
This object essentially contains the mapping between words and embeddings. To compute the sentence embeddings
the wv.vocab and wv.vector elements are required.
sv_mapfile_path : str, optional
Optional path to store the sentence-vectors in for very large datasets. Used for memmap.
wv_mapfile_path : str, optional
Optional path to store the word-vectors in for very large datasets. Used for memmap.
Use sv_mapfile_path and wv_mapfile_path to train disk-to-disk without needing much ram.
workers : int, optional
Number of working threads, used for multithreading. For most tasks (few words in a sentence)
a value of 1 should be more than enough.
lang_freq : str, optional
Some pre-trained embeddings, i.e. "GoogleNews-vectors-negative300.bin", do not contain information about
the frequency of a word. As the frequency is required for estimating the word weights, we induce
frequencies into the wv.vocab.count based on :class:`~wordfreq`
If no frequency information is available, you can choose the language to estimate the frequency.
See https://github.com/LuminosoInsight/wordfreq
fast_version : {-1, 1}, optional
Whether or not the fast cython implementation of the internal training methods is available. 1 means it is.
batch_words : int, optional
Number of words to be processed by a single job.
batch_ngrams : int, optional
Number of maxium ngrams for oov words.
**kwargs : object
Key word arguments needed to allow children classes to accept more arguments.
"""
"""
TODO:
[ ] global:
[ ] windows support
[ ] documentation
[ ] more benchmarks
[ ] remove wv_mapfile_path?
[ ] modifiable sv_mapfile_path?
[ ] models:
[ ] check feasibility first
[ ] max-pooling -> easy
[ ] hierarchical pooling -> easy
[ ] discrete cosine transform -> somewhat easy, questionable
[ ] valve -> unclear, not cited enough
[ ] power-means embedding -> very large dimensionalty
[ ] z-score transformation is quite nice
[ ] sentencevectors:
[X] similar_by_sentence model type check
[ ] approximate NN search for large files
[ ] compare ANN libraries
[ ] ease-of-use
[ ] dependencies
[ ] compatibility
[ ] memory-usage
"""
set_madvise_for_mmap()
self.workers = int(workers)
self.batch_words = batch_words
self.batch_ngrams = batch_ngrams
self.wv = None
self.is_ft = False
self.wv_mapfile_path = (Path(wv_mapfile_path)
if wv_mapfile_path is not None else None)
self.wv_mapfile_shapes = {}
if fast_version < 0:
warnings.warn(
"C extension not loaded, training/inferring will be slow. "
"Install a C compiler and reinstall fse.")
self._check_and_include_model(model)
if self.wv_mapfile_path is not None:
self._map_all_vectors_to_disk(self.wv_mapfile_path)
if lang_freq is not None:
self._check_language_settings(lang_freq)
self._induce_frequencies()
self.sv = SentenceVectors(vector_size=self.wv.vector_size,
mapfile_path=sv_mapfile_path)
self.prep = BaseSentence2VecPreparer()
self.word_weights = ones(len(self.wv.vocab), REAL)