gensim logo

gensim
gensim tagline

Get Expert Help From The Gensim Authors

Consulting in Machine Learning & NLP

• Commercial document similarity engine: ScaleText.ai

Corporate trainings in Python Data Science and Deep Learning

models.fasttext – FastText model

models.fasttext – FastText model

Learn word representations via fasttext’s “skip-gram and CBOW models”, using either hierarchical softmax or negative sampling [1].

Notes

There are more ways to get word vectors in Gensim than just FastText. See wrappers for VarEmbed and WordRank or Word2Vec

This module allows training a word embedding from a training corpus with the additional ability to obtain word vectors for out-of-vocabulary words.

For a tutorial on gensim’s native fasttext, refer to the noteboook – [2]

Make sure you have a C compiler before installing gensim, to use optimized (compiled) fasttext training

[1](1, 2) P. Bojanowski, E. Grave, A. Joulin, T. Mikolov Enriching Word Vectors with Subword Information. In arXiv preprint arXiv:1607.04606. https://arxiv.org/abs/1607.04606
[2]https://github.com/RaRe-Technologies/gensim/blob/develop/docs/notebooks/FastText_Tutorial.ipynb
class gensim.models.fasttext.FastText(sentences=None, sg=0, hs=0, size=100, alpha=0.025, window=5, min_count=5, max_vocab_size=None, word_ngrams=1, sample=0.001, seed=1, workers=3, min_alpha=0.0001, negative=5, cbow_mean=1, hashfxn=<built-in function hash>, iter=5, null_word=0, min_n=3, max_n=6, sorted_vocab=1, bucket=2000000, trim_rule=None, batch_words=10000, callbacks=())

Bases: gensim.models.base_any2vec.BaseWordEmbeddingsModel

Class for training, using and evaluating word representations learned using method described in [1] aka Fasttext.

The model can be stored/loaded via its save() and load() methods, or loaded in a format compatible with the original fasttext implementation via load_fasttext_format().

Initialize the model from an iterable of sentences. Each sentence is a list of words (unicode strings) that will be used for training.

Parameters:
  • sentences (iterable of iterables) – The sentences iterable can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See BrownCorpus, Text8Corpus or LineSentence in word2vec module for such examples. If you don’t supply sentences, the model is left uninitialized – use if you plan to initialize it in some other way.
  • sg (int {1, 0}) – Defines the training algorithm. If 1, skip-gram is used, otherwise, CBOW is employed.
  • size (int) – Dimensionality of the feature vectors.
  • window (int) – The maximum distance between the current and predicted word within a sentence.
  • alpha (float) – The initial learning rate.
  • min_alpha (float) – Learning rate will linearly drop to min_alpha as training progresses.
  • seed (int) – Seed for the random number generator. Initial vectors for each word are seeded with a hash of the concatenation of word + str(seed). Note that for a fully deterministically-reproducible run, you must also limit the model to a single worker thread (workers=1), to eliminate ordering jitter from OS thread scheduling. (In Python 3, reproducibility between interpreter launches also requires use of the PYTHONHASHSEED environment variable to control hash randomization).
  • min_count (int) – Ignores all words with total frequency lower than this.
  • max_vocab_size (int) – Limits the RAM during vocabulary building; if there are more unique words than this, then prune the infrequent ones. Every 10 million word types need about 1GB of RAM. Set to None for no limit.
  • sample (float) – The threshold for configuring which higher-frequency words are randomly downsampled, useful range is (0, 1e-5).
  • workers (int) – Use these many worker threads to train the model (=faster training with multicore machines).
  • hs (int {1,0}) – If 1, hierarchical softmax will be used for model training. If set to 0, and negative is non-zero, negative sampling will be used.
  • negative (int) – If > 0, negative sampling will be used, the int for negative specifies how many “noise words” should be drawn (usually between 5-20). If set to 0, no negative sampling is used.
  • cbow_mean (int {1,0}) – If 0, use the sum of the context word vectors. If 1, use the mean, only applies when cbow is used.
  • hashfxn (function) – Hash function to use to randomly initialize weights, for increased training reproducibility.
  • iter (int) – Number of iterations (epochs) over the corpus.
  • trim_rule (function) – Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to keep_vocab_item()), or a callable that accepts parameters (word, count, min_count) and returns either gensim.utils.RULE_DISCARD, gensim.utils.RULE_KEEP or gensim.utils.RULE_DEFAULT. Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part of the model.
  • sorted_vocab (int {1,0}) – If 1, sort the vocabulary by descending frequency before assigning word indexes.
  • batch_words (int) – Target size (in words) for batches of examples passed to worker threads (and thus cython routines).(Larger batches will be passed if individual texts are longer than 10000 words, but the standard cython code truncates to that maximum.)
  • min_n (int) – Min length of char ngrams to be used for training word representations.
  • max_n (int) – Max length of char ngrams to be used for training word representations. Set max_n to be lesser than min_n to avoid char ngrams being used.
  • word_ngrams (int {1,0}) – If 1, uses enriches word vectors with subword(ngrams) information. If 0, this is equivalent to word2vec.
  • bucket (int) – Character ngrams are hashed into a fixed number of buckets, in order to limit the memory usage of the model. This option specifies the number of buckets used by the model.
  • callbacks – List of callbacks that need to be executed/run at specific stages during training.

Examples

Initialize and train a FastText model

>>> from gensim.models import FastText
>>> sentences = [["cat", "say", "meow"], ["dog", "say", "woof"]]
>>>
>>> model = FastText(sentences, min_count=1)
>>> say_vector = model['say']  # get vector for word
>>> of_vector = model['of']  # get vector for out-of-vocab word
__getitem__(**kwargs)

Deprecated. Use self.wv.__getitem__() instead. Refer to the documentation for gensim.models.KeyedVectors.__getitem__

accuracy(**kwargs)
bucket
build_vocab(sentences, update=False, progress_per=10000, keep_raw_vocab=False, trim_rule=None, **kwargs)

Build vocabulary from a sequence of sentences (can be a once-only generator stream). Each sentence must be a list of unicode strings.

Parameters:
  • sentences (iterable of iterables) – The sentences iterable can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See BrownCorpus, Text8Corpus or LineSentence in word2vec module for such examples.
  • keep_raw_vocab (bool) – If not true, delete the raw vocabulary after the scaling is done and free up RAM.
  • trim_rule (function) – Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to keep_vocab_item()), or a callable that accepts parameters (word, count, min_count) and returns either gensim.utils.RULE_DISCARD, gensim.utils.RULE_KEEP or gensim.utils.RULE_DEFAULT. Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part of the model.
  • progress_per (int) – Indicates how many words to process before showing/updating the progress.
  • update (bool) – If true, the new words in sentences will be added to model’s vocab.

Example

Train a model and update vocab for online training

>>> from gensim.models import FastText
>>> sentences_1 = [["cat", "say", "meow"], ["dog", "say", "woof"]]
>>> sentences_2 = [["dude", "say", "wazzup!"]]
>>>
>>> model = FastText(min_count=1)
>>> model.build_vocab(sentences_1)
>>> model.train(sentences_1, total_examples=model.corpus_count, epochs=model.iter)
>>> model.build_vocab(sentences_2, update=True)
>>> model.train(sentences_2, total_examples=model.corpus_count, epochs=model.iter)
build_vocab_from_freq(word_freq, keep_raw_vocab=False, corpus_count=None, trim_rule=None, update=False)

Build vocabulary from a dictionary of word frequencies. Build model vocabulary from a passed dictionary that contains (word,word count). Words must be of type unicode strings.

Parameters:
  • word_freq (dict) – Word,Word_Count dictionary.
  • keep_raw_vocab (bool) – If not true, delete the raw vocabulary after the scaling is done and free up RAM.
  • corpus_count (int) – Even if no corpus is provided, this argument can set corpus_count explicitly.
  • trim_rule (function) – Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). Can be None (min_count will be used, look to keep_vocab_item()), or a callable that accepts parameters (word, count, min_count) and returns either gensim.utils.RULE_DISCARD, gensim.utils.RULE_KEEP or gensim.utils.RULE_DEFAULT. Note: The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part of the model.
  • update (bool) – If true, the new provided words in word_freq dict will be added to model’s vocab.

Examples

>>> from gensim.models import Word2Vec
>>>
>>> model= Word2Vec()
>>> model.build_vocab_from_freq({"Word1": 15, "Word2": 20})
clear_sims()

Removes all L2-normalized vectors for words from the model. You will have to recompute them using init_sims method.

cum_table
doesnt_match(**kwargs)

Deprecated. Use self.wv.doesnt_match() instead. Refer to the documentation for gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.doesnt_match

estimate_memory(vocab_size=None, report=None)

Estimate required memory for a model using current settings and provided vocabulary size.

evaluate_word_pairs(**kwargs)

Deprecated. Use self.wv.evaluate_word_pairs() instead. Refer to the documentation for gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.evaluate_word_pairs

hashfxn
init_sims(replace=False)

init_sims() resides in KeyedVectors because it deals with syn0 mainly, but because syn1 is not an attribute of KeyedVectors, it has to be deleted in this class, and the normalizing of syn0 happens inside of KeyedVectors

iter
layer1_size
classmethod load(*args, **kwargs)

Loads a previously saved FastText model. Also see save().

Parameters:fname (str) – Path to the saved file.
Returns:Returns the loaded model as an instance of :class: ~gensim.models.fasttext.FastText.
Return type:obj: ~gensim.models.fasttext.FastText
load_binary_data(encoding='utf8')

Loads data from the output binary file created by FastText training

classmethod load_fasttext_format(model_file, encoding='utf8')

Load the input-hidden weight matrix from the fast text output files.

Note that due to limitations in the FastText API, you cannot continue training with a model loaded this way, though you can query for word similarity etc.

Parameters:
  • model_file (str) – Path to the FastText output files. FastText outputs two model files - /path/to/model.vec and /path/to/model.bin Expected value for this example: /path/to/model or /path/to/model.bin, as gensim requires only .bin file to load entire fastText model.
  • encoding (str) – Specifies the encoding.
Returns:

Returns the loaded model as an instance of :class: ~gensim.models.fasttext.FastText.

Return type:

obj: ~gensim.models.fasttext.FastText

max_n
min_count
min_n
most_similar(**kwargs)

Deprecated. Use self.wv.most_similar() instead. Refer to the documentation for gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.most_similar

most_similar_cosmul(**kwargs)

Deprecated. Use self.wv.most_similar_cosmul() instead. Refer to the documentation for gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.most_similar_cosmul

n_similarity(**kwargs)

Deprecated. Use self.wv.n_similarity() instead. Refer to the documentation for gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.n_similarity

num_ngram_vectors
sample
save(*args, **kwargs)

Save the model. This saved model can be loaded again using load(), which supports online training and getting vectors for out-of-vocabulary words.

Parameters:fname (str) – Path to the file.
similar_by_vector(**kwargs)

Deprecated. Use self.wv.similar_by_vector() instead. Refer to the documentation for gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similar_by_vector

similar_by_word(**kwargs)

Deprecated. Use self.wv.similar_by_word() instead. Refer to the documentation for gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similar_by_word

similarity(**kwargs)

Deprecated. Use self.wv.similarity() instead. Refer to the documentation for gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.similarity

struct_unpack(file_handle, fmt)
syn0_lockf
syn0_ngrams_lockf
syn0_vocab_lockf
syn1
syn1neg
train(sentences, total_examples=None, total_words=None, epochs=None, start_alpha=None, end_alpha=None, word_count=0, queue_factor=2, report_delay=1.0, callbacks=(), **kwargs)

Update the model’s neural weights from a sequence of sentences (can be a once-only generator stream). For FastText, each sentence must be a list of unicode strings.

To support linear learning-rate decay from (initial) alpha to min_alpha, and accurate progress-percentage logging, either total_examples (count of sentences) or total_words (count of raw words in sentences) MUST be provided (if the corpus is the same as was provided to build_vocab(), the count of examples in that corpus will be available in the model’s corpus_count property).

To avoid common mistakes around the model’s ability to do multiple training passes itself, an explicit epochs argument MUST be provided. In the common and recommended case, where train() is only called once, the model’s cached iter value should be supplied as epochs value.

Parameters:
  • sentences (iterable of iterables) – The sentences iterable can be simply a list of lists of tokens, but for larger corpora, consider an iterable that streams the sentences directly from disk/network. See BrownCorpus, Text8Corpus or LineSentence in word2vec module for such examples.
  • total_examples (int) – Count of sentences.
  • total_words (int) – Count of raw words in sentences.
  • epochs (int) – Number of iterations (epochs) over the corpus.
  • start_alpha (float) – Initial learning rate.
  • end_alpha (float) – Final learning rate. Drops linearly from start_alpha.
  • word_count (int) – Count of words already trained. Set this to 0 for the usual case of training on all words in sentences.
  • queue_factor (int) – Multiplier for size of queue (number of workers * queue_factor).
  • report_delay (float) – Seconds to wait before reporting progress.
  • callbacks – List of callbacks that need to be executed/run at specific stages during training.

Examples

>>> from gensim.models import FastText
>>> sentences = [["cat", "say", "meow"], ["dog", "say", "woof"]]
>>>
>>> model = FastText(min_count=1)
>>> model.build_vocab(sentences)
>>> model.train(sentences, total_examples=model.corpus_count, epochs=model.iter)
wmdistance(**kwargs)

Deprecated. Use self.wv.wmdistance() instead. Refer to the documentation for gensim.models.keyedvectors.WordEmbeddingsKeyedVectors.wmdistance

class gensim.models.fasttext.FastTextTrainables(vector_size=100, seed=1, hashfxn=<built-in function hash>, bucket=2000000)

Bases: gensim.models.word2vec.Word2VecTrainables

get_vocab_word_vecs(wv)

Calculate vectors for words in vocabulary and stores them in vectors.

init_ngrams_post_load(file_name, wv)

Computes ngrams of all words present in vocabulary and stores vectors for only those ngrams. Vectors for other ngrams are initialized with a random uniform distribution in FastText. These vectors are discarded here to save space.

init_ngrams_weights(wv, update=False, vocabulary=None)

Compute ngrams of all words present in vocabulary and stores vectors for only those ngrams. Vectors for other ngrams are initialized with a random uniform distribution in FastText.

Parameters:update (bool) – If True, the new vocab words and their new ngrams word vectors are initialized with random uniform distribution and updated/added to the existing vocab word and ngram vectors.
classmethod load(fname, mmap=None)

Load a previously saved object (using save()) from file.

Parameters:
  • fname (str) – Path to file that contains needed object.
  • mmap (str, optional) – Memory-map option. If the object was saved with large arrays stored separately, you can load these arrays via mmap (shared memory) using mmap=’r’. If the file being loaded is compressed (either ‘.gz’ or ‘.bz2’), then `mmap=None must be set.

See also

save()

Returns:Object loaded from fname.
Return type:object
Raises:IOError – When methods are called on instance (should be called from class).
prepare_weights(hs, negative, wv, update=False, vocabulary=None)

Build tables and model weights based on final vocabulary settings.

reset_ngrams_weights(wv)

Reset all projection weights to an initial (untrained) state, but keep the existing vocabulary and their ngrams.

reset_weights(hs, negative, wv)

Reset all projection weights to an initial (untrained) state, but keep the existing vocabulary.

save(fname_or_handle, separately=None, sep_limit=10485760, ignore=frozenset([]), pickle_protocol=2)

Save the object to file.

Parameters:
  • fname_or_handle (str or file-like) – Path to output file or already opened file-like object. If the object is a file handle, no special array handling will be performed, all attributes will be saved to the same file.
  • separately (list of str or None, optional) – If None - automatically detect large numpy/scipy.sparse arrays in the object being stored, and store them into separate files. This avoids pickle memory errors and allows mmap’ing large arrays back on load efficiently. If list of str - this attributes will be stored in separate files, the automatic check is not performed in this case.
  • sep_limit (int) – Limit for automatic separation.
  • ignore (frozenset of str) – Attributes that shouldn’t be serialize/store.
  • pickle_protocol (int) – Protocol number for pickle.

See also

load()

seeded_vector(seed_string, vector_size)

Create one ‘random’ vector (but deterministic by seed_string)

update_weights(hs, negative, wv)

Copy all the existing weights, and reset the weights for the newly added vocabulary.

class gensim.models.fasttext.FastTextVocab(max_vocab_size=None, min_count=5, sample=0.001, sorted_vocab=True, null_word=0)

Bases: gensim.models.word2vec.Word2VecVocab

add_null_word(wv)
create_binary_tree(wv)

Create a binary Huffman tree using stored vocabulary word counts. Frequent words will have shorter binary codes. Called internally from build_vocab().

classmethod load(fname, mmap=None)

Load a previously saved object (using save()) from file.

Parameters:
  • fname (str) – Path to file that contains needed object.
  • mmap (str, optional) – Memory-map option. If the object was saved with large arrays stored separately, you can load these arrays via mmap (shared memory) using mmap=’r’. If the file being loaded is compressed (either ‘.gz’ or ‘.bz2’), then `mmap=None must be set.

See also

save()

Returns:Object loaded from fname.
Return type:object
Raises:IOError – When methods are called on instance (should be called from class).
make_cum_table(wv, power=0.75, domain=2147483647)

Create a cumulative-distribution table using stored vocabulary word counts for drawing random words in the negative-sampling training routines.

To draw a word index, choose a random integer up to the maximum value in the table (cum_table[-1]), then finding that integer’s sorted insertion point (as if by bisect_left or ndarray.searchsorted()). That insertion point is the drawn index, coming up in proportion equal to the increment at that slot.

Called internally from ‘build_vocab()’.

prepare_vocab(hs, negative, wv, update=False, keep_raw_vocab=False, trim_rule=None, min_count=None, sample=None, dry_run=False)

Apply vocabulary settings for min_count (discarding less-frequent words) and sample (controlling the downsampling of more-frequent words).

Calling with dry_run=True will only simulate the provided settings and report the size of the retained vocabulary, effective corpus length, and estimated memory requirements. Results are both printed via logging and returned as a dict.

Delete the raw vocabulary after the scaling is done to free up RAM, unless keep_raw_vocab is set.

save(fname_or_handle, separately=None, sep_limit=10485760, ignore=frozenset([]), pickle_protocol=2)

Save the object to file.

Parameters:
  • fname_or_handle (str or file-like) – Path to output file or already opened file-like object. If the object is a file handle, no special array handling will be performed, all attributes will be saved to the same file.
  • separately (list of str or None, optional) – If None - automatically detect large numpy/scipy.sparse arrays in the object being stored, and store them into separate files. This avoids pickle memory errors and allows mmap’ing large arrays back on load efficiently. If list of str - this attributes will be stored in separate files, the automatic check is not performed in this case.
  • sep_limit (int) – Limit for automatic separation.
  • ignore (frozenset of str) – Attributes that shouldn’t be serialize/store.
  • pickle_protocol (int) – Protocol number for pickle.

See also

load()

scan_vocab(sentences, progress_per=10000, trim_rule=None)

Do an initial scan of all words appearing in sentences.

sort_vocab(wv)

Sort the vocabulary so the most frequent words have the lowest indexes.