pyfasttext
Warning! pyfasttext is no longer maintained: use the official Python binding from the fastText repository: https://github.com/facebookresearch/fastText/tree/master/python
Yet another Python binding for fastText.
The binding supports Python 2.6, 2.7 and Python 3. It requires Cython.
Numpy and cysignals are also dependencies, but are optional.
pyfasttext has been tested successfully on Linux and Mac OS X.
Warning: if you want to compile pyfasttext on Windows, do not compile with the cysignals module because it does not support this platform.
Table of Contents
- pyfasttext
- Table of Contents
Installation
To compile pyfasttext, make sure you have the following compiler:
- GCC (
g++) with C++11 support. - LLVM (
clang++) with (at least) partial C++17 support.
Simplest way to install pyfasttext: use pip
Just type these lines:
pip install cython
pip install pyfasttext
Possible compilation error
If you have a compilation error, you can try to install cysignals manually:
pip install cysignals
Then, retry to install pyfasttext with the already mentioned pip command.
Cloning
pyfasttext uses git submodules.
So, you need to add the --recursive option when you clone the repository.
git clone --recursive https://github.com/vrasneur/pyfasttext.git
cd pyfasttext
Requirements for Python 2.7
Python 2.7 support relies on the future module: pyfasttext needs bytes objects, which are not available natively in Python2.
You can install the future module with pip.
pip install future
Building and installing manually
First, install all the requirements:
pip install -r requirements.txt
Then, build and install with setup.py:
python setup.py install
Building and installing without optional dependencies
pyfasttext can export word vectors as numpy ndarrays, however this feature can be disabled at compile time.
To compile without numpy, pyfasttext has a USE_NUMPY environment variable. Set this variable to 0 (or empty), like this:
USE_NUMPY=0 python setup.py install
If you want to compile without cysignals, likewise, you can set the USE_CYSIGNALS environment variable to 0 (or empty).
Usage
How to load the library?
>>> from pyfasttext import FastText
How to load an existing model?
>>> model = FastText('/path/to/model.bin')
or
>>> model = FastText()
>>> model.load_model('/path/to/model.bin')
Word representation learning
You can use all the options provided by the fastText binary (input, output, epoch, lr, ...).
Just use keyword arguments in the training methods of the FastText object.
Training using Skipgram
>>> model = FastText()
>>> model.skipgram(input='data.txt', output='model', epoch=100, lr=0.7)
Training using CBoW
>>> model = FastText()
>>> model.cbow(input='data.txt', output='model', epoch=100, lr=0.7)
Word vectors
Word vectors access
Vector for a given word
By default, a single word vector is returned as a regular Python array of floats.
>>> model['dog']
array('f', [-1.308749794960022, -1.8326224088668823, ...])
Numpy ndarray
The model.get_numpy_vector(word) method returns the word vector as a numpy ndarray.
>>> model.get_numpy_vector('dog')
array([-1.30874979, -1.83262241, ...], dtype=float32)
If you want a normalized vector (i.e. the vector divided by its norm), there is an optional boolean parameter named normalized.
>>> model.get_numpy_vector('dog', normalized=True)
array([-0.07084749, -0.09920666, ...], dtype=float32)
Words for a given vector
The inverse operation of model[word] or model.get_numpy_vector(word) is model.words_for_vector(vector, k).
It returns a list of the k words closest to the provided vector. The default value for k is 1.
>>> king = model.get_numpy_vector('king')
>>> man = model.get_numpy_vector('man')
>>> woman = model.get_numpy_vector('woman')
>>> model.words_for_vector(king + woman - man, k=1)
[('queen', 0.77121970653533936)]
Get the number of words in the model
>>> model.nwords
500000
Get all the word vectors in a model
>>> for word in model.words:
... print(word, model[word])
Numpy ndarray
If you want all the word vectors as a big numpy ndarray, you can use the numpy_normalized_vectors member. Note that all these vectors are normalized.
>>> model.nwords
500000
>>> model.numpy_normalized_vectors
array([[-0.07549749, -0.09407753, ...],
[ 0.00635979, -0.17272158, ...],
...,
[-0.01009259, 0.14604086, ...],
[ 0.12467574, -0.0609326 , ...]], dtype=float32)
>>> model.numpy_normalized_vectors.shape
(500000, 100) # (number of words, dimension)
Misc operations with word vectors
Word similarity
>>> model.similarity('dog', 'cat')
0.75596606254577637
Most similar words
>>> model.nearest_neighbors('dog', k=2)
[('dogs', 0.7843924736976624), ('cat', 75596606254577637)]
Analogies
The model.most_similar() method works similarly as the one in gensim.
>>> model.most_similar(positive=['woman', 'king'], negative=['man'], k=1)
[('queen', 0.77121970653533936)]
Text classification
Supervised learning
>>> model = FastText()
>>> model.supervised(input='/path/to/input.txt', output='/path/to/model', epoch=100, lr=0.7)
Get all the labels
>>> model.labels
['LABEL1', 'LABEL2', ...]
Get the number of labels
>>> model.nlabels
100
Prediction
To obtain the k most likely labels from test sentences, there are multiple model.predict_*() methods.
The default value for k is 1. If you want to obtain all the possible labels, use None for k.
Labels and probabilities
If you have a list of strings (or an iterable object), use this:
>>> model.predict_proba(['first sentence\n', 'second sentence\n'], k=2)
[[('LABEL1', 0.99609375), ('LABEL3', 1.953126549381068e-08)], [('LABEL2', 1.0), ('LABEL3', 1.953126549381068e-08)]]
If you want to test a single string, use this:
>>> model.predict_proba_single('first sentence\n', k=2)
[('LABEL1', 0.99609375), ('LABEL3', 1.953126549381068e-08)]
WARNING: In order to get the same probabilities as the fastText binary, you have to add a newline (\n) at the end of each string.
If your test data is stored inside a file, use this:
>>> model.predict_proba_file('/path/to/test.txt', k=2)
[[('LABEL1', 0.99609375), ('LABEL3', 1.953126549381068e-08)], [('LABEL2', 1.0), ('LABEL3', 1.953126549381068e-08)]]
Normalized probabilities
For performance reasons, fastText probabilities often do not sum up to 1.0.
If you want normalized probabilities (where the sum is closer to 1.0 than the original probabilities), you can use the normalized=True parameter in all the methods that output probabilities (model.predict_proba(), model.predict_proba_file() and model.predict_proba_single()).
>>> sum(proba for label, proba in model.predict_proba_single('this is a sentence that needs to be classified\n', k=None))
0.9785203068801335
>>> sum(proba for label, proba in model.predict_proba_single('this is a sentence that needs to be classified\n', k=None, normalized=True))
0.9999999999999898
Labels only
If you have a list of strings (or an iterable object), use this:
>>> model.predict(['first sentence\n', 'second sentence\n'], k=2)
[['LABEL1', 'LABEL3'], ['LABEL2', 'LABEL3']]
If you want to test a single string, use this:
>>> model.predict_single('first sentence\n', k=2)
['LABEL1', 'LABEL3']
WARNING: In order to get the same probabilities as the fastText binary, you have to add a newline (\n) at the end of each string.
If your test data is stored inside a file, use this:
>>> model.predict_file('/path/to/test.txt', k=2)
[['LABEL1', 'LABEL3'], ['LABEL2', 'LABEL3']]
Quantization
Use keyword arguments in the model.quantize() method.
>>> model.quantize(input='/path/to/input.txt', output='/path/to/model')
You can load quantized models using the FastText constructor or the model.load_model() method.
Is a model quantized?
If you want to know if a model has been quantized before, use the model.quantized attribute.
>>> model = FastText('/path/to/model.bin')
>>> model.quantized
False
>>> model = FastText('/path/to/model.ftz')
>>> model.quantized
True
Subwords
fastText can use subwords (i.e. character ngrams) when doing unsupervised or supervised learning.
You can access the subwords, and their associated vectors, using pyfasttext.
Get the subwords
fastText's word embeddings can be augmented with subword-level information. It is possible to retrieve the subwords and their associated vectors from a model using pyfasttext.
To retrieve all the subwords for a given word, use the model.get_all_subwords(word) method.
>>> model.args.get('minn'), model.args.get('maxn')
(2, 4)
>>> model.get_all_subwords('hello') # word + subwords from 2 to 4 characters
['hello', '<h', '<he', '<hel', 'he', 'hel', 'hell', 'el', 'ell', 'ello', 'll', 'llo', 'llo>', 'lo', 'lo>', 'o>']
For fastText, < means "beginning of a word" and > means "end of a word".
As you can see, fastText includes the full word. You can omit it using the omit_word=True keyword argument.
>>> model.get_all_subwords('hello', omit_word=True)
['<h', '<he', '<hel', 'he', 'hel', 'hell', 'el', 'ell', 'ello', 'll', 'llo', 'llo>', 'lo', 'lo>', 'o>']
When a model is quantized, fastText may prune some subwords. If you want to see only the subwords that are really used when computing a word vector, you should use the model.get_subwords(word) method.
>>> model.quantized
True
>>> model.get_subwords('beautiful')
['eau', 'aut', 'ful', 'ul']
>>> model.get_subwords('hello')
['hello'] # fastText will not use any subwords when computing the word vector, only the full word
Get the subword vectors
To get the individual vectors given the subwords, use the model.get_numpy_subword_vectors(word) method.
>>> model.get_numpy_subword_vectors('beautiful') # 4 vectors, so 4 rows
array([[ 0.49022141, 0.13586822, ..., -0.14065443, 0.89617103], # subword "eau"
[-0.42594951, 0.06260503, ..., -0.18182631, 0.34219387], # subword "aut"
[ 0.49958718, 2.93831301, ..., -1.97498322, -1.16815805], # subword "ful"
[-0.4368791 , -1.92924356, ..., 1.62921488, 1.90240896]], dtype=float32) # subword "ul"
In fastText, the final word vector is the average of these individual vectors.
>>> import numpy as np
>>> vec1 = model.get_numpy_vector('beautiful')
>>> vecs2 = model.get_numpy_subword_vectors('beautiful')
>>> np.allclose(vec1, np.average(vecs2, axis=0))
True
Sentence and text vectors
To compute the vector of a sequence of words (i.e. a sentence), fastText uses two different methods:
- one for unsupervised models
- another one for supervised models
When fastText computes a word vector, recall that it uses the average of the following vectors: the word itself and its subwords.
Unsupervised models
For unsupervised models, the representation of a sentence for fastText is the average of the normalized word vectors.
To get the resulting vector as a regular Python array, use the model.get_sentence_vector(line) method.
To get the resulting vector as a numpy ndarray, use the model.get_numpy_sentence_vector(line) method.
>>> vec = model.get_numpy_sentence_vector('beautiful cats')
>>> vec1 = model.get_numpy_vector('beautiful', normalized=True)
>>> vec2 = model.get_numpy_vector('cats', normalized=True)
>>> np.allclose(vec, np.average([vec1, vec2], axis=0)
True
Supervised models
For supervised models, fastText uses the regular word vectors, as well as vectors computed using word ngrams (i.e. shorter sequences of words from the sentence). When computing the average, these vectors are not normalized.
To get the resulting vector as a regular Python array, use the model.get_text_vector(line) method.
To get the resulting vector as a numpy ndarray, use the model.get_numpy_text_vector(line) method.
>>> model.get_numpy_sentence_vector('beautiful cats') # for an unsupervised model
array([-0.20266785, 0.3407566 , ..., 0.03044436, 0.39055538], dtype=float32)
>>> model.get_numpy_text_vector('beautiful cats') # for a supervised model
array([-0.20840774, 0.4289546 , ..., -0.00457615, 0.52417743], dtype=float32)
Misc utilities
Show the module version
>>> import pyfasttext
>>> pyfasttext.__version__
'0.4.3'
Show fastText version
As there is no version number in fastText, we use the latest fastText commit hash (from HEAD) as a substitute.
>>> import pyfasttext
>>> pyfasttext.__fasttext_version__
'431c9e2a9b5149369cc60fb9f5beba58dcf8ca17'
Show the model (hyper)parameters
>>> model.args
{'bucket': 11000000,
'cutoff': 0,
'dim': 100,
'dsub': 2,
'epoch': 100,
...
}
Show the model version number
fastText uses a versioning scheme for its generated models. You can retrieve the model version number using the model.version attribute.
| version number | description |
|---|---|
| -1 | for really old models with no version number |
| 11 | first version number added by fastText |
| 12 | for models generated after fastText added support for subwords in supervised learning |
>>> model.version
12
Extract labels or classes from a dataset
You can use the FastText object to extract labels or classes from a dataset. The label prefix (which is __label__ by default) is set using the label parameter in the constructor.
If you load an existing model, the label prefix will be the one defined in the model.
>>> model = FastText(label='__my_prefix__')
Extract labels
There can be multiple labels per line.
>>> model.extract_labels('/path/to/dataset1.txt')
[['LABEL2', 'LABEL5'], ['LABEL1'], ...]
Extract classes
There can be only one class per line.
>>> model.extract_classes('/path/to/dataset2.txt')
['LABEL3', 'LABEL1', 'LABEL2', ...]
Exceptions
The fastText source code directly calls exit() when something wrong happens (e.g. a model file does not exist, ...).
Instead of exiting, pyfasttext raises a Python exception (RuntimeError).
>>> import pyfasttext
>>> model = pyfasttext.FastText('/path/to/non-existing_model.bin')
Model file cannot be opened for loading!
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "src/pyfasttext.pyx", line 124, in pyfasttext.FastText.__cinit__ (src/pyfasttext.cpp:1800)
File "src/pyfasttext.pyx", line 348, in pyfasttext.FastText.load_model (src/pyfasttext.cpp:5947)
RuntimeError: fastext tried to exit: 1
Interruptible operations
pyfasttext uses cysignals to make all the computationally intensive operations (e.g. training) interruptible.
To easily interrupt such an operation, just type Ctrl-C in your Python shell.
>>> model.skipgram(input='/path/to/input.txt', output='/path/to/mymodel')
Read 12M words
Number of words: 60237
Number of labels: 0
... # type Ctrl-C during training
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "src/pyfasttext.pyx", line 680, in pyfasttext.FastText.skipgram (src/pyfasttext.cpp:11125)
File "src/pyfasttext.pyx", line 674, in pyfasttext.FastText.train (src/pyfasttext.cpp:11009)
File "src/pyfasttext.pyx", line 668, in pyfasttext.FastText.train (src/pyfasttext.cpp:10926)
File "src/cysignals/signals.pyx", line 94, in cysignals.signals.sig_raise_exception (build/src/cysignals/signals.c:1328)
KeyboardInterrupt
>>> # you can have your shell back!
449 Jan 04, 2023
25.6k Jan 06, 2023
5 Oct 21, 2022
102 Dec 07, 2022
5 Jan 03, 2022
85 Dec 26, 2022
3 May 29, 2022
49 Dec 30, 2022
1.5k Jan 04, 2023
23 Sep 05, 2022
12 Nov 25, 2022
947 Dec 28, 2022
564 Jan 08, 2023
15.3k Jan 03, 2023
70 Dec 11, 2022
483 Jan 02, 2023
1 Sep 14, 2022
0 Feb 13, 2022
6 Feb 16, 2022
20 Jul 14, 2022