nltk.tag.PerceptronTagger¶

class nltk.tag.PerceptronTagger[source]¶

Bases: TaggerI

Greedy Averaged Perceptron tagger, as implemented by Matthew Honnibal. See more implementation details here: https://explosion.ai/blog/part-of-speech-pos-tagger-in-python

>>> from nltk.tag.perceptron import PerceptronTagger

Train the model

>>> tagger = PerceptronTagger(load=False)

>>> tagger.train([[('today','NN'),('is','VBZ'),('good','JJ'),('day','NN')],
... [('yes','NNS'),('it','PRP'),('beautiful','JJ')]])

>>> tagger.tag(['today','is','a','beautiful','day'])
[('today', 'NN'), ('is', 'PRP'), ('a', 'PRP'), ('beautiful', 'JJ'), ('day', 'NN')]

Use the pretrain model (the default constructor)

>>> pretrain = PerceptronTagger()

>>> pretrain.tag('The quick brown fox jumps over the lazy dog'.split())
[('The', 'DT'), ('quick', 'JJ'), ('brown', 'NN'), ('fox', 'NN'), ('jumps', 'VBZ'), ('over', 'IN'), ('the', 'DT'), ('lazy', 'JJ'), ('dog', 'NN')]

>>> pretrain.tag("The red cat".split())
[('The', 'DT'), ('red', 'JJ'), ('cat', 'NN')]

json_tag = 'nltk.tag.sequential.PerceptronTagger'¶

START = ['-START-', '-START2-']¶

END = ['-END-', '-END2-']¶

__init__(load=True)[source]¶

Parameters: load – Load the pickled model upon instantiation.

tag(tokens, return_conf=False, use_tagdict=True)[source]¶: Tag tokenized sentences. :params tokens: list of word :type tokens: list(str)

train(sentences, save_loc=None, nr_iter=5)[source]¶

Train a model from sentences, and save it at save_loc. nr_iter controls the number of Perceptron training iterations.

Parameters

sentences – A list or iterator of sentences, where each sentence is a list of (words, tags) tuples.
save_loc – If not None, saves a pickled model in this location.
nr_iter – Number of training iterations.

load(loc)[source]¶

Parameters: loc (str) – Load a pickled model at location.

encode_json_obj()[source]¶

classmethod decode_json_obj(obj)[source]¶

normalize(word)[source]¶

Normalization used in pre-processing. - All words are lower cased - Groups of digits of length 4 are represented as !YEAR; - Other digits are represented as !DIGITS

Return type: str

accuracy(gold)[source]¶

Score the accuracy of the tagger against the gold standard. Strip the tags from the gold standard text, retag it using the tagger, then compute the accuracy score.

Parameters: gold (list(list(tuple(str, str)))) – The list of tagged sentences to score the tagger on.
Return type: float

confusion(gold)[source]¶

Return a ConfusionMatrix with the tags from gold as the reference values, with the predictions from tag_sents as the predicted values.

>>> from nltk.tag import PerceptronTagger
>>> from nltk.corpus import treebank
>>> tagger = PerceptronTagger()
>>> gold_data = treebank.tagged_sents()[:10]
>>> print(tagger.confusion(gold_data))
       |        -                                                                                     |
       |        N                                                                                     |
       |        O                                               P                                     |
       |        N                       J  J        N  N  P  P  R     R           V  V  V  V  V  W    |
       |  '     E     C  C  D  E  I  J  J  J  M  N  N  N  O  R  P  R  B  R  T  V  B  B  B  B  B  D  ` |
       |  '  ,  -  .  C  D  T  X  N  J  R  S  D  N  P  S  S  P  $  B  R  P  O  B  D  G  N  P  Z  T  ` |
-------+----------------------------------------------------------------------------------------------+
    '' | <1> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
     , |  .<15> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
-NONE- |  .  . <.> .  .  2  .  .  .  2  .  .  .  5  1  .  .  .  .  2  .  .  .  .  .  .  .  .  .  .  . |
     . |  .  .  .<10> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
    CC |  .  .  .  . <1> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
    CD |  .  .  .  .  . <5> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
    DT |  .  .  .  .  .  .<20> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
    EX |  .  .  .  .  .  .  . <1> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
    IN |  .  .  .  .  .  .  .  .<22> .  .  .  .  .  .  .  .  .  .  3  .  .  .  .  .  .  .  .  .  .  . |
    JJ |  .  .  .  .  .  .  .  .  .<16> .  .  .  .  1  .  .  .  .  1  .  .  .  .  .  .  .  .  .  .  . |
   JJR |  .  .  .  .  .  .  .  .  .  . <.> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
   JJS |  .  .  .  .  .  .  .  .  .  .  . <1> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
    MD |  .  .  .  .  .  .  .  .  .  .  .  . <1> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
    NN |  .  .  .  .  .  .  .  .  .  .  .  .  .<28> 1  1  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
   NNP |  .  .  .  .  .  .  .  .  .  .  .  .  .  .<25> .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
   NNS |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .<19> .  .  .  .  .  .  .  .  .  .  .  .  .  .  . |
   POS |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <1> .  .  .  .  .  .  .  .  .  .  .  .  .  . |
   PRP |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <4> .  .  .  .  .  .  .  .  .  .  .  .  . |
  PRP$ |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <2> .  .  .  .  .  .  .  .  .  .  .  . |
    RB |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <4> .  .  .  .  .  .  .  .  .  .  . |
   RBR |  .  .  .  .  .  .  .  .  .  .  1  .  .  .  .  .  .  .  .  . <1> .  .  .  .  .  .  .  .  .  . |
    RP |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <1> .  .  .  .  .  .  .  .  . |
    TO |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <5> .  .  .  .  .  .  .  . |
    VB |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <3> .  .  .  .  .  .  . |
   VBD |  .  .  .  .  .  .  .  .  .  .  .  .  .  1  .  .  .  .  .  .  .  .  .  . <6> .  .  .  .  .  . |
   VBG |  .  .  .  .  .  .  .  .  .  .  .  .  .  1  .  .  .  .  .  .  .  .  .  .  . <4> .  .  .  .  . |
   VBN |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  1  . <4> .  .  .  . |
   VBP |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <3> .  .  . |
   VBZ |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <7> .  . |
   WDT |  .  .  .  .  .  .  .  .  2  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <.> . |
    `` |  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  .  . <1>|
-------+----------------------------------------------------------------------------------------------+
(row = reference; col = test)

Parameters: gold (list(list(tuple(str, str)))) – The list of tagged sentences to run the tagger with, also used as the reference values in the generated confusion matrix.
Return type: ConfusionMatrix

evaluate(**kwargs)[source]¶: @deprecated: Use accuracy(gold) instead.

evaluate_per_tag(gold, alpha=0.5, truncate=None, sort_by_count=False)[source]¶

Tabulate the recall, precision and f-measure for each tag from gold or from running tag on the tokenized sentences from gold.

>>> from nltk.tag import PerceptronTagger
>>> from nltk.corpus import treebank
>>> tagger = PerceptronTagger()
>>> gold_data = treebank.tagged_sents()[:10]
>>> print(tagger.evaluate_per_tag(gold_data))
   Tag | Prec.  | Recall | F-measure
-------+--------+--------+-----------
    '' | 1.0000 | 1.0000 | 1.0000
     , | 1.0000 | 1.0000 | 1.0000
-NONE- | 0.0000 | 0.0000 | 0.0000
     . | 1.0000 | 1.0000 | 1.0000
    CC | 1.0000 | 1.0000 | 1.0000
    CD | 0.7143 | 1.0000 | 0.8333
    DT | 1.0000 | 1.0000 | 1.0000
    EX | 1.0000 | 1.0000 | 1.0000
    IN | 0.9167 | 0.8800 | 0.8980
    JJ | 0.8889 | 0.8889 | 0.8889
   JJR | 0.0000 | 0.0000 | 0.0000
   JJS | 1.0000 | 1.0000 | 1.0000
    MD | 1.0000 | 1.0000 | 1.0000
    NN | 0.8000 | 0.9333 | 0.8615
   NNP | 0.8929 | 1.0000 | 0.9434
   NNS | 0.9500 | 1.0000 | 0.9744
   POS | 1.0000 | 1.0000 | 1.0000
   PRP | 1.0000 | 1.0000 | 1.0000
  PRP$ | 1.0000 | 1.0000 | 1.0000
    RB | 0.4000 | 1.0000 | 0.5714
   RBR | 1.0000 | 0.5000 | 0.6667
    RP | 1.0000 | 1.0000 | 1.0000
    TO | 1.0000 | 1.0000 | 1.0000
    VB | 1.0000 | 1.0000 | 1.0000
   VBD | 0.8571 | 0.8571 | 0.8571
   VBG | 1.0000 | 0.8000 | 0.8889
   VBN | 1.0000 | 0.8000 | 0.8889
   VBP | 1.0000 | 1.0000 | 1.0000
   VBZ | 1.0000 | 1.0000 | 1.0000
   WDT | 0.0000 | 0.0000 | 0.0000
    `` | 1.0000 | 1.0000 | 1.0000

Parameters

gold (list(list(tuple(str, str)))) – The list of tagged sentences to score the tagger on.
alpha (float) – Ratio of the cost of false negative compared to false positives, as used in the f-measure computation. Defaults to 0.5, where the costs are equal.
truncate (int, optional) – If specified, then only show the specified number of values. Any sorting (e.g., sort_by_count) will be performed before truncation. Defaults to None
sort_by_count (bool, optional) – Whether to sort the outputs on number of occurrences of that tag in the gold data, defaults to False

Returns

A tabulated recall, precision and f-measure string

Return type

str

f_measure(gold, alpha=0.5)[source]¶

Compute the f-measure for each tag from gold or from running tag on the tokenized sentences from gold. Then, return the dictionary with mappings from tag to f-measure. The f-measure is the harmonic mean of the precision and recall, weighted by alpha. In particular, given the precision p and recall r defined by:

p = true positive / (true positive + false negative)
r = true positive / (true positive + false positive)

The f-measure is:

1/(alpha/p + (1-alpha)/r)

With alpha = 0.5, this reduces to:

2pr / (p + r)

Parameters

gold (list(list(tuple(str, str)))) – The list of tagged sentences to score the tagger on.
alpha (float) – Ratio of the cost of false negative compared to false positives. Defaults to 0.5, where the costs are equal.

Returns

A mapping from tags to precision

Return type

Dict[str, float]

precision(gold)[source]¶

Compute the precision for each tag from gold or from running tag on the tokenized sentences from gold. Then, return the dictionary with mappings from tag to precision. The precision is defined as:

p = true positive / (true positive + false negative)

Parameters: gold (list(list(tuple(str, str)))) – The list of tagged sentences to score the tagger on.
Returns: A mapping from tags to precision
Return type: Dict[str, float]

recall(gold) → Dict[str, float][source]¶

Compute the recall for each tag from gold or from running tag on the tokenized sentences from gold. Then, return the dictionary with mappings from tag to recall. The recall is defined as:

r = true positive / (true positive + false positive)

Parameters: gold (list(list(tuple(str, str)))) – The list of tagged sentences to score the tagger on.
Returns: A mapping from tags to recall
Return type: Dict[str, float]

tag_sents(sentences)[source]¶

Apply self.tag() to each element of sentences. I.e.:

return [self.tag(sent) for sent in sentences]

NLTK

Documentation

nltk.tag.PerceptronTagger¶