spaCy/website/docs/usage/lightning-tour.jade

//- 💫 DOCS > USAGE > LIGHTNING TOUR

include ../../_includes/_mixins

p
    |  The following examples and code snippets give you an overview of spaCy's
    |  functionality and its usage.

+h(2, "models") Install and load models

+code(false, "bash").
    python -m spacy download en

+code.
    import spacy
    nlp = spacy.load('en')

+h(2, "examples-resources") Load resources and process text

+code.
    import spacy
    en_nlp = spacy.load('en')
    de_nlp = spacy.load('de')
    en_doc = en_nlp(u'Hello, world. Here are two sentences.')
    de_doc = de_nlp(u'ich bin ein Berliner.')

+h(2, "multi-threaded") Multi-threaded generator

+code.
    texts = [u'One document.', u'...', u'Lots of documents']
    # .pipe streams input, and produces streaming output
    iter_texts = (texts[i % 3] for i in xrange(100000000))
    for i, doc in enumerate(nlp.pipe(iter_texts, batch_size=50, n_threads=4)):
        assert doc.is_parsed
        if i == 100:
            break

+h(2, "examples-tokens-sentences") Get tokens and sentences

+code.
    token = doc[0]
    sentence = next(doc.sents)
    assert token is sentence[0]
    assert sentence.text == 'Hello, world.'

+h(2, "examples-integer-ids") Use integer IDs for any string

+code.
    hello_id = nlp.vocab.strings['Hello']
    hello_str = nlp.vocab.strings[hello_id]

    assert token.orth  == hello_id  == 3125
    assert token.orth_ == hello_str == 'Hello'

+h(2, "examples-string-views-flags") Get and set string views and flags

+code.
    assert token.shape_ == 'Xxxxx'
    for lexeme in nlp.vocab:
        if lexeme.is_alpha:
            lexeme.shape_ = 'W'
        elif lexeme.is_digit:
            lexeme.shape_ = 'D'
        elif lexeme.is_punct:
            lexeme.shape_ = 'P'
        else:
            lexeme.shape_ = 'M'
    assert token.shape_ == 'W'

+h(2, "examples-numpy-arrays") Export to numpy arrays

+code.
    from spacy.attrs import ORTH, LIKE_URL, IS_OOV

    attr_ids = [ORTH, LIKE_URL, IS_OOV]
    doc_array = doc.to_array(attr_ids)
    assert doc_array.shape == (len(doc), len(attr_ids))
    assert doc[0].orth == doc_array[0, 0]
    assert doc[1].orth == doc_array[1, 0]
    assert doc[0].like_url == doc_array[0, 1]
    assert list(doc_array[:, 1]) == [t.like_url for t in doc]

+h(2, "examples-word-vectors") Word vectors

+code.
    doc = nlp(u"Apples and oranges are similar. Boots and hippos aren't.")

    apples = doc[0]
    oranges = doc[2]
    boots = doc[6]
    hippos = doc[8]

    assert apples.similarity(oranges) > boots.similarity(hippos)

+h(2, "examples-pos-tags") Part-of-speech tags

+code.
    from spacy.parts_of_speech import ADV

    def is_adverb(token):
        return token.pos == spacy.parts_of_speech.ADV

    # These are data-specific, so no constants are provided. You have to look
    # up the IDs from the StringStore.
    NNS = nlp.vocab.strings['NNS']
    NNPS = nlp.vocab.strings['NNPS']
    def is_plural_noun(token):
        return token.tag == NNS or token.tag == NNPS

    def print_coarse_pos(token):
        print(token.pos_)

    def print_fine_pos(token):
        print(token.tag_)

+h(2, "examples-dependencies") Syntactic dependencies

+code.
    def dependency_labels_to_root(token):
        '''Walk up the syntactic tree, collecting the arc labels.'''
        dep_labels = []
        while token.head is not token:
            dep_labels.append(token.dep)
            token = token.head
        return dep_labels

+h(2, "examples-entities") Named entities

+code.
    def iter_products(docs):
        for doc in docs:
            for ent in doc.ents:
                if ent.label_ == 'PRODUCT':
                    yield ent

    def word_is_in_entity(word):
        return word.ent_type != 0

    def count_parent_verb_by_person(docs):
        counts = defaultdict(lambda: defaultdict(int))
        for doc in docs:
            for ent in doc.ents:
                if ent.label_ == 'PERSON' and ent.root.head.pos == VERB:
                    counts[ent.orth_][ent.root.head.lemma_] += 1
        return counts

+h(2, "examples-inline") Calculate inline mark-up on original string

+code.
    def put_spans_around_tokens(doc, get_classes):
        """Given some function to compute class names, put each token in a
        span element, with the appropriate classes computed. All whitespace is
        preserved, outside of the spans. (Of course, HTML won't display more than
        one whitespace character it – but the point is, no information is lost
        and you can calculate what you need, e.g. <br />, <p> etc.)
        """
        output = []
        html = '<span class="{classes}">{word}</span>{space}'
        for token in doc:
            if token.is_space:
                output.append(token.text)
            else:
                classes = ' '.join(get_classes(token))
                output.append(html.format(classes=classes, word=token.text, space=token.whitespace_))
        string = ''.join(output)
        string = string.replace('\n', '')
        string = string.replace('\t', '    ')
        return string

+h(2, "examples-binary") Efficient binary serialization

+code.
    import spacy
    from spacy.tokens.doc import Doc

    byte_string = doc.to_bytes()
    open('moby_dick.bin', 'wb').write(byte_string)

    nlp = spacy.load('en')
    for byte_string in Doc.read_bytes(open('moby_dick.bin', 'rb')):
       doc = Doc(nlp.vocab)
       doc.from_bytes(byte_string)