From 173b1551afe3e5468fb76431447b169eb222e9a2 Mon Sep 17 00:00:00 2001 From: ines Date: Tue, 7 Nov 2017 01:22:30 +0100 Subject: [PATCH] Update examples --- examples/deep_learning_keras.py | 30 +++++++++++-------- .../entity_relations.py | 2 +- .../information_extraction/parse_subtrees.py | 2 +- .../information_extraction/phrase_matcher.py | 2 +- examples/pipeline/custom_attr_methods.py | 2 +- .../custom_component_countries_api.py | 2 +- .../pipeline/custom_component_entities.py | 2 +- examples/pipeline/multi_processing.py | 2 +- examples/training/train_intent_parser.py | 2 +- examples/training/train_ner.py | 2 +- examples/training/train_new_entity_type.py | 2 +- examples/training/train_parser.py | 2 +- examples/training/train_tagger.py | 2 +- examples/training/train_textcat.py | 2 +- examples/vectors_fast_text.py | 2 +- website/usage/examples.jade | 23 +++++++------- 16 files changed, 42 insertions(+), 39 deletions(-) diff --git a/examples/deep_learning_keras.py b/examples/deep_learning_keras.py index ee3bba006..45faf0d98 100644 --- a/examples/deep_learning_keras.py +++ b/examples/deep_learning_keras.py @@ -1,18 +1,24 @@ -import plac -import collections -import random +""" +This example shows how to use an LSTM sentiment classification model trained using Keras in spaCy. spaCy splits the document into sentences, and each sentence is classified using the LSTM. The scores for the sentences are then aggregated to give the document score. This kind of hierarchical model is quite difficult in "pure" Keras or Tensorflow, but it's very effective. The Keras example on this dataset performs quite poorly, because it cuts off the documents so that they're a fixed size. This hurts review accuracy a lot, because people often summarise their rating in the final sentence +Prerequisites: +spacy download en_vectors_web_lg +pip install keras==2.0.9 + +Compatible with: spaCy v2.0.0+ +""" + +import plac +import random import pathlib import cytoolz import numpy from keras.models import Sequential, model_from_json -from keras.layers import LSTM, Dense, Embedding, Dropout, Bidirectional +from keras.layers import LSTM, Dense, Embedding, Bidirectional from keras.layers import TimeDistributed from keras.optimizers import Adam -from spacy.compat import pickle - import thinc.extra.datasets - +from spacy.compat import pickle import spacy @@ -84,8 +90,8 @@ def get_features(docs, max_length): def train(train_texts, train_labels, dev_texts, dev_labels, - lstm_shape, lstm_settings, lstm_optimizer, batch_size=100, nb_epoch=5, - by_sentence=True): + lstm_shape, lstm_settings, lstm_optimizer, batch_size=100, + nb_epoch=5, by_sentence=True): print("Loading spaCy") nlp = spacy.load('en_vectors_web_lg') nlp.add_pipe(nlp.create_pipe('sentencizer')) @@ -97,7 +103,7 @@ def train(train_texts, train_labels, dev_texts, dev_labels, if by_sentence: train_docs, train_labels = get_labelled_sentences(train_docs, train_labels) dev_docs, dev_labels = get_labelled_sentences(dev_docs, dev_labels) - + train_X = get_features(train_docs, lstm_shape['max_length']) dev_X = get_features(dev_docs, lstm_shape['max_length']) model.fit(train_X, train_labels, validation_data=(dev_X, dev_labels), @@ -138,12 +144,12 @@ def evaluate(model_dir, texts, labels, max_length=100): ''' return [nlp.tagger, nlp.parser, SentimentAnalyser.load(model_dir, nlp, max_length=max_length)] - + nlp = spacy.load('en') nlp.pipeline = create_pipeline(nlp) correct = 0 - i = 0 + i = 0 for doc in nlp.pipe(texts, batch_size=1000, n_threads=4): correct += bool(doc.sentiment >= 0.5) == bool(labels[i]) i += 1 diff --git a/examples/information_extraction/entity_relations.py b/examples/information_extraction/entity_relations.py index 816481c89..ef920ab00 100644 --- a/examples/information_extraction/entity_relations.py +++ b/examples/information_extraction/entity_relations.py @@ -6,7 +6,7 @@ money and currency values (entities labelled as MONEY) and then check the dependency tree to find the noun phrase they are referring to – for example: $9.4 million --> Net income. -Compatible with: spaCy 2.0.0a18+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/information_extraction/parse_subtrees.py b/examples/information_extraction/parse_subtrees.py index 5576735a6..ade4627de 100644 --- a/examples/information_extraction/parse_subtrees.py +++ b/examples/information_extraction/parse_subtrees.py @@ -16,7 +16,7 @@ show you how computers understand [language] I'm assuming that we can use the token.head to build these groups." -Compatible with: spaCy 2.0.0a18+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/information_extraction/phrase_matcher.py b/examples/information_extraction/phrase_matcher.py index d394f2606..a7feea264 100644 --- a/examples/information_extraction/phrase_matcher.py +++ b/examples/information_extraction/phrase_matcher.py @@ -34,7 +34,7 @@ formatted in jsonl as a sequence of entries like this: {"text":"Appalachia"} {"text":"Argentina"} -Compatible with: spaCy 2.0.0a17+ +Compatible with: spaCy v2.0.0+ """ from __future__ import print_function, unicode_literals, division diff --git a/examples/pipeline/custom_attr_methods.py b/examples/pipeline/custom_attr_methods.py index 0d123a02c..c5387aae2 100644 --- a/examples/pipeline/custom_attr_methods.py +++ b/examples/pipeline/custom_attr_methods.py @@ -7,7 +7,7 @@ they're called on is passed in as the first argument. * Custom pipeline components: https://alpha.spacy.io//usage/processing-pipelines#custom-components -Compatible with: spaCy 2.0.0a17+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/pipeline/custom_component_countries_api.py b/examples/pipeline/custom_component_countries_api.py index 3b06dba20..eeb8f9f5c 100644 --- a/examples/pipeline/custom_component_countries_api.py +++ b/examples/pipeline/custom_component_countries_api.py @@ -8,7 +8,7 @@ coordinates. Can be extended with more details from the API. * REST Countries API: https://restcountries.eu (Mozilla Public License MPL 2.0) * Custom pipeline components: https://alpha.spacy.io//usage/processing-pipelines#custom-components -Compatible with: spaCy 2.0.0a17+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/pipeline/custom_component_entities.py b/examples/pipeline/custom_component_entities.py index 52c7f6c8d..248356b1f 100644 --- a/examples/pipeline/custom_component_entities.py +++ b/examples/pipeline/custom_component_entities.py @@ -8,7 +8,7 @@ respectively. * Custom pipeline components: https://alpha.spacy.io//usage/processing-pipelines#custom-components -Compatible with: spaCy 2.0.0a17+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/pipeline/multi_processing.py b/examples/pipeline/multi_processing.py index d136f9950..bf5b8d516 100644 --- a/examples/pipeline/multi_processing.py +++ b/examples/pipeline/multi_processing.py @@ -6,7 +6,7 @@ each "sentence" on a newline, and spaces between tokens. Data is loaded from the IMDB movie reviews dataset and will be loaded automatically via Thinc's built-in dataset loader. -Compatible with: spaCy 2.0.0a18+ +Compatible with: spaCy v2.0.0+ """ from __future__ import print_function, unicode_literals from toolz import partition_all diff --git a/examples/training/train_intent_parser.py b/examples/training/train_intent_parser.py index 6d31bd777..6d804c5d9 100644 --- a/examples/training/train_intent_parser.py +++ b/examples/training/train_intent_parser.py @@ -15,7 +15,7 @@ following types of relations: ROOT, PLACE, QUALITY, ATTRIBUTE, TIME, LOCATION. ('hotel', 'PLACE', 'show') --> show PLACE hotel ('berlin', 'LOCATION', 'hotel') --> hotel with LOCATION berlin -Compatible with: spaCy 2.0.0a20+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/training/train_ner.py b/examples/training/train_ner.py index e67b1522d..5af684022 100644 --- a/examples/training/train_ner.py +++ b/examples/training/train_ner.py @@ -7,7 +7,7 @@ For more details, see the documentation: * Training: https://alpha.spacy.io/usage/training * NER: https://alpha.spacy.io/usage/linguistic-features#named-entities -Compatible with: spaCy 2.0.0a20+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/training/train_new_entity_type.py b/examples/training/train_new_entity_type.py index 6970a6921..9a150461a 100644 --- a/examples/training/train_new_entity_type.py +++ b/examples/training/train_new_entity_type.py @@ -23,7 +23,7 @@ For more details, see the documentation: * Training: https://alpha.spacy.io/usage/training * NER: https://alpha.spacy.io/usage/linguistic-features#named-entities -Compatible with: spaCy 2.0.0a20+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/training/train_parser.py b/examples/training/train_parser.py index 662dfffa4..35637e275 100644 --- a/examples/training/train_parser.py +++ b/examples/training/train_parser.py @@ -5,7 +5,7 @@ model or a blank model. For more details, see the documentation: * Training: https://alpha.spacy.io/usage/training * Dependency Parse: https://alpha.spacy.io/usage/linguistic-features#dependency-parse -Compatible with: spaCy 2.0.0a20+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/training/train_tagger.py b/examples/training/train_tagger.py index a97491c63..a50a5738d 100644 --- a/examples/training/train_tagger.py +++ b/examples/training/train_tagger.py @@ -8,7 +8,7 @@ the documentation: * Training: https://alpha.spacy.io/usage/training * POS Tagging: https://alpha.spacy.io/usage/linguistic-features#pos-tagging -Compatible with: spaCy 2.0.0a20+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function diff --git a/examples/training/train_textcat.py b/examples/training/train_textcat.py index 6405c0f99..367832a00 100644 --- a/examples/training/train_textcat.py +++ b/examples/training/train_textcat.py @@ -8,7 +8,7 @@ see the documentation: * Training: https://alpha.spacy.io/usage/training * Text classification: https://alpha.spacy.io/usage/text-classification -Compatible with: spaCy 2.0.0a20+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals, print_function import plac diff --git a/examples/vectors_fast_text.py b/examples/vectors_fast_text.py index 5e411259c..03999f24a 100644 --- a/examples/vectors_fast_text.py +++ b/examples/vectors_fast_text.py @@ -2,7 +2,7 @@ # coding: utf8 """Load vectors for a language trained using fastText https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md -Compatible with: spaCy v2.0.0a17+ +Compatible with: spaCy v2.0.0+ """ from __future__ import unicode_literals import plac diff --git a/website/usage/examples.jade b/website/usage/examples.jade index 9ad800954..8eae67cdf 100644 --- a/website/usage/examples.jade +++ b/website/usage/examples.jade @@ -165,18 +165,15 @@ include ../_includes/_mixins +h(3, "keras") Text classification with Keras p - | In this example, we're using spaCy to pre-process text for use with - | a #[+a("https://keras.io") Keras] text classification model. + | This example shows how to use a #[+a("https://keras.io") Keras] + | LSTM sentiment classification model in spaCy. spaCy splits + | the document into sentences, and each sentence is classified using + | the LSTM. The scores for the sentences are then aggregated to give + | the document score. This kind of hierarchical model is quite + | difficult in "pure" Keras or Tensorflow, but it's very effective. + | The Keras example on this dataset performs quite poorly, because it + | cuts off the documents so that they're a fixed size. This hurts + | review accuracy a lot, because people often summarise their rating + | in the final sentence. +github("spacy", "examples/deep_learning_keras.py") - - +h(3, "keras-parikh-entailment") A decomposable attention model for Natural Language Inference - - p - | This example contains an implementation of the entailment prediction - | model described by #[+a("https://arxiv.org/pdf/1606.01933.pdf") Parikh et al. (2016)]. - | The model is notable for its competitive performance with very few - | parameters, and was implemented using #[+a("https://keras.io") Keras] - | and spaCy. - - +github("spacy", "examples/keras_parikh_entailment/__main__.py", false, "examples/keras_parikh_entailment")