diff --git a/README.rst b/README.rst index eadf1f018..5633ef86c 100644 --- a/README.rst +++ b/README.rst @@ -5,7 +5,7 @@ spaCy is a library for advanced Natural Language Processing in Python and Cython It's built on the very latest research, and was designed from day one to be used in real products. spaCy comes with `pre-trained statistical models `_ and word -vectors, and currently supports tokenization for **20+ languages**. It features +vectors, and currently supports tokenization for **30+ languages**. It features the **fastest syntactic parser** in the world, convolutional **neural network models** for tagging, parsing and **named entity recognition** and easy **deep learning** integration. It's commercial open-source software, released under the MIT license. @@ -32,9 +32,9 @@ integration. It's commercial open-source software, released under the MIT licens :target: https://anaconda.org/conda-forge/spacy :alt: conda Version -.. image:: https://img.shields.io/badge/chat-join%20%E2%86%92-09a3d5.svg?style=flat-square&logo=gitter-white - :target: https://gitter.im/explosion/spaCy - :alt: spaCy on Gitter +.. image:: https://img.shields.io/badge/wheels-%E2%9C%93-4c1.svg?longCache=true&style=flat-square&logo=python&logoColor=white + :target: https://github.com/explosion/wheelwright/releases + :alt: Python wheels .. image:: https://img.shields.io/twitter/follow/spacy_io.svg?style=social&label=Follow :target: https://twitter.com/spacy_io @@ -113,7 +113,7 @@ the `documentation `_. ==================== === **Operating system** macOS / OS X, Linux, Windows (Cygwin, MinGW, Visual Studio) **Python version** CPython 2.7, 3.4+. Only 64 bit. -**Package managers** `pip`_ (source packages only), `conda`_ (via ``conda-forge``) +**Package managers** `pip`_, `conda`_ (via ``conda-forge``) ==================== === .. _pip: https://pypi.python.org/pypi/spacy @@ -122,7 +122,8 @@ the `documentation `_. pip --- -Using pip, spaCy releases are currently only available as source packages. +Using pip, spaCy releases are available as source packages and binary wheels +(as of ``v2.0.13``). .. code:: bash diff --git a/spacy/lang/si/examples.py b/spacy/lang/si/examples.py index 68862d3cf..842dfdd7e 100644 --- a/spacy/lang/si/examples.py +++ b/spacy/lang/si/examples.py @@ -11,6 +11,7 @@ Example sentences to test spaCy and its language models. sentences = [ + "මෙය වාක්‍යයකි.", "ඔබ කවුද?", "ගූගල් සමාගම ඩොලර් මිලියන 500 කට එම ආයතනය මිලදී ගන්නා ලදී.", "කොළඹ ශ්‍රී ලංකාවේ ප්‍රධානතම නගරය යි.", diff --git a/website/_harp.json b/website/_harp.json index f866c554d..8867cf61c 100644 --- a/website/_harp.json +++ b/website/_harp.json @@ -14,7 +14,7 @@ "MODELS_REPO": "explosion/spacy-models", "SPACY_VERSION": "2.0", - "BINDER_VERSION": "2.0.12", + "BINDER_VERSION": "2.0.13", "SOCIAL": { "twitter": "spacy_io", diff --git a/website/api/cli.jade b/website/api/cli.jade index dcc1a0551..28c76c09c 100644 --- a/website/api/cli.jade +++ b/website/api/cli.jade @@ -346,6 +346,7 @@ p +row +cell #[code --verbose] + +tag-new("2.0.13") +cell flag +cell Show more detail message during training. diff --git a/website/api/doc.jade b/website/api/doc.jade index 574865fb3..7d304926c 100644 --- a/website/api/doc.jade +++ b/website/api/doc.jade @@ -581,7 +581,7 @@ p | web applications. +aside-code("Example"). - doc = nlp('Alice ate the pizza.') + doc = nlp(u'Alice ate the pizza.') trees = doc.print_tree() # {'modifiers': [ # {'modifiers': [], 'NE': 'PERSON', 'word': 'Alice', 'arc': 'nsubj', 'POS_coarse': 'PROPN', 'POS_fine': 'NNP', 'lemma': 'Alice'}, @@ -615,8 +615,8 @@ p | document. +aside-code("Example"). - tokens = nlp(u'Mr. Best flew to New York on Saturday morning.') - ents = list(tokens.ents) + doc = nlp(u'Mr. Best flew to New York on Saturday morning.') + ents = list(doc.ents) assert ents[0].label == 346 assert ents[0].label_ == 'PERSON' assert ents[0].text == 'Mr. Best' diff --git a/website/api/span.jade b/website/api/span.jade index 681664269..7be1ad4a4 100644 --- a/website/api/span.jade +++ b/website/api/span.jade @@ -349,6 +349,30 @@ p Retokenize the document, such that the span is merged into a single token. +cell #[code Token] +cell The newly merged token. ++h(2, "ents") Span.ents + +tag property + +tag-model("NER") + +p + | Iterate over the entities in the span. Yields named-entity + | #[code Span] objects, if the entity recognizer has been applied to the + | parent document. + ++aside-code("Example"). + doc = nlp(u'Mr. Best flew to New York on Saturday morning.') + span = doc[0:6] + ents = list(span.ents) + assert ents[0].label == 346 + assert ents[0].label_ == 'PERSON' + assert ents[0].text == 'Mr. Best' + ++table(["Name", "Type", "Description"]) + +row("foot") + +cell yields + +cell #[code Span] + +cell Entities in the document. + + +h(2, "as_doc") Span.as_doc p diff --git a/website/models/_data.json b/website/models/_data.json index 4eda2564a..d1f3862f5 100644 --- a/website/models/_data.json +++ b/website/models/_data.json @@ -27,17 +27,6 @@ } }, - "comparison": { - "title": "Model Comparison", - "teaser": "Compare spaCy's statistical models and their accuracy.", - "tag": "experimental", - "compare_models": true, - "default_models": { - "model1": "en_core_web_sm", - "model2": "en_core_web_lg" - } - }, - "MODELS": { "en": ["en_core_web_sm", "en_core_web_md", "en_core_web_lg", "en_vectors_web_lg"], "de": ["de_core_news_sm"], @@ -122,6 +111,8 @@ "fa": "Persian", "ur": "Urdu", "tt": "Tatar", + "te": "Telugu", + "si": "Sinhala", "ga": "Irish", "bn": "Bengali", "hi": "Hindi", diff --git a/website/usage/_install/_instructions.jade b/website/usage/_install/_instructions.jade index fb9247bb6..12d175723 100644 --- a/website/usage/_install/_instructions.jade +++ b/website/usage/_install/_instructions.jade @@ -3,7 +3,9 @@ +h(3, "pip") pip +badge("https://img.shields.io/pypi/v/spacy.svg?style=flat-square", "https://pypi.python.org/pypi/spacy") -p Using pip, spaCy releases are currently only available as source packages. +p + | Using pip, spaCy releases are available as source packages and binary + | wheels (as of #[code v2.0.13]). +code(false, "bash"). pip install -U spacy