diff --git a/spacy/util.py b/spacy/util.py index 911970831..429d9bae5 100644 --- a/spacy/util.py +++ b/spacy/util.py @@ -181,10 +181,9 @@ def is_package(name): name (unicode): Name of package. RETURNS (bool): True if installed package, False if not. """ - name = name.lower() # compare package name against lowercase name packages = pkg_resources.working_set.by_key.keys() for package in packages: - if package.lower().replace('-', '_') == name: + if package.replace('-', '_') == name: return True return False @@ -195,7 +194,6 @@ def get_package_path(name): name (unicode): Package name. RETURNS (Path): Path to installed package. """ - name = name.lower() # use lowercase version to be safe # Here we're importing the module just to find it. This is worryingly # indirect, but it's otherwise very difficult to find the package. pkg = importlib.import_module(name) diff --git a/website/usage/spacy-101.jade b/website/usage/spacy-101.jade deleted file mode 100644 index a57137674..000000000 --- a/website/usage/spacy-101.jade +++ /dev/null @@ -1,300 +0,0 @@ -//- 💫 DOCS > USAGE > SPACY 101 - -include ../_includes/_mixins - -p - | Whether you're new to spaCy, or just want to brush up on some - | NLP basics and implementation details – this page should have you covered. - | Each section will explain one of spaCy's features in simple terms and - | with examples or illustrations. Some sections will also reappear across - | the usage guides as a quick introduction. - -+aside("Help us improve the docs") - | Did you spot a mistake or come across explanations that - | are unclear? We always appreciate improvement - | #[+a(gh("spaCy") + "/issues") suggestions] or - | #[+a(gh("spaCy") + "/pulls") pull requests]. You can find a "Suggest - | edits" link at the bottom of each page that points you to the source. - -+h(2, "whats-spacy") What's spaCy? - -+grid.o-no-block - +grid-col("half") - p - | spaCy is a #[strong free, open-source library] for advanced - | #[strong Natural Language Processing] (NLP) in Python. - - p - | If you're working with a lot of text, you'll eventually want to - | know more about it. For example, what's it about? What do the - | words mean in context? Who is doing what to whom? What companies - | and products are mentioned? Which texts are similar to each other? - - p - | spaCy is designed specifically for #[strong production use] and - | helps you build applications that process and "understand" - | large volumes of text. It can be used to build - | #[strong information extraction] or - | #[strong natural language understanding] systems, or to - | pre-process text for #[strong deep learning]. - - +table-of-contents - +item #[+a("#features") Features] - +item #[+a("#annotations") Linguistic annotations] - +item #[+a("#annotations-token") Tokenization] - +item #[+a("#annotations-pos-deps") POS tags and dependencies] - +item #[+a("#annotations-ner") Named entities] - +item #[+a("#vectors-similarity") Word vectors and similarity] - +item #[+a("#pipelines") Pipelines] - +item #[+a("#vocab") Vocab, hashes and lexemes] - +item #[+a("#serialization") Serialization] - +item #[+a("#training") Training] - +item #[+a("#language-data") Language data] - +item #[+a("#lightning-tour") Lightning tour] - +item #[+a("#architecture") Architecture] - +item #[+a("#community") Community & FAQ] - -+h(3, "what-spacy-isnt") What spaCy isn't - -+list - +item #[strong spaCy is not a platform or "an API"]. - | Unlike a platform, spaCy does not provide a software as a service, or - | a web application. It's an open-source library designed to help you - | build NLP applications, not a consumable service. - +item #[strong spaCy is not an out-of-the-box chat bot engine]. - | While spaCy can be used to power conversational applications, it's - | not designed specifically for chat bots, and only provides the - | underlying text processing capabilities. - +item #[strong spaCy is not research software]. - | It's built on the latest research, but it's designed to get - | things done. This leads to fairly different design decisions than - | #[+a("https://github./nltk/nltk") NLTK] - | or #[+a("https://stanfordnlp.github.io/CoreNLP/") CoreNLP], which were - | created as platforms for teaching and research. The main difference - | is that spaCy is integrated and opinionated. spaCy tries to avoid asking - | the user to choose between multiple algorithms that deliver equivalent - | functionality. Keeping the menu small lets spaCy deliver generally better - | performance and developer experience. - +item #[strong spaCy is not a company]. - | It's an open-source library. Our company publishing spaCy and other - | software is called #[+a(COMPANY_URL, true) Explosion AI]. - -+section("features") - +h(2, "features") Features - - p - | In the documentation, you'll come across mentions of spaCy's - | features and capabilities. Some of them refer to linguistic concepts, - | while others are related to more general machine learning - | functionality. - - +aside - | If one of spaCy's functionalities #[strong needs a model], it means - | that you need to have one of the available - | #[+a("/models") statistical models] installed. Models are used - | to #[strong predict] linguistic annotations – for example, if a word - | is a verb or a noun. - - +table(["Name", "Description", "Needs model"]) - +row - +cell #[strong Tokenization] - +cell Segmenting text into words, punctuations marks etc. - +cell #[+procon("con")] - - +row - +cell #[strong Part-of-speech] (POS) #[strong Tagging] - +cell Assigning word types to tokens, like verb or noun. - +cell #[+procon("pro")] - - +row - +cell #[strong Dependency Parsing] - +cell - | Assigning syntactic dependency labels, describing the - | relations between individual tokens, like subject or object. - +cell #[+procon("pro")] - - +row - +cell #[strong Lemmatization] - +cell - | Assigning the base forms of words. For example, the lemma of - | "was" is "be", and the lemma of "rats" is "rat". - +cell #[+procon("pro")] - - +row - +cell #[strong Sentence Boundary Detection] (SBD) - +cell Finding and segmenting individual sentences. - +cell #[+procon("pro")] - - +row - +cell #[strong Named Entity Recongition] (NER) - +cell - | Labelling named "real-world" objects, like persons, companies - | or locations. - +cell #[+procon("pro")] - - +row - +cell #[strong Similarity] - +cell - | Comparing words, text spans and documents and how similar - | they are to each other. - +cell #[+procon("pro")] - - +row - +cell #[strong Text Classification] - +cell - | Assigning categories or labels to a whole document, or parts - | of a document. - +cell #[+procon("pro")] - - +row - +cell #[strong Rule-based Matching] - +cell - | Finding sequences of tokens based on their texts and - | linguistic annotations, similar to regular expressions. - +cell #[+procon("con")] - - +row - +cell #[strong Training] - +cell Updating and improving a statistical model's predictions. - +cell #[+procon("neutral")] - - +row - +cell #[strong Serialization] - +cell Saving objects to files or byte strings. - +cell #[+procon("neutral")] - - +h(2, "annotations") Linguistic annotations - - p - | spaCy provides a variety of linguistic annotations to give you - | #[strong insights into a text's grammatical structure]. This - | includes the word types, like the parts of speech, and how the words - | are related to each other. For example, if you're analysing text, it - | makes a huge difference whether a noun is the subject of a sentence, - | or the object – or whether "google" is used as a verb, or refers to - | the website or company in a specific context. - - p - | Once you've downloaded and installed a #[+a("/usage/models") model], - | you can load it via #[+api("spacy#load") #[code spacy.load()]]. This will - | return a #[code Language] object contaning all components and data needed - | to process text. We usually call it #[code nlp]. Calling the #[code nlp] - | object on a string of text will return a processed #[code Doc]: - - +code. - import spacy - - nlp = spacy.load('en') - doc = nlp(u'Apple is looking at buying U.K. startup for $1 billion') - - p - | Even though a #[code Doc] is processed – e.g. split into individual words - | and annotated – it still holds #[strong all information of the original text], - | like whitespace characters. You can always get the offset of a token into the - | original string, or reconstruct the original by joining the tokens and their - | trailing whitespace. This way, you'll never lose any information - | when processing text with spaCy. - - +h(3, "annotations-token") Tokenization - - include _spacy-101/_tokenization - - +infobox - | To learn more about how spaCy's tokenization rules work in detail, - | how to #[strong customise and replace] the default tokenizer and how to - | #[strong add language-specific data], see the usage guides on - | #[+a("/usage/adding-languages") adding languages] and - | #[+a("/usage/linguistic-features#tokenization") customising the tokenizer]. - - +h(3, "annotations-pos-deps") Part-of-speech tags and dependencies - +tag-model("dependency parse") - - include _spacy-101/_pos-deps - - +infobox - | To learn more about #[strong part-of-speech tagging] and rule-based - | morphology, and how to #[strong navigate and use the parse tree] - | effectively, see the usage guides on - | #[+a("/usage/linguistic-features#pos-tagging") part-of-speech tagging] and - | #[+a("/usage/linguistic-features#dependency-parse") using the dependency parse]. - - +h(3, "annotations-ner") Named Entities - +tag-model("named entities") - - include _spacy-101/_named-entities - - +infobox - | To learn more about entity recognition in spaCy, how to - | #[strong add your own entities] to a document and how to - | #[strong train and update] the entity predictions of a model, see the - | usage guides on - | #[+a("/usage/linguistic-features#named-entities") named entity recognition] and - | #[+a("/usage/training#ner") training the named entity recognizer]. - - +h(2, "vectors-similarity") Word vectors and similarity - +tag-model("vectors") - - include _spacy-101/_similarity - - include _spacy-101/_word-vectors - - +infobox - | To learn more about word vectors, how to #[strong customise them] and - | how to load #[strong your own vectors] into spaCy, see the usage - | guide on - | #[+a("/usage/word-vectors-similarities") using word vectors and semantic similarities]. - - +h(2, "pipelines") Pipelines - - include _spacy-101/_pipelines - - +infobox - | To learn more about #[strong how processing pipelines work] in detail, - | how to enable and disable their components, and how to - | #[strong create your own], see the usage guide on - | #[+a("/usage/processing-pipelines") language processing pipelines]. - - +h(2, "vocab") Vocab, hashes and lexemes - - include _spacy-101/_vocab - - +h(2, "serialization") Serialization - - include _spacy-101/_serialization - - +infobox - | To learn more about how to #[strong save and load your own models], - | see the usage guide on - | #[+a("/usage/training#saving-loading") saving and loading]. - - +h(2, "training") Training - - include _spacy-101/_training - - +infobox - | To learn more about #[strong training and updating] models, how to create - | training data and how to improve spaCy's named entity recognition models, - | see the usage guides on #[+a("/usage/training") training]. - - +h(2, "language-data") Language data - - include _spacy-101/_language-data - - +infobox - | To learn more about the individual components of the language data and - | how to #[strong add a new language] to spaCy in preparation for training - | a language model, see the usage guide on - | #[+a("/usage/adding-languages") adding languages]. - - -+section("lightning-tour") - +h(2, "lightning-tour") Lightning tour - include _spacy-101/_lightning-tour - -+section("architecture") - +h(2, "architecture") Architecture - include _spacy-101/_architecture - -+section("community-faq") - +h(2, "community") Community & FAQ - include _spacy-101/_community-faq