mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
Fix code branch for v2.x site [ci skip]
This commit is contained in:
Ines Montani
parent
6daf2381fa
commit
c70e6ee72d
|
|
@ -250,7 +250,7 @@ POS tag set.
|
|||
<Infobox title="Annotation schemes for other models">
|
||||
|
||||
For the label schemes used by the other models, see the respective `tag_map.py`
|
||||
in [`spacy/lang`](https://github.com/explosion/spaCy/tree/master/spacy/lang).
|
||||
in [`spacy/lang`](https://github.com/explosion/spaCy/tree/v2.x/spacy/lang).
|
||||
|
||||
</Infobox>
|
||||
|
||||
|
|
@ -564,7 +564,7 @@ Here's an example of dependencies, part-of-speech tags and names entities, taken
|
|||
from the English Wall Street Journal portion of the Penn Treebank:
|
||||
|
||||
```json
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/training-data.json
|
||||
https://github.com/explosion/spaCy/tree/v2.x/examples/training/training-data.json
|
||||
```
|
||||
|
||||
### Lexical data for vocabulary {#vocab-jsonl new="2"}
|
||||
|
|
@ -619,5 +619,5 @@ data.
|
|||
Here's an example of the 20 most frequent lexemes in the English training data:
|
||||
|
||||
```json
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/vocab-data.jsonl
|
||||
https://github.com/explosion/spaCy/tree/v2.x/examples/training/vocab-data.jsonl
|
||||
```
|
||||
|
|
|
|||
|
|
@ -166,13 +166,13 @@ All output files generated by this command are compatible with
|
|||
|
||||
### Converter options
|
||||
|
||||
| ID | Description |
|
||||
| ------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `auto` | Automatically pick converter based on file extension and file content (default). |
|
||||
| `conll`, `conllu`, `conllubio` | Universal Dependencies `.conllu` or `.conll` format. |
|
||||
| `ner` | NER with IOB/IOB2 tags, one token per line with columns separated by whitespace. The first column is the token and the final column is the IOB tag. Sentences are separated by blank lines and documents are separated by the line `-DOCSTART- -X- O O`. Supports CoNLL 2003 NER format. See [sample data](https://github.com/explosion/spaCy/tree/master/examples/training/ner_example_data). |
|
||||
| `iob` | NER with IOB/IOB2 tags, one sentence per line with tokens separated by whitespace and annotation separated by `|`, either `word|B-ENT` or `word|POS|B-ENT`. See [sample data](https://github.com/explosion/spaCy/tree/master/examples/training/ner_example_data). |
|
||||
| `jsonl` | NER data formatted as JSONL with one dict per line and a `"text"` and `"spans"` key. This is also the format exported by the [Prodigy](https://prodi.gy) annotation tool. See [sample data](https://raw.githubusercontent.com/explosion/projects/master/ner-fashion-brands/fashion_brands_training.jsonl). |
|
||||
| ID | Description |
|
||||
| ------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `auto` | Automatically pick converter based on file extension and file content (default). |
|
||||
| `conll`, `conllu`, `conllubio` | Universal Dependencies `.conllu` or `.conll` format. |
|
||||
| `ner` | NER with IOB/IOB2 tags, one token per line with columns separated by whitespace. The first column is the token and the final column is the IOB tag. Sentences are separated by blank lines and documents are separated by the line `-DOCSTART- -X- O O`. Supports CoNLL 2003 NER format. See [sample data](https://github.com/explosion/spaCy/tree/v2.x/examples/training/ner_example_data). |
|
||||
| `iob` | NER with IOB/IOB2 tags, one sentence per line with tokens separated by whitespace and annotation separated by `|`, either `word|B-ENT` or `word|POS|B-ENT`. See [sample data](https://github.com/explosion/spaCy/tree/v2.x/examples/training/ner_example_data). |
|
||||
| `jsonl` | NER data formatted as JSONL with one dict per line and a `"text"` and `"spans"` key. This is also the format exported by the [Prodigy](https://prodi.gy) annotation tool. See [sample data](https://raw.githubusercontent.com/explosion/projects/master/ner-fashion-brands/fashion_brands_training.jsonl). |
|
||||
|
||||
## Debug data {#debug-data new="2.2"}
|
||||
|
||||
|
|
@ -473,7 +473,7 @@ $ python -m spacy pretrain [texts_loc] [vectors_model] [output_dir]
|
|||
| `--use-chars`, `-chr` <Tag variant="new">2.2.2</Tag> | flag | Whether to use character-based embedding. |
|
||||
| `--sa-depth`, `-sa` <Tag variant="new">2.2.2</Tag> | option | Depth of self-attention layers. |
|
||||
| `--embed-rows`, `-er` | option | Number of embedding rows. |
|
||||
| `--loss-func`, `-L` | option | Loss function to use for the objective. Either `"cosine"`, `"L2"` or `"characters"`. |
|
||||
| `--loss-func`, `-L` | option | Loss function to use for the objective. Either `"cosine"`, `"L2"` or `"characters"`. |
|
||||
| `--dropout`, `-d` | option | Dropout rate. |
|
||||
| `--batch-size`, `-bs` | option | Number of words per training batch. |
|
||||
| `--max-length`, `-xw` | option | Maximum words per example. Longer examples are discarded. |
|
||||
|
|
|
|||
|
|
@ -23,12 +23,12 @@ abruptly.
|
|||
With Cython there are four ways of declaring complex data types. Unfortunately
|
||||
we use all four in different places, as they all have different utility:
|
||||
|
||||
| Declaration | Description | Example |
|
||||
| --------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- |
|
||||
| `class` | A normal Python class. | [`Language`](/api/language) |
|
||||
| `cdef class` | A Python extension type. Differs from a normal Python class in that its attributes can be defined on the underlying struct. Can have C-level objects as attributes (notably structs and pointers), and can have methods which have C-level objects as arguments or return types. | [`Lexeme`](/api/cython-classes#lexeme) |
|
||||
| `cdef struct` | A struct is just a collection of variables, sort of like a named tuple, except the memory is contiguous. Structs can't have methods, only attributes. | [`LexemeC`](/api/cython-structs#lexemec) |
|
||||
| `cdef cppclass` | A C++ class. Like a struct, this can be allocated on the stack, but can have methods, a constructor and a destructor. Differs from `cdef class` in that it can be created and destroyed without acquiring the Python global interpreter lock. This style is the most obscure. | [`StateC`](https://github.com/explosion/spaCy/tree/master/spacy/syntax/_state.pxd) |
|
||||
| Declaration | Description | Example |
|
||||
| --------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- |
|
||||
| `class` | A normal Python class. | [`Language`](/api/language) |
|
||||
| `cdef class` | A Python extension type. Differs from a normal Python class in that its attributes can be defined on the underlying struct. Can have C-level objects as attributes (notably structs and pointers), and can have methods which have C-level objects as arguments or return types. | [`Lexeme`](/api/cython-classes#lexeme) |
|
||||
| `cdef struct` | A struct is just a collection of variables, sort of like a named tuple, except the memory is contiguous. Structs can't have methods, only attributes. | [`LexemeC`](/api/cython-structs#lexemec) |
|
||||
| `cdef cppclass` | A C++ class. Like a struct, this can be allocated on the stack, but can have methods, a constructor and a destructor. Differs from `cdef class` in that it can be created and destroyed without acquiring the Python global interpreter lock. This style is the most obscure. | [`StateC`](https://github.com/explosion/spaCy/tree/v2.x/spacy/syntax/_state.pxd) |
|
||||
|
||||
The most important classes in spaCy are defined as `cdef class` objects. The
|
||||
underlying data for these objects is usually gathered into a struct, which is
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@ Create a `GoldCorpus`. IF the input data is an iterable, each item should be a
|
|||
`(text, paragraphs)` tuple, where each paragraph is a tuple
|
||||
`(sentences, brackets)`, and each sentence is a tuple
|
||||
`(ids, words, tags, heads, ner)`. See the implementation of
|
||||
[`gold.read_json_file`](https://github.com/explosion/spaCy/tree/master/spacy/gold.pyx)
|
||||
[`gold.read_json_file`](https://github.com/explosion/spaCy/tree/v2.x/spacy/gold.pyx)
|
||||
for further details.
|
||||
|
||||
| Name | Type | Description |
|
||||
|
|
|
|||
|
|
@ -107,7 +107,7 @@ meta data as a dictionary instead, you can use the `meta` attribute on your
|
|||
|
||||
Get a description for a given POS tag, dependency label or entity type. For a
|
||||
list of available terms, see
|
||||
[`glossary.py`](https://github.com/explosion/spaCy/tree/master/spacy/glossary.py).
|
||||
[`glossary.py`](https://github.com/explosion/spaCy/tree/v2.x/spacy/glossary.py).
|
||||
|
||||
> #### Example
|
||||
>
|
||||
|
|
@ -279,7 +279,7 @@ to add custom labels and their colors automatically.
|
|||
## Utility functions {#util source="spacy/util.py"}
|
||||
|
||||
spaCy comes with a small collection of utility functions located in
|
||||
[`spacy/util.py`](https://github.com/explosion/spaCy/tree/master/spacy/util.py).
|
||||
[`spacy/util.py`](https://github.com/explosion/spaCy/tree/v2.x/spacy/util.py).
|
||||
Because utility functions are mostly intended for **internal use within spaCy**,
|
||||
their behavior may change with future releases. The functions documented on this
|
||||
page should be safe to use and we'll try to ensure backwards compatibility.
|
||||
|
|
@ -538,10 +538,10 @@ Compile a sequence of prefix rules into a regex object.
|
|||
> nlp.tokenizer.prefix_search = prefix_regex.search
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `entries` | tuple | The prefix rules, e.g. [`lang.punctuation.TOKENIZER_PREFIXES`](https://github.com/explosion/spaCy/tree/master/spacy/lang/punctuation.py). |
|
||||
| **RETURNS** | [regex](https://docs.python.org/3/library/re.html#re-objects) | The regex object. to be used for [`Tokenizer.prefix_search`](/api/tokenizer#attributes). |
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `entries` | tuple | The prefix rules, e.g. [`lang.punctuation.TOKENIZER_PREFIXES`](https://github.com/explosion/spaCy/tree/v2.x/spacy/lang/punctuation.py). |
|
||||
| **RETURNS** | [regex](https://docs.python.org/3/library/re.html#re-objects) | The regex object. to be used for [`Tokenizer.prefix_search`](/api/tokenizer#attributes). |
|
||||
|
||||
### util.compile_suffix_regex {#util.compile_suffix_regex tag="function"}
|
||||
|
||||
|
|
@ -555,10 +555,10 @@ Compile a sequence of suffix rules into a regex object.
|
|||
> nlp.tokenizer.suffix_search = suffix_regex.search
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `entries` | tuple | The suffix rules, e.g. [`lang.punctuation.TOKENIZER_SUFFIXES`](https://github.com/explosion/spaCy/tree/master/spacy/lang/punctuation.py). |
|
||||
| **RETURNS** | [regex](https://docs.python.org/3/library/re.html#re-objects) | The regex object. to be used for [`Tokenizer.suffix_search`](/api/tokenizer#attributes). |
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `entries` | tuple | The suffix rules, e.g. [`lang.punctuation.TOKENIZER_SUFFIXES`](https://github.com/explosion/spaCy/tree/v2.x/spacy/lang/punctuation.py). |
|
||||
| **RETURNS** | [regex](https://docs.python.org/3/library/re.html#re-objects) | The regex object. to be used for [`Tokenizer.suffix_search`](/api/tokenizer#attributes). |
|
||||
|
||||
### util.compile_infix_regex {#util.compile_infix_regex tag="function"}
|
||||
|
||||
|
|
@ -572,10 +572,10 @@ Compile a sequence of infix rules into a regex object.
|
|||
> nlp.tokenizer.infix_finditer = infix_regex.finditer
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `entries` | tuple | The infix rules, e.g. [`lang.punctuation.TOKENIZER_INFIXES`](https://github.com/explosion/spaCy/tree/master/spacy/lang/punctuation.py). |
|
||||
| **RETURNS** | [regex](https://docs.python.org/3/library/re.html#re-objects) | The regex object. to be used for [`Tokenizer.infix_finditer`](/api/tokenizer#attributes). |
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `entries` | tuple | The infix rules, e.g. [`lang.punctuation.TOKENIZER_INFIXES`](https://github.com/explosion/spaCy/tree/v2.x/spacy/lang/punctuation.py). |
|
||||
| **RETURNS** | [regex](https://docs.python.org/3/library/re.html#re-objects) | The regex object. to be used for [`Tokenizer.infix_finditer`](/api/tokenizer#attributes). |
|
||||
|
||||
### util.minibatch {#util.minibatch tag="function" new="2"}
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ Every language is different – and usually full of **exceptions and special
|
|||
cases**, especially amongst the most common words. Some of these exceptions are
|
||||
shared across languages, while others are **entirely specific** – usually so
|
||||
specific that they need to be hard-coded. The
|
||||
[`lang`](https://github.com/explosion/spaCy/tree/master/spacy/lang) module
|
||||
[`lang`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang) module
|
||||
contains all language-specific data, organized in simple Python files. This
|
||||
makes the data easy to update and extend.
|
||||
|
||||
|
|
@ -39,21 +39,21 @@ together all components and creating the `Language` subclass – for example,
|
|||
| **Lemmatizer**<br />[`spacy-lookups-data`][spacy-lookups-data] | Lemmatization rules or a lookup-based lemmatization table to assign base forms, for example "be" for "was". |
|
||||
|
||||
[stop_words.py]:
|
||||
https://github.com/explosion/spaCy/tree/master/spacy/lang/en/stop_words.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/spacy/lang/en/stop_words.py
|
||||
[tokenizer_exceptions.py]:
|
||||
https://github.com/explosion/spaCy/tree/master/spacy/lang/de/tokenizer_exceptions.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/spacy/lang/de/tokenizer_exceptions.py
|
||||
[norm_exceptions.py]:
|
||||
https://github.com/explosion/spaCy/tree/master/spacy/lang/norm_exceptions.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/spacy/lang/norm_exceptions.py
|
||||
[punctuation.py]:
|
||||
https://github.com/explosion/spaCy/tree/master/spacy/lang/punctuation.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/spacy/lang/punctuation.py
|
||||
[char_classes.py]:
|
||||
https://github.com/explosion/spaCy/tree/master/spacy/lang/char_classes.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/spacy/lang/char_classes.py
|
||||
[lex_attrs.py]:
|
||||
https://github.com/explosion/spaCy/tree/master/spacy/lang/en/lex_attrs.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/spacy/lang/en/lex_attrs.py
|
||||
[syntax_iterators.py]:
|
||||
https://github.com/explosion/spaCy/tree/master/spacy/lang/en/syntax_iterators.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/spacy/lang/en/syntax_iterators.py
|
||||
[tag_map.py]:
|
||||
https://github.com/explosion/spaCy/tree/master/spacy/lang/en/tag_map.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/spacy/lang/en/tag_map.py
|
||||
[morph_rules.py]:
|
||||
https://github.com/explosion/spaCy/tree/master/spacy/lang/en/morph_rules.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/spacy/lang/en/morph_rules.py
|
||||
[spacy-lookups-data]: https://github.com/explosion/spacy-lookups-data
|
||||
|
|
|
|||
|
|
@ -15,8 +15,8 @@ the specific workflows for each component.
|
|||
>
|
||||
> To add a new language to spaCy, you'll need to **modify the library's code**.
|
||||
> The easiest way to do this is to clone the
|
||||
> [repository](https://github.com/explosion/spaCy/tree/master/) and **build
|
||||
> spaCy from source**. For more information on this, see the
|
||||
> [repository](https://github.com/explosion/spacy/tree/v2.x/) and **build spaCy
|
||||
> from source**. For more information on this, see the
|
||||
> [installation guide](/usage). Unlike spaCy's core, which is mostly written in
|
||||
> Cython, all language data is stored in regular Python files. This means that
|
||||
> you won't have to rebuild anything in between – you can simply make edits and
|
||||
|
|
@ -88,7 +88,7 @@ language and training a language model.
|
|||
> #### Should I ever update the global data?
|
||||
>
|
||||
> Reusable language data is collected as atomic pieces in the root of the
|
||||
> [`spacy.lang`](https://github.com/explosion/spaCy/tree/master/spacy/lang)
|
||||
> [`spacy.lang`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang)
|
||||
> module. Often, when a new language is added, you'll find a pattern or symbol
|
||||
> that's missing. Even if it isn't common in other languages, it might be best
|
||||
> to add it to the shared language data, unless it has some conflicting
|
||||
|
|
@ -102,7 +102,7 @@ In order for the tokenizer to split suffixes, prefixes and infixes, spaCy needs
|
|||
to know the language's character set. If the language you're adding uses
|
||||
non-latin characters, you might need to define the required character classes in
|
||||
the global
|
||||
[`char_classes.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/char_classes.py).
|
||||
[`char_classes.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/char_classes.py).
|
||||
For efficiency, spaCy uses hard-coded unicode ranges to define character
|
||||
classes, the definitions of which can be found on
|
||||
[Wikipedia](https://en.wikipedia.org/wiki/Unicode_block). If the language
|
||||
|
|
@ -120,7 +120,7 @@ code and resources specific to Spanish are placed into a directory
|
|||
`spacy/lang/es`, which can be imported as `spacy.lang.es`.
|
||||
|
||||
To get started, you can check out the
|
||||
[existing languages](https://github.com/explosion/spacy/tree/master/spacy/lang).
|
||||
[existing languages](https://github.com/explosion/spacy/tree/v2.x/spacy/lang).
|
||||
Here's what the class could look like:
|
||||
|
||||
```python
|
||||
|
|
@ -291,14 +291,14 @@ weren't common in the training data, but are equivalent to other words – for
|
|||
example, "realise" and "realize", or "thx" and "thanks".
|
||||
|
||||
Similarly, spaCy also includes
|
||||
[global base norms](https://github.com/explosion/spaCy/tree/master/spacy/lang/norm_exceptions.py)
|
||||
[global base norms](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/norm_exceptions.py)
|
||||
for normalizing different styles of quotation marks and currency symbols. Even
|
||||
though `$` and `€` are very different, spaCy normalizes them both to `$`. This
|
||||
way, they'll always be seen as similar, no matter how common they were in the
|
||||
training data.
|
||||
|
||||
As of spaCy v2.3, language-specific norm exceptions are provided as a
|
||||
JSON dictionary in the package
|
||||
As of spaCy v2.3, language-specific norm exceptions are provided as a JSON
|
||||
dictionary in the package
|
||||
[`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data) rather
|
||||
than in the main library. For a full example, see
|
||||
[`en_lexeme_norm.json`](https://github.com/explosion/spacy-lookups-data/blob/master/spacy_lookups_data/data/en_lexeme_norm.json).
|
||||
|
|
@ -378,7 +378,7 @@ number words), requires some customization.
|
|||
> of possible number words).
|
||||
|
||||
Here's an example from the English
|
||||
[`lex_attrs.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/en/lex_attrs.py):
|
||||
[`lex_attrs.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/en/lex_attrs.py):
|
||||
|
||||
```python
|
||||
### lex_attrs.py
|
||||
|
|
@ -430,17 +430,17 @@ iterators:
|
|||
> assert chunks[1].text == "another phrase"
|
||||
> ```
|
||||
|
||||
| Language | Code | Source |
|
||||
| ---------------- | ---- | ----------------------------------------------------------------------------------------------------------------- |
|
||||
| English | `en` | [`lang/en/syntax_iterators.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/en/syntax_iterators.py) |
|
||||
| German | `de` | [`lang/de/syntax_iterators.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/de/syntax_iterators.py) |
|
||||
| French | `fr` | [`lang/fr/syntax_iterators.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/fr/syntax_iterators.py) |
|
||||
| Spanish | `es` | [`lang/es/syntax_iterators.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/es/syntax_iterators.py) |
|
||||
| Greek | `el` | [`lang/el/syntax_iterators.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/el/syntax_iterators.py) |
|
||||
| Norwegian Bokmål | `nb` | [`lang/nb/syntax_iterators.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/nb/syntax_iterators.py) |
|
||||
| Swedish | `sv` | [`lang/sv/syntax_iterators.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/sv/syntax_iterators.py) |
|
||||
| Indonesian | `id` | [`lang/id/syntax_iterators.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/id/syntax_iterators.py) |
|
||||
| Persian | `fa` | [`lang/fa/syntax_iterators.py`](https://github.com/explosion/spaCy/tree/master/spacy/lang/fa/syntax_iterators.py) |
|
||||
| Language | Code | Source |
|
||||
| ---------------- | ---- | --------------------------------------------------------------------------------------------------------------- |
|
||||
| English | `en` | [`lang/en/syntax_iterators.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/en/syntax_iterators.py) |
|
||||
| German | `de` | [`lang/de/syntax_iterators.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/de/syntax_iterators.py) |
|
||||
| French | `fr` | [`lang/fr/syntax_iterators.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/fr/syntax_iterators.py) |
|
||||
| Spanish | `es` | [`lang/es/syntax_iterators.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/es/syntax_iterators.py) |
|
||||
| Greek | `el` | [`lang/el/syntax_iterators.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/el/syntax_iterators.py) |
|
||||
| Norwegian Bokmål | `nb` | [`lang/nb/syntax_iterators.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/nb/syntax_iterators.py) |
|
||||
| Swedish | `sv` | [`lang/sv/syntax_iterators.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/sv/syntax_iterators.py) |
|
||||
| Indonesian | `id` | [`lang/id/syntax_iterators.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/id/syntax_iterators.py) |
|
||||
| Persian | `fa` | [`lang/fa/syntax_iterators.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/fa/syntax_iterators.py) |
|
||||
|
||||
### Lemmatizer {#lemmatizer new="2"}
|
||||
|
||||
|
|
@ -561,7 +561,7 @@ be causing regressions.
|
|||
spaCy uses the [pytest framework](https://docs.pytest.org/en/latest/) for
|
||||
testing. For more details on how the tests are structured and best practices for
|
||||
writing your own tests, see our
|
||||
[tests documentation](https://github.com/explosion/spaCy/tree/master/spacy/tests).
|
||||
[tests documentation](https://github.com/explosion/spacy/tree/v2.x/spacy/tests).
|
||||
|
||||
</Infobox>
|
||||
|
||||
|
|
@ -569,10 +569,10 @@ writing your own tests, see our
|
|||
|
||||
It's recommended to always add at least some tests with examples specific to the
|
||||
language. Language tests should be located in
|
||||
[`tests/lang`](https://github.com/explosion/spaCy/tree/master/spacy/tests/lang)
|
||||
in a directory named after the language ID. You'll also need to create a fixture
|
||||
[`tests/lang`](https://github.com/explosion/spacy/tree/v2.x/spacy/tests/lang) in
|
||||
a directory named after the language ID. You'll also need to create a fixture
|
||||
for your tokenizer in the
|
||||
[`conftest.py`](https://github.com/explosion/spaCy/tree/master/spacy/tests/conftest.py).
|
||||
[`conftest.py`](https://github.com/explosion/spacy/tree/v2.x/spacy/tests/conftest.py).
|
||||
Always use the [`get_lang_class`](/api/top-level#util.get_lang_class) helper
|
||||
function within the fixture, instead of importing the class at the top of the
|
||||
file. This will load the language data only when it's needed. (Otherwise, _all
|
||||
|
|
@ -585,7 +585,7 @@ def en_tokenizer():
|
|||
```
|
||||
|
||||
When adding test cases, always
|
||||
[`parametrize`](https://github.com/explosion/spaCy/tree/master/spacy/tests#parameters)
|
||||
[`parametrize`](https://github.com/explosion/spacy/tree/v2.x/spacy/tests#parameters)
|
||||
them – this will make it easier for others to add more test cases without having
|
||||
to modify the test itself. You can also add parameter tuples, for example, a
|
||||
test sentence and its expected length, or a list of expected tokens. Here's an
|
||||
|
|
@ -630,13 +630,13 @@ of using deep learning for NLP with limited labeled data. The vectors are also
|
|||
useful by themselves – they power the `.similarity` methods in spaCy. For best
|
||||
results, you should pre-process the text with spaCy before training the Word2vec
|
||||
model. This ensures your tokenization will match. You can use our
|
||||
[word vectors training script](https://github.com/explosion/spacy/tree/master/bin/train_word_vectors.py),
|
||||
[word vectors training script](https://github.com/explosion/spacy/tree/v2.x/bin/train_word_vectors.py),
|
||||
which pre-processes the text with your language-specific tokenizer and trains
|
||||
the model using [Gensim](https://radimrehurek.com/gensim/). The `vectors.bin`
|
||||
file should consist of one word and vector per line.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spacy/tree/master/bin/train_word_vectors.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/bin/train_word_vectors.py
|
||||
```
|
||||
|
||||
If you don't have a large sample of text available, you can also convert word
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@ This example shows how to use the new [`PhraseMatcher`](/api/phrasematcher) to
|
|||
efficiently find entities from a large terminology list.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/information_extraction/phrase_matcher.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/information_extraction/phrase_matcher.py
|
||||
```
|
||||
|
||||
### Extracting entity relations {#entity-relations}
|
||||
|
|
@ -29,7 +29,7 @@ tree to find the noun phrase they are referring to – for example:
|
|||
`"$9.4 million"` → `"Net income"`.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/information_extraction/entity_relations.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/information_extraction/entity_relations.py
|
||||
```
|
||||
|
||||
### Navigating the parse tree and subtrees {#subtrees}
|
||||
|
|
@ -38,7 +38,7 @@ This example shows how to navigate the parse tree including subtrees attached to
|
|||
a word.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/information_extraction/parse_subtrees.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/information_extraction/parse_subtrees.py
|
||||
```
|
||||
|
||||
## Pipeline {#pipeline hidden="true"}
|
||||
|
|
@ -51,7 +51,7 @@ entities into one token and sets custom attributes on the `Doc`, `Span` and
|
|||
`Token`.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/pipeline/custom_component_entities.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/pipeline/custom_component_entities.py
|
||||
```
|
||||
|
||||
### Custom pipeline components and attribute extensions via a REST API {#custom-components-api new="2"}
|
||||
|
|
@ -63,7 +63,7 @@ attributes on the `Doc`, `Span` and `Token` – for example, the capital,
|
|||
latitude/longitude coordinates and the country flag.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/pipeline/custom_component_countries_api.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/pipeline/custom_component_countries_api.py
|
||||
```
|
||||
|
||||
### Custom method extensions {#custom-components-attr-methods new="2"}
|
||||
|
|
@ -72,7 +72,7 @@ A collection of snippets showing examples of extensions adding custom methods to
|
|||
the `Doc`, `Token` and `Span`.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/pipeline/custom_attr_methods.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/pipeline/custom_attr_methods.py
|
||||
```
|
||||
|
||||
### Multi-processing with Joblib {#multi-processing}
|
||||
|
|
@ -85,7 +85,7 @@ IMDB movie reviews dataset and will be loaded automatically via Thinc's built-in
|
|||
dataset loader.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/pipeline/multi_processing.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/pipeline/multi_processing.py
|
||||
```
|
||||
|
||||
## Training {#training hidden="true"}
|
||||
|
|
@ -93,11 +93,11 @@ https://github.com/explosion/spaCy/tree/master/examples/pipeline/multi_processin
|
|||
### Training spaCy's Named Entity Recognizer {#training-ner}
|
||||
|
||||
This example shows how to update spaCy's entity recognizer with your own
|
||||
examples, starting off with an existing, pretrained model, or from scratch
|
||||
using a blank `Language` class.
|
||||
examples, starting off with an existing, pretrained model, or from scratch using
|
||||
a blank `Language` class.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_ner.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_ner.py
|
||||
```
|
||||
|
||||
### Training an additional entity type {#new-entity-type}
|
||||
|
|
@ -108,28 +108,28 @@ examples. In practice, you'll need many more — a few hundred would be a good
|
|||
start.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_new_entity_type.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_new_entity_type.py
|
||||
```
|
||||
|
||||
### Creating a Knowledge Base for Named Entity Linking {#kb}
|
||||
|
||||
This example shows how to create a knowledge base in spaCy,
|
||||
which is needed to implement entity linking functionality.
|
||||
It requires as input a spaCy model with pretrained word vectors,
|
||||
and it stores the KB to file (if an `output_dir` is provided).
|
||||
This example shows how to create a knowledge base in spaCy, which is needed to
|
||||
implement entity linking functionality. It requires as input a spaCy model with
|
||||
pretrained word vectors, and it stores the KB to file (if an `output_dir` is
|
||||
provided).
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/create_kb.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/create_kb.py
|
||||
```
|
||||
|
||||
### Training spaCy's Named Entity Linker {#nel}
|
||||
|
||||
This example shows how to train spaCy's entity linker with your own custom
|
||||
examples, starting off with a predefined knowledge base and its vocab,
|
||||
and using a blank `English` class.
|
||||
examples, starting off with a predefined knowledge base and its vocab, and using
|
||||
a blank `English` class.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_entity_linker.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_entity_linker.py
|
||||
```
|
||||
|
||||
### Training spaCy's Dependency Parser {#parser}
|
||||
|
|
@ -138,7 +138,7 @@ This example shows how to update spaCy's dependency parser, starting off with an
|
|||
existing, pretrained model, or from scratch using a blank `Language` class.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_parser.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_parser.py
|
||||
```
|
||||
|
||||
### Training spaCy's Part-of-speech Tagger {#tagger}
|
||||
|
|
@ -148,7 +148,7 @@ map, mapping our own tags to the mapping those tags to the
|
|||
[Universal Dependencies scheme](http://universaldependencies.github.io/docs/u/pos/index.html).
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_tagger.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_tagger.py
|
||||
```
|
||||
|
||||
### Training a custom parser for chat intent semantics {#intent-parser}
|
||||
|
|
@ -162,7 +162,7 @@ following types of relations: `ROOT`, `PLACE`, `QUALITY`, `ATTRIBUTE`, `TIME`
|
|||
and `LOCATION`.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_intent_parser.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_intent_parser.py
|
||||
```
|
||||
|
||||
### Training spaCy's text classifier {#textcat new="2"}
|
||||
|
|
@ -174,7 +174,7 @@ automatically via Thinc's built-in dataset loader. Predictions are available via
|
|||
[`Doc.cats`](/api/doc#attributes).
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_textcat.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_textcat.py
|
||||
```
|
||||
|
||||
## Vectors {#vectors hidden="true"}
|
||||
|
|
@ -186,7 +186,7 @@ This script lets you load any spaCy model containing word vectors into
|
|||
[embedding visualization](https://github.com/tensorflow/tensorboard/blob/master/docs/tensorboard_projector_plugin.ipynb).
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/vectors_tensorboard.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/vectors_tensorboard.py
|
||||
```
|
||||
|
||||
## Deep Learning {#deep-learning hidden="true"}
|
||||
|
|
@ -203,5 +203,5 @@ documents so that they're a fixed size. This hurts review accuracy a lot,
|
|||
because people often summarize their rating in the final sentence.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/deep_learning_keras.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/deep_learning_keras.py
|
||||
```
|
||||
|
|
|
|||
|
|
@ -176,7 +176,7 @@ pip install -r requirements.txt
|
|||
```
|
||||
|
||||
Compared to regular install via pip, the
|
||||
[`requirements.txt`](https://github.com/explosion/spaCy/tree/master/requirements.txt)
|
||||
[`requirements.txt`](https://github.com/explosion/spacy/tree/v2.x/requirements.txt)
|
||||
additionally installs developer dependencies such as Cython. See the the
|
||||
[quickstart widget](#quickstart) to get the right commands for your platform and
|
||||
Python version.
|
||||
|
|
@ -243,14 +243,14 @@ source code and recompiling frequently.
|
|||
### Run tests {#run-tests}
|
||||
|
||||
spaCy comes with an
|
||||
[extensive test suite](https://github.com/explosion/spaCy/tree/master/spacy/tests).
|
||||
[extensive test suite](https://github.com/explosion/spacy/tree/v2.x/spacy/tests).
|
||||
In order to run the tests, you'll usually want to clone the
|
||||
[repository](https://github.com/explosion/spaCy/tree/master/) and
|
||||
[repository](https://github.com/explosion/spacy/tree/v2.x/) and
|
||||
[build spaCy from source](#source). This will also install the required
|
||||
development dependencies and test utilities defined in the `requirements.txt`.
|
||||
|
||||
Alternatively, you can run `pytest` on the tests packaged with the install
|
||||
`spacy package. Don't forget to also install the test utilities via spaCy's [`requirements.txt`](https://github.com/explosion/spaCy/tree/master/requirements.txt):
|
||||
`spacy package. Don't forget to also install the test utilities via spaCy's [`requirements.txt`](https://github.com/explosion/spacy/tree/v2.x/requirements.txt):
|
||||
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
|
|
|
|||
|
|
@ -540,7 +540,7 @@ gold = GoldParse(doc, entities=["U-ANIMAL", "O", "O", "O"])
|
|||
|
||||
For more details on **training and updating** the named entity recognizer, see
|
||||
the usage guides on [training](/usage/training) or check out the runnable
|
||||
[training script](https://github.com/explosion/spaCy/tree/master/examples/training/train_ner.py)
|
||||
[training script](https://github.com/explosion/spacy/tree/v2.x/examples/training/train_ner.py)
|
||||
on GitHub.
|
||||
|
||||
</Infobox>
|
||||
|
|
@ -646,7 +646,7 @@ import Tokenization101 from 'usage/101/\_tokenization.md'
|
|||
|
||||
**Global** and **language-specific** tokenizer data is supplied via the language
|
||||
data in
|
||||
[`spacy/lang`](https://github.com/explosion/spaCy/tree/master/spacy/lang). The
|
||||
[`spacy/lang`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang). The
|
||||
tokenizer exceptions define special cases like "don't" in English, which needs
|
||||
to be split into two tokens: `{ORTH: "do"}` and `{ORTH: "n't", NORM: "not"}`.
|
||||
The prefixes, suffixes and infixes mostly define punctuation rules – for
|
||||
|
|
@ -666,7 +666,7 @@ For more details on the language-specific data, see the usage guide on
|
|||
|
||||
Tokenization rules that are specific to one language, but can be **generalized
|
||||
across that language** should ideally live in the language data in
|
||||
[`spacy/lang`](https://github.com/explosion/spaCy/tree/master/spacy/lang) – we
|
||||
[`spacy/lang`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang) – we
|
||||
always appreciate pull requests! Anything that's specific to a domain or text
|
||||
type – like financial trading abbreviations, or Bavarian youth slang – should be
|
||||
added as a special case rule to your tokenizer instance. If you're dealing with
|
||||
|
|
@ -843,7 +843,7 @@ domain. There are six things you may need to define:
|
|||
be split, overriding the infix rules. Useful for things like numbers.
|
||||
6. An optional boolean function `url_match`, which is similar to `token_match`
|
||||
except that prefixes and suffixes are removed before applying the match.
|
||||
|
||||
|
||||
<Infobox title="Important note: token match in spaCy v2.2" variant="warning">
|
||||
|
||||
In spaCy v2.2.2-v2.2.4, the `token_match` was equivalent to the `url_match`
|
||||
|
|
|
|||
|
|
@ -78,7 +78,7 @@ As of v2.0, spaCy supports models trained on more than one language. This is
|
|||
especially useful for named entity recognition. The language ID used for
|
||||
multi-language or language-neutral models is `xx`. The language class, a generic
|
||||
subclass containing only the base language data, can be found in
|
||||
[`lang/xx`](https://github.com/explosion/spaCy/tree/master/spacy/lang/xx).
|
||||
[`lang/xx`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang/xx).
|
||||
|
||||
To load your model with the neutral, multi-language class, simply set
|
||||
`"language": "xx"` in your [model package](/usage/training#models-generating)'s
|
||||
|
|
|
|||
|
|
@ -489,7 +489,7 @@ When you call `nlp` on a text, the custom pipeline component is applied to the
|
|||
`Doc`.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/pipeline/custom_component_entities.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/pipeline/custom_component_entities.py
|
||||
```
|
||||
|
||||
Wrapping this functionality in a pipeline component allows you to reuse the
|
||||
|
|
@ -650,7 +650,7 @@ attributes on the `Doc`, `Span` and `Token` – for example, the capital,
|
|||
latitude/longitude coordinates and even the country flag.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/pipeline/custom_component_countries_api.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/pipeline/custom_component_countries_api.py
|
||||
```
|
||||
|
||||
In this case, all data can be fetched on initialization in one request. However,
|
||||
|
|
|
|||
|
|
@ -193,7 +193,7 @@ computed properties can't be accessed.
|
|||
|
||||
The uppercase attribute names like `LOWER` or `IS_PUNCT` refer to symbols from
|
||||
the
|
||||
[`spacy.attrs`](https://github.com/explosion/spaCy/tree/master/spacy/attrs.pyx)
|
||||
[`spacy.attrs`](https://github.com/explosion/spacy/tree/v2.x/spacy/attrs.pyx)
|
||||
enum table. They're passed into a function that essentially is a big case/switch
|
||||
statement, to figure out which struct field to return. The same attribute
|
||||
identifiers are used in [`Doc.to_array`](/api/doc#to_array), and a few other
|
||||
|
|
|
|||
|
|
@ -194,7 +194,7 @@ add to that data and saves and loads the data to and from a JSON file.
|
|||
>
|
||||
> To see custom serialization methods in action, check out the new
|
||||
> [`EntityRuler`](/api/entityruler) component and its
|
||||
> [source](https://github.com/explosion/spaCy/tree/master/spacy/pipeline/entityruler.py).
|
||||
> [source](https://github.com/explosion/spacy/tree/v2.x/spacy/pipeline/entityruler.py).
|
||||
> Patterns added to the component will be saved to a `.jsonl` file if the
|
||||
> pipeline is serialized to disk, and to a bytestring if the pipeline is
|
||||
> serialized to bytes. This allows saving out a model with a rule-based entity
|
||||
|
|
|
|||
|
|
@ -915,9 +915,9 @@ via the following platforms:
|
|||
questions** and everything related to problems with your specific code. The
|
||||
Stack Overflow community is much larger than ours, so if your problem can be
|
||||
solved by others, you'll receive help much quicker.
|
||||
- [GitHub discussions](https://github.com/explosion/spaCy/discussions): **General
|
||||
discussion**, **project ideas** and **usage questions**. Meet other community
|
||||
members to get help with a specific code implementation, discuss ideas for new
|
||||
- [GitHub discussions](https://github.com/explosion/spaCy/discussions): **General
|
||||
discussion**, **project ideas** and **usage questions**. Meet other community
|
||||
members to get help with a specific code implementation, discuss ideas for new
|
||||
projects/plugins, support more languages, and share best practices.
|
||||
- [GitHub issue tracker](https://github.com/explosion/spaCy/issues): **Bug
|
||||
reports** and **improvement suggestions**, i.e. everything that's likely
|
||||
|
|
@ -959,7 +959,7 @@ regressions to the parts of the library that you care about the most.
|
|||
|
||||
**For more details on the types of contributions we're looking for, the code
|
||||
conventions and other useful tips, make sure to check out the
|
||||
[contributing guidelines](https://github.com/explosion/spaCy/tree/master/CONTRIBUTING.md).**
|
||||
[contributing guidelines](https://github.com/explosion/spacy/tree/v2.x/CONTRIBUTING.md).**
|
||||
|
||||
<Infobox title="Code of Conduct" variant="warning">
|
||||
|
||||
|
|
|
|||
|
|
@ -352,7 +352,7 @@ a blank `Language` class. To do this, you'll need **example texts** and the
|
|||
**character offsets** and **labels** of each entity contained in the texts.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_ner.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_ner.py
|
||||
```
|
||||
|
||||
#### Step by step guide {#step-by-step-ner}
|
||||
|
|
@ -384,7 +384,7 @@ entity recognizer over unlabelled sentences, and adding their annotations to the
|
|||
training set.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_new_entity_type.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_new_entity_type.py
|
||||
```
|
||||
|
||||
<Infobox title="Important note" variant="warning">
|
||||
|
|
@ -426,7 +426,7 @@ the respective **heads** and **dependency label** for each token of the example
|
|||
texts.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_parser.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_parser.py
|
||||
```
|
||||
|
||||
#### Step by step guide {#step-by-step-parser}
|
||||
|
|
@ -460,7 +460,7 @@ those tags to the
|
|||
[Universal Dependencies scheme](http://universaldependencies.github.io/docs/u/pos/index.html).
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_tagger.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_tagger.py
|
||||
```
|
||||
|
||||
#### Step by step guide {#step-by-step-tagger}
|
||||
|
|
@ -528,7 +528,7 @@ message semantics will have the following types of relations: `ROOT`, `PLACE`,
|
|||
`QUALITY`, `ATTRIBUTE`, `TIME` and `LOCATION`.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_intent_parser.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_intent_parser.py
|
||||
```
|
||||
|
||||
#### Step by step guide {#step-by-step-parser-custom}
|
||||
|
|
@ -567,7 +567,7 @@ automatically via Thinc's built-in dataset loader. Predictions are available via
|
|||
[`Doc.cats`](/api/doc#attributes).
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_textcat.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_textcat.py
|
||||
```
|
||||
|
||||
#### Step by step guide {#step-by-step-textcat}
|
||||
|
|
@ -614,7 +614,7 @@ pretrained word vectors to obtain an encoding of an entity's description as its
|
|||
vector.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/create_kb.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/create_kb.py
|
||||
```
|
||||
|
||||
#### Step by step guide {#step-by-step-kb}
|
||||
|
|
@ -639,7 +639,7 @@ offsets** and **knowledge base identifiers** of each entity contained in the
|
|||
texts.
|
||||
|
||||
```python
|
||||
https://github.com/explosion/spaCy/tree/master/examples/training/train_entity_linker.py
|
||||
https://github.com/explosion/spacy/tree/v2.x/examples/training/train_entity_linker.py
|
||||
```
|
||||
|
||||
#### Step by step guide {#step-by-step-entity-linker}
|
||||
|
|
|
|||
|
|
@ -180,7 +180,7 @@ entirely **in Markdown**, without having to compromise on easy-to-use custom UI
|
|||
components. We're hoping that the Markdown source will make it even easier to
|
||||
contribute to the documentation. For more details, check out the
|
||||
[styleguide](/styleguide) and
|
||||
[source](https://github.com/explosion/spaCy/tree/master/website). While
|
||||
[source](https://github.com/explosion/spacy/tree/v2.x/website). While
|
||||
converting the pages to Markdown, we've also fixed a bunch of typos, improved
|
||||
the existing pages and added some new content:
|
||||
|
||||
|
|
|
|||
|
|
@ -161,8 +161,8 @@ debugging your tokenizer configuration.
|
|||
|
||||
spaCy's custom warnings have been replaced with native Python
|
||||
[`warnings`](https://docs.python.org/3/library/warnings.html). Instead of
|
||||
setting `SPACY_WARNING_IGNORE`, use the [`warnings`
|
||||
filters](https://docs.python.org/3/library/warnings.html#the-warnings-filter)
|
||||
setting `SPACY_WARNING_IGNORE`, use the
|
||||
[`warnings` filters](https://docs.python.org/3/library/warnings.html#the-warnings-filter)
|
||||
to manage warnings.
|
||||
|
||||
```diff
|
||||
|
|
@ -176,7 +176,7 @@ import spacy
|
|||
#### Normalization tables
|
||||
|
||||
The normalization tables have moved from the language data in
|
||||
[`spacy/lang`](https://github.com/explosion/spaCy/tree/master/spacy/lang) to the
|
||||
[`spacy/lang`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang) to the
|
||||
package [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data).
|
||||
If you're adding data for a new language, the normalization table should be
|
||||
added to `spacy-lookups-data`. See
|
||||
|
|
@ -190,8 +190,8 @@ lexemes will be added to the vocab automatically, just as in small models
|
|||
without vectors.
|
||||
|
||||
To see the number of unique vectors and number of words with vectors, see
|
||||
`nlp.meta['vectors']`, for example for `en_core_web_md` there are `20000`
|
||||
unique vectors and `684830` words with vectors:
|
||||
`nlp.meta['vectors']`, for example for `en_core_web_md` there are `20000` unique
|
||||
vectors and `684830` words with vectors:
|
||||
|
||||
```python
|
||||
{
|
||||
|
|
@ -210,8 +210,8 @@ for orth in nlp.vocab.vectors:
|
|||
_ = nlp.vocab[orth]
|
||||
```
|
||||
|
||||
If your workflow previously iterated over `nlp.vocab`, a similar alternative
|
||||
is to iterate over words with vectors instead:
|
||||
If your workflow previously iterated over `nlp.vocab`, a similar alternative is
|
||||
to iterate over words with vectors instead:
|
||||
|
||||
```diff
|
||||
- lexemes = [w for w in nlp.vocab]
|
||||
|
|
@ -220,9 +220,9 @@ is to iterate over words with vectors instead:
|
|||
|
||||
Be aware that the set of preloaded lexemes in a v2.2 model is not equivalent to
|
||||
the set of words with vectors. For English, v2.2 `md/lg` models have 1.3M
|
||||
provided lexemes but only 685K words with vectors. The vectors have been
|
||||
updated for most languages in v2.2, but the English models contain the same
|
||||
vectors for both v2.2 and v2.3.
|
||||
provided lexemes but only 685K words with vectors. The vectors have been updated
|
||||
for most languages in v2.2, but the English models contain the same vectors for
|
||||
both v2.2 and v2.3.
|
||||
|
||||
#### Lexeme.is_oov and Token.is_oov
|
||||
|
||||
|
|
@ -234,8 +234,7 @@ fixed in the next patch release v2.3.1.
|
|||
</Infobox>
|
||||
|
||||
In v2.3, `Lexeme.is_oov` and `Token.is_oov` are `True` if the lexeme does not
|
||||
have a word vector. This is equivalent to `token.orth not in
|
||||
nlp.vocab.vectors`.
|
||||
have a word vector. This is equivalent to `token.orth not in nlp.vocab.vectors`.
|
||||
|
||||
Previously in v2.2, `is_oov` corresponded to whether a lexeme had stored
|
||||
probability and cluster features. The probability and cluster features are no
|
||||
|
|
@ -270,8 +269,8 @@ as part of the model vocab.
|
|||
|
||||
To load the probability table into a provided model, first make sure you have
|
||||
`spacy-lookups-data` installed. To load the table, remove the empty provided
|
||||
`lexeme_prob` table and then access `Lexeme.prob` for any word to load the
|
||||
table from `spacy-lookups-data`:
|
||||
`lexeme_prob` table and then access `Lexeme.prob` for any word to load the table
|
||||
from `spacy-lookups-data`:
|
||||
|
||||
```diff
|
||||
+ # prerequisite: pip install spacy-lookups-data
|
||||
|
|
@ -321,9 +320,9 @@ the [train CLI](/api/cli#train), you can use the new `--tag-map-path` option to
|
|||
provide in the tag map as a JSON dict.
|
||||
|
||||
If you want to export a tag map from a provided model for use with the train
|
||||
CLI, you can save it as a JSON dict. To only use string keys as required by
|
||||
JSON and to make it easier to read and edit, any internal integer IDs need to
|
||||
be converted back to strings:
|
||||
CLI, you can save it as a JSON dict. To only use string keys as required by JSON
|
||||
and to make it easier to read and edit, any internal integer IDs need to be
|
||||
converted back to strings:
|
||||
|
||||
```python
|
||||
import spacy
|
||||
|
|
|
|||
|
|
@ -306,7 +306,7 @@ lookup-based lemmatization – and **many new languages**!
|
|||
<Infobox>
|
||||
|
||||
**API:** [`Language`](/api/language) **Code:**
|
||||
[`spacy/lang`](https://github.com/explosion/spaCy/tree/master/spacy/lang)
|
||||
[`spacy/lang`](https://github.com/explosion/spacy/tree/v2.x/spacy/lang)
|
||||
**Usage:** [Adding languages](/usage/adding-languages)
|
||||
|
||||
</Infobox>
|
||||
|
|
|
|||
|
|
@ -4,7 +4,8 @@
|
|||
"slogan": "Industrial-strength Natural Language Processing in Python",
|
||||
"siteUrl": "https://v2.spacy.io",
|
||||
"domain": "v2.spacy.io",
|
||||
"legacy": true,
|
||||
"legacy": false,
|
||||
"codeBranch": "v2.x",
|
||||
"email": "contact@explosion.ai",
|
||||
"company": "Explosion AI",
|
||||
"companyUrl": "https://explosion.ai",
|
||||
|
|
|
|||
|
|
@ -6,6 +6,7 @@ import siteMetadata from '../../meta/site.json'
|
|||
|
||||
const htmlToReactParser = new HtmlToReactParser()
|
||||
|
||||
export const defaultBranch = siteMetadata.codeBranch
|
||||
export const repo = siteMetadata.repo
|
||||
export const modelsRepo = siteMetadata.modelsRepo
|
||||
|
||||
|
|
@ -18,11 +19,11 @@ export const headingTextClassName = 'heading-text'
|
|||
/**
|
||||
* Create a link to the spaCy repository on GitHub
|
||||
* @param {string} filepath - The file path relative to the root of the repo.
|
||||
* @param {string} [branch] - Optional branch. Defaults to master.
|
||||
* @param {string} [branch] - Optional branch.
|
||||
* @returns {string} - URL to the file on GitHub.
|
||||
*/
|
||||
export function github(filepath, branch = 'master') {
|
||||
const path = filepath ? '/tree/' + (branch || 'master') + '/' + filepath : ''
|
||||
export function github(filepath, branch = defaultBranch) {
|
||||
const path = filepath ? '/tree/' + (branch || defaultBranch) + '/' + filepath : ''
|
||||
return `https://github.com/${repo}${path}`
|
||||
}
|
||||
|
||||
|
|
@ -30,9 +31,9 @@ export function github(filepath, branch = 'master') {
|
|||
* Get the source of a file in the documentation based on its slug
|
||||
* @param {string} slug - The slug, e.g. /api/doc.
|
||||
* @param {boolean} [isIndex] - Whether the page is an index, e.g. /api/index.md
|
||||
* @param {string} [branch] - Optional branch on GitHub. Defaults to master.
|
||||
* @param {string} [branch] - Optional branch on GitHub.
|
||||
*/
|
||||
export function getCurrentSource(slug, isIndex = false, branch = 'master') {
|
||||
export function getCurrentSource(slug, isIndex = false, branch = defaultBranch) {
|
||||
const ext = isIndex ? '/index.md' : '.md'
|
||||
return github(`website/docs${slug}${ext}`, branch)
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user