mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 01:46:28 +03:00
Add Morphology and MorphAnalsysis API docs
Add initial draft of `Morphology` and `MorphAnalysis` API docs.
This commit is contained in:
Adriane Boyd
parent
311d0bde29
commit
14df00ae98
154
website/docs/api/morphanalysis.md
Normal file
154
website/docs/api/morphanalysis.md
Normal file
|
|
@ -0,0 +1,154 @@
|
|||
---
|
||||
title: MorphAnalysis
|
||||
tag: class
|
||||
source: spacy/tokens/morphanalysis.pyx
|
||||
---
|
||||
|
||||
Stores a single morphological analysis.
|
||||
|
||||
|
||||
## MorphAnalysis.\_\_init\_\_ {#init tag="method"}
|
||||
|
||||
Initialize a MorphAnalysis object from a UD FEATS string or a dictionary of
|
||||
morphological features.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> from spacy.tokens import MorphAnalysis
|
||||
>
|
||||
> feats = "Feat1=Val1|Feat2=Val2"
|
||||
> m = MorphAnalysis(nlp.vocab, feats)
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------------------ | ----------------------------- |
|
||||
| `vocab` | `Vocab` | The vocab. |
|
||||
| `features` | `Union[Dict, str]` | The morphological features. |
|
||||
| **RETURNS** | `MorphAnalysis` | The newly constructed object. |
|
||||
|
||||
|
||||
## MorphAnalysis.\_\_contains\_\_ {#contains tag="method"}
|
||||
|
||||
Whether a feature/value pair is in the analysis.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> feats = "Feat1=Val1,Val2|Feat2=Val2"
|
||||
> morph = MorphAnalysis(nlp.vocab, feats)
|
||||
> assert "Feat1=Val1" in morph
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ----- | ------------------------------------- |
|
||||
| **RETURNS** | `str` | A feature/value pair in the analysis. |
|
||||
|
||||
|
||||
## MorphAnalysis.\_\_iter\_\_ {#iter tag="method"}
|
||||
|
||||
Iterate over the feature/value pairs in the analysis.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> feats = "Feat1=Val1|Feat2=Val2"
|
||||
> morph = MorphAnalysis(nlp.vocab, feats)
|
||||
> for feat in morph:
|
||||
> print(feat)
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ---------- | ----- | ------------------------------------- |
|
||||
| **YIELDS** | `str` | A feature/value pair in the analysis. |
|
||||
|
||||
|
||||
## MorphAnalysis.\_\_len\_\_ {#len tag="method"}
|
||||
|
||||
Returns the number of features in the analysis.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> feats = "Feat1=Val1,Val2|Feat2=Val2"
|
||||
> morph = MorphAnalysis(nlp.vocab, feats)
|
||||
> assert len(morph) == 3
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ----- | --------------------------------------- |
|
||||
| **RETURNS** | `int` | The number of features in the analysis. |
|
||||
|
||||
|
||||
## MorphAnalysis.\_\_str\_\_ {#str tag="method"}
|
||||
|
||||
Returns the morphological analysis in the UD FEATS string format.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> feats = "Feat1=Val1,Val2|Feat2=Val2"
|
||||
> morph = MorphAnalysis(nlp.vocab, feats)
|
||||
> assert str(morph) == feats
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ----- | ---------------------------------|
|
||||
| **RETURNS** | `str` | The analysis in UD FEATS format. |
|
||||
|
||||
|
||||
## MorphAnalysis.get {#get tag="method"}
|
||||
|
||||
Retrieve a feature by field.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> feats = "Feat1=Val1,Val2"
|
||||
> morph = MorphAnalysis(nlp.vocab, feats)
|
||||
> assert morph.get("Feat1") == ['Feat1=Val1', 'Feat1=Val2']
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------ | ----------------------------------- |
|
||||
| `field` | `str` | The field to retrieve. |
|
||||
| **RETURNS** | `list` | A list of the individual features. |
|
||||
|
||||
|
||||
## MorphAnalysis.to_dict {#to_dict tag="method"}
|
||||
|
||||
Produce a dict representation of the analysis, in the same format as the tag
|
||||
map.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> feats = "Feat1=Val1,Val2|Feat2=Val2"
|
||||
> morph = MorphAnalysis(nlp.vocab, feats)
|
||||
> assert morph.to_dict() == {'Feat1': 'Val1,Val2', 'Feat2': 'Val2'}
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------ | -----------------------------------------|
|
||||
| **RETURNS** | `dict` | The dict representation of the analysis. |
|
||||
|
||||
|
||||
## MorphAnalysis.from_id {#from_id tag="classmethod"}
|
||||
|
||||
Create a morphological analysis from a given hash ID.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> feats = "Feat1=Val1|Feat2=Val2"
|
||||
> hash = nlp.vocab.strings[feats]
|
||||
> morph = MorphAnalysis.from_id(nlp.vocab, hash)
|
||||
> assert str(morph) == feats
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ------- | ------- | -------------------------------- |
|
||||
| `vocab` | `Vocab` | The vocab. |
|
||||
| `key` | `int` | The hash of the features string. |
|
||||
|
||||
|
||||
165
website/docs/api/morphology.md
Normal file
165
website/docs/api/morphology.md
Normal file
|
|
@ -0,0 +1,165 @@
|
|||
---
|
||||
title: Morphology
|
||||
tag: class
|
||||
source: spacy/morphology.pyx
|
||||
---
|
||||
|
||||
Store the possible morphological analyses for a language, and index them
|
||||
by hash. To save space on each token, tokens only know the hash of their
|
||||
morphological analysis, so queries of morphological attributes are delegated to
|
||||
this class.
|
||||
|
||||
|
||||
## Morphology.\_\_init\_\_ {#init tag="method"}
|
||||
|
||||
Create a Morphology object using the tag map, lemmatizer and exceptions.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> from spacy.morphology import Morphology
|
||||
>
|
||||
> morphology = Morphology(strings, tag_map, lemmatizer)
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ---------------------------------------- | --------------------------------------------------------------------------------------------------------- |
|
||||
| `strings` | `StringStore` | The string store. |
|
||||
| `tag_map` | `Dict[str, Dict]` | The tag map. |
|
||||
| `lemmatizer`| `Lemmatizer` | The lemmatizer. |
|
||||
| `exc` | `Dict[str, Dict]` | A dictionary of exceptions in the format `{tag: {orth: {"POS": "X", "Feat1": "Val1, "Feat2": "Val2", ...}` |
|
||||
| **RETURNS** | `Morphology` | The newly constructed object. |
|
||||
|
||||
|
||||
## Morphology.add {#add tag="method"}
|
||||
|
||||
Insert a morphological analysis in the morphology table, if not already
|
||||
present. The morphological analysis may be provided in the UD FEATS format as a
|
||||
string or in the tag map dictionary format. Returns the hash of the new
|
||||
analysis.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> feats = "Feat1=Val1|Feat2=Val2"
|
||||
> hash = nlp.vocab.morphology.add(feats)
|
||||
> assert hash == nlp.vocab.strings[feats]
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------------------- | --------------------------- |
|
||||
| `features` | `Union[Dict, str]` | The morphological features. |
|
||||
|
||||
|
||||
## Morphology.get {#get tag="method"}
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> feats = "Feat1=Val1|Feat2=Val2"
|
||||
> hash = nlp.vocab.morphology.add(feats)
|
||||
> assert nlp.vocab.morphology.get(hash) == feats
|
||||
> ```
|
||||
|
||||
Get the FEATS string for the hash of the morphological analysis.
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------ | --------------------------------------- |
|
||||
| `morph` | int | The hash of the morphological analysis. |
|
||||
|
||||
|
||||
## Morphology.load_tag_map {#load_tag_map tag="method"}
|
||||
|
||||
Replace the current tag map with the provided tag map.
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ------------------ | ------------ |
|
||||
| `tag_map` | `Dict[str, Dict]` | The tag map. |
|
||||
|
||||
|
||||
## Morphology.load_morph_exceptions {#load_morph_exceptions tag="method"}
|
||||
|
||||
Replace the current morphological exceptions with the provided exceptions.
|
||||
|
||||
| Name | Type | Description |
|
||||
| ------------- | ------------------ | ----------------------------- |
|
||||
| `morph_rules` | `Dict[str, Dict]` | The morphological exceptions. |
|
||||
|
||||
|
||||
## Morphology.add_special_case {#add_special_case tag="method"}
|
||||
|
||||
Add a special-case rule to the morphological analyzer. Tokens whose tag and
|
||||
orth match the rule will receive the specified properties.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> attrs = {"POS": "DET", "Definite": "Def"}
|
||||
> morphology.add_special_case("DT", "the", attrs)
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ---- | ---------------------------------------------- |
|
||||
| `tag_str` | str | The fine-grained tag. |
|
||||
| `orth_str` | str | The token text. |
|
||||
| `attrs` | dict | The features to assign for this token and tag. |
|
||||
|
||||
|
||||
## Morphology.exc {#exc tag="property"}
|
||||
|
||||
The current morphological exceptions.
|
||||
|
||||
| Name | Type | Description |
|
||||
| ---------- | ----- | --------------------------------------------------- |
|
||||
| **YIELDS** | dict | The current dictionary of morphological exceptions. |
|
||||
|
||||
|
||||
## Morphology.lemmatize {#lemmatize tag="method"}
|
||||
|
||||
TODO
|
||||
|
||||
|
||||
## Morphology.feats_to_dict {#feats_to_dict tag="staticmethod"}
|
||||
|
||||
Convert a string FEATS representation to a dictionary of features and values in
|
||||
the same format as the tag map.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> from spacy.morphology import Morphology
|
||||
> d = Morphology.feats_to_dict("Feat1=Val1|Feat2=Val2")
|
||||
> assert d == {"Feat1": "Val1", "Feat2": "Val2"}
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ----------- | ---- | ------------------------------------------------------------- |
|
||||
| `feats` | str | The morphological features in Universal Dependencies FEATS format. |
|
||||
| **RETURNS** | dict | The morphological features as a dictionary. |
|
||||
|
||||
|
||||
## Morphology.dict_to_feats {#dict_to_feats tag="staticmethod"}
|
||||
|
||||
Convert a dictionary of features and values to a string FEATS representation.
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```python
|
||||
> from spacy.morphology import Morphology
|
||||
> f = Morphology.dict_to_feats({"Feat1": "Val1", "Feat2": "Val2"})
|
||||
> assert f == "Feat1=Val1|Feat2=Val2"
|
||||
> ```
|
||||
|
||||
| Name | Type | Description |
|
||||
| ------------ | ----------------- | --------------------------------------------------------------------- |
|
||||
| `feats_dict` | `Dict[str, Dict]` | The morphological features as a dictionary. |
|
||||
| **RETURNS** | str | The morphological features as in Universal Dependencies FEATS format. |
|
||||
|
||||
|
||||
## Attributes {#attributes}
|
||||
|
||||
| Name | Type | Description |
|
||||
| ------------- | ----- | -------------------------------------------- |
|
||||
| `FEATURE_SEP` | `str` | The FEATS feature separator. Default is `|`. |
|
||||
| `FIELD_SEP` | `str` | The FEATS field separator. Default is `=`. |
|
||||
| `VALUE_SEP` | `str` | The FEATS value separator. Default is `,`. |
|
||||
|
|
@ -70,6 +70,7 @@
|
|||
{ "text": "Token", "url": "/api/token" },
|
||||
{ "text": "Span", "url": "/api/span" },
|
||||
{ "text": "Lexeme", "url": "/api/lexeme" },
|
||||
{ "text": "MorphAnalysis", "url": "/api/morphanalysis" },
|
||||
{ "text": "Example", "url": "/api/example" },
|
||||
{ "text": "DocBin", "url": "/api/docbin" }
|
||||
]
|
||||
|
|
@ -102,6 +103,7 @@
|
|||
{ "text": "StringStore", "url": "/api/stringstore" },
|
||||
{ "text": "Vectors", "url": "/api/vectors" },
|
||||
{ "text": "Lookups", "url": "/api/lookups" },
|
||||
{ "text": "Morphology", "url": "/api/morphology" },
|
||||
{ "text": "KnowledgeBase", "url": "/api/kb" },
|
||||
{ "text": "Scorer", "url": "/api/scorer" },
|
||||
{ "text": "Corpus", "url": "/api/corpus" }
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user