-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat: implement flair sklearn vectorizer wrappers
- Loading branch information
Showing
4 changed files
with
53 additions
and
10 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Empty file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,46 @@ | ||
import abc | ||
from typing import Any, Dict, Generic, List, Optional, TypeVar | ||
|
||
import numpy as np | ||
from flair.data import Sentence | ||
from numpy import typing as nptyping | ||
from sklearn.base import BaseEstimator, TransformerMixin | ||
from sklearn.feature_extraction.text import _VectorizerMixin | ||
|
||
from embeddings.embedding.flair_embedding import FlairEmbedding | ||
from embeddings.utils.array_like import ArrayLike | ||
|
||
Output = TypeVar("Output") | ||
|
||
|
||
# ignoring the mypy error due to no types (Any) in TransformerMixin and BaseEstimator classes | ||
class FlairVectorizer(TransformerMixin, _VectorizerMixin, BaseEstimator, Generic[Output]): # type: ignore | ||
def __init__(self, flair_embedding: FlairEmbedding) -> None: | ||
self.embedder = flair_embedding | ||
|
||
def fit(self, x: ArrayLike, y: Optional[ArrayLike] = None) -> None: | ||
pass | ||
|
||
@abc.abstractmethod | ||
def transform(self, x: ArrayLike) -> Output: | ||
pass | ||
|
||
def fit_transform(self, x: ArrayLike, y: Optional[ArrayLike] = None, **kwargs: Any) -> Output: | ||
return self.transform(x) | ||
|
||
|
||
class FlairDocumentVectorizer(FlairVectorizer[nptyping.NDArray[np.float_]]): | ||
def transform(self, x: ArrayLike) -> nptyping.NDArray[np.float_]: | ||
sentences = [Sentence(example) for example in x] | ||
embeddings = [sentence.embedding.numpy() for sentence in self.embedder.embed(sentences)] | ||
return np.vstack(embeddings) | ||
|
||
|
||
class FlairWordVectorizer(FlairVectorizer[List[List[Dict[int, float]]]]): | ||
def transform(self, x: ArrayLike) -> List[List[Dict[int, float]]]: | ||
sentences = [Sentence(example) for example in x] | ||
embeddings = [sentence for sentence in self.embedder.embed(sentences)] | ||
return [ | ||
[{i: value for i, value in enumerate(word.embedding.numpy())} for word in sent] | ||
for sent in embeddings | ||
] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters