File size: 2,388 Bytes
19b102a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
import numpy as np
from typing import List


class BaseEmbedder:
    """ The Base Embedder used for creating embedding models

    Arguments:
        embedding_model: The main embedding model to be used for extracting
                         document and word embedding
        word_embedding_model: The embedding model used for extracting word
                              embeddings only. If this model is selected,
                              then the `embedding_model` is purely used for
                              creating document embeddings.
    """
    def __init__(self,
                 embedding_model=None,
                 word_embedding_model=None):
        self.embedding_model = embedding_model
        self.word_embedding_model = word_embedding_model

    def embed(self,
              documents: List[str],
              verbose: bool = False) -> np.ndarray:
        """ Embed a list of n documents/words into an n-dimensional
        matrix of embeddings

        Arguments:
            documents: A list of documents or words to be embedded
            verbose: Controls the verbosity of the process

        Returns:
            Document/words embeddings with shape (n, m) with `n` documents/words
            that each have an embeddings size of `m`
        """
        pass

    def embed_words(self,
                    words: List[str],
                    verbose: bool = False) -> np.ndarray:
        """ Embed a list of n words into an n-dimensional
        matrix of embeddings

        Arguments:
            words: A list of words to be embedded
            verbose: Controls the verbosity of the process

        Returns:
            Word embeddings with shape (n, m) with `n` words
            that each have an embeddings size of `m`

        """
        return self.embed(words, verbose)

    def embed_documents(self,
                        document: List[str],
                        verbose: bool = False) -> np.ndarray:
        """ Embed a list of n words into an n-dimensional
        matrix of embeddings

        Arguments:
            document: A list of documents to be embedded
            verbose: Controls the verbosity of the process

        Returns:
            Document embeddings with shape (n, m) with `n` documents
            that each have an embeddings size of `m`
        """
        return self.embed(document, verbose)