Spaces:
Build error
Build error
File size: 3,248 Bytes
dab2de2 2f6222b dab2de2 |
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 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
"""Generate a doc-term score matrix based on textacy.representation.Vectorizer.
refer also to fast-scores fast_scores.py and gen_model.py (sklearn.feature_extraction.text.TfidfVectorizer).
"""
from typing import Dict, Iterable, List, Optional, Union # noqa
import numpy as np
from itertools import chain
from psutil import virtual_memory
from more_itertools import ilen
from textacy.representations import Vectorizer
from logzero import logger
from radiobee.gen_model import gen_model
# fmt: off
def docterm_scores(
doc1: Iterable[Iterable[str]], # List[List[str]],
doc2: Iterable[Iterable[str]],
model: Vectorizer = None,
tf_type: str = 'linear',
idf_type: Optional[str] = "smooth",
# dl_type: Optional[str] = "sqrt", # "lucene-style tfidf"
dl_type: Optional[str] = None, #
norm: Optional[str] = "l2", # + "l2"
min_df: Union[int, float] = 1,
max_df: Union[int, float] = 1.0,
max_n_terms: Optional[int] = None,
vocabulary_terms: Optional[Union[Dict[str, int], Iterable[str]]] = None
) -> np.ndarray:
# fmt: on
"""Generate a doc-term score matrix based on textacy.representation.Vectorizer.
Args
doc1: tokenized doc of n1
doc2: tokenized doc of n2
model: if None, generate one ad hoc from doc1 and doc2 ("lucene-style tfidf").
rest: refer to textacy.representation.Vectorizer
Attributes
vectorizer
Returns
n1 x n2 similarity matrix of float numbers
"""
# make sure doc1/doc2 is of the right typing
try:
for xelm in iter(doc1):
for elm in iter(xelm):
assert isinstance(elm, str)
except AssertionError:
raise AssertionError(" doc1 is not of the typing Iterable[Iterable[str]] ")
except Exception as e:
logger.error(e)
raise
try:
for xelm in iter(doc2):
for elm in iter(xelm):
assert isinstance(elm, str)
except AssertionError:
raise AssertionError(" doc2 is not of the typing Iterable[Iterable[str]] ")
except Exception as e:
logger.error(e)
raise
if model is None:
model = gen_model(
[*chain(doc1, doc2)],
tf_type=tf_type,
idf_type=idf_type,
dl_type=dl_type,
norm=norm,
min_df=min_df,
max_df=max_df,
max_n_terms=max_n_terms,
vocabulary_terms=vocabulary_terms
)
docterm_scores.model = model
# a1 = dt.toarray(), a2 = doc_term_matrix.toarray()
# np.all(np.isclose(a1, a2))
dt1 = model.transform(doc1)
dt2 = model.transform(doc2)
# virtual_memory().available / 8: 64bits float
require_ram = ilen(iter(doc1)) * ilen(iter(doc2)) * 8
if require_ram > virtual_memory().available:
logger.warning("virtual_memory().available: %s", virtual_memory().available)
logger.warning("memory required: %s", require_ram)
if require_ram > virtual_memory().available * 10:
logger.warning("You'll likely encounter memory problem, such as slow down response and/or OOM.")
# return dt1.doc(dt2.T)
return dt2.toarray().dot(dt1.toarray().T)
|