nlp_architect.models.absa package

Subpackages

• nlp_architect.models.absa.inference package
  • Submodules
  • nlp_architect.models.absa.inference.data_types module
  • nlp_architect.models.absa.inference.inference module
  • Module contents
• nlp_architect.models.absa.train package
  • Submodules
  • nlp_architect.models.absa.train.acquire_terms module
  • nlp_architect.models.absa.train.data_types module
  • nlp_architect.models.absa.train.generate_lexicons module
  • nlp_architect.models.absa.train.rerank_terms module
  • nlp_architect.models.absa.train.rules module
  • nlp_architect.models.absa.train.train module
  • Module contents

Submodules

nlp_architect.models.absa.utils module

nlp_architect.models.absa.utils.csv_line_iterator(csv_file)

nlp_architect.models.absa.utils.load_opinion_lex(file_name: Union[str, os.PathLike]) → dict

Read opinion lexicon from CSV file.

Returns:Dictionary of LexiconElements, each LexiconElement presents a row.

nlp_architect.models.absa.utils.parse_dir(parser, input_dir: Union[str, os.PathLike], out_dir: Union[str, os.PathLike] = None, show_tok=True, show_doc=True)

Parse a directory of raw text documents, one by one.

Parameters:

• parser (SpacyBISTParser) –
• input_dir (str or PathLike) –
• out_dir (str or PathLike) – If specified, the output will also be written to this path.
• show_tok (bool, optional) – Specifies whether to include token text in output.
• show_doc (bool, optional) – Specifies whether to include document text in output.

Yields:

CoreNLPDoc – the annotated document.

nlp_architect.models.absa.utils.parse_docs(parser, docs: Union[str, os.PathLike], out_dir: Union[str, os.PathLike] = None)

nlp_architect.models.absa.utils.parse_docs_bist(parser, docs: Union[str, os.PathLike], out_dir: Union[str, os.PathLike] = None, show_tok=True, show_doc=True)

Parse raw documents in the form of text files in a directory or lines in a text file.

Parameters:

• parser –
• docs (str or PathLike) –
• out_dir (str or PathLike) – If specified, the output will also be written to this path.
• show_tok (bool, optional) – Specifies whether to include token text in output.
• show_doc (bool, optional) – Specifies whether to include document text in output.

Returns:

(list of CoreNLPDoc)

nlp_architect.models.absa.utils.parse_txt(parser: nlp_architect.pipelines.spacy_bist.SpacyBISTParser, txt_path: Union[str, os.PathLike], out_dir: Union[str, os.PathLike] = None, show_tok=True, show_doc=True)

Parse raw documents in the form of lines in a text file.

Parameters:

• parser (SpacyBISTParser) –
• txt_path (str or PathLike) –
• out_dir (str or PathLike) – If specified, the output will also be written to this path.
• show_tok (bool, optional) – Specifies whether to include token text in output.
• show_doc (bool, optional) – Specifies whether to include document text in output.

Yields:

CoreNLPDoc – the annotated document.

nlp_architect.models.absa.utils.read_generic_lex_from_file(file_name: Union[str, os.PathLike])

Read generic opinion lex for term acquisition.

Parameters:file_name (str or PathLike) – name of csv file

nlp_architect.models.absa.utils.txt_line_generator(txt_file)

Module contents