e2edutch.stanza

Complexity

Total Complexity

3

Size/Duplication

Total Lines	75
Duplicated Lines	0 %

Importance

Changes

0

3 Methods

Rating	Name	Duplication	Size	Complexity
A	CorefProcessor._set_up_model()	0	3	1
A	CorefProcessor.__init__()	0	22	1
A	CorefProcessor.process()	0	20	1

import os

Missing module docstring

The import os seems to be unused.

import stanza

The import stanza seems to be unused.

import logging

standard import "import logging" should be placed before "import stanza"

from pathlib import Path

standard import "from pathlib import Path" should be placed before "import stanza"

from e2edutch import util
from e2edutch import coref_model as cm

Unused coref_model imported from e2edutch as cm

from e2edutch.download import download_data
from e2edutch.predict import Predictor

from stanza.pipeline.processor import Processor, register_processor

third party import "from stanza.pipeline.processor import Processor, register_processor" should be placed before "from e2edutch import util"

from stanza.models.common.doc import Document

Unused Document imported from stanza.models.common.doc

third party import "from stanza.models.common.doc import Document" should be placed before "from e2edutch import util"

import tensorflow.compat.v1 as tf

Unable to import 'tensorflow.compat.v1'

Unused tensorflow.compat.v1 imported as tf

third party import "import tensorflow.compat.v1 as tf" should be placed before "from e2edutch import util"

logger = logging.getLogger('e2edutch')
logger.setLevel(logging.INFO)
logger.addHandler(logging.StreamHandler())


@register_processor('coref')
class CorefProcessor(Processor):
    ''' Processor that appends coreference information '''
    _requires = set(['tokenize'])
    _provides = set(['coref'])
    

Trailing whitespace

    def __init__(self, config, pipeline, use_gpu):

The __init__ method of the super-class Processor is not called.

        # Make e2edutch follow Stanza's GPU settings:
        # set the environment value for GPU, so that initialize_from_env picks it up.
        #if use_gpu:
        #    os.environ['GPU'] = ' '.join(tf.config.experimental.list_physical_devices('GPU'))
        #else:
        #    if 'GPU' in os.environ['GPU'] :
        #        os.environ.pop('GPU')

        self.e2econfig = util.initialize_from_env(model_name='final')

        # Override datapath and log_root:
        # store e2edata with the Stanza resources, ie. a 'stanza_resources/nl/coref' directory
        self.e2econfig['datapath'] = Path(config['model_path']).parent
        self.e2econfig['log_root'] = Path(config['model_path']).parent

        # Download data files if not present
        download_data(self.e2econfig)

        # Start and stop a session to cache all models
        predictor = Predictor(config=self.e2econfig)
        predictor.end_session()

    def _set_up_model(self, *args):

The argument args seems to be unused.

This method could be written as a function/class method.

        print ('_set_up_model')

No space allowed before bracket

        pass

Unnecessary pass statement

    def process(self, doc):

        predictor = Predictor(config=self.e2econfig)

        # build the example argument for predict:
        #   example (dict): dict with the following fields:
        #                     sentences ([[str]])
        #                     doc_id (str)
        #                     clusters ([[(int, int)]]) (optional)
        example = {}
        example['sentences'] = [sentence.text for sentence in doc.sentences]
        example['doc_id'] = 'document_from_stanza'
        example['doc_key'] = 'undocumented'

        # predicted_clusters, _ = predictor.predict(example)
        print(predictor.predict(example))

        predictor.end_session()

        return doc