INNER CODE UNIT · Python

__call__

NorskRegnesentral/skweak · skweak/aggregation.py:42

    def __call__(self, doc: Doc) -> Doc:
        """Aggregates all weak supervision sources"""

        # Extracting the sources to consider (and filtering out the ones to avoid)
        sources = self._get_sources_to_aggregate(doc)
        
        # If we have no labelling sources, we can skip the document
        if len(sources)==0:
            doc.spans[self.name] = []
            doc.spans[self.name].attrs = {"probs":{}, "aggregated":True, "sources":[]}
            return doc
            
        # Extracting the observation data
        df = self.get_observation_df(doc)
        
        # Special case: if the document has no observation whatsoever
        if len(df.columns)==0:
            output_spans, output_probs = [], []

View source record →