src/inference.py

import spacy 
import pandas as pd

def inference(model: spacy, texts: list, batch_size: int=8):
    """
    To perform batch inferencing

    Parameters:
        model: type of model 
        texts: input text example
        batch_size: batch size of the inference
    
    Returns:
        data: pandas.DataFrame of the output from inference
    """

    docs = model.pipe(texts,batch_size=batch_size)

    records = []
    for no, doc in enumerate(docs):
        if len(doc.ents)>0:           
            records.append([{'id':no+1,'text':doc.text,'span': entity.text, 
                            'entity': entity.label_, 'start': entity.start, 'end': entity.end} 
                            for entity in doc.ents])
        else:
            records.append([{'id':no+1,'text':doc.text,'span': None, 
                'entity': None, 'start':None, 'end': None}])
                 
    data = pd.DataFrame.from_dict(sum(records,[])).set_index(['text','id'])

    return data