utils/ghg_classifier.py

from typing import List, Tuple
from typing_extensions import Literal
import logging
import pandas as pd
from pandas import DataFrame, Series
from utils.config import getconfig
from utils.preprocessing import processingpipeline
import streamlit as st
from transformers import pipeline

# Labels dictionary ###
_lab_dict = {
                      'GHG':'GHG',
                      'NOT_GHG':'NON GHG TRANSPORT TARGET',
                      'NEGATIVE':'OTHERS',
                      }
        

@st.cache_resource
def load_ghgClassifier(config_file:str = None, classifier_name:str = None):
    """
    loads the document classifier using haystack, where the name/path of model
    in HF-hub as string is used to fetch the model object.Either configfile or 
    model should be passed.
    1. https://docs.haystack.deepset.ai/reference/document-classifier-api
    2. https://docs.haystack.deepset.ai/docs/document_classifier
    Params
    --------
    config_file: config file path from which to read the model name
    classifier_name: if modelname is passed, it takes a priority if not \
    found then will look for configfile, else raise error.
    Return: document classifier model
    """
    if not classifier_name:
        if not config_file:
            logging.warning("Pass either model name or config file")
            return
        else:
            config = getconfig(config_file)
            classifier_name = config.get('ghg','MODEL')
    
    logging.info("Loading ghg classifier")    
    doc_classifier = pipeline("text-classification", 
                            model=classifier_name, 
                            top_k =1)

    return doc_classifier


@st.cache_data
def ghg_classification(haystack_doc:pd.DataFrame,
                        threshold:float = 0.5, 
                        classifier_model:pipeline= None
                        )->Tuple[DataFrame,Series]:
    """
    Text-Classification on the list of texts provided. Classifier provides the 
    most appropriate label for each text. It identifies if text contains 'GHG'
    related information or not.
    Params
    ---------
    haystack_doc: List of haystack Documents. The output of Preprocessing Pipeline 
    contains the list of paragraphs in different format,here the list of 
    Haystack Documents is used.
    threshold: threshold value for the model to keep the results from classifier
    classifiermodel: you can pass the classifier model directly,which takes priority
    however if not then looks for model in streamlit session.
    In case of streamlit avoid passing the model directly.
    Returns
    ----------
    df: Dataframe  
    """
    logging.info("Working on GHG Extraction")
    haystack_doc['GHG Label'] = 'NA'
    haystack_doc['GHG Score'] = 0.0
    # applying GHG Identifier to only 'Target' paragraphs.
    temp = haystack_doc[haystack_doc['Target Label'] == 'TARGET']
    temp = temp.reset_index(drop=True)
    df = haystack_doc[haystack_doc['Target Label'] == 'NEGATIVE']
    df = df.reset_index(drop=True)

    if not classifier_model:
        classifier_model = st.session_state['ghg_classifier']
    
    results = classifier_model(list(temp.text))
    labels_= [(l[0]['label'],l[0]['score']) for l in results]
    temp['GHG Label'],temp['GHG Score'] = zip(*labels_)
    temp['GHG Label'] = temp['GHG Label'].apply(lambda x: _lab_dict[x])
    # merge back Target and non-Target dataframe
    df = pd.concat([df,temp])
    df = df.reset_index(drop =True)
    df['GHG Score'] = df['GHG Score'].round(2)
    df.index += 1

    return df