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 @st.cache_resource def load_indicatorClassifier(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('indicator','MODEL') logging.info("Loading indicator classifier") # we are using the pipeline as the model is multilabel and DocumentClassifier # from Haystack doesnt support multilabel # in pipeline we use 'sigmoid' to explicitly tell pipeline to make it multilabel # if not then it will automatically use softmax, which is not a desired thing. # doc_classifier = TransformersDocumentClassifier( # model_name_or_path=classifier_name, # task="text-classification", # top_k = None) doc_classifier = pipeline("text-classification", model=classifier_name, return_all_scores=True, function_to_apply= "sigmoid") return doc_classifier @st.cache_data def indicator_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. these labels are in terms of if text belongs to which particular Sustainable Devleopment Goal (SDG). 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 with two columns['SDG:int', 'text'] x: Series object with the unique SDG covered in the document uploaded and the number of times it is covered/discussed/count_of_paragraphs. """ logging.info("Working on Indicator Identification") haystack_doc['Indicator Label'] = 'NA' haystack_doc['PA_check'] = haystack_doc['Policy-Action Label'].apply(lambda x: True if len(x) != 0 else False) df1 = haystack_doc[haystack_doc['PA_check'] == True] df = haystack_doc[haystack_doc['PA_check'] == False] if not classifier_model: classifier_model = st.session_state['indicator_classifier'] predictions = classifier_model(list(df1.text)) list_ = [] for i in range(len(predictions)): temp = predictions[i] placeholder = {} for j in range(len(temp)): placeholder[temp[j]['label']] = temp[j]['score'] list_.append(placeholder) labels_ = [{**list_[l]} for l in range(len(predictions))] truth_df = DataFrame.from_dict(labels_) truth_df = truth_df.round(2) truth_df = truth_df.astype(float) >= threshold truth_df = truth_df.astype(str) categories = list(truth_df.columns) truth_df['Indicator Label'] = truth_df.apply(lambda x: {i if x[i]=='True' else None for i in categories}, axis=1) truth_df['Indicator Label'] = truth_df.apply(lambda x: list(x['Indicator Label'] -{None}),axis=1) df1['Indicator Label'] = list(truth_df['Indicator Label']) df = pd.concat([df,df1]) df = df.drop(columns = ['PA_check']) return df