|
from haystack.nodes import TransformersDocumentClassifier
|
|
from haystack.schema import Document
|
|
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
|
|
|
|
|
|
_lab_dict = {
|
|
'NEGATIVE':'NO GHG TARGET',
|
|
'TARGET':'GHG TARGET',
|
|
}
|
|
|
|
@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. 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 GHG Extraction")
|
|
haystack_doc['GHG Label'] = 'NA'
|
|
haystack_doc['GHG Score'] = 'NA'
|
|
temp = haystack_doc[haystack_doc['Target Label'] == 'TARGET']
|
|
df = haystack_doc[haystack_doc['Target Label'] == 'NEGATIVE']
|
|
|
|
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_)
|
|
df = pd.concat([df,temp])
|
|
df = df.reset_index(drop =True)
|
|
df.index += 1
|
|
|
|
return df
|
|
|
