File size: 4,750 Bytes
031e5e2 6d737a4 031e5e2 6d737a4 031e5e2 6d737a4 031e5e2 6d737a4 031e5e2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
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 haystack.nodes import TransformersDocumentClassifier
from transformers import pipeline
@st.cache_resource
def load_sectorClassifier(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('sector','MODEL')
logging.info("Loading sector 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 sector_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 Sector Identification")
haystack_doc['Sector Label'] = 'NA'
df1 = haystack_doc[haystack_doc['Target Label'] == 'TARGET']
df = haystack_doc[haystack_doc['Target Label'] == 'NEGATIVE']
if not classifier_model:
classifier_model = st.session_state['sector_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['Sector Label'] = truth_df.apply(lambda x: {i if x[i]=='True' else
None for i in categories}, axis=1)
truth_df['Sector Label'] = truth_df.apply(lambda x: list(x['Sector Label']
-{None}),axis=1)
df1['Sector Label'] = list(truth_df['Sector Label'])
df = pd.concat([df,df1])
return df
|