File size: 5,077 Bytes
cc0fb09
 
 
 
 
 
 
 
e5b30ca
ab71d04
cd7bf6b
cc0fb09
46f16fa
cc0fb09
 
 
cd7bf6b
cc0fb09
5d407bd
cc0fb09
 
5d407bd
cc0fb09
6fef1b7
 
fa5983b
5d407bd
cc0fb09
 
5d407bd
cc0fb09
6fef1b7
5d407bd
cc0fb09
 
 
 
 
5d407bd
cc0fb09
 
 
 
 
5d407bd
cc0fb09
 
5d407bd
cc0fb09
5d407bd
cc0fb09
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd7bf6b
cc0fb09
c6ebb8e
 
 
cd7bf6b
cc0fb09
cd7bf6b
 
cc0fb09
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5cb79de
cc0fb09
5cb79de
cc0fb09
9f5b6c4
 
 
abe2730
5cb79de
9f5b6c4
5cb79de
9f5b6c4
 
 
cc0fb09
f691218
9f5b6c4
69fa6c8
cc0fb09
ed00025
9f5b6c4
 
cc0fb09
 
5cb79de
10d367b
cc0fb09
 
3efd370
cd7bf6b
3efd370
 
 
cd7bf6b
 
3efd370
 
cd7bf6b
3efd370
 
 
 
cd7bf6b
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
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
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 setfit import SetFitModel
from transformers import pipeline

## Labels dictionary ###
label_dict = {
            '0':'NO',
            '1':'YES',
            }

def get_target_labels(preds):

    """
    Function that takes the numerical predictions as an input and returns a list of the labels.
    
    """

    # Turn into list 
    preds_list = preds.to_list()
    
    # Get label names
    predictions_names=[]
    
    # loop through each prediction
    for ele in preds_list:
    
      # see if there is a value 1 and retrieve index
      try:
        index_of_one = ele.index(1)
      except ValueError:
        index_of_one = "NA"
    
      # Retrieve the name of the label (if no prediction made = NA)
      if index_of_one != "NA":
        name  = label_dict[index_of_one]
      else:
        name = "Other"
    
      # Append name to list
      predictions_names.append(name)
    
    return predictions_names

@st.cache_resource
def load_targetClassifier(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('target','MODEL')
    
    logging.info("Loading classifier")  

    # Loading classifier
    doc_classifier = SetFitModel.from_pretrained("leavoigt/vulnerability_target")

    return doc_classifier


@st.cache_data
def target_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. There labels indicate whether the paragraph
    references a specific action, target or measure in the paragraph.
    ---------
    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 target/action identification")
                            
    haystack_doc['Target Label'] = 'NA'
    st.write("haystack_doc")
    st.write(haystack_doc)
                            
    if not classifier_model:

        st.write("No classifier_model")

        classifier_model = st.session_state['target_classifier']
        st.write("classifier model defined")
        
        # Get predictions
        predictions = classifier_model(list(haystack_doc.text))
        st.write("predictions made")
        st.write(predictions)
        # Get labels for predictions
        pred_labels = get_target_labels(predictions)
        st.write("pred_labels")
        st.write(pred_labels)
        # Save labels
        haystack_doc['Target Label'] = pred_labels

        return haystack_doc            
    # logging.info("Working on action/target extraction")
    # if not classifier_model:
#     #     classifier_model = st.session_state['target_classifier']
    
#     # results = classifier_model(list(haystack_doc.text))
#     # labels_= [(l[0]['label'],
#     #            l[0]['score']) for l in results]
           

#     # df1 = DataFrame(labels_, columns=["Target Label","Target Score"])
#     # df = pd.concat([haystack_doc,df1],axis=1)
    
#     # df = df.sort_values(by="Target Score", ascending=False).reset_index(drop=True)
#     # df['Target Score'] = df['Target Score'].round(2)
#     # df.index += 1
#     # # df['Label_def'] = df['Target Label'].apply(lambda i: _lab_dict[i])