File size: 5,019 Bytes
3d8edaf
 
 
 
 
 
 
 
 
 
 
ea00796
 
 
 
 
 
 
3d8edaf
 
 
834345a
 
 
 
 
 
 
 
 
 
 
 
3d8edaf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
834345a
833c58b
3d8edaf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
834de5e
3d8edaf
 
 
2639906
 
3d8edaf
 
 
 
834de5e
3d8edaf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
834345a
3d8edaf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
834345a
3d8edaf
834345a
 
c0c151c
834345a
3d8edaf
 
 
 
 
2639906
5ad0224
3d8edaf
 
 
 
e557652
661c2a9
3d8edaf
58555b2
2639906
 
a701044
79c52cc
a701044
661c2a9
 
3d8edaf
 
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
149
150
151
152
153
import streamlit as st
from predict import run_prediction
from io import StringIO
import json

st.set_page_config(layout="wide")
st.cache(show_spinner=False, persist=True)


def load_questions():
    questions = []
    with open('data/questions.txt') as f:
        questions = f.readlines()

    # questions = []
    # for i, q in enumerate(data['data'][0]['paragraphs'][0]['qas']):
    #     question = data['data'][0]['paragraphs'][0]['qas'][i]['question']
    #     questions.append(question)
    return questions


def load_questions_short():
    questions_short = []
    with open('data/questions_short.txt') as f:
        questions_short = f.readlines()

    # questions = []
    # for i, q in enumerate(data['data'][0]['paragraphs'][0]['qas']):
    #     question = data['data'][0]['paragraphs'][0]['qas'][i]['question']
    #     questions.append(question)
    return questions_short


st.cache(show_spinner=False, persist=True)


def load_contracts():
    with open('data/test.json') as json_file:
        data = json.load(json_file)

    contracts = []
    for i, q in enumerate(data['data']):
        contract = ' '.join(data['data'][i]['paragraphs'][0]['context'].split())
        contracts.append(contract)
    return contracts


questions = load_questions()
questions_short = load_questions_short()
# contracts = load_contracts()

### DEFINE SIDEBAR
st.sidebar.title("Interactive Contract Analysis")
st.sidebar.markdown(
"""
Process text with [Huggingface](https://huggingface.co) models and visualize the results.  

This model uses a pretrained snapshot trained on the [Atticus](https://www.atticusprojectai.org/) Dataset - CUAD


"""
)

st.sidebar.header("Contract Selection")

# select contract
contracts_drop = ['contract 1', 'contract 2', 'contract 3']
contracts_files = ['contract-1.txt', 'contract-2.txt', 'contract-3.txt']
contract = st.sidebar.selectbox('Please Select a Contract', contracts_drop)


idx = contracts_drop.index(contract)
with open('data/'+contracts_files[idx]) as f:
    contract_data = f.read()

# upload contract
user_upload = st.sidebar.file_uploader('Please upload your own', type=['docx', 'pdf', 'txt'],
                                       accept_multiple_files=False)
print(user_upload)

# process upload
if user_upload is not None:
    print(user_upload.name, user_upload.type)
    extension = user_upload.name.split('.')[-1].lower()
    if extension == 'txt':
        print('text file uploaded')
         # To convert to a string based IO:
        stringio = StringIO(user_upload.getvalue().decode("utf-8"))

        # To read file as string:
        contract_data = stringio.read()

    elif extension == 'pdf':
        import PyPDF4
        try:
            # Extracting Text from PDFs
            pdfReader = PyPDF4.PdfFileReader(user_upload)
            print(pdfReader.numPages)
            contract_data = ''
            for i in range(0, pdfReader.numPages):

                print(i)
                pageobj = pdfReader.getPage(i)
                contract_data = contract_data + pageobj.extractText()
        except:
            st.warning('Unable to read PDF, please try another file')

    elif extension == 'docx':
        import docx2txt

        contract_data = docx2txt.process(user_upload)

    else:
        st.warning('Unknown uploaded file type, please try again')

results_drop = ['1', '2', '3']
number_results = st.sidebar.selectbox('Select number of results', results_drop)

### DEFINE MAIN PAGE
st.header("Legal Contract Review Demo")
st.write("This demo uses the CUAD dataset for Contract Understanding.")

paragraph = st.text_area(label="Contract", value=contract_data, height=300)

questions_drop = questions_short
question_short = st.selectbox('Choose one of the 41 queries from the CUAD dataset:', questions_drop)
idxq = questions_drop.index(question_short)
question = questions[idxq]

if st.button('Analyze'):
    if (not len(paragraph)==0) and not (len(question)==0):
        print('getting predictions')
        with st.spinner(text='Analysis in progress...'):
            predictions = run_prediction([question], paragraph, 'akdeniz27/roberta-base-cuad',
                                         n_best_size=int(number_results))
        if predictions['0'] == "":
            answer = 'No answer found in document'
        else:
            if number_results == '1':
                answer = f"Answer: {predictions['0']}"
                # st.text_area(label="Answer", value=f"{answer}")
            else:
                answer = ""
                with open("nbest.json") as jf:
                    data = json.load(jf)
                    for i in range(int(number_results)):
                        answer += f"Answer {i+1}: {data['0'][i]['text']} -- \n"
                        answer += f"Probability: {round(data['0'][i]['probability']*100,1)}%\n\n"
            st.success(answer)
            # st.success("Successfully processed contract!")
    else:
        st.write("Unable to call model, please select question and contract")