File size: 11,747 Bytes
40cca74
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1558ee3
40cca74
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
280332c
40cca74
 
280332c
40cca74
280332c
 
 
 
 
40cca74
 
280332c
 
 
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
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
import requests
import streamlit as st
from bs4 import BeautifulSoup
import pandas as pd
from transformers import pipeline
import plotly.express as px
import time
import io
import os  
from comet_ml import Experiment 
import zipfile
import re
from streamlit_extras.stylable_container import stylable_container


st.set_page_config(layout="wide", page_title="Named Entity Recognition App")




COMET_API_KEY = os.environ.get("COMET_API_KEY")
COMET_WORKSPACE = os.environ.get("COMET_WORKSPACE")
COMET_PROJECT_NAME = os.environ.get("COMET_PROJECT_NAME")

comet_initialized = False
if COMET_API_KEY and COMET_WORKSPACE and COMET_PROJECT_NAME:
    comet_initialized = True



st.subheader("9-Personal Data Named Entity Recognition Web App", divider="rainbow")
st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")

expander = st.expander("**Important notes on the 9-Personal Data Named Entity Recognition Web App**")
expander.write('''
    
    **Named Entities:**
    This 9-Personal Data Named Entity Recognition Web App predicts nine (9) categories:
    
    1. **Account-related information**: Account name, account number, and transaction amounts 
    
    2. **Banking details**: BIC, IBAN, and Bitcoin or Ethereum addresses 
     
    3. **Personal information**: Full name, first name, middle name, last name, gender, and date of birth   
     
    4. **Contact information**: Email, phone number, and street address (including building number, city, county, state, and zip code) 
     
    5. **Job-related data**: Job title, job area, job descriptor, and job type
     
    6. **Financial data**: Credit card number, issuer, CVV, and currency information (code, name, and symbol)  
     
    7. **Digital identifiers**: IP addresses (IPv4 and IPv6), MAC addresses, and user agents 
     
    8. **Online presence**: URL, usernames, and passwords    
     
    9. **Other sensitive data**: SSN, vehicle VIN and VRM, phone IMEI, and nearby GPS coordinates 
    
    Results are presented in an easy-to-read table, visualized in an interactive tree map, pie chart, and bar chart, and are available for download along with a Glossary of tags.
    
    **How to Use:**
    Paste a URL, and then press Enter. If you type or paste text, just press Ctrl + Enter.
    
    **Usage Limits:**
     You can request results up to 10 times.
 
    **Customization:**
    To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts.
    
    **Technical issues:**
    If your connection times out, please refresh the page or reopen the app's URL.
    
    For any errors or inquiries, please contact us at info@nlpblogs.com
    
''')




with st.sidebar:
    container = st.container(border=True)
    container.write("**Named Entity Recognition (NER)** is the task of extracting and tagging entities in text data. Entities can be persons, organizations, locations, countries, products, events etc.")
    st.subheader("Related NLP Web Apps", divider="rainbow")
    st.link_button("8-Named Entity Recognition Web App", "https://nlpblogs.com/shop/named-entity-recognition-ner/8-named-entity-recognition-web-app/", type="primary")
    

if 'source_type_attempts' not in st.session_state:
    st.session_state['source_type_attempts'] = 0
max_attempts = 10 

def clear_url_input():
    
    st.session_state.url = ""

def clear_text_input():
    
    st.session_state.my_text_area = ""

url = st.text_input("Enter URL from the internet, and then press Enter:", key="url")
st.button("Clear URL", on_click=clear_url_input)

text = st.text_area("Type or paste your text below, and then press Ctrl + Enter", key='my_text_area')
st.button("Clear Text", on_click=clear_text_input)


source_type = None
input_content = None
text_to_process = None 

if url:
    source_type = 'url'
    input_content = url
elif text:
    source_type = 'text'
    input_content = text

if source_type:
    
    st.subheader("Results", divider = "rainbow")

    
    if st.session_state['source_type_attempts'] >= max_attempts:
        st.error(f"You have requested results {max_attempts} times. You have reached your daily request limit.")
        st.stop()

    st.session_state['source_type_attempts'] += 1

    
    @st.cache_resource
    def load_ner_model():
        
        return pipeline("token-classification", model="h2oai/deberta_finetuned_pii", aggregation_strategy="first")

    model = load_ner_model()
    experiment = None 

    try:
        if source_type == 'url':
            if not url.startswith(("http://", "https://")):
                st.error("Please enter a valid URL starting with 'http://' or 'https://'.")
            else:
                with st.spinner(f"Fetching and parsing content from **{url}**...", show_time=True):
                    f = requests.get(url, timeout=10)
                    f.raise_for_status()  # Raise an HTTPError for bad responses (4xx or 5xx)
                    soup = BeautifulSoup(f.text, 'html.parser')
                    text_to_process = soup.get_text(separator=' ', strip=True)
                    st.divider()
                    st.write("**Input text content**")
                    st.write(text_to_process[:500] + "..." if len(text_to_process) > 500 else text_to_process)

                    

        elif source_type == 'text':
            text_to_process = text
            st.divider()
            st.write("**Input text content**")
            
            st.write(text_to_process[:500] + "..." if len(text_to_process) > 500 else text_to_process)

        if text_to_process and len(text_to_process.strip()) > 0: 
            with st.spinner("Analyzing text...", show_time=True):
                entities = model(text_to_process)
                data = []
                for entity in entities:
                    data.append({
                        'word': entity['word'],
                        'entity_group': entity['entity_group'],
                        'score': entity['score'],
                        'start': entity['start'], # Include start and end for download
                        'end': entity['end']
                    })
                df = pd.DataFrame(data)

                
                pattern = r'[^\w\s]'
                df['word'] = df['word'].replace(pattern, '', regex=True)
                
                df = df.replace('', 'Unknown')
                st.dataframe(df)

                
                if comet_initialized:
                    experiment = Experiment(
                        api_key=COMET_API_KEY,
                        workspace=COMET_WORKSPACE,
                        project_name=COMET_PROJECT_NAME,
                    )
                    experiment.log_parameter("input_source_type", source_type)
                    experiment.log_parameter("input_content_length", len(input_content))
                    experiment.log_table("predicted_entities", df)

                with st.expander("See Glossary of tags"):
                    st.write('''
                    '**word**': ['entity extracted from your text data']
                    
                    '**score**': ['accuracy score; how accurately a tag has been assigned to a given entity']
            
                    '**entity_group**': ['label (tag) assigned to a given extracted entity']
            
                    '**start**': ['index of the start of the corresponding entity']
            
                    '**end**': ['index of the end of the corresponding entity'] 
                    ''')
                
                
                if not df.empty:
                    
                    st.markdown("---")
                    st.subheader("Treemap", divider="rainbow")
                    fig = px.treemap(df, path=[px.Constant("all"), 'entity_group', 'word'],
                                     values='score', color='entity_group',
                                     )
                    fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
                    st.plotly_chart(fig, use_container_width=True)
                    if comet_initialized and experiment: 
                        experiment.log_figure(figure=fig, figure_name="entity_treemap")

                    
                    
                    value_counts = df['entity_group'].value_counts().reset_index()
                    value_counts.columns = ['entity_group', 'count']

                    col1, col2 = st.columns(2)
                    with col1:
                        st.subheader("Pie Chart", divider="rainbow")
                        fig1 = px.pie(value_counts, values='count', names='entity_group',
                                      hover_data=['count'], labels={'count': 'count'},
                                      title='Percentage of Predicted Labels')
                        fig1.update_traces(textposition='inside', textinfo='percent+label')
                        st.plotly_chart(fig1, use_container_width=True)
                        if comet_initialized and experiment: # Check if experiment is initialized
                            experiment.log_figure(figure=fig1, figure_name="label_pie_chart")

                    with col2:
                        st.subheader("Bar Chart", divider="rainbow")
                        fig2 = px.bar(value_counts, x="count", y="entity_group", color="entity_group",
                                      text_auto=True, title='Occurrences of Predicted Labels')
                        st.plotly_chart(fig2, use_container_width=True)
                        if comet_initialized and experiment: # Check if experiment is initialized
                            experiment.log_figure(figure=fig2, figure_name="label_bar_chart")
                else:
                    st.warning("No entities were extracted from the provided text.")

                
                
                dfa = pd.DataFrame(
                    data={
                        'word': ['entity extracted from your text data'],
                        'score': ['accuracy score; how accurately a tag has been assigned to a given entity'],
                        'entity_group': ['label (tag) assigned to a given extracted entity'],
                        'start': ['index of the start of the corresponding entity'],
                        'end': ['index of the end of the corresponding entity'],
                    }
                )
                buf = io.BytesIO()
                with zipfile.ZipFile(buf, "w") as myzip:
                    if not df.empty:
                        myzip.writestr("Summary_of_results.csv", df.to_csv(index=False))
                    myzip.writestr("Glossary_of_tags.csv", dfa.to_csv(index=False))

                with stylable_container(
                     key="download_button",
                     css_styles="""button { background-color: yellow; border: 1px solid black; padding: 5px; color: black; }""",
                 ):
                    st.download_button(
                         label="Download zip file",
                         data=buf.getvalue(),
                         file_name="nlpblogs_ner_results.zip",
                         mime="application/zip",)
                    

                st.divider()
        else:
            st.warning("No meaningful text found to process. Please enter a URL or text.")

    
    except Exception as e:
        st.error(f"An unexpected error occurred: {e}")
    finally:
        if comet_initialized and experiment:
            experiment.end()

st.write(f"Number of times you requested results: **{st.session_state['source_type_attempts']}/{max_attempts}**")