Maria Tsilimos
commited on
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,386 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import requests
|
2 |
+
import streamlit as st
|
3 |
+
from bs4 import BeautifulSoup
|
4 |
+
import pandas as pd
|
5 |
+
from transformers import pipeline
|
6 |
+
import plotly.express as px
|
7 |
+
import time
|
8 |
+
import io
|
9 |
+
import os
|
10 |
+
from comet_ml import Experiment
|
11 |
+
import zipfile
|
12 |
+
import re
|
13 |
+
from streamlit_extras.stylable_container import stylable_container
|
14 |
+
|
15 |
+
|
16 |
+
st.set_page_config(layout="wide", page_title="Named Entity Recognition App")
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
|
21 |
+
COMET_API_KEY = os.environ.get("COMET_API_KEY")
|
22 |
+
COMET_WORKSPACE = os.environ.get("COMET_WORKSPACE")
|
23 |
+
COMET_PROJECT_NAME = os.environ.get("COMET_PROJECT_NAME")
|
24 |
+
|
25 |
+
comet_initialized = False
|
26 |
+
if COMET_API_KEY and COMET_WORKSPACE and COMET_PROJECT_NAME:
|
27 |
+
comet_initialized = True
|
28 |
+
|
29 |
+
|
30 |
+
|
31 |
+
st.subheader("58-Italian Named Entity Recognition Web App", divider="rainbow")
|
32 |
+
st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")
|
33 |
+
|
34 |
+
expander = st.expander("**Important notes on the 58-Italian-Named Entity Recognition Web App**")
|
35 |
+
expander.write('''
|
36 |
+
|
37 |
+
**Named Entities:**
|
38 |
+
This 58-Italian-Named Entity Recognition Web App predicts fifty-eight (58) labels
|
39 |
+
|
40 |
+
("**INDIRIZZO**: Identifica un indirizzo fisico.
|
41 |
+
|
42 |
+
**VALUTA**: Rappresenta una valuta.
|
43 |
+
|
44 |
+
**CVV**: Codice di sicurezza della carta di credito.
|
45 |
+
|
46 |
+
**NUMERO_CONTO**: Numero di un conto bancario.
|
47 |
+
|
48 |
+
**BIC**: Codice identificativo di una banca (Bank Identifier Code).
|
49 |
+
|
50 |
+
**IBAN**: Numero di conto bancario internazionale.
|
51 |
+
|
52 |
+
**STATO**: Identifica un paese o una nazione.
|
53 |
+
|
54 |
+
**NOME**: Riferito al nome di una persona.
|
55 |
+
|
56 |
+
**COGNOME**: Riferito al cognome di una persona.
|
57 |
+
|
58 |
+
**CODICE_POSTALE**: Codice postale di un'area geografica.
|
59 |
+
|
60 |
+
**IP**: Indirizzo IP di un dispositivo in rete.
|
61 |
+
|
62 |
+
**ORARIO**: Riferito a un orario specifico.
|
63 |
+
|
64 |
+
**URL**: Indirizzo web (Uniform Resource Locator).
|
65 |
+
|
66 |
+
**LUOGO**: Identifica un luogo geografico.
|
67 |
+
|
68 |
+
**IMPORTO**: Riferito a una somma di denaro.
|
69 |
+
|
70 |
+
**EMAIL**: Indirizzo di posta elettronica.
|
71 |
+
|
72 |
+
**PASSWORD**: Parola chiave per l'accesso a sistemi protetti.
|
73 |
+
|
74 |
+
**NUMERO_CARTA**: Numero di una carta di credito o debito.
|
75 |
+
|
76 |
+
**TARGA_VEICOLO**: Numero di targa di un veicolo.
|
77 |
+
|
78 |
+
**DATA_NASCITA**: Data di nascita di una persona.
|
79 |
+
|
80 |
+
**DATA_MORTE**: Data di decesso di una persona.
|
81 |
+
|
82 |
+
**RAGIONE_SOCIALE**: Nome legale di un'azienda o entità commerciale.
|
83 |
+
|
84 |
+
**ETA**: Età di una persona.
|
85 |
+
|
86 |
+
**DATA**: Riferita a una data generica.
|
87 |
+
|
88 |
+
**PROFESSIONE**: Occupazione o lavoro di una persona.
|
89 |
+
|
90 |
+
**PIN**: Numero di identificazione personale.
|
91 |
+
|
92 |
+
**NUMERO_TELEFONO**: Numero telefonico.
|
93 |
+
|
94 |
+
**FOGLIO**: Riferito a un foglio di documentazione.
|
95 |
+
|
96 |
+
**PARTICELLA**: Riferito a una particella catastale.
|
97 |
+
|
98 |
+
**CARTELLA_CLINICA**: Documentazione medica di un paziente.
|
99 |
+
|
100 |
+
**MALATTIA**: Identifica una malattia o condizione medica.
|
101 |
+
|
102 |
+
**MEDICINA**: Riferito a un farmaco o trattamento medico.
|
103 |
+
|
104 |
+
**CODICE_FISCALE**: Codice fiscale personale o aziendale.
|
105 |
+
|
106 |
+
**NUMERO_DOCUMENTO**: Numero di un documento ufficiale.
|
107 |
+
|
108 |
+
**STORIA_CLINICA**: Registro delle condizioni mediche di un paziente.
|
109 |
+
|
110 |
+
**AVV_NOTAIO**: Identifica un avvocato o notaio.
|
111 |
+
|
112 |
+
**P_IVA**: Partita IVA di un'azienda o professionista.
|
113 |
+
|
114 |
+
**LEGGE**: Riferito a una legge specifica.
|
115 |
+
|
116 |
+
**TASSO_MUTUO**: Tasso di interesse di un mutuo.
|
117 |
+
|
118 |
+
**N_SENTENZA**: Numero di una sentenza legale.
|
119 |
+
|
120 |
+
**MAPPALE**: Riferito a un mappale catastale.
|
121 |
+
|
122 |
+
**SUBALTERNO**: Riferito a un subalterno catastale.
|
123 |
+
|
124 |
+
**REGIME_PATRIMONIALE**: Stato patrimoniale in ambito legale.
|
125 |
+
|
126 |
+
**STATO_CIVILE**: Stato civile di una persona.
|
127 |
+
|
128 |
+
**BANCA**: Identifica una banca o istituto di credito.
|
129 |
+
|
130 |
+
**BRAND**: Marchio o brand commerciale.
|
131 |
+
|
132 |
+
**NUM_ASSEGNO_BANCARIO**: Numero di un assegno bancario.
|
133 |
+
|
134 |
+
**IMEI**: Numero di identificazione internazionale di un dispositivo mobile.
|
135 |
+
|
136 |
+
**N_LICENZA**: Numero di una licenza specifica.
|
137 |
+
|
138 |
+
**IPV6_1**: Indirizzo IP versione 6.
|
139 |
+
|
140 |
+
**MAC**: Indirizzo MAC di un dispositivo di rete.
|
141 |
+
|
142 |
+
**USER_AGENT**: Identifica il software usato per accedere a una rete.
|
143 |
+
|
144 |
+
**TRIBUNALE**: Identifica un tribunale specifico.
|
145 |
+
|
146 |
+
**STRENGTH**: Riferito alla forza o intensità di del medicinale.
|
147 |
+
|
148 |
+
**FREQUENZA**: Riferito alla frequenza di un trattamento medico.
|
149 |
+
|
150 |
+
**DURATION**: Durata di un evento o trattamento.
|
151 |
+
|
152 |
+
**DOSAGGIO**: Quantità di un medicinale da assumere.
|
153 |
+
|
154 |
+
**FORM**: Forma del medicinale, ad esempio compresse").
|
155 |
+
|
156 |
+
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.
|
157 |
+
|
158 |
+
**How to Use:**
|
159 |
+
Paste a URL, and then press Enter. If you type or paste text, just press Ctrl + Enter.
|
160 |
+
|
161 |
+
**Usage Limits:**
|
162 |
+
You can request results up to 10 times.
|
163 |
+
|
164 |
+
**Customization:**
|
165 |
+
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.
|
166 |
+
|
167 |
+
**Technical issues:**
|
168 |
+
If your connection times out, please refresh the page or reopen the app's URL.
|
169 |
+
|
170 |
+
For any errors or inquiries, please contact us at [email protected]
|
171 |
+
|
172 |
+
''')
|
173 |
+
|
174 |
+
|
175 |
+
|
176 |
+
|
177 |
+
|
178 |
+
|
179 |
+
with st.sidebar:
|
180 |
+
container = st.container(border=True)
|
181 |
+
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.")
|
182 |
+
st.subheader("Related NLP Web Apps", divider="rainbow")
|
183 |
+
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")
|
184 |
+
|
185 |
+
|
186 |
+
if 'source_type_attempts' not in st.session_state:
|
187 |
+
st.session_state['source_type_attempts'] = 0
|
188 |
+
max_attempts = 10
|
189 |
+
|
190 |
+
def clear_url_input():
|
191 |
+
|
192 |
+
st.session_state.url = ""
|
193 |
+
|
194 |
+
def clear_text_input():
|
195 |
+
|
196 |
+
st.session_state.my_text_area = ""
|
197 |
+
|
198 |
+
url = st.text_input("Enter URL from the internet, and then press Enter:", key="url")
|
199 |
+
st.button("Clear URL", on_click=clear_url_input)
|
200 |
+
|
201 |
+
text = st.text_area("Type or paste your text below, and then press Ctrl + Enter", key='my_text_area')
|
202 |
+
st.button("Clear Text", on_click=clear_text_input)
|
203 |
+
|
204 |
+
|
205 |
+
source_type = None
|
206 |
+
input_content = None
|
207 |
+
text_to_process = None
|
208 |
+
|
209 |
+
if url:
|
210 |
+
source_type = 'url'
|
211 |
+
input_content = url
|
212 |
+
elif text:
|
213 |
+
source_type = 'text'
|
214 |
+
input_content = text
|
215 |
+
|
216 |
+
if source_type:
|
217 |
+
|
218 |
+
st.subheader("Results", divider = "rainbow")
|
219 |
+
|
220 |
+
|
221 |
+
if st.session_state['source_type_attempts'] >= max_attempts:
|
222 |
+
st.error(f"You have requested results {max_attempts} times. You have reached your daily request limit.")
|
223 |
+
st.stop()
|
224 |
+
|
225 |
+
st.session_state['source_type_attempts'] += 1
|
226 |
+
|
227 |
+
|
228 |
+
@st.cache_resource
|
229 |
+
def load_ner_model():
|
230 |
+
|
231 |
+
return pipeline("token-classification", model="DeepMount00/Italian_NER_XXL", aggregation_strategy="max")
|
232 |
+
|
233 |
+
model = load_ner_model()
|
234 |
+
experiment = None
|
235 |
+
|
236 |
+
try:
|
237 |
+
if source_type == 'url':
|
238 |
+
if not url.startswith(("http://", "https://")):
|
239 |
+
st.error("Please enter a valid URL starting with 'http://' or 'https://'.")
|
240 |
+
else:
|
241 |
+
with st.spinner(f"Fetching and parsing content from **{url}**...", show_time=True):
|
242 |
+
f = requests.get(url, timeout=10)
|
243 |
+
f.raise_for_status() # Raise an HTTPError for bad responses (4xx or 5xx)
|
244 |
+
soup = BeautifulSoup(f.text, 'html.parser')
|
245 |
+
text_to_process = soup.get_text(separator=' ', strip=True)
|
246 |
+
st.divider()
|
247 |
+
st.write("**Input text content**")
|
248 |
+
st.write(text_to_process[:500] + "..." if len(text_to_process) > 500 else text_to_process)
|
249 |
+
|
250 |
+
|
251 |
+
|
252 |
+
elif source_type == 'text':
|
253 |
+
text_to_process = text
|
254 |
+
st.divider()
|
255 |
+
st.write("**Input text content**")
|
256 |
+
|
257 |
+
st.write(text_to_process[:500] + "..." if len(text_to_process) > 500 else text_to_process)
|
258 |
+
|
259 |
+
if text_to_process and len(text_to_process.strip()) > 0:
|
260 |
+
with st.spinner("Analyzing text...", show_time=True):
|
261 |
+
entities = model(text_to_process)
|
262 |
+
data = []
|
263 |
+
for entity in entities:
|
264 |
+
data.append({
|
265 |
+
'word': entity['word'],
|
266 |
+
'entity_group': entity['entity_group'],
|
267 |
+
'score': entity['score'],
|
268 |
+
'start': entity['start'], # Include start and end for download
|
269 |
+
'end': entity['end']
|
270 |
+
})
|
271 |
+
df = pd.DataFrame(data)
|
272 |
+
|
273 |
+
|
274 |
+
pattern = r'[^\w\s]'
|
275 |
+
df['word'] = df['word'].replace(pattern, '', regex=True)
|
276 |
+
|
277 |
+
df = df.replace('', 'Unknown')
|
278 |
+
st.dataframe(df)
|
279 |
+
|
280 |
+
|
281 |
+
if comet_initialized:
|
282 |
+
experiment = Experiment(
|
283 |
+
api_key=COMET_API_KEY,
|
284 |
+
workspace=COMET_WORKSPACE,
|
285 |
+
project_name=COMET_PROJECT_NAME,
|
286 |
+
)
|
287 |
+
experiment.log_parameter("input_source_type", source_type)
|
288 |
+
experiment.log_parameter("input_content_length", len(input_content))
|
289 |
+
experiment.log_table("predicted_entities", df)
|
290 |
+
|
291 |
+
with st.expander("See Glossary of tags"):
|
292 |
+
st.write('''
|
293 |
+
'**word**': ['entity extracted from your text data']
|
294 |
+
|
295 |
+
'**score**': ['accuracy score; how accurately a tag has been assigned to a given entity']
|
296 |
+
|
297 |
+
'**entity_group**': ['label (tag) assigned to a given extracted entity']
|
298 |
+
|
299 |
+
'**start**': ['index of the start of the corresponding entity']
|
300 |
+
|
301 |
+
'**end**': ['index of the end of the corresponding entity']
|
302 |
+
|
303 |
+
''')
|
304 |
+
|
305 |
+
|
306 |
+
if not df.empty:
|
307 |
+
|
308 |
+
st.markdown("---")
|
309 |
+
st.subheader("Treemap", divider="rainbow")
|
310 |
+
fig = px.treemap(df, path=[px.Constant("all"), 'entity_group', 'word'],
|
311 |
+
values='score', color='entity_group',
|
312 |
+
)
|
313 |
+
fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
|
314 |
+
st.plotly_chart(fig, use_container_width=True)
|
315 |
+
if comet_initialized and experiment:
|
316 |
+
experiment.log_figure(figure=fig, figure_name="entity_treemap")
|
317 |
+
|
318 |
+
|
319 |
+
|
320 |
+
value_counts = df['entity_group'].value_counts().reset_index()
|
321 |
+
value_counts.columns = ['entity_group', 'count']
|
322 |
+
|
323 |
+
col1, col2 = st.columns(2)
|
324 |
+
with col1:
|
325 |
+
st.subheader("Pie Chart", divider="rainbow")
|
326 |
+
fig1 = px.pie(value_counts, values='count', names='entity_group',
|
327 |
+
hover_data=['count'], labels={'count': 'count'},
|
328 |
+
title='Percentage of Predicted Labels')
|
329 |
+
fig1.update_traces(textposition='inside', textinfo='percent+label')
|
330 |
+
st.plotly_chart(fig1, use_container_width=True)
|
331 |
+
if comet_initialized and experiment: # Check if experiment is initialized
|
332 |
+
experiment.log_figure(figure=fig1, figure_name="label_pie_chart")
|
333 |
+
|
334 |
+
with col2:
|
335 |
+
st.subheader("Bar Chart", divider="rainbow")
|
336 |
+
fig2 = px.bar(value_counts, x="count", y="entity_group", color="entity_group",
|
337 |
+
text_auto=True, title='Occurrences of Predicted Labels')
|
338 |
+
st.plotly_chart(fig2, use_container_width=True)
|
339 |
+
if comet_initialized and experiment: # Check if experiment is initialized
|
340 |
+
experiment.log_figure(figure=fig2, figure_name="label_bar_chart")
|
341 |
+
else:
|
342 |
+
st.warning("No entities were extracted from the provided text.")
|
343 |
+
|
344 |
+
|
345 |
+
|
346 |
+
dfa = pd.DataFrame(
|
347 |
+
data={
|
348 |
+
'word': ['entity extracted from your text data'],
|
349 |
+
'score': ['accuracy score; how accurately a tag has been assigned to a given entity'],
|
350 |
+
'entity_group': ['label (tag) assigned to a given extracted entity'],
|
351 |
+
'start': ['index of the start of the corresponding entity'],
|
352 |
+
'end': ['index of the end of the corresponding entity'],
|
353 |
+
|
354 |
+
|
355 |
+
}
|
356 |
+
)
|
357 |
+
buf = io.BytesIO()
|
358 |
+
with zipfile.ZipFile(buf, "w") as myzip:
|
359 |
+
if not df.empty:
|
360 |
+
myzip.writestr("Summary_of_results.csv", df.to_csv(index=False))
|
361 |
+
myzip.writestr("Glossary_of_tags.csv", dfa.to_csv(index=False))
|
362 |
+
|
363 |
+
with stylable_container(
|
364 |
+
key="download_button",
|
365 |
+
css_styles="""button { background-color: yellow; border: 1px solid black; padding: 5px; color: black; }""",
|
366 |
+
):
|
367 |
+
st.download_button(
|
368 |
+
label="Download zip file",
|
369 |
+
data=buf.getvalue(),
|
370 |
+
file_name="nlpblogs_ner_results.zip",
|
371 |
+
mime="application/zip",)
|
372 |
+
|
373 |
+
|
374 |
+
|
375 |
+
st.divider()
|
376 |
+
else:
|
377 |
+
st.warning("No meaningful text found to process. Please enter a URL or text.")
|
378 |
+
|
379 |
+
|
380 |
+
except Exception as e:
|
381 |
+
st.error(f"An unexpected error occurred: {e}")
|
382 |
+
finally:
|
383 |
+
if comet_initialized and experiment:
|
384 |
+
experiment.end()
|
385 |
+
|
386 |
+
st.write(f"Number of times you requested results: **{st.session_state['source_type_attempts']}/{max_attempts}**")
|