Palak Deb Patra commited on
Commit
c650664
·
verified ·
1 Parent(s): 0d42106

Upload 4 files

Browse files
Files changed (4) hide show
  1. Tagify.py +154 -0
  2. Tags.py +680 -0
  3. font.css +3 -0
  4. requirements.txt +0 -0
Tagify.py ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """Topic Modelling and Labelling App"""
2
+
3
+ import base64
4
+ import heapq
5
+ import re
6
+
7
+ # Importing packages
8
+ import gensim
9
+ import streamlit as st
10
+ from gensim import corpora, models
11
+ from Tags import industries
12
+
13
+
14
+ # ...
15
+ # Topic Modelling on a given text
16
+ def preprocess_text(text):
17
+ # Replace this with your own preprocessing code
18
+ # This example simply tokenizes the text and removes stop words
19
+ tokens = gensim.utils.simple_preprocess(text)
20
+ stop_words = gensim.parsing.preprocessing.STOPWORDS
21
+ preprocessed_text = [[token for token in tokens if token not in stop_words]]
22
+ return preprocessed_text
23
+
24
+
25
+ def perform_topic_modeling(transcript_text, num_topics=5, num_words=10):
26
+ # Preprocess the transcript text
27
+ # Replace this with your own preprocessing code
28
+ preprocessed_text = preprocess_text(transcript_text)
29
+ # Create a dictionary of all unique words in the transcripts
30
+ dictionary = corpora.Dictionary(preprocessed_text)
31
+ # Convert the preprocessed transcripts into a bag-of-words representation
32
+ corpus = [dictionary.doc2bow(text) for text in preprocessed_text]
33
+ # Train an LDA model with the specified number of topics
34
+ lda_model = models.LdaModel(
35
+ corpus=corpus, id2word=dictionary, num_topics=num_topics
36
+ )
37
+ # Extract the most probable words for each topic
38
+ Topics = []
39
+ for idx, Topic in lda_model.print_topics(-1, num_words=num_words):
40
+ # Extract the top words for each topic and store in a list
41
+ topic_words = [
42
+ word.split("*")[1].replace('"', "").strip() for word in Topic.split("+")
43
+ ]
44
+ Topics.append((f"Topic {idx}", topic_words))
45
+ return Topics
46
+
47
+
48
+ def label_topic(labelling_text):
49
+ """
50
+ Given a piece of text, this function returns the top five industry labels that best match the topics discussed
51
+ in the text.
52
+ """
53
+ # Count the number of occurrences of each keyword in the text for each industry
54
+ counts = {}
55
+ for industry, keywords in industries.items():
56
+ count = sum(
57
+ [
58
+ 1
59
+ for keyword in keywords
60
+ if re.search(r"\b{}\b".format(keyword), labelling_text, re.IGNORECASE)
61
+ ]
62
+ )
63
+ counts[industry] = count
64
+ # Get the top five industries based on their counts
65
+ top_industries = heapq.nlargest(5, counts, key=counts.get)
66
+
67
+ # If only one industry was found, return it
68
+ if len(top_industries) == 1:
69
+ return top_industries[0]
70
+ # If five industries were found, return them both
71
+ else:
72
+ return top_industries
73
+
74
+
75
+ # ...
76
+
77
+ # Streamlit Code
78
+ st.set_page_config(layout="wide")
79
+
80
+ # Font Style
81
+ with open("font.css") as f:
82
+ st.markdown("<style>{}</style>".format(f.read()), unsafe_allow_html=True)
83
+
84
+
85
+ # Display Background
86
+ def add_bg_from_local(image_file):
87
+ with open(image_file, "rb") as image_file:
88
+ encoded_string = base64.b64encode(image_file.read())
89
+ st.markdown(
90
+ f"""
91
+ <style>
92
+ .stApp {{
93
+ background-image: url(data:image/{"png"};base64,{encoded_string.decode()});
94
+ background-size: cover;
95
+ }}
96
+ </style>
97
+ """,
98
+ unsafe_allow_html=True,
99
+ )
100
+
101
+
102
+ add_bg_from_local("Images/background.png")
103
+ # Main content
104
+ st.markdown(
105
+ """
106
+ <style>
107
+ .tagify-title {
108
+ font-size: 62px;
109
+ text-align: center;
110
+ transition: transform 0.2s ease-in-out;
111
+ }
112
+ .tagify-title span {
113
+ transition: color 0.2s ease-in-out;
114
+ }
115
+ .tagify-title:hover span {
116
+ color: #f5fefd; /* Hover color */
117
+ }
118
+ .tagify-title:hover {
119
+ transform: scale(1.15);
120
+ }
121
+ </style>
122
+ """,
123
+ unsafe_allow_html=True,
124
+ )
125
+
126
+ text = "Tagify" # Text to be styled
127
+ colored_text = ''.join(
128
+ ['<span style="color: hsl({}, 70%, 50%);">{}</span>'.format(20 + (i * 30 / len(text)), char) for i, char in
129
+ enumerate(text)])
130
+ colored_text_with_malt = colored_text + ' <span style="color: hsl(40, 70%, 50%);">&#9778;</span>'
131
+ st.markdown(f'<h1 class="tagify-title">{colored_text_with_malt}</h1>', unsafe_allow_html=True)
132
+
133
+ st.markdown(
134
+ '<h2 style="font-size:30px;color: #F5FEFD; text-align: center;">Topic Modelling and Labelling</h2>',
135
+ unsafe_allow_html=True,
136
+ )
137
+
138
+ input_text = st.text_area("Paste your Input Text", height=200)
139
+ if st.button("Analyze Text"):
140
+ col1, col2 = st.columns([2, 2])
141
+ with col1:
142
+ st.info("Text is below")
143
+ st.write(input_text)
144
+ with col2:
145
+ # Perform topic modeling on the transcript text
146
+ topics = perform_topic_modeling(input_text)
147
+ # Display the resulting topics in the app
148
+ st.info("Topics in the Text")
149
+ for topic in topics:
150
+ st.success(f"{topic[0]}: {', '.join(topic[1])}", icon="✅")
151
+ # Label the text with the top five industries
152
+ label = label_topic(input_text)
153
+ st.info("Top Five Industries")
154
+ st.success(f"{', '.join(label)}", icon="✅")
Tags.py ADDED
@@ -0,0 +1,680 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Topic labeling
2
+
3
+ insurance_keywords = [
4
+ "actuary",
5
+ "claims",
6
+ "coverage",
7
+ "deductible",
8
+ "policyholder",
9
+ "premium",
10
+ "underwriter",
11
+ "risk assessment",
12
+ "insurable interest",
13
+ "loss ratio",
14
+ "reinsurance",
15
+ "actuarial tables",
16
+ "property damage",
17
+ "liability",
18
+ "flood insurance",
19
+ "term life insurance",
20
+ "whole life insurance",
21
+ "health insurance",
22
+ "auto insurance",
23
+ "homeowners insurance",
24
+ "marine insurance",
25
+ "crop insurance",
26
+ "catastrophe insurance",
27
+ "umbrella insurance",
28
+ "pet insurance",
29
+ "travel insurance",
30
+ "professional liability insurance",
31
+ "disability insurance",
32
+ "long-term care insurance",
33
+ "annuity",
34
+ "pension plan",
35
+ "group insurance",
36
+ "insurtech",
37
+ "insured",
38
+ "insurer",
39
+ "subrogation",
40
+ "adjuster",
41
+ "third-party administrator",
42
+ "excess and surplus lines",
43
+ "captives",
44
+ "workers compensation",
45
+ "insurance fraud",
46
+ "health savings account",
47
+ "health maintenance organization",
48
+ "preferred provider organization",
49
+ ]
50
+
51
+ finance_keywords = [
52
+ "asset",
53
+ "liability",
54
+ "equity",
55
+ "capital",
56
+ "portfolio",
57
+ "dividend",
58
+ "financial statement",
59
+ "balance sheet",
60
+ "income statement",
61
+ "cash flow statement",
62
+ "statement of retained earnings",
63
+ "financial ratio",
64
+ "valuation",
65
+ "bond",
66
+ "stock",
67
+ "mutual fund",
68
+ "exchange-traded fund",
69
+ "hedge fund",
70
+ "private equity",
71
+ "venture capital",
72
+ "mergers and acquisitions",
73
+ "initial public offering",
74
+ "secondary market",
75
+ "primary market",
76
+ "securities",
77
+ "derivative",
78
+ "option",
79
+ "futures",
80
+ "forward contract",
81
+ "swaps",
82
+ "commodities",
83
+ "credit rating",
84
+ "credit score",
85
+ "credit report",
86
+ "credit bureau",
87
+ "credit history",
88
+ "credit limit",
89
+ "credit utilization",
90
+ "credit counseling",
91
+ "credit card",
92
+ "debit card",
93
+ "ATM",
94
+ "bankruptcy",
95
+ "foreclosure",
96
+ "debt consolidation",
97
+ "taxes",
98
+ "tax return",
99
+ "tax deduction",
100
+ "tax credit",
101
+ "tax bracket",
102
+ "taxable income",
103
+ ]
104
+
105
+ banking_capital_markets_keywords = [
106
+ "bank",
107
+ "credit union",
108
+ "savings and loan association",
109
+ "commercial bank",
110
+ "investment bank",
111
+ "retail bank",
112
+ "wholesale bank",
113
+ "online bank",
114
+ "mobile banking",
115
+ "checking account",
116
+ "savings account",
117
+ "money market account",
118
+ "certificate of deposit",
119
+ "loan",
120
+ "mortgage",
121
+ "home equity loan",
122
+ "line of credit",
123
+ "credit card",
124
+ "debit card",
125
+ "ATM",
126
+ "automated clearing house",
127
+ "wire transfer",
128
+ "ACH",
129
+ "SWIFT",
130
+ "international banking",
131
+ "foreign exchange",
132
+ "forex",
133
+ "currency exchange",
134
+ "central bank",
135
+ "Federal Reserve",
136
+ "interest rate",
137
+ "inflation",
138
+ "deflation",
139
+ "monetary policy",
140
+ "fiscal policy",
141
+ "quantitative easing",
142
+ "securities",
143
+ "stock",
144
+ "bond",
145
+ "mutual fund",
146
+ "exchange-traded fund",
147
+ "hedge fund",
148
+ "private equity",
149
+ "venture capital",
150
+ "investment management",
151
+ "portfolio management",
152
+ "wealth management",
153
+ "financial planning",
154
+ ]
155
+
156
+ healthcare_life_sciences_keywords = [
157
+ "medical device",
158
+ "pharmaceutical",
159
+ "biotechnology",
160
+ "clinical trial",
161
+ "FDA",
162
+ "healthcare provider",
163
+ "healthcare plan",
164
+ "healthcare insurance",
165
+ "patient",
166
+ "doctor",
167
+ "nurse",
168
+ "pharmacist",
169
+ "hospital",
170
+ "clinic",
171
+ "healthcare system",
172
+ "healthcare policy",
173
+ "public health",
174
+ "healthcare IT",
175
+ "electronic health record",
176
+ "telemedicine",
177
+ "personalized medicine",
178
+ "genomics",
179
+ "proteomics",
180
+ "clinical research",
181
+ "drug development",
182
+ "drug discovery",
183
+ "medicine",
184
+ "health",
185
+ ]
186
+
187
+ law_keywords = [
188
+ "law",
189
+ "legal",
190
+ "attorney",
191
+ "lawyer",
192
+ "litigation",
193
+ "arbitration",
194
+ "dispute resolution",
195
+ "contract law",
196
+ "intellectual property",
197
+ "corporate law",
198
+ "labor law",
199
+ "tax law",
200
+ "real estate law",
201
+ "environmental law",
202
+ "criminal law",
203
+ "family law",
204
+ "immigration law",
205
+ "bankruptcy law",
206
+ ]
207
+
208
+ sports_keywords = [
209
+ "sports",
210
+ "football",
211
+ "basketball",
212
+ "baseball",
213
+ "hockey",
214
+ "soccer",
215
+ "golf",
216
+ "tennis",
217
+ "olympics",
218
+ "athletics",
219
+ "coaching",
220
+ "sports management",
221
+ "sports medicine",
222
+ "sports psychology",
223
+ "sports broadcasting",
224
+ "sports journalism",
225
+ "esports",
226
+ "fitness",
227
+ ]
228
+
229
+ media_keywords = [
230
+ "media",
231
+ "entertainment",
232
+ "film",
233
+ "television",
234
+ "radio",
235
+ "music",
236
+ "news",
237
+ "journalism",
238
+ "publishing",
239
+ "public relations",
240
+ "advertising",
241
+ "marketing",
242
+ "social media",
243
+ "digital media",
244
+ "animation",
245
+ "graphic design",
246
+ "web design",
247
+ "video production",
248
+ ]
249
+
250
+ manufacturing_keywords = [
251
+ "manufacturing",
252
+ "production",
253
+ "assembly",
254
+ "logistics",
255
+ "supply chain",
256
+ "quality control",
257
+ "lean manufacturing",
258
+ "six sigma",
259
+ "industrial engineering",
260
+ "process improvement",
261
+ "machinery",
262
+ "automation",
263
+ "aerospace",
264
+ "automotive",
265
+ "chemicals",
266
+ "construction materials",
267
+ "consumer goods",
268
+ "electronics",
269
+ "semiconductors",
270
+ ]
271
+
272
+ automobile_keywords = [
273
+ "automotive",
274
+ "cars",
275
+ "trucks",
276
+ "SUVs",
277
+ "electric vehicles",
278
+ "hybrid vehicles",
279
+ "autonomous " "vehicles",
280
+ "car manufacturing",
281
+ "automotive design",
282
+ "car dealerships",
283
+ "auto parts",
284
+ "vehicle maintenance",
285
+ "car rental",
286
+ "fleet management",
287
+ "telematics",
288
+ ]
289
+
290
+ telecom_keywords = [
291
+ "telecom",
292
+ "telecommunications",
293
+ "wireless",
294
+ "networks",
295
+ "internet",
296
+ "broadband",
297
+ "fiber optics",
298
+ "5G",
299
+ "telecom infrastructure",
300
+ "telecom equipment",
301
+ "VoIP",
302
+ "satellite communications",
303
+ "mobile devices",
304
+ "smartphones",
305
+ "telecom services",
306
+ "telecom regulation",
307
+ "telecom policy",
308
+ ]
309
+
310
+ digital_world_keywords = [
311
+ "Artificial intelligence",
312
+ "Machine learning",
313
+ "Data Science",
314
+ "Big Data",
315
+ "Cloud Computing",
316
+ "Cybersecurity",
317
+ "Information security",
318
+ "Network security",
319
+ "Blockchain",
320
+ "Cryptocurrency",
321
+ "Internet of things",
322
+ "IoT",
323
+ "Web development",
324
+ "Mobile development",
325
+ "Frontend development",
326
+ "Backend development",
327
+ "Software engineering",
328
+ "Software development",
329
+ "Programming",
330
+ "Database",
331
+ "Data analytics",
332
+ "Business intelligence",
333
+ "DevOps",
334
+ "Agile",
335
+ "Scrum",
336
+ "Product management",
337
+ "Project management",
338
+ "IT consulting",
339
+ "IT service management",
340
+ "ERP",
341
+ "CRM",
342
+ "SaaS",
343
+ "PaaS",
344
+ "IaaS",
345
+ "Virtualization",
346
+ "Artificial reality",
347
+ "AR",
348
+ "Virtual reality",
349
+ "VR",
350
+ "Gaming",
351
+ "E-commerce",
352
+ "Digital marketing",
353
+ "SEO",
354
+ "SEM",
355
+ "Content marketing",
356
+ "Social media marketing",
357
+ "User experience",
358
+ "UX design",
359
+ "UI design",
360
+ "Cloud-native",
361
+ "Microservices",
362
+ "Serverless",
363
+ "Containerization",
364
+ ]
365
+ technology_keywords = [
366
+ "technology",
367
+ "innovation",
368
+ "research",
369
+ "development",
370
+ "software",
371
+ "hardware",
372
+ "artificial intelligence",
373
+ "machine learning",
374
+ "data science",
375
+ "big data",
376
+ "cloud computing",
377
+ "cybersecurity",
378
+ "blockchain",
379
+ "internet of things",
380
+ "IoT",
381
+ "web development",
382
+ "mobile development",
383
+ "data analytics",
384
+ "business intelligence",
385
+ "virtual reality",
386
+ "VR",
387
+ "augmented reality",
388
+ "AR",
389
+ "gaming",
390
+ "e-commerce",
391
+ "digital marketing",
392
+ ]
393
+
394
+ healthcare_keywords = [
395
+ "healthcare",
396
+ "medical",
397
+ "medicine",
398
+ "hospital",
399
+ "clinic",
400
+ "doctor",
401
+ "nurse",
402
+ "pharmacist",
403
+ "patient care",
404
+ "healthcare system",
405
+ "public health",
406
+ "healthcare policy",
407
+ "telemedicine",
408
+ "electronic health records",
409
+ "medical devices",
410
+ "clinical trials",
411
+ "pharmaceuticals",
412
+ ]
413
+
414
+ education_keywords = [
415
+ "education",
416
+ "teaching",
417
+ "learning",
418
+ "school",
419
+ "university",
420
+ "college",
421
+ "student",
422
+ "teacher",
423
+ "curriculum",
424
+ "online education",
425
+ "e-learning",
426
+ "distance learning",
427
+ "educational technology",
428
+ "learning management system",
429
+ "educational resources",
430
+ ]
431
+
432
+ energy_keywords = [
433
+ "energy",
434
+ "renewable energy",
435
+ "solar energy",
436
+ "wind energy",
437
+ "hydropower",
438
+ "nuclear energy",
439
+ "fossil fuels",
440
+ "oil",
441
+ "natural gas",
442
+ "coal",
443
+ "electricity",
444
+ "energy efficiency",
445
+ "smart grid",
446
+ "sustainability",
447
+ ]
448
+
449
+ retail_keywords = [
450
+ "retail",
451
+ "shopping",
452
+ "e-commerce",
453
+ "online shopping",
454
+ "brick and mortar",
455
+ "store",
456
+ "customer",
457
+ "consumer behavior",
458
+ "inventory management",
459
+ "supply chain",
460
+ "logistics",
461
+ "retail analytics",
462
+ ]
463
+
464
+ hospitality_keywords = [
465
+ "hospitality",
466
+ "hotel",
467
+ "restaurant",
468
+ "tourism",
469
+ "travel",
470
+ "hospitality management",
471
+ "customer service",
472
+ "guest experience",
473
+ "hospitality industry",
474
+ "event management",
475
+ ]
476
+
477
+ real_estate_keywords = [
478
+ "real estate",
479
+ "property",
480
+ "home",
481
+ "house",
482
+ "apartment",
483
+ "commercial property",
484
+ "real estate agent",
485
+ "real estate market",
486
+ "mortgage",
487
+ "real estate investment",
488
+ "property management",
489
+ "housing market",
490
+ "rental properties",
491
+ ]
492
+
493
+ agriculture_keywords = [
494
+ "agriculture",
495
+ "farming",
496
+ "crop",
497
+ "livestock",
498
+ "agribusiness",
499
+ "sustainable agriculture",
500
+ "precision agriculture",
501
+ "agricultural technology",
502
+ "food security",
503
+ ]
504
+
505
+ environment_keywords = [
506
+ "environment",
507
+ "sustainability",
508
+ "conservation",
509
+ "climate change",
510
+ "renewable resources",
511
+ "ecology",
512
+ "green energy",
513
+ "eco-friendly",
514
+ "environmental policy",
515
+ "carbon footprint",
516
+ ]
517
+
518
+ art_culture_keywords = [
519
+ "art",
520
+ "culture",
521
+ "creativity",
522
+ "music",
523
+ "film",
524
+ "literature",
525
+ "painting",
526
+ "sculpture",
527
+ "performing arts",
528
+ "cultural heritage",
529
+ "artistic expression",
530
+ ]
531
+
532
+ travel_keywords = [
533
+ "travel",
534
+ "tourism",
535
+ "vacation",
536
+ "holiday",
537
+ "adventure",
538
+ "travel agency",
539
+ "travel planning",
540
+ "travel destination",
541
+ "sightseeing",
542
+ "cruise",
543
+ ]
544
+
545
+ fashion_keywords = [
546
+ "fashion",
547
+ "clothing",
548
+ "apparel",
549
+ "style",
550
+ "designer",
551
+ "fashion trends",
552
+ "fashion industry",
553
+ "fashion show",
554
+ "fashion accessories",
555
+ "fashion retail",
556
+ ]
557
+
558
+ architecture_keywords = [
559
+ "architecture",
560
+ "building",
561
+ "design",
562
+ "construction",
563
+ "architect",
564
+ "urban planning",
565
+ "architecture styles",
566
+ "sustainable architecture",
567
+ "interior design",
568
+ "landscape architecture",
569
+ ]
570
+
571
+ aviation_keywords = [
572
+ "aviation",
573
+ "aircraft",
574
+ "airline",
575
+ "flight",
576
+ "pilot",
577
+ "aviation safety",
578
+ "aerospace",
579
+ "aviation technology",
580
+ "air traffic control",
581
+ "airport",
582
+ ]
583
+
584
+ gaming_keywords = [
585
+ "gaming",
586
+ "video games",
587
+ "gamer",
588
+ "gaming industry",
589
+ "game development",
590
+ "esports",
591
+ "gaming community",
592
+ "gaming platform",
593
+ "online gaming",
594
+ "gaming tournaments",
595
+ ]
596
+
597
+ food_beverage_keywords = [
598
+ "food",
599
+ "beverage",
600
+ "cuisine",
601
+ "restaurant",
602
+ "chef",
603
+ "culinary arts",
604
+ "food industry",
605
+ "food culture",
606
+ "food technology",
607
+ "food sustainability",
608
+ ]
609
+
610
+ fitness_keywords = [
611
+ "fitness",
612
+ "exercise",
613
+ "workout",
614
+ "gym",
615
+ "fitness training",
616
+ "fitness equipment",
617
+ "health and fitness",
618
+ "personal training",
619
+ "fitness classes",
620
+ "wellness",
621
+ ]
622
+
623
+ pharmaceuticals_keywords = [
624
+ "pharmaceuticals",
625
+ "drugs",
626
+ "medicine",
627
+ "pharmaceutical industry",
628
+ "drug development",
629
+ "clinical trials",
630
+ "pharmaceutical research",
631
+ "pharmacy",
632
+ "pharmacology",
633
+ "pharmaceutical manufacturing",
634
+ ]
635
+
636
+ music_keywords = [
637
+ "music",
638
+ "musical",
639
+ "artist",
640
+ "concert",
641
+ "music production",
642
+ "music industry",
643
+ "music performance",
644
+ "music streaming",
645
+ "music festival",
646
+ "music education",
647
+ ]
648
+
649
+ industries = {
650
+ "Insurance": insurance_keywords,
651
+ "Finance": finance_keywords,
652
+ "Banking": banking_capital_markets_keywords,
653
+ "Health": healthcare_life_sciences_keywords,
654
+ "Law": law_keywords,
655
+ "Sports": sports_keywords,
656
+ "Entertainment": media_keywords,
657
+ "Manufacturing": manufacturing_keywords,
658
+ "Automobile": automobile_keywords,
659
+ "Telecom": telecom_keywords,
660
+ "Digital World": digital_world_keywords,
661
+ "Technology": technology_keywords,
662
+ "Healthcare": healthcare_keywords,
663
+ "Education": education_keywords,
664
+ "Energy": energy_keywords,
665
+ "Retail": retail_keywords,
666
+ "Hospitality": hospitality_keywords,
667
+ "Real Estate": real_estate_keywords,
668
+ "Agriculture": agriculture_keywords,
669
+ "Environment": environment_keywords,
670
+ "Art & Culture": art_culture_keywords,
671
+ "Travel": travel_keywords,
672
+ "Fashion": fashion_keywords,
673
+ "Architecture": architecture_keywords,
674
+ "Aviation": aviation_keywords,
675
+ "Gaming": gaming_keywords,
676
+ "Food & Beverage": food_beverage_keywords,
677
+ "Fitness": fitness_keywords,
678
+ "Pharmaceuticals": pharmaceuticals_keywords,
679
+ "Music": music_keywords,
680
+ }
font.css ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ @import url('https://fonts.googleapis.com/css2?family=Open+Sans:wght@300&display=swap');
2
+
3
+ *{font-family: 'Open Sans';}
requirements.txt ADDED
Binary file (1.62 kB). View file