File size: 43,020 Bytes
948e385
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Filename: Fazni_Resume.pdf\n",
      "Text: FAZNI FAROOKAI/ML /ne /♀nedn Farook Fazni | Linked In Hugging Face SKILLSPython Data Analytics SQLTensorflow Visualization Research Py Spark Neural Network Excel Power BI Transformers Numpy Generative AI Langchain Streamlit LLM MLOps Keras Scikit-Learn Cloud Platform(Azure,Oracle)Azure Synapse Analytics Pandas Azure Machine Learning Studio Oracle integration Cloud Azure Dev Ops STRENGTH•Analytical Skills•Programming Proficiency•Problem-Solving Ability•Data Engineering•Deep Learning Expertise•Cloud Computing Skills•Collaborative Team Player•Continuous Learning PROJECTSResume Filter using Skills Self ProjectὌNov 2023 – present Colombo•Developed a role prediction model using Hugging Face’s pre-trained model.•Trained the model on a custom datasetwith diverse skills and associated roles.•Integrated the model into a user-friendlyinterface using Streamlit.•Implemented Lang Chain for advancednatural language processing capabilities.•Used Bard API to enable dynamic Question-Answering (QA) based onresume content.•Ongoing project with continuousenhancements and refinements.•Model and dataset hosted on Hugging Face for accessibility and collaboration.•Technologies used: Hugging Facepre-trained model, Streamlit, Lang Chain,Bard API.EXPERIENCEAssociate Engineer - AI/MLVirtusa Pvt LtdὌDec 2022 – Present Dr Danister De Silva Mawatha, Colombo•Spearheaded data prepossessing tasks in Azure Synapse Analyticsusing Py Spark, ensuring efficient and scalable data transformationsfor various projects.•Proficiently designed and implemented data pipelines using Azure Synapse Pipelines, ensuring efficient data movement andtransformation.•Monitored and optimized Azure Synapse Pipelines for performance,reliability, and scalability, contributing to the overall stability of dataworkflows.•Successfully integrated Oracle systems into the workflow,streamlining data processes and enhancing overall system efficiency.•Demonstrated proficiency in working with Azure Blob Storage,managing and optimizing data storage solutions.•Gained valuable experience in data visualization by utilizing Power BI,contributing to the creation of insightful and visually appealingreports.•Demonstrated proficiency in working with Oracle Bucket Storage and Oracle Data Science Platform, contributing to efficient data storageand advanced analytics solutions.•Demonstrated proficiency in Agile methodologies, particularly Scrum,through active involvement in daily Scrum meetings, sprint planning,and retrospectives.•Utilized Azure Dev Ops to manage project tasks, user stories, andbacklogs, ensuring streamlined development workflows and timelydelivery of high-quality software solutions.Trainee Associate Software Engineer)Virtusa Pvt LtdὌMar 2022 – Nov 2022 Dr Danister De Silva Mawatha, Colombo•Completed an extensive Spring Boot training program, gaininghands-on experience in developing robust and scalable Javaapplications.•Completed comprehensive training in Angular and React frameworks,acquiring skills in front-end development and building dynamic userinterfaces.EDUCATIONB.Sc(Hons) Computer Science and Technology Uva Wellassa University of Sri LankaὌ2018 – 2022CERTIFICATIONSDeep Learning Specialization Certificate CourseraὌOct 2021\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import re\n",
    "from PyPDF2 import PdfReader\n",
    "\n",
    "def preprocess_text(text):\n",
    "    # Your preprocessing steps here...\n",
    "    text = re.sub(r'\\n|\\t', '', text)\n",
    "    text = re.sub(r'\\s[A-Z]\\s', ' ', text)\n",
    "    text = re.sub(r'\\S+@\\S+', '', text)\n",
    "    text = re.sub(r'\\d{2}[-/]\\d{2}[-/]\\d{4}', '', text)\n",
    "    text = re.sub(r'\\+\\d{2}\\s?\\d{2,3}\\s?\\d{3,4}\\s?\\d{4}', '', text)\n",
    "    text = re.sub(r'Issued\\s\\w+\\s\\d{4}Credential ID \\w+', '', text)\n",
    "    text = re.sub(r'\\s+', ' ', text)\n",
    "    text = re.sub(r'(?<=[a-z])(?=[A-Z])', ' ', text)\n",
    "    return text\n",
    "\n",
    "def get_pdf_text(pdfs, preprocess=True):\n",
    "    if isinstance(pdfs, str):\n",
    "        # Handle a single PDF file\n",
    "        pdfs = [pdfs]\n",
    "\n",
    "    all_text = []\n",
    "    for pdf_path in pdfs:\n",
    "        # Process each PDF file\n",
    "        pdf_reader = PdfReader(pdf_path)\n",
    "\n",
    "        # Get the filename of the PDF\n",
    "        filename = pdf_path.split(\"/\")[-1]\n",
    "\n",
    "        text = \"\"\n",
    "        # Read each page\n",
    "        for page in pdf_reader.pages:\n",
    "            # Extract text from each page\n",
    "            text += page.extract_text()\n",
    "\n",
    "        # Preprocess the text if needed\n",
    "        if preprocess:\n",
    "            text = preprocess_text(text)\n",
    "\n",
    "        # Append to the array\n",
    "        all_text.append({\"filename\": filename, \"text\": text})\n",
    "\n",
    "    return all_text\n",
    "\n",
    "# Example usage with a list of PDFs\n",
    "pdf_files = [\"F:/Resume/Fazni_Resume.pdf\"]\n",
    "all_text = get_pdf_text(pdf_files)\n",
    "\n",
    "# Display the preprocessed text from each PDF\n",
    "for pdf_info in all_text:\n",
    "    print(f\"Filename: {pdf_info['filename']}\\nText: {pdf_info['text']}\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'filename': 'Fazni_Resume.pdf',\n",
       "  'text': 'FAZNI FAROOKAI/ML /ne /♀nedn Farook Fazni | Linked In Hugging Face SKILLSPython Data Analytics SQLTensorflow Visualization Research Py Spark Neural Network Excel Power BI Transformers Numpy Generative AI Langchain Streamlit LLM MLOps Keras Scikit-Learn Cloud Platform(Azure,Oracle)Azure Synapse Analytics Pandas Azure Machine Learning Studio Oracle integration Cloud Azure Dev Ops STRENGTH•Analytical Skills•Programming Proficiency•Problem-Solving Ability•Data Engineering•Deep Learning Expertise•Cloud Computing Skills•Collaborative Team Player•Continuous Learning PROJECTSResume Filter using Skills Self ProjectὌNov 2023 – present Colombo•Developed a role prediction model using Hugging Face’s pre-trained model.•Trained the model on a custom datasetwith diverse skills and associated roles.•Integrated the model into a user-friendlyinterface using Streamlit.•Implemented Lang Chain for advancednatural language processing capabilities.•Used Bard API to enable dynamic Question-Answering (QA) based onresume content.•Ongoing project with continuousenhancements and refinements.•Model and dataset hosted on Hugging Face for accessibility and collaboration.•Technologies used: Hugging Facepre-trained model, Streamlit, Lang Chain,Bard API.EXPERIENCEAssociate Engineer - AI/MLVirtusa Pvt LtdὌDec 2022 – Present Dr Danister De Silva Mawatha, Colombo•Spearheaded data prepossessing tasks in Azure Synapse Analyticsusing Py Spark, ensuring efficient and scalable data transformationsfor various projects.•Proficiently designed and implemented data pipelines using Azure Synapse Pipelines, ensuring efficient data movement andtransformation.•Monitored and optimized Azure Synapse Pipelines for performance,reliability, and scalability, contributing to the overall stability of dataworkflows.•Successfully integrated Oracle systems into the workflow,streamlining data processes and enhancing overall system efficiency.•Demonstrated proficiency in working with Azure Blob Storage,managing and optimizing data storage solutions.•Gained valuable experience in data visualization by utilizing Power BI,contributing to the creation of insightful and visually appealingreports.•Demonstrated proficiency in working with Oracle Bucket Storage and Oracle Data Science Platform, contributing to efficient data storageand advanced analytics solutions.•Demonstrated proficiency in Agile methodologies, particularly Scrum,through active involvement in daily Scrum meetings, sprint planning,and retrospectives.•Utilized Azure Dev Ops to manage project tasks, user stories, andbacklogs, ensuring streamlined development workflows and timelydelivery of high-quality software solutions.Trainee Associate Software Engineer)Virtusa Pvt LtdὌMar 2022 – Nov 2022 Dr Danister De Silva Mawatha, Colombo•Completed an extensive Spring Boot training program, gaininghands-on experience in developing robust and scalable Javaapplications.•Completed comprehensive training in Angular and React frameworks,acquiring skills in front-end development and building dynamic userinterfaces.EDUCATIONB.Sc(Hons) Computer Science and Technology Uva Wellassa University of Sri LankaὌ2018 – 2022CERTIFICATIONSDeep Learning Specialization Certificate CourseraὌOct 2021'}]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "text = all_text[0]['text']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'FAZNI FAROOKAI/ML /ne /♀nedn Farook Fazni | Linked In Hugging Face SKILLSPython Data Analytics SQLTensorflow Visualization Research Py Spark Neural Network Excel Power BI Transformers Numpy Generative AI Langchain Streamlit LLM MLOps Keras Scikit-Learn Cloud Platform(Azure,Oracle)Azure Synapse Analytics Pandas Azure Machine Learning Studio Oracle integration Cloud Azure Dev Ops STRENGTH•Analytical Skills•Programming Proficiency•Problem-Solving Ability•Data Engineering•Deep Learning Expertise•Cloud Computing Skills•Collaborative Team Player•Continuous Learning PROJECTSResume Filter using Skills Self ProjectὌNov 2023 – present Colombo•Developed a role prediction model using Hugging Face’s pre-trained model.•Trained the model on a custom datasetwith diverse skills and associated roles.•Integrated the model into a user-friendlyinterface using Streamlit.•Implemented Lang Chain for advancednatural language processing capabilities.•Used Bard API to enable dynamic Question-Answering (QA) based onresume content.•Ongoing project with continuousenhancements and refinements.•Model and dataset hosted on Hugging Face for accessibility and collaboration.•Technologies used: Hugging Facepre-trained model, Streamlit, Lang Chain,Bard API.EXPERIENCEAssociate Engineer - AI/MLVirtusa Pvt LtdὌDec 2022 – Present Dr Danister De Silva Mawatha, Colombo•Spearheaded data prepossessing tasks in Azure Synapse Analyticsusing Py Spark, ensuring efficient and scalable data transformationsfor various projects.•Proficiently designed and implemented data pipelines using Azure Synapse Pipelines, ensuring efficient data movement andtransformation.•Monitored and optimized Azure Synapse Pipelines for performance,reliability, and scalability, contributing to the overall stability of dataworkflows.•Successfully integrated Oracle systems into the workflow,streamlining data processes and enhancing overall system efficiency.•Demonstrated proficiency in working with Azure Blob Storage,managing and optimizing data storage solutions.•Gained valuable experience in data visualization by utilizing Power BI,contributing to the creation of insightful and visually appealingreports.•Demonstrated proficiency in working with Oracle Bucket Storage and Oracle Data Science Platform, contributing to efficient data storageand advanced analytics solutions.•Demonstrated proficiency in Agile methodologies, particularly Scrum,through active involvement in daily Scrum meetings, sprint planning,and retrospectives.•Utilized Azure Dev Ops to manage project tasks, user stories, andbacklogs, ensuring streamlined development workflows and timelydelivery of high-quality software solutions.Trainee Associate Software Engineer)Virtusa Pvt LtdὌMar 2022 – Nov 2022 Dr Danister De Silva Mawatha, Colombo•Completed an extensive Spring Boot training program, gaininghands-on experience in developing robust and scalable Javaapplications.•Completed comprehensive training in Angular and React frameworks,acquiring skills in front-end development and building dynamic userinterfaces.EDUCATIONB.Sc(Hons) Computer Science and Technology Uva Wellassa University of Sri LankaὌ2018 – 2022CERTIFICATIONSDeep Learning Specialization Certificate CourseraὌOct 2021'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install transformers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install pytorch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "^C\n"
     ]
    }
   ],
   "source": [
    "# !pip install torch torchvision torchaudio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "f:\\Users\\FarookFazni\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoModelForSequenceClassification, AutoTokenizer\n",
    "model_name = \"fazni/distilbert-base-uncased-career-path-prediction\"\n",
    "\n",
    "# Load the model\n",
    "model = AutoModelForSequenceClassification.from_pretrained(model_name)\n",
    "\n",
    "# Load the tokenizer\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "inputs = tokenizer(text, return_tensors=\"pt\",truncation=True, max_length=512)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "outputs = model(**inputs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "probs = outputs.logits.softmax(dim=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Machine Learning Engineer'"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import torch\n",
    "outcome_labels = ['Business Analyst', 'Cyber Security','Data Engineer','Data Science','DevOps','Machine Learning Engineer','Mobile App Developer','Network Engineer','Quality Assurance','Software Engineer']\n",
    "outcome_labels[torch.argmax(probs)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting fileupload\n",
      "  Downloading fileupload-0.1.5-py2.py3-none-any.whl (6.2 kB)\n",
      "Requirement already satisfied: notebook>=4.2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from fileupload) (7.0.6)\n",
      "Requirement already satisfied: ipywidgets>=5.1 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from fileupload) (8.1.1)\n",
      "Requirement already satisfied: traitlets>=4.2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from fileupload) (5.13.0)\n",
      "Requirement already satisfied: jupyterlab-widgets~=3.0.9 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipywidgets>=5.1->fileupload) (3.0.9)\n",
      "Requirement already satisfied: comm>=0.1.3 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipywidgets>=5.1->fileupload) (0.2.0)\n",
      "Requirement already satisfied: widgetsnbextension~=4.0.9 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipywidgets>=5.1->fileupload) (4.0.9)\n",
      "Requirement already satisfied: ipython>=6.1.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipywidgets>=5.1->fileupload) (8.17.2)\n",
      "Requirement already satisfied: notebook-shim<0.3,>=0.2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from notebook>=4.2->fileupload) (0.2.3)\n",
      "Requirement already satisfied: jupyterlab-server<3,>=2.22.1 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from notebook>=4.2->fileupload) (2.25.0)\n",
      "Requirement already satisfied: jupyter-server<3,>=2.4.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from notebook>=4.2->fileupload) (2.10.0)\n",
      "Requirement already satisfied: jupyterlab<5,>=4.0.2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from notebook>=4.2->fileupload) (4.0.8)\n",
      "Requirement already satisfied: tornado>=6.2.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from notebook>=4.2->fileupload) (6.3.3)\n",
      "Requirement already satisfied: jedi>=0.16 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipython>=6.1.0->ipywidgets>=5.1->fileupload) (0.19.1)\n",
      "Requirement already satisfied: matplotlib-inline in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipython>=6.1.0->ipywidgets>=5.1->fileupload) (0.1.6)\n",
      "Requirement already satisfied: exceptiongroup in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipython>=6.1.0->ipywidgets>=5.1->fileupload) (1.1.3)\n",
      "Requirement already satisfied: pygments>=2.4.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipython>=6.1.0->ipywidgets>=5.1->fileupload) (2.16.1)\n",
      "Requirement already satisfied: stack-data in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipython>=6.1.0->ipywidgets>=5.1->fileupload) (0.6.3)\n",
      "Requirement already satisfied: colorama in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipython>=6.1.0->ipywidgets>=5.1->fileupload) (0.4.6)\n",
      "Requirement already satisfied: decorator in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipython>=6.1.0->ipywidgets>=5.1->fileupload) (5.1.1)\n",
      "Requirement already satisfied: prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipython>=6.1.0->ipywidgets>=5.1->fileupload) (3.0.39)\n",
      "Requirement already satisfied: anyio>=3.1.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (4.0.0)\n",
      "Requirement already satisfied: nbconvert>=6.4.4 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (7.11.0)\n",
      "Requirement already satisfied: overrides in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (7.4.0)\n",
      "Requirement already satisfied: prometheus-client in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.18.0)\n",
      "Requirement already satisfied: send2trash>=1.8.2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (1.8.2)\n",
      "Requirement already satisfied: websocket-client in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (1.6.4)\n",
      "Requirement already satisfied: argon2-cffi in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (23.1.0)\n",
      "Requirement already satisfied: terminado>=0.8.3 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.17.1)\n",
      "Requirement already satisfied: pyzmq>=24 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (25.1.1)\n",
      "Requirement already satisfied: pywinpty in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (2.0.12)\n",
      "Requirement already satisfied: jupyter-core!=5.0.*,>=4.12 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (5.5.0)\n",
      "Requirement already satisfied: jupyter-server-terminals in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.4.4)\n",
      "Requirement already satisfied: nbformat>=5.3.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (5.9.2)\n",
      "Requirement already satisfied: jupyter-client>=7.4.4 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (8.6.0)\n",
      "Requirement already satisfied: packaging in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (23.2)\n",
      "Requirement already satisfied: jupyter-events>=0.6.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.9.0)\n",
      "Requirement already satisfied: jinja2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (3.1.2)\n",
      "Requirement already satisfied: tomli in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyterlab<5,>=4.0.2->notebook>=4.2->fileupload) (2.0.1)\n",
      "Requirement already satisfied: ipykernel in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyterlab<5,>=4.0.2->notebook>=4.2->fileupload) (6.26.0)\n",
      "Requirement already satisfied: jupyter-lsp>=2.0.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyterlab<5,>=4.0.2->notebook>=4.2->fileupload) (2.2.0)\n",
      "Requirement already satisfied: async-lru>=1.0.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyterlab<5,>=4.0.2->notebook>=4.2->fileupload) (2.0.4)\n",
      "Requirement already satisfied: requests>=2.31 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (2.31.0)\n",
      "Requirement already satisfied: json5>=0.9.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (0.9.14)\n",
      "Requirement already satisfied: babel>=2.10 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (2.13.1)\n",
      "Requirement already satisfied: jsonschema>=4.18.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (4.19.2)\n",
      "Requirement already satisfied: idna>=2.8 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from anyio>=3.1.0->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (3.4)\n",
      "Requirement already satisfied: sniffio>=1.1 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from anyio>=3.1.0->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (1.3.0)\n",
      "Requirement already satisfied: typing-extensions>=4.0.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from async-lru>=1.0.0->jupyterlab<5,>=4.0.2->notebook>=4.2->fileupload) (4.8.0)\n",
      "Requirement already satisfied: parso<0.9.0,>=0.8.3 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jedi>=0.16->ipython>=6.1.0->ipywidgets>=5.1->fileupload) (0.8.3)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jinja2->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (2.1.3)\n",
      "Requirement already satisfied: rpds-py>=0.7.1 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (0.12.0)\n",
      "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (2023.7.1)\n",
      "Requirement already satisfied: attrs>=22.2.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (23.1.0)\n",
      "Requirement already satisfied: referencing>=0.28.4 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (0.30.2)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-client>=7.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (2.8.2)\n",
      "Requirement already satisfied: pywin32>=300 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-core!=5.0.*,>=4.12->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (306)\n",
      "Requirement already satisfied: platformdirs>=2.5 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-core!=5.0.*,>=4.12->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (3.11.0)\n",
      "Requirement already satisfied: pyyaml>=5.3 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-events>=0.6.0->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (6.0.1)\n",
      "Requirement already satisfied: rfc3986-validator>=0.1.1 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-events>=0.6.0->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.1.1)\n",
      "Requirement already satisfied: rfc3339-validator in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-events>=0.6.0->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.1.4)\n",
      "Requirement already satisfied: python-json-logger>=2.0.4 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jupyter-events>=0.6.0->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (2.0.7)\n",
      "Requirement already satisfied: beautifulsoup4 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (4.12.2)\n",
      "Requirement already satisfied: tinycss2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (1.2.1)\n",
      "Requirement already satisfied: jupyterlab-pygments in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.2.2)\n",
      "Requirement already satisfied: bleach!=5.0.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (6.1.0)\n",
      "Requirement already satisfied: mistune<4,>=2.0.3 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (3.0.2)\n",
      "Requirement already satisfied: pandocfilters>=1.4.1 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (1.5.0)\n",
      "Requirement already satisfied: nbclient>=0.5.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.9.0)\n",
      "Requirement already satisfied: defusedxml in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.7.1)\n",
      "Requirement already satisfied: fastjsonschema in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from nbformat>=5.3.0->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (2.18.1)\n",
      "Requirement already satisfied: wcwidth in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30->ipython>=6.1.0->ipywidgets>=5.1->fileupload) (0.2.9)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from requests>=2.31->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (2023.7.22)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from requests>=2.31->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (2.0.7)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from requests>=2.31->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (3.3.2)\n",
      "Requirement already satisfied: argon2-cffi-bindings in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from argon2-cffi->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (21.2.0)\n",
      "Requirement already satisfied: psutil in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipykernel->jupyterlab<5,>=4.0.2->notebook>=4.2->fileupload) (5.9.6)\n",
      "Requirement already satisfied: nest-asyncio in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipykernel->jupyterlab<5,>=4.0.2->notebook>=4.2->fileupload) (1.5.8)\n",
      "Requirement already satisfied: debugpy>=1.6.5 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from ipykernel->jupyterlab<5,>=4.0.2->notebook>=4.2->fileupload) (1.8.0)\n",
      "Requirement already satisfied: executing>=1.2.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from stack-data->ipython>=6.1.0->ipywidgets>=5.1->fileupload) (2.0.1)\n",
      "Requirement already satisfied: asttokens>=2.1.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from stack-data->ipython>=6.1.0->ipywidgets>=5.1->fileupload) (2.4.1)\n",
      "Requirement already satisfied: pure-eval in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from stack-data->ipython>=6.1.0->ipywidgets>=5.1->fileupload) (0.2.2)\n",
      "Requirement already satisfied: six>=1.12.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from asttokens>=2.1.0->stack-data->ipython>=6.1.0->ipywidgets>=5.1->fileupload) (1.16.0)\n",
      "Requirement already satisfied: webencodings in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from bleach!=5.0.0->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (0.5.1)\n",
      "Requirement already satisfied: uri-template in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (1.3.0)\n",
      "Requirement already satisfied: fqdn in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (1.5.1)\n",
      "Requirement already satisfied: isoduration in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (20.11.0)\n",
      "Requirement already satisfied: webcolors>=1.11 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (1.13)\n",
      "Requirement already satisfied: jsonpointer>1.13 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (2.4)\n",
      "Requirement already satisfied: cffi>=1.0.1 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from argon2-cffi-bindings->argon2-cffi->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (1.16.0)\n",
      "Requirement already satisfied: soupsieve>1.2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from beautifulsoup4->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (2.5)\n",
      "Requirement already satisfied: pycparser in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi->jupyter-server<3,>=2.4.0->notebook>=4.2->fileupload) (2.21)\n",
      "Requirement already satisfied: arrow>=0.15.0 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from isoduration->jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (1.3.0)\n",
      "Requirement already satisfied: types-python-dateutil>=2.8.10 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from arrow>=0.15.0->isoduration->jsonschema>=4.18.0->jupyterlab-server<3,>=2.22.1->notebook>=4.2->fileupload) (2.8.19.14)\n",
      "Installing collected packages: fileupload\n",
      "Successfully installed fileupload-0.1.5\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip available: 22.2.1 -> 23.3.2\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "!pip install fileupload"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting PyPDF2\n",
      "  Using cached pypdf2-3.0.1-py3-none-any.whl (232 kB)\n",
      "Installing collected packages: PyPDF2\n",
      "Successfully installed PyPDF2-3.0.1\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "[notice] A new release of pip available: 22.2.1 -> 23.3.2\n",
      "[notice] To update, run: python.exe -m pip install --upgrade pip\n"
     ]
    }
   ],
   "source": [
    "!pip install PyPDF2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Page 1:\n",
      "FAZNI FAROOK\n",
      "AI/ML Engineer\n",
      "[email protected] /ne+94 757502298 /♀nednFarook Fazni | LinkedIn HuggingFace\n",
      "SKILLS\n",
      "Python Data Analytics SQL\n",
      "Tensorflow Visualization Research\n",
      "PySpark Neural Network Excel\n",
      "PowerBI Transformers Numpy\n",
      "Generative AI Langchain Streamlit\n",
      "LLM MLOps Keras Scikit-Learn\n",
      "Cloud Platform(Azure,Oracle)\n",
      "Azure Synapse Analytics Pandas\n",
      "Azure Machine Learning Studio\n",
      "Oracle integration Cloud\n",
      "Azure DevOps\n",
      "STRENGTH\n",
      "•Analytical Skills\n",
      "•Programming Proficiency\n",
      "•Problem-Solving Ability\n",
      "•Data Engineering\n",
      "•Deep Learning Expertise\n",
      "•Cloud Computing Skills\n",
      "•Collaborative Team Player\n",
      "•Continuous Learning\n",
      "PROJECTS\n",
      "Resume Filter using Skills\n",
      "Self Project\n",
      "ὌNov 2023 – present Colombo\n",
      "•Developed a role prediction model using\n",
      "Hugging Face’s pre-trained model.\n",
      "•Trained the model on a custom dataset\n",
      "with diverse skills and associated roles.\n",
      "•Integrated the model into a user-friendly\n",
      "interface using Streamlit.\n",
      "•Implemented LangChain for advanced\n",
      "natural language processing capabilities.\n",
      "•Used Bard API to enable dynamic\n",
      "Question-Answering (QA) based on\n",
      "resume content.\n",
      "•Ongoing project with continuous\n",
      "enhancements and refinements.\n",
      "•Model and dataset hosted on Hugging\n",
      "Face for accessibility and collaboration.\n",
      "•Technologies used: Hugging Face\n",
      "pre-trained model, Streamlit, LangChain,\n",
      "Bard API.EXPERIENCE\n",
      "Associate Engineer - AI/ML\n",
      "Virtusa Pvt Ltd\n",
      "ὌDec 2022 – Present Dr Danister De Silva Mawatha, Colombo\n",
      "•Spearheaded data prepossessing tasks in Azure Synapse Analytics\n",
      "using PySpark, ensuring efficient and scalable data transformations\n",
      "for various projects.\n",
      "•Proficiently designed and implemented data pipelines using Azure\n",
      "Synapse Pipelines, ensuring efficient data movement and\n",
      "transformation.\n",
      "•Monitored and optimized Azure Synapse Pipelines for performance,\n",
      "reliability, and scalability, contributing to the overall stability of data\n",
      "workflows.\n",
      "•Successfully integrated Oracle systems into the workflow,\n",
      "streamlining data processes and enhancing overall system efficiency.\n",
      "•Demonstrated proficiency in working with Azure Blob Storage,\n",
      "managing and optimizing data storage solutions.\n",
      "•Gained valuable experience in data visualization by utilizing Power BI,\n",
      "contributing to the creation of insightful and visually appealing\n",
      "reports.\n",
      "•Demonstrated proficiency in working with Oracle Bucket Storage and\n",
      "Oracle Data Science Platform, contributing to efficient data storage\n",
      "and advanced analytics solutions.\n",
      "•Demonstrated proficiency in Agile methodologies, particularly Scrum,\n",
      "through active involvement in daily Scrum meetings, sprint planning,\n",
      "and retrospectives.\n",
      "•Utilized Azure DevOps to manage project tasks, user stories, and\n",
      "backlogs, ensuring streamlined development workflows and timely\n",
      "delivery of high-quality software solutions.\n",
      "Trainee Associate Software Engineer)\n",
      "Virtusa Pvt Ltd\n",
      "ὌMar 2022 – Nov 2022 Dr Danister De Silva Mawatha, Colombo\n",
      "•Completed an extensive Spring Boot training program, gaining\n",
      "hands-on experience in developing robust and scalable Java\n",
      "applications.\n",
      "•Completed comprehensive training in Angular and React frameworks,\n",
      "acquiring skills in front-end development and building dynamic user\n",
      "interfaces.\n",
      "EDUCATION\n",
      "B.Sc(Hons) Computer Science and Technology\n",
      "Uva Wellassa University of Sri Lanka\n",
      "Ὄ2018 – 2022\n",
      "CERTIFICATIONS\n",
      "Deep Learning Specialization Certificate\n",
      "Coursera\n",
      "ὌOct 2021\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import PyPDF2\n",
    "\n",
    "def read_pdf(file_path):\n",
    "    with open(file_path, 'rb') as file:\n",
    "        # Create a PDF reader object\n",
    "        pdf_reader = PyPDF2.PdfReader(file)\n",
    "\n",
    "        # Iterate over pages\n",
    "        for page_num in range(len(pdf_reader.pages)):\n",
    "            # Get a specific page\n",
    "            page = pdf_reader.pages[page_num]\n",
    "\n",
    "            # Extract text from the page\n",
    "            text = page.extract_text()\n",
    "\n",
    "            # Print text from the page\n",
    "            print(f\"Page {page_num + 1}:\\n{text}\\n\")\n",
    "\n",
    "# Example usage\n",
    "pdf_file_path = \"F:/Resume/Fazni_Resume.pdf\"\n",
    "pdf = read_pdf(pdf_file_path)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_text = get_pdf_text(pdf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}