added research file
Browse files- Components/model_Responce.py +2 -2
- Research/Research.ipynb +571 -0
Components/model_Responce.py
CHANGED
@@ -53,8 +53,8 @@ def model_prediction(text, model=model, tokenizer=tokenizer, labels=outcome_labe
|
|
53 |
|
54 |
# Hugging face model
|
55 |
# Tokenize the text
|
56 |
-
inputs = tokenizer(text, return_tensors="pt")
|
57 |
-
outputs = model(inputs)
|
58 |
|
59 |
# Get the predicted class probabilities
|
60 |
probs = outputs.logits.softmax(dim=-1)
|
|
|
53 |
|
54 |
# Hugging face model
|
55 |
# Tokenize the text
|
56 |
+
inputs = tokenizer(text, return_tensors="pt",truncation=True, max_length=512)
|
57 |
+
outputs = model(**inputs)
|
58 |
|
59 |
# Get the predicted class probabilities
|
60 |
probs = outputs.logits.softmax(dim=-1)
|
Research/Research.ipynb
ADDED
@@ -0,0 +1,571 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 3,
|
6 |
+
"metadata": {},
|
7 |
+
"outputs": [
|
8 |
+
{
|
9 |
+
"name": "stdout",
|
10 |
+
"output_type": "stream",
|
11 |
+
"text": [
|
12 |
+
"Filename: Fazni_Resume.pdf\n",
|
13 |
+
"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",
|
14 |
+
"\n"
|
15 |
+
]
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"source": [
|
19 |
+
"import re\n",
|
20 |
+
"from PyPDF2 import PdfReader\n",
|
21 |
+
"\n",
|
22 |
+
"def preprocess_text(text):\n",
|
23 |
+
" # Your preprocessing steps here...\n",
|
24 |
+
" text = re.sub(r'\\n|\\t', '', text)\n",
|
25 |
+
" text = re.sub(r'\\s[A-Z]\\s', ' ', text)\n",
|
26 |
+
" text = re.sub(r'\\S+@\\S+', '', text)\n",
|
27 |
+
" text = re.sub(r'\\d{2}[-/]\\d{2}[-/]\\d{4}', '', text)\n",
|
28 |
+
" text = re.sub(r'\\+\\d{2}\\s?\\d{2,3}\\s?\\d{3,4}\\s?\\d{4}', '', text)\n",
|
29 |
+
" text = re.sub(r'Issued\\s\\w+\\s\\d{4}Credential ID \\w+', '', text)\n",
|
30 |
+
" text = re.sub(r'\\s+', ' ', text)\n",
|
31 |
+
" text = re.sub(r'(?<=[a-z])(?=[A-Z])', ' ', text)\n",
|
32 |
+
" return text\n",
|
33 |
+
"\n",
|
34 |
+
"def get_pdf_text(pdfs, preprocess=True):\n",
|
35 |
+
" if isinstance(pdfs, str):\n",
|
36 |
+
" # Handle a single PDF file\n",
|
37 |
+
" pdfs = [pdfs]\n",
|
38 |
+
"\n",
|
39 |
+
" all_text = []\n",
|
40 |
+
" for pdf_path in pdfs:\n",
|
41 |
+
" # Process each PDF file\n",
|
42 |
+
" pdf_reader = PdfReader(pdf_path)\n",
|
43 |
+
"\n",
|
44 |
+
" # Get the filename of the PDF\n",
|
45 |
+
" filename = pdf_path.split(\"/\")[-1]\n",
|
46 |
+
"\n",
|
47 |
+
" text = \"\"\n",
|
48 |
+
" # Read each page\n",
|
49 |
+
" for page in pdf_reader.pages:\n",
|
50 |
+
" # Extract text from each page\n",
|
51 |
+
" text += page.extract_text()\n",
|
52 |
+
"\n",
|
53 |
+
" # Preprocess the text if needed\n",
|
54 |
+
" if preprocess:\n",
|
55 |
+
" text = preprocess_text(text)\n",
|
56 |
+
"\n",
|
57 |
+
" # Append to the array\n",
|
58 |
+
" all_text.append({\"filename\": filename, \"text\": text})\n",
|
59 |
+
"\n",
|
60 |
+
" return all_text\n",
|
61 |
+
"\n",
|
62 |
+
"# Example usage with a list of PDFs\n",
|
63 |
+
"pdf_files = [\"F:/Resume/Fazni_Resume.pdf\"]\n",
|
64 |
+
"all_text = get_pdf_text(pdf_files)\n",
|
65 |
+
"\n",
|
66 |
+
"# Display the preprocessed text from each PDF\n",
|
67 |
+
"for pdf_info in all_text:\n",
|
68 |
+
" print(f\"Filename: {pdf_info['filename']}\\nText: {pdf_info['text']}\\n\")"
|
69 |
+
]
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"cell_type": "code",
|
73 |
+
"execution_count": 13,
|
74 |
+
"metadata": {},
|
75 |
+
"outputs": [
|
76 |
+
{
|
77 |
+
"data": {
|
78 |
+
"text/plain": [
|
79 |
+
"[{'filename': 'Fazni_Resume.pdf',\n",
|
80 |
+
" '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'}]"
|
81 |
+
]
|
82 |
+
},
|
83 |
+
"execution_count": 13,
|
84 |
+
"metadata": {},
|
85 |
+
"output_type": "execute_result"
|
86 |
+
}
|
87 |
+
],
|
88 |
+
"source": [
|
89 |
+
"all_text"
|
90 |
+
]
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"cell_type": "code",
|
94 |
+
"execution_count": 4,
|
95 |
+
"metadata": {},
|
96 |
+
"outputs": [],
|
97 |
+
"source": [
|
98 |
+
"text = all_text[0]['text']"
|
99 |
+
]
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"cell_type": "code",
|
103 |
+
"execution_count": 5,
|
104 |
+
"metadata": {},
|
105 |
+
"outputs": [
|
106 |
+
{
|
107 |
+
"data": {
|
108 |
+
"text/plain": [
|
109 |
+
"'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'"
|
110 |
+
]
|
111 |
+
},
|
112 |
+
"execution_count": 5,
|
113 |
+
"metadata": {},
|
114 |
+
"output_type": "execute_result"
|
115 |
+
}
|
116 |
+
],
|
117 |
+
"source": [
|
118 |
+
"text"
|
119 |
+
]
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"cell_type": "code",
|
123 |
+
"execution_count": null,
|
124 |
+
"metadata": {},
|
125 |
+
"outputs": [],
|
126 |
+
"source": [
|
127 |
+
"# !pip install transformers"
|
128 |
+
]
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"cell_type": "code",
|
132 |
+
"execution_count": null,
|
133 |
+
"metadata": {},
|
134 |
+
"outputs": [],
|
135 |
+
"source": [
|
136 |
+
"# !pip install pytorch"
|
137 |
+
]
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"cell_type": "code",
|
141 |
+
"execution_count": 2,
|
142 |
+
"metadata": {},
|
143 |
+
"outputs": [
|
144 |
+
{
|
145 |
+
"name": "stdout",
|
146 |
+
"output_type": "stream",
|
147 |
+
"text": [
|
148 |
+
"^C\n"
|
149 |
+
]
|
150 |
+
}
|
151 |
+
],
|
152 |
+
"source": [
|
153 |
+
"# !pip install torch torchvision torchaudio"
|
154 |
+
]
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"cell_type": "code",
|
158 |
+
"execution_count": null,
|
159 |
+
"metadata": {},
|
160 |
+
"outputs": [],
|
161 |
+
"source": [
|
162 |
+
"# !pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118"
|
163 |
+
]
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"cell_type": "code",
|
167 |
+
"execution_count": 1,
|
168 |
+
"metadata": {},
|
169 |
+
"outputs": [
|
170 |
+
{
|
171 |
+
"name": "stderr",
|
172 |
+
"output_type": "stream",
|
173 |
+
"text": [
|
174 |
+
"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",
|
175 |
+
" from .autonotebook import tqdm as notebook_tqdm\n"
|
176 |
+
]
|
177 |
+
}
|
178 |
+
],
|
179 |
+
"source": [
|
180 |
+
"from transformers import AutoModelForSequenceClassification, AutoTokenizer\n",
|
181 |
+
"model_name = \"fazni/distilbert-base-uncased-career-path-prediction\"\n",
|
182 |
+
"\n",
|
183 |
+
"# Load the model\n",
|
184 |
+
"model = AutoModelForSequenceClassification.from_pretrained(model_name)\n",
|
185 |
+
"\n",
|
186 |
+
"# Load the tokenizer\n",
|
187 |
+
"tokenizer = AutoTokenizer.from_pretrained(model_name)"
|
188 |
+
]
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"cell_type": "code",
|
192 |
+
"execution_count": 10,
|
193 |
+
"metadata": {},
|
194 |
+
"outputs": [],
|
195 |
+
"source": [
|
196 |
+
"inputs = tokenizer(text, return_tensors=\"pt\",truncation=True, max_length=512)"
|
197 |
+
]
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"cell_type": "code",
|
201 |
+
"execution_count": 11,
|
202 |
+
"metadata": {},
|
203 |
+
"outputs": [],
|
204 |
+
"source": [
|
205 |
+
"outputs = model(**inputs)"
|
206 |
+
]
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"cell_type": "code",
|
210 |
+
"execution_count": 12,
|
211 |
+
"metadata": {},
|
212 |
+
"outputs": [],
|
213 |
+
"source": [
|
214 |
+
"probs = outputs.logits.softmax(dim=-1)"
|
215 |
+
]
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"cell_type": "code",
|
219 |
+
"execution_count": 13,
|
220 |
+
"metadata": {},
|
221 |
+
"outputs": [
|
222 |
+
{
|
223 |
+
"data": {
|
224 |
+
"text/plain": [
|
225 |
+
"'Machine Learning Engineer'"
|
226 |
+
]
|
227 |
+
},
|
228 |
+
"execution_count": 13,
|
229 |
+
"metadata": {},
|
230 |
+
"output_type": "execute_result"
|
231 |
+
}
|
232 |
+
],
|
233 |
+
"source": [
|
234 |
+
"import torch\n",
|
235 |
+
"outcome_labels = ['Business Analyst', 'Cyber Security','Data Engineer','Data Science','DevOps','Machine Learning Engineer','Mobile App Developer','Network Engineer','Quality Assurance','Software Engineer']\n",
|
236 |
+
"outcome_labels[torch.argmax(probs)]"
|
237 |
+
]
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"cell_type": "code",
|
241 |
+
"execution_count": null,
|
242 |
+
"metadata": {},
|
243 |
+
"outputs": [],
|
244 |
+
"source": []
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"cell_type": "code",
|
248 |
+
"execution_count": null,
|
249 |
+
"metadata": {},
|
250 |
+
"outputs": [],
|
251 |
+
"source": []
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"cell_type": "code",
|
255 |
+
"execution_count": 4,
|
256 |
+
"metadata": {},
|
257 |
+
"outputs": [
|
258 |
+
{
|
259 |
+
"name": "stdout",
|
260 |
+
"output_type": "stream",
|
261 |
+
"text": [
|
262 |
+
"Collecting fileupload\n",
|
263 |
+
" Downloading fileupload-0.1.5-py2.py3-none-any.whl (6.2 kB)\n",
|
264 |
+
"Requirement already satisfied: notebook>=4.2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from fileupload) (7.0.6)\n",
|
265 |
+
"Requirement already satisfied: ipywidgets>=5.1 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from fileupload) (8.1.1)\n",
|
266 |
+
"Requirement already satisfied: traitlets>=4.2 in f:\\machine learning\\python-projects\\llm-model\\cuda\\lib\\site-packages (from fileupload) (5.13.0)\n",
|
267 |
+
"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",
|
268 |
+
"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",
|
269 |
+
"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",
|
270 |
+
"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",
|
271 |
+
"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",
|
272 |
+
"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",
|
273 |
+
"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",
|
274 |
+
"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",
|
275 |
+
"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",
|
276 |
+
"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",
|
277 |
+
"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",
|
278 |
+
"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",
|
279 |
+
"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",
|
280 |
+
"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",
|
281 |
+
"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",
|
282 |
+
"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",
|
283 |
+
"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",
|
284 |
+
"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",
|
285 |
+
"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",
|
286 |
+
"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",
|
287 |
+
"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",
|
288 |
+
"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",
|
289 |
+
"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",
|
290 |
+
"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",
|
291 |
+
"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",
|
292 |
+
"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",
|
293 |
+
"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",
|
294 |
+
"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",
|
295 |
+
"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",
|
296 |
+
"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",
|
297 |
+
"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",
|
298 |
+
"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",
|
299 |
+
"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",
|
300 |
+
"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",
|
301 |
+
"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",
|
302 |
+
"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",
|
303 |
+
"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",
|
304 |
+
"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",
|
305 |
+
"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",
|
306 |
+
"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",
|
307 |
+
"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",
|
308 |
+
"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",
|
309 |
+
"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",
|
310 |
+
"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",
|
311 |
+
"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",
|
312 |
+
"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",
|
313 |
+
"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",
|
314 |
+
"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",
|
315 |
+
"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",
|
316 |
+
"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",
|
317 |
+
"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",
|
318 |
+
"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",
|
319 |
+
"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",
|
320 |
+
"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",
|
321 |
+
"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",
|
322 |
+
"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",
|
323 |
+
"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",
|
324 |
+
"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",
|
325 |
+
"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",
|
326 |
+
"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",
|
327 |
+
"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",
|
328 |
+
"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",
|
329 |
+
"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",
|
330 |
+
"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",
|
331 |
+
"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",
|
332 |
+
"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",
|
333 |
+
"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",
|
334 |
+
"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",
|
335 |
+
"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",
|
336 |
+
"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",
|
337 |
+
"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",
|
338 |
+
"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",
|
339 |
+
"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",
|
340 |
+
"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",
|
341 |
+
"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",
|
342 |
+
"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",
|
343 |
+
"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",
|
344 |
+
"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",
|
345 |
+
"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",
|
346 |
+
"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",
|
347 |
+
"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",
|
348 |
+
"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",
|
349 |
+
"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",
|
350 |
+
"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",
|
351 |
+
"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",
|
352 |
+
"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",
|
353 |
+
"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",
|
354 |
+
"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",
|
355 |
+
"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",
|
356 |
+
"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",
|
357 |
+
"Installing collected packages: fileupload\n",
|
358 |
+
"Successfully installed fileupload-0.1.5\n"
|
359 |
+
]
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"name": "stderr",
|
363 |
+
"output_type": "stream",
|
364 |
+
"text": [
|
365 |
+
"\n",
|
366 |
+
"[notice] A new release of pip available: 22.2.1 -> 23.3.2\n",
|
367 |
+
"[notice] To update, run: python.exe -m pip install --upgrade pip\n"
|
368 |
+
]
|
369 |
+
}
|
370 |
+
],
|
371 |
+
"source": [
|
372 |
+
"!pip install fileupload"
|
373 |
+
]
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"cell_type": "code",
|
377 |
+
"execution_count": 2,
|
378 |
+
"metadata": {},
|
379 |
+
"outputs": [
|
380 |
+
{
|
381 |
+
"name": "stdout",
|
382 |
+
"output_type": "stream",
|
383 |
+
"text": [
|
384 |
+
"Collecting PyPDF2\n",
|
385 |
+
" Using cached pypdf2-3.0.1-py3-none-any.whl (232 kB)\n",
|
386 |
+
"Installing collected packages: PyPDF2\n",
|
387 |
+
"Successfully installed PyPDF2-3.0.1\n"
|
388 |
+
]
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"name": "stderr",
|
392 |
+
"output_type": "stream",
|
393 |
+
"text": [
|
394 |
+
"\n",
|
395 |
+
"[notice] A new release of pip available: 22.2.1 -> 23.3.2\n",
|
396 |
+
"[notice] To update, run: python.exe -m pip install --upgrade pip\n"
|
397 |
+
]
|
398 |
+
}
|
399 |
+
],
|
400 |
+
"source": [
|
401 |
+
"!pip install PyPDF2"
|
402 |
+
]
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"cell_type": "code",
|
406 |
+
"execution_count": 9,
|
407 |
+
"metadata": {},
|
408 |
+
"outputs": [
|
409 |
+
{
|
410 |
+
"name": "stdout",
|
411 |
+
"output_type": "stream",
|
412 |
+
"text": [
|
413 |
+
"Page 1:\n",
|
414 |
+
"FAZNI FAROOK\n",
|
415 |
+
"AI/ML Engineer\n",
|
416 |
+
"[email protected] /ne+94 757502298 /♀nednFarook Fazni | LinkedIn HuggingFace\n",
|
417 |
+
"SKILLS\n",
|
418 |
+
"Python Data Analytics SQL\n",
|
419 |
+
"Tensorflow Visualization Research\n",
|
420 |
+
"PySpark Neural Network Excel\n",
|
421 |
+
"PowerBI Transformers Numpy\n",
|
422 |
+
"Generative AI Langchain Streamlit\n",
|
423 |
+
"LLM MLOps Keras Scikit-Learn\n",
|
424 |
+
"Cloud Platform(Azure,Oracle)\n",
|
425 |
+
"Azure Synapse Analytics Pandas\n",
|
426 |
+
"Azure Machine Learning Studio\n",
|
427 |
+
"Oracle integration Cloud\n",
|
428 |
+
"Azure DevOps\n",
|
429 |
+
"STRENGTH\n",
|
430 |
+
"•Analytical Skills\n",
|
431 |
+
"•Programming Proficiency\n",
|
432 |
+
"•Problem-Solving Ability\n",
|
433 |
+
"•Data Engineering\n",
|
434 |
+
"•Deep Learning Expertise\n",
|
435 |
+
"•Cloud Computing Skills\n",
|
436 |
+
"•Collaborative Team Player\n",
|
437 |
+
"•Continuous Learning\n",
|
438 |
+
"PROJECTS\n",
|
439 |
+
"Resume Filter using Skills\n",
|
440 |
+
"Self Project\n",
|
441 |
+
"ὌNov 2023 – present Colombo\n",
|
442 |
+
"•Developed a role prediction model using\n",
|
443 |
+
"Hugging Face’s pre-trained model.\n",
|
444 |
+
"•Trained the model on a custom dataset\n",
|
445 |
+
"with diverse skills and associated roles.\n",
|
446 |
+
"•Integrated the model into a user-friendly\n",
|
447 |
+
"interface using Streamlit.\n",
|
448 |
+
"•Implemented LangChain for advanced\n",
|
449 |
+
"natural language processing capabilities.\n",
|
450 |
+
"•Used Bard API to enable dynamic\n",
|
451 |
+
"Question-Answering (QA) based on\n",
|
452 |
+
"resume content.\n",
|
453 |
+
"•Ongoing project with continuous\n",
|
454 |
+
"enhancements and refinements.\n",
|
455 |
+
"•Model and dataset hosted on Hugging\n",
|
456 |
+
"Face for accessibility and collaboration.\n",
|
457 |
+
"•Technologies used: Hugging Face\n",
|
458 |
+
"pre-trained model, Streamlit, LangChain,\n",
|
459 |
+
"Bard API.EXPERIENCE\n",
|
460 |
+
"Associate Engineer - AI/ML\n",
|
461 |
+
"Virtusa Pvt Ltd\n",
|
462 |
+
"ὌDec 2022 – Present Dr Danister De Silva Mawatha, Colombo\n",
|
463 |
+
"•Spearheaded data prepossessing tasks in Azure Synapse Analytics\n",
|
464 |
+
"using PySpark, ensuring efficient and scalable data transformations\n",
|
465 |
+
"for various projects.\n",
|
466 |
+
"•Proficiently designed and implemented data pipelines using Azure\n",
|
467 |
+
"Synapse Pipelines, ensuring efficient data movement and\n",
|
468 |
+
"transformation.\n",
|
469 |
+
"•Monitored and optimized Azure Synapse Pipelines for performance,\n",
|
470 |
+
"reliability, and scalability, contributing to the overall stability of data\n",
|
471 |
+
"workflows.\n",
|
472 |
+
"•Successfully integrated Oracle systems into the workflow,\n",
|
473 |
+
"streamlining data processes and enhancing overall system efficiency.\n",
|
474 |
+
"•Demonstrated proficiency in working with Azure Blob Storage,\n",
|
475 |
+
"managing and optimizing data storage solutions.\n",
|
476 |
+
"•Gained valuable experience in data visualization by utilizing Power BI,\n",
|
477 |
+
"contributing to the creation of insightful and visually appealing\n",
|
478 |
+
"reports.\n",
|
479 |
+
"•Demonstrated proficiency in working with Oracle Bucket Storage and\n",
|
480 |
+
"Oracle Data Science Platform, contributing to efficient data storage\n",
|
481 |
+
"and advanced analytics solutions.\n",
|
482 |
+
"•Demonstrated proficiency in Agile methodologies, particularly Scrum,\n",
|
483 |
+
"through active involvement in daily Scrum meetings, sprint planning,\n",
|
484 |
+
"and retrospectives.\n",
|
485 |
+
"•Utilized Azure DevOps to manage project tasks, user stories, and\n",
|
486 |
+
"backlogs, ensuring streamlined development workflows and timely\n",
|
487 |
+
"delivery of high-quality software solutions.\n",
|
488 |
+
"Trainee Associate Software Engineer)\n",
|
489 |
+
"Virtusa Pvt Ltd\n",
|
490 |
+
"ὌMar 2022 – Nov 2022 Dr Danister De Silva Mawatha, Colombo\n",
|
491 |
+
"•Completed an extensive Spring Boot training program, gaining\n",
|
492 |
+
"hands-on experience in developing robust and scalable Java\n",
|
493 |
+
"applications.\n",
|
494 |
+
"•Completed comprehensive training in Angular and React frameworks,\n",
|
495 |
+
"acquiring skills in front-end development and building dynamic user\n",
|
496 |
+
"interfaces.\n",
|
497 |
+
"EDUCATION\n",
|
498 |
+
"B.Sc(Hons) Computer Science and Technology\n",
|
499 |
+
"Uva Wellassa University of Sri Lanka\n",
|
500 |
+
"Ὄ2018 – 2022\n",
|
501 |
+
"CERTIFICATIONS\n",
|
502 |
+
"Deep Learning Specialization Certificate\n",
|
503 |
+
"Coursera\n",
|
504 |
+
"ὌOct 2021\n",
|
505 |
+
"\n"
|
506 |
+
]
|
507 |
+
}
|
508 |
+
],
|
509 |
+
"source": [
|
510 |
+
"import PyPDF2\n",
|
511 |
+
"\n",
|
512 |
+
"def read_pdf(file_path):\n",
|
513 |
+
" with open(file_path, 'rb') as file:\n",
|
514 |
+
" # Create a PDF reader object\n",
|
515 |
+
" pdf_reader = PyPDF2.PdfReader(file)\n",
|
516 |
+
"\n",
|
517 |
+
" # Iterate over pages\n",
|
518 |
+
" for page_num in range(len(pdf_reader.pages)):\n",
|
519 |
+
" # Get a specific page\n",
|
520 |
+
" page = pdf_reader.pages[page_num]\n",
|
521 |
+
"\n",
|
522 |
+
" # Extract text from the page\n",
|
523 |
+
" text = page.extract_text()\n",
|
524 |
+
"\n",
|
525 |
+
" # Print text from the page\n",
|
526 |
+
" print(f\"Page {page_num + 1}:\\n{text}\\n\")\n",
|
527 |
+
"\n",
|
528 |
+
"# Example usage\n",
|
529 |
+
"pdf_file_path = \"F:/Resume/Fazni_Resume.pdf\"\n",
|
530 |
+
"pdf = read_pdf(pdf_file_path)\n"
|
531 |
+
]
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"cell_type": "code",
|
535 |
+
"execution_count": null,
|
536 |
+
"metadata": {},
|
537 |
+
"outputs": [],
|
538 |
+
"source": [
|
539 |
+
"all_text = get_pdf_text(pdf)"
|
540 |
+
]
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"cell_type": "code",
|
544 |
+
"execution_count": null,
|
545 |
+
"metadata": {},
|
546 |
+
"outputs": [],
|
547 |
+
"source": []
|
548 |
+
}
|
549 |
+
],
|
550 |
+
"metadata": {
|
551 |
+
"kernelspec": {
|
552 |
+
"display_name": "base",
|
553 |
+
"language": "python",
|
554 |
+
"name": "python3"
|
555 |
+
},
|
556 |
+
"language_info": {
|
557 |
+
"codemirror_mode": {
|
558 |
+
"name": "ipython",
|
559 |
+
"version": 3
|
560 |
+
},
|
561 |
+
"file_extension": ".py",
|
562 |
+
"mimetype": "text/x-python",
|
563 |
+
"name": "python",
|
564 |
+
"nbconvert_exporter": "python",
|
565 |
+
"pygments_lexer": "ipython3",
|
566 |
+
"version": "3.10.6"
|
567 |
+
}
|
568 |
+
},
|
569 |
+
"nbformat": 4,
|
570 |
+
"nbformat_minor": 2
|
571 |
+
}
|