mirror of
https://github.com/SkalaraAI/management-llm.git
synced 2025-04-03 20:10:20 -04:00
1166 lines
49 KiB
Plaintext
1166 lines
49 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 46,
|
||
"id": "ceb6f4a0",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"import matplotlib.pyplot as plt"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 47,
|
||
"id": "f0cb1998",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Tool</th>\n",
|
||
" <th>Example Task</th>\n",
|
||
" <th>Unnamed: 2</th>\n",
|
||
" <th>Unnamed: 3</th>\n",
|
||
" <th>Unnamed: 4</th>\n",
|
||
" <th>Unnamed: 5</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>Java</td>\n",
|
||
" <td>Developing a web application using Java Spring...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>Python</td>\n",
|
||
" <td>Implementing data analysis algorithms in Pytho...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>C++</td>\n",
|
||
" <td>Creating a game engine in C++ with DirectX or ...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>PHP</td>\n",
|
||
" <td>Building a dynamic website with PHP and MySQL</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>HTML/CSS</td>\n",
|
||
" <td>Designing and styling a responsive webpage wit...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Tool Example Task Unnamed: 2 \\\n",
|
||
"0 Java Developing a web application using Java Spring... NaN \n",
|
||
"1 Python Implementing data analysis algorithms in Pytho... NaN \n",
|
||
"2 C++ Creating a game engine in C++ with DirectX or ... NaN \n",
|
||
"3 PHP Building a dynamic website with PHP and MySQL NaN \n",
|
||
"4 HTML/CSS Designing and styling a responsive webpage wit... NaN \n",
|
||
"\n",
|
||
" Unnamed: 3 Unnamed: 4 Unnamed: 5 \n",
|
||
"0 NaN NaN NaN \n",
|
||
"1 NaN NaN NaN \n",
|
||
"2 NaN NaN NaN \n",
|
||
"3 NaN NaN NaN \n",
|
||
"4 NaN NaN NaN "
|
||
]
|
||
},
|
||
"execution_count": 47,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df = pd.read_csv('sample_data.csv')\n",
|
||
"df.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 48,
|
||
"id": "02e3d7da",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Tool</th>\n",
|
||
" <th>Example Task</th>\n",
|
||
" <th>Unnamed: 2</th>\n",
|
||
" <th>Unnamed: 3</th>\n",
|
||
" <th>Unnamed: 4</th>\n",
|
||
" <th>Unnamed: 5</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>4214</th>\n",
|
||
" <td>RESTful APIs</td>\n",
|
||
" <td>Create a RESTful API with Django REST framewor...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4215</th>\n",
|
||
" <td>Elasticsearch</td>\n",
|
||
" <td>Set up a search engine with Elasticsearch and ...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4216</th>\n",
|
||
" <td>Firebase</td>\n",
|
||
" <td>Develop a real-time quiz app with Firebase Rea...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4217</th>\n",
|
||
" <td>Redux.js</td>\n",
|
||
" <td>Implement data caching and offline support in ...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4218</th>\n",
|
||
" <td>SAS</td>\n",
|
||
" <td>Conduct predictive modeling with SAS Enterpris...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Tool Example Task \\\n",
|
||
"4214 RESTful APIs Create a RESTful API with Django REST framewor... \n",
|
||
"4215 Elasticsearch Set up a search engine with Elasticsearch and ... \n",
|
||
"4216 Firebase Develop a real-time quiz app with Firebase Rea... \n",
|
||
"4217 Redux.js Implement data caching and offline support in ... \n",
|
||
"4218 SAS Conduct predictive modeling with SAS Enterpris... \n",
|
||
"\n",
|
||
" Unnamed: 2 Unnamed: 3 Unnamed: 4 Unnamed: 5 \n",
|
||
"4214 NaN NaN NaN NaN \n",
|
||
"4215 NaN NaN NaN NaN \n",
|
||
"4216 NaN NaN NaN NaN \n",
|
||
"4217 NaN NaN NaN NaN \n",
|
||
"4218 NaN NaN NaN NaN "
|
||
]
|
||
},
|
||
"execution_count": 48,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.tail()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 49,
|
||
"id": "63bb12b0",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"Tool object\n",
|
||
"Example Task object\n",
|
||
"Unnamed: 2 object\n",
|
||
"Unnamed: 3 object\n",
|
||
"Unnamed: 4 object\n",
|
||
"Unnamed: 5 object\n",
|
||
"dtype: object"
|
||
]
|
||
},
|
||
"execution_count": 49,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.dtypes"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "a05d6965",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"pd.set_option('max_colwidth', 800)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"id": "76cc4d67",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Category</th>\n",
|
||
" <th>Resume</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>957</th>\n",
|
||
" <td>Testing</td>\n",
|
||
" <td>Computer Skills: ⢠Proficient in MS office (Word, Basic Excel, Power point) Strength: ⢠Hard working, Loyalty & Creativity ⢠Self-motivated, Responsible & Initiative ⢠Good people management skill & positive attitude. ⢠knowledge of windows, Internet.Education Details \\r\\n Bachelor of Electrical Engineering Electrical Engineering Nashik, Maharashtra Guru Gobind Singh College of Engineering and Research Centre\\r\\n Diploma Electrical Engineering Nashik, Maharashtra S. M. E. S. Polytechnic College\\r\\nTesting Engineer \\r\\n\\r\\n\\r\\nSkill Details \\r\\nEXCEL- Exprience - 6 months\\r\\nMS OFFICE- Exprience - 6 months\\r\\nWORD- Exprience - 6 monthsCompany Details \\r\\ncompany - \\r\\ndescription - Department: Testing\\r\\n\\r\\nResponsibilities: ⢠To check ACB and VCB of Circuit Breaker.\\r\\nâ...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>958</th>\n",
|
||
" <td>Testing</td>\n",
|
||
" <td>â Willingness to accept the challenges. â Positive thinking. â Good learner. â Team Player. DECLARATION: I hereby declare that the above mentioned information is correct up to my knowledge and I bear the responsibility for the correctness of the above mentioned particulars. Date: / / Name: Dongare Mandakini Murlidhar Signature: Education Details \\r\\nJune 2015 Electronics and Telecommunication Engineering Kolhapur, Maharashtra Shivaji University\\r\\nJune 2012 Education Secondary and Higher Secondary\\r\\n B.E. Electronics and Telecommunication Jaywant College of Engineering and Management\\r\\nTesting Engineer \\r\\n\\r\\nElectronics Engineer - Abacus Electronics Pvt Ltd\\r\\nSkill Details \\r\\nLanguage - C, C++- Exprience - Less than 1 year months\\r\\nOperating Systems- Windows 7-8/NT/X...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>959</th>\n",
|
||
" <td>Testing</td>\n",
|
||
" <td>PERSONAL SKILLS ⢠Quick learner, ⢠Eagerness to learn new things, ⢠Competitive attitude, ⢠Good leadership qualities, ⢠Ability to deal with people diplomatically. PERSONAL DOSSIER Fathers Name: Dhanraj WaghEducation Details \\r\\nJanuary 2012 to January 2016 Bachelors of Engineering Engineering Pune, Maharashtra Pune University\\r\\nJanuary 2012 Higher Secondary Certificate Nashik, Maharashtra SND College of Engineering and Research Center\\r\\nJanuary 2010 Secondary School Certificate Yeola, Maharashtra Swami Muktanand Jr. College\\r\\n HSC Maharashtra State Board\\r\\n SSC Maharashtra State Bard\\r\\n BE Rajapur, Uttar Pradesh Madhyamik Vidya Mandir Rajapur\\r\\nTesting and Quality Control Engineer \\r\\n\\r\\nTesting and Quality Control Engineer - M/S Rakesh Transformer Industries ...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>960</th>\n",
|
||
" <td>Testing</td>\n",
|
||
" <td>COMPUTER SKILLS & SOFTWARE KNOWLEDGE MS-Power Point, MS - Office, C, Protius (PCB Design), Multisim, Micro wind, Matlab, Keil, Latex, Basic I nternet Fundamentals, Software and Hardware Knowledge PROJECT DETAILS Diploma Project: Speed Control of DC Motor Using Heart Beats. Mini Project: Water Gardening System Using Solar Panel. Final Year BE Project: Iris Recognition system.Education Details \\r\\nJanuary 2016 BE EDUCATION Pune, Maharashtra PUNE University\\r\\nJanuary 2010 SSC Maharashtra Board\\r\\nQuality Engineer \\r\\n\\r\\nQuality Engineer - Matrix Technologies\\r\\nSkill Details \\r\\nMATLAB- Exprience - 6 months\\r\\nPCB- Exprience - 6 months\\r\\nPCB DESIGN- Exprience - 6 monthsCompany Details \\r\\ncompany - Matrix Technologies\\r\\ndescription - \\r\\ncompany - RB Electronics\\r\\ndescription -</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>961</th>\n",
|
||
" <td>Testing</td>\n",
|
||
" <td>Skill Set OS Windows XP/7/8/8.1/10 Database MYSQL, sql server 2005, 2008 & 2012 Languages Core Java Web Technology HTML, CSS Testing Manual Testing, Database Testing Other Bug tracking and reporting, End user handling.Education Details \\r\\nJanuary 2016 MCS Pune, Maharashtra P.V.P College Pravaranagar\\r\\nJanuary 2011 HSC A.K.Junior College\\r\\nJanuary 2009 SSC A.K.Mahavidyalya\\r\\nJR TESTING ENGINEER \\r\\n\\r\\nJR TESTING ENGINEER - M-Tech Innovations Ltd\\r\\nSkill Details \\r\\nTESTING- Exprience - 24 months\\r\\nWINDOWS XP- Exprience - 24 months\\r\\nCSS- Exprience - 6 months\\r\\nDATABASE- Exprience - 6 months\\r\\nDATABASE TESTING- Exprience - 6 monthsCompany Details \\r\\ncompany - M-Tech Innovations Ltd\\r\\ndescription - Responsibilities ⢠Analyzing the Testing Requirements ⢠Prepar...</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Category \\\n",
|
||
"957 Testing \n",
|
||
"958 Testing \n",
|
||
"959 Testing \n",
|
||
"960 Testing \n",
|
||
"961 Testing \n",
|
||
"\n",
|
||
" Resume \n",
|
||
"957 Computer Skills: ⢠Proficient in MS office (Word, Basic Excel, Power point) Strength: ⢠Hard working, Loyalty & Creativity ⢠Self-motivated, Responsible & Initiative ⢠Good people management skill & positive attitude. ⢠knowledge of windows, Internet.Education Details \\r\\n Bachelor of Electrical Engineering Electrical Engineering Nashik, Maharashtra Guru Gobind Singh College of Engineering and Research Centre\\r\\n Diploma Electrical Engineering Nashik, Maharashtra S. M. E. S. Polytechnic College\\r\\nTesting Engineer \\r\\n\\r\\n\\r\\nSkill Details \\r\\nEXCEL- Exprience - 6 months\\r\\nMS OFFICE- Exprience - 6 months\\r\\nWORD- Exprience - 6 monthsCompany Details \\r\\ncompany - \\r\\ndescription - Department: Testing\\r\\n\\r\\nResponsibilities: ⢠To check ACB and VCB of Circuit Breaker.\\r\\nâ... \n",
|
||
"958 â Willingness to accept the challenges. â Positive thinking. â Good learner. â Team Player. DECLARATION: I hereby declare that the above mentioned information is correct up to my knowledge and I bear the responsibility for the correctness of the above mentioned particulars. Date: / / Name: Dongare Mandakini Murlidhar Signature: Education Details \\r\\nJune 2015 Electronics and Telecommunication Engineering Kolhapur, Maharashtra Shivaji University\\r\\nJune 2012 Education Secondary and Higher Secondary\\r\\n B.E. Electronics and Telecommunication Jaywant College of Engineering and Management\\r\\nTesting Engineer \\r\\n\\r\\nElectronics Engineer - Abacus Electronics Pvt Ltd\\r\\nSkill Details \\r\\nLanguage - C, C++- Exprience - Less than 1 year months\\r\\nOperating Systems- Windows 7-8/NT/X... \n",
|
||
"959 PERSONAL SKILLS ⢠Quick learner, ⢠Eagerness to learn new things, ⢠Competitive attitude, ⢠Good leadership qualities, ⢠Ability to deal with people diplomatically. PERSONAL DOSSIER Fathers Name: Dhanraj WaghEducation Details \\r\\nJanuary 2012 to January 2016 Bachelors of Engineering Engineering Pune, Maharashtra Pune University\\r\\nJanuary 2012 Higher Secondary Certificate Nashik, Maharashtra SND College of Engineering and Research Center\\r\\nJanuary 2010 Secondary School Certificate Yeola, Maharashtra Swami Muktanand Jr. College\\r\\n HSC Maharashtra State Board\\r\\n SSC Maharashtra State Bard\\r\\n BE Rajapur, Uttar Pradesh Madhyamik Vidya Mandir Rajapur\\r\\nTesting and Quality Control Engineer \\r\\n\\r\\nTesting and Quality Control Engineer - M/S Rakesh Transformer Industries ... \n",
|
||
"960 COMPUTER SKILLS & SOFTWARE KNOWLEDGE MS-Power Point, MS - Office, C, Protius (PCB Design), Multisim, Micro wind, Matlab, Keil, Latex, Basic I nternet Fundamentals, Software and Hardware Knowledge PROJECT DETAILS Diploma Project: Speed Control of DC Motor Using Heart Beats. Mini Project: Water Gardening System Using Solar Panel. Final Year BE Project: Iris Recognition system.Education Details \\r\\nJanuary 2016 BE EDUCATION Pune, Maharashtra PUNE University\\r\\nJanuary 2010 SSC Maharashtra Board\\r\\nQuality Engineer \\r\\n\\r\\nQuality Engineer - Matrix Technologies\\r\\nSkill Details \\r\\nMATLAB- Exprience - 6 months\\r\\nPCB- Exprience - 6 months\\r\\nPCB DESIGN- Exprience - 6 monthsCompany Details \\r\\ncompany - Matrix Technologies\\r\\ndescription - \\r\\ncompany - RB Electronics\\r\\ndescription - \n",
|
||
"961 Skill Set OS Windows XP/7/8/8.1/10 Database MYSQL, sql server 2005, 2008 & 2012 Languages Core Java Web Technology HTML, CSS Testing Manual Testing, Database Testing Other Bug tracking and reporting, End user handling.Education Details \\r\\nJanuary 2016 MCS Pune, Maharashtra P.V.P College Pravaranagar\\r\\nJanuary 2011 HSC A.K.Junior College\\r\\nJanuary 2009 SSC A.K.Mahavidyalya\\r\\nJR TESTING ENGINEER \\r\\n\\r\\nJR TESTING ENGINEER - M-Tech Innovations Ltd\\r\\nSkill Details \\r\\nTESTING- Exprience - 24 months\\r\\nWINDOWS XP- Exprience - 24 months\\r\\nCSS- Exprience - 6 months\\r\\nDATABASE- Exprience - 6 months\\r\\nDATABASE TESTING- Exprience - 6 monthsCompany Details \\r\\ncompany - M-Tech Innovations Ltd\\r\\ndescription - Responsibilities ⢠Analyzing the Testing Requirements ⢠Prepar... "
|
||
]
|
||
},
|
||
"execution_count": 11,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.tail()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "6d7bcf55",
|
||
"metadata": {},
|
||
"source": [
|
||
" "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 50,
|
||
"id": "c13f2641",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"Index(['Tool', 'Example Task', 'Unnamed: 2', 'Unnamed: 3', 'Unnamed: 4',\n",
|
||
" 'Unnamed: 5'],\n",
|
||
" dtype='object')"
|
||
]
|
||
},
|
||
"execution_count": 50,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.columns"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 54,
|
||
"id": "5382d028",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"Python 101\n",
|
||
"Java 95\n",
|
||
"JavaScript 94\n",
|
||
"C++ 89\n",
|
||
"Swift 89\n",
|
||
"HTML/CSS 83\n",
|
||
"C# 82\n",
|
||
"PHP 81\n",
|
||
"SQL 81\n",
|
||
"Ruby 81\n",
|
||
"Kotlin 80\n",
|
||
"Rust 80\n",
|
||
"TypeScript 80\n",
|
||
"AutoCAD 80\n",
|
||
"Groovy 80\n",
|
||
"Adobe Creative Suite 80\n",
|
||
"Perl 80\n",
|
||
"Go 80\n",
|
||
"Microsoft Office Suite 80\n",
|
||
"Objective-C 80\n",
|
||
"ReactJS 80\n",
|
||
"AngularJS 80\n",
|
||
"Scala 79\n",
|
||
"Tableau 79\n",
|
||
"VMware 79\n",
|
||
"Linux/Unix 79\n",
|
||
"Docker 79\n",
|
||
"Git/Github 79\n",
|
||
"XML 79\n",
|
||
"Apache Kafka 79\n",
|
||
"Node.js 79\n",
|
||
"jQuery 79\n",
|
||
"MATLAB 79\n",
|
||
"R language 79\n",
|
||
"Shell Scripting 79\n",
|
||
"Jenkins 77\n",
|
||
"Bootstrap 77\n",
|
||
"TensorFlow 74\n",
|
||
"Hadoop 72\n",
|
||
"MongoDB 71\n",
|
||
"AWS 69\n",
|
||
".NET 66\n",
|
||
"Azure 66\n",
|
||
"Google Cloud 66\n",
|
||
"PostgreSQL 66\n",
|
||
"Redux.js 64\n",
|
||
"Artificial Intelligence (AI) 64\n",
|
||
"Oracle 64\n",
|
||
"Machine Learning 63\n",
|
||
"Data Analysis 63\n",
|
||
"API Integration 63\n",
|
||
"RESTful APIs 63\n",
|
||
"Elasticsearch 63\n",
|
||
"Firebase 63\n",
|
||
"SAS 61\n",
|
||
"C 5\n",
|
||
"JQuery 4\n",
|
||
"Name: Tool, dtype: int64"
|
||
]
|
||
},
|
||
"execution_count": 54,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.Tool.value_counts()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 52,
|
||
"id": "e195ccbe",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"\n",
|
||
"\n",
|
||
"# Calculate the value counts for the 'Tool' column\n",
|
||
"tool_counts = df['Tool'].value_counts()\n",
|
||
"\n",
|
||
"# Create a mask for rows where the 'Tool' value count is greater than 1\n",
|
||
"mask = df['Tool'].isin(tool_counts[tool_counts > 1].index)\n",
|
||
"\n",
|
||
"# Filter the DataFrame using the mask\n",
|
||
"df_filtered = df[mask]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 53,
|
||
"id": "10450f83",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df = df_filtered"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 23,
|
||
"id": "4aafa2ff",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"RangeIndex: 1173 entries, 0 to 1172\n",
|
||
"Data columns (total 6 columns):\n",
|
||
" # Column Non-Null Count Dtype \n",
|
||
"--- ------ -------------- ----- \n",
|
||
" 0 Tool 1173 non-null object\n",
|
||
" 1 Example Task 1173 non-null object\n",
|
||
" 2 Unnamed: 2 22 non-null object\n",
|
||
" 3 Unnamed: 3 22 non-null object\n",
|
||
" 4 Cleaned Example Task 1173 non-null object\n",
|
||
" 5 Labels 1173 non-null int64 \n",
|
||
"dtypes: int64(1), object(5)\n",
|
||
"memory usage: 55.1+ KB\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"df.info()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 55,
|
||
"id": "f73c3981",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from string import punctuation\n",
|
||
"print(punctuation)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 56,
|
||
"id": "34e8e0fc",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import re\n",
|
||
"\n",
|
||
"def cleanResume(resumeText):\n",
|
||
" resumeText = re.sub('[%s]' % re.escape(\"\"\"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~\"\"\"), ' ', resumeText) # remove punctuations\n",
|
||
" resumeText = re.sub(r'[^\\x00-\\x7f]',r' ', resumeText) # remove non-ascii characters\n",
|
||
" resumeText = re.sub('\\s+', ' ', resumeText) # remove extra whitespace\n",
|
||
" resumeText = re.sub(r'[0-9]+', '', resumeText) #remove numbers\n",
|
||
" return resumeText.lower()\n",
|
||
" "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 57,
|
||
"id": "902ccead",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"70"
|
||
]
|
||
},
|
||
"execution_count": 57,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df[\"Cleaned Example Task\"] = df[\"Example Task\"].apply(lambda x: cleanResume(x))\n",
|
||
"len(df[\"Cleaned Example Task\"][1])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 58,
|
||
"id": "d1a33e2d",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Tool</th>\n",
|
||
" <th>Example Task</th>\n",
|
||
" <th>Unnamed: 2</th>\n",
|
||
" <th>Unnamed: 3</th>\n",
|
||
" <th>Unnamed: 4</th>\n",
|
||
" <th>Unnamed: 5</th>\n",
|
||
" <th>Cleaned Example Task</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>Java</td>\n",
|
||
" <td>Developing a web application using Java Spring...</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>developing a web application using java spring...</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Tool Example Task Unnamed: 2 \\\n",
|
||
"0 Java Developing a web application using Java Spring... NaN \n",
|
||
"\n",
|
||
" Unnamed: 3 Unnamed: 4 Unnamed: 5 \\\n",
|
||
"0 NaN NaN NaN \n",
|
||
"\n",
|
||
" Cleaned Example Task \n",
|
||
"0 developing a web application using java spring... "
|
||
]
|
||
},
|
||
"execution_count": 58,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.head(1)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 59,
|
||
"id": "d1f26006",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"179"
|
||
]
|
||
},
|
||
"execution_count": 59,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"import nltk\n",
|
||
"#nltk.download('stopwords')\n",
|
||
"import string\n",
|
||
"from nltk.corpus import stopwords\n",
|
||
"from nltk import word_tokenize\n",
|
||
"\n",
|
||
"len(stopwords.words('english'))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 60,
|
||
"id": "1591434a",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"ds_df = df[df.Tool == 'Java']\n",
|
||
"resumes=\"\"\n",
|
||
"total_words = []\n",
|
||
"for resume in ds_df[\"Cleaned Example Task\"]:\n",
|
||
" resumes += resume\n",
|
||
" words = word_tokenize(resume)\n",
|
||
" for word in words :\n",
|
||
" if word not in set(stopwords.words('english')) and word not in string.punctuation:\n",
|
||
" total_words.append(word)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 61,
|
||
"id": "66a36d4b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from sklearn.preprocessing import LabelEncoder\n",
|
||
"\n",
|
||
"encoder = LabelEncoder()\n",
|
||
"df['Labels']=encoder.fit_transform(df.Tool)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "10a9e258",
|
||
"metadata": {},
|
||
"source": [
|
||
"To check if we successfully convert our labels into integers, let's run info() method of the pandas one more time. "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 62,
|
||
"id": "a577090e",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"Int64Index: 4207 entries, 0 to 4218\n",
|
||
"Data columns (total 8 columns):\n",
|
||
" # Column Non-Null Count Dtype \n",
|
||
"--- ------ -------------- ----- \n",
|
||
" 0 Tool 4207 non-null object\n",
|
||
" 1 Example Task 4207 non-null object\n",
|
||
" 2 Unnamed: 2 65 non-null object\n",
|
||
" 3 Unnamed: 3 65 non-null object\n",
|
||
" 4 Unnamed: 4 1 non-null object\n",
|
||
" 5 Unnamed: 5 1 non-null object\n",
|
||
" 6 Cleaned Example Task 4207 non-null object\n",
|
||
" 7 Labels 4207 non-null int64 \n",
|
||
"dtypes: int64(1), object(7)\n",
|
||
"memory usage: 424.8+ KB\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"df.info()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 63,
|
||
"id": "27b2b6c2",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"39 101\n",
|
||
"24 95\n",
|
||
"25 94\n",
|
||
"12 89\n",
|
||
"50 89\n",
|
||
"Name: Labels, dtype: int64"
|
||
]
|
||
},
|
||
"execution_count": 63,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.Labels.value_counts()[:5]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "ee39bb5b",
|
||
"metadata": {},
|
||
"source": [
|
||
"df.sample() will help us to have a look at two random resumes, and the labels. "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 26,
|
||
"id": "87448c16",
|
||
"metadata": {
|
||
"scrolled": true
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>Category</th>\n",
|
||
" <th>Resume</th>\n",
|
||
" <th>Cleaned Resume</th>\n",
|
||
" <th>Labels</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>14</th>\n",
|
||
" <td>Data Science</td>\n",
|
||
" <td>Education Details \\r\\n MCA YMCAUST, Faridabad, Haryana\\r\\nData Science internship \\r\\n\\r\\n\\r\\nSkill Details \\r\\nData Structure- Exprience - Less than 1 year months\\r\\nC- Exprience - Less than 1 year months\\r\\nData Analysis- Exprience - Less than 1 year months\\r\\nPython- Exprience - Less than 1 year months\\r\\nCore Java- Exprience - Less than 1 year months\\r\\nDatabase Management- Exprience - Less than 1 year monthsCompany Details \\r\\ncompany - Itechpower\\r\\ndescription -</td>\n",
|
||
" <td>education details mca ymcaust faridabad haryana data science internship skill details data structure exprience less than year months c exprience less than year months data analysis exprience less than year months python exprience less than year months core java exprience less than year months database management exprience less than year monthscompany details company itechpower description</td>\n",
|
||
" <td>6</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>738</th>\n",
|
||
" <td>Database</td>\n",
|
||
" <td>Software Skills: * RDBMS: MS SQL SERVER 2000/2005/2008 & 2012, 2014 * Operating Systems: WINDOWS XP/7, WINDOWS SERVER 2008, 12 * Fundamentals: MS Office 03/07 * Tools: SSMS, Performance Monitor, Sql profiler, SQL lite speed. Company name: Barclays Technology Centre India. Team Size: 24 Role: Database Administrator Support Description: Barclays Technology is a UK based retail & invest bank and 300 years of old bank.. It has operations in over 40 countries and employs approximately 120, 000 people. Barclays is organised into four core businesses: Personal & Corporate (Personal Banking, Corporate Banking, Wealth & Investment Management), Barclaycard, Investment Banking. Responsibilities: â Attending various calls from all over the world on various database issues. â Working on Web Gui...</td>\n",
|
||
" <td>software skills rdbms ms sql server operating systems windows xp windows server fundamentals ms office tools ssms performance monitor sql profiler sql lite speed company name barclays technology centre india team size role database administrator support description barclays technology is a uk based retail invest bank and years of old bank it has operations in over countries and employs approximately people barclays is organised into four core businesses personal corporate personal banking corporate banking wealth investment management barclaycard investment banking responsibilities attending various calls from all over the world on various database issues working on web gui alerts and resolving incident tickets within the time lines troubleshoooting log shipping issues a...</td>\n",
|
||
" <td>7</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" Category \\\n",
|
||
"14 Data Science \n",
|
||
"738 Database \n",
|
||
"\n",
|
||
" Resume \\\n",
|
||
"14 Education Details \\r\\n MCA YMCAUST, Faridabad, Haryana\\r\\nData Science internship \\r\\n\\r\\n\\r\\nSkill Details \\r\\nData Structure- Exprience - Less than 1 year months\\r\\nC- Exprience - Less than 1 year months\\r\\nData Analysis- Exprience - Less than 1 year months\\r\\nPython- Exprience - Less than 1 year months\\r\\nCore Java- Exprience - Less than 1 year months\\r\\nDatabase Management- Exprience - Less than 1 year monthsCompany Details \\r\\ncompany - Itechpower\\r\\ndescription - \n",
|
||
"738 Software Skills: * RDBMS: MS SQL SERVER 2000/2005/2008 & 2012, 2014 * Operating Systems: WINDOWS XP/7, WINDOWS SERVER 2008, 12 * Fundamentals: MS Office 03/07 * Tools: SSMS, Performance Monitor, Sql profiler, SQL lite speed. Company name: Barclays Technology Centre India. Team Size: 24 Role: Database Administrator Support Description: Barclays Technology is a UK based retail & invest bank and 300 years of old bank.. It has operations in over 40 countries and employs approximately 120, 000 people. Barclays is organised into four core businesses: Personal & Corporate (Personal Banking, Corporate Banking, Wealth & Investment Management), Barclaycard, Investment Banking. Responsibilities: â Attending various calls from all over the world on various database issues. â Working on Web Gui... \n",
|
||
"\n",
|
||
" Cleaned Resume \\\n",
|
||
"14 education details mca ymcaust faridabad haryana data science internship skill details data structure exprience less than year months c exprience less than year months data analysis exprience less than year months python exprience less than year months core java exprience less than year months database management exprience less than year monthscompany details company itechpower description \n",
|
||
"738 software skills rdbms ms sql server operating systems windows xp windows server fundamentals ms office tools ssms performance monitor sql profiler sql lite speed company name barclays technology centre india team size role database administrator support description barclays technology is a uk based retail invest bank and years of old bank it has operations in over countries and employs approximately people barclays is organised into four core businesses personal corporate personal banking corporate banking wealth investment management barclaycard investment banking responsibilities attending various calls from all over the world on various database issues working on web gui alerts and resolving incident tickets within the time lines troubleshoooting log shipping issues a... \n",
|
||
"\n",
|
||
" Labels \n",
|
||
"14 6 \n",
|
||
"738 7 "
|
||
]
|
||
},
|
||
"execution_count": 26,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"df.sample(2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 64,
|
||
"id": "d1fab8e5",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"(3155,)\n",
|
||
"(3155,)\n",
|
||
"(1052,)\n",
|
||
"(1052,)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"\n",
|
||
"text = df[\"Cleaned Example Task\"].values\n",
|
||
"labels = df[\"Labels\"].values\n",
|
||
"\n",
|
||
"text_train,text_test,y_train,y_test = train_test_split(text, labels, random_state=0, test_size=0.25, stratify=df.Labels)\n",
|
||
"print(text_train.shape)\n",
|
||
"print(y_train.shape)\n",
|
||
"print(text_test.shape)\n",
|
||
"print(y_test.shape)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a8bcf140",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Vectorization\n",
|
||
"\n",
|
||
"The simplest form of text vectorization is the Bag of Words (BoW) model. Sklearn library makes the BoW application very easy with CountVectorizer, TfidfVectorizer, and TfidfTransformer. Let's use the TfidfVectorizer with the default tokenizer, and by removing the English stopwords. "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 65,
|
||
"id": "e0084e02",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
|
||
"\n",
|
||
"word_vectorizer = TfidfVectorizer(\n",
|
||
" sublinear_tf=True,\n",
|
||
" use_idf = True,\n",
|
||
" stop_words='english',\n",
|
||
" max_features=1000)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 66,
|
||
"id": "53f59ebb",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"(3155, 1000)"
|
||
]
|
||
},
|
||
"execution_count": 66,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"X_train = word_vectorizer.fit_transform(text_train)\n",
|
||
"X_train.shape"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 67,
|
||
"id": "63cbbb52",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"(1052, 1000)"
|
||
]
|
||
},
|
||
"execution_count": 67,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"X_test = word_vectorizer.transform(text_test)\n",
|
||
"X_test.shape"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 68,
|
||
"id": "23835a72",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Accuracy on training set: 0.97\n",
|
||
"Accuracy on test set: 0.90\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from sklearn.svm import SVC\n",
|
||
"from sklearn.multiclass import OneVsRestClassifier\n",
|
||
"\n",
|
||
"# Assuming you have already split your data into X_train, X_test, y_train, y_test\n",
|
||
"\n",
|
||
"# Step 1: Train the SVM model\n",
|
||
"svm_model = OneVsRestClassifier(SVC(kernel='linear'))\n",
|
||
"svm_model.fit(X_train, y_train)\n",
|
||
"\n",
|
||
"# Step 2: Make predictions using the SVM model\n",
|
||
"prediction_svm = svm_model.predict(X_test)\n",
|
||
"print('Accuracy on training set: {:.2f}'.format(svm_model.score(X_train, y_train)))\n",
|
||
"print('Accuracy on test set: {:.2f}'.format(svm_model.score(X_test, y_test)))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 75,
|
||
"id": "98f10b74",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"['svm_model.sav']"
|
||
]
|
||
},
|
||
"execution_count": 75,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"import joblib\n",
|
||
"\n",
|
||
"# Assuming your trained SVM model object is 'svm_model'\n",
|
||
"model_filename = 'svm_model.sav'\n",
|
||
"joblib.dump(svm_model, model_filename)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 69,
|
||
"id": "2fa1e46b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"sample = [\"Implement a login page with form validation using React.js.\",\n",
|
||
"\"Set up a RESTful API using Node.js and Express.js.\",\n",
|
||
"\n",
|
||
"\n",
|
||
"\"Design a user-friendly dashboard layout with interactive charts and graphs.\",\n",
|
||
"\n",
|
||
"\n",
|
||
"\"Implement authentication and authorization using JWT and bcrypt.\",\n",
|
||
"\n",
|
||
"\n",
|
||
"\"Create a database schema for storing employee data and performance metrics.\",\n",
|
||
"\n",
|
||
"\n",
|
||
"\"Design a responsive user interface with a modern and clean aesthetic.\",\n",
|
||
"\n",
|
||
"\n",
|
||
"\"Implement data visualization using a charting library like D3.js.\",\n",
|
||
"\n",
|
||
"\n",
|
||
" \"Set up a MongoDB database for storing and querying analytics data.\",\n",
|
||
"\n",
|
||
"\n",
|
||
" \"Create wireframes for the employee profile page displaying key performance indicators.\",\n",
|
||
"\n",
|
||
"\"Implement CRUD operations for managing employee data using REST APIs.\",\n",
|
||
"\n",
|
||
" \"Design a visually appealing landing page with clear call-to-action buttons.\",\n",
|
||
"\n",
|
||
" \"Implement user authentication using Firebase Authentication.\",\n",
|
||
"\n",
|
||
"\n",
|
||
"\"Set up a Next.js project with server-side rendering for improved performance.\",\n",
|
||
"\n",
|
||
"\n",
|
||
"\"Design a mobile-friendly layout for seamless viewing on different devices.\",\n",
|
||
"\n",
|
||
"\n",
|
||
" \"Implement a search functionality for easily finding employee records.\"]\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 74,
|
||
"id": "cbaf2b24",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Implement a login page with form validation using React.js.\n",
|
||
"Top 3 predicted labels: ['ReactJS' 'JavaScript' 'Bootstrap']\n",
|
||
"Set up a RESTful API using Node.js and Express.js.\n",
|
||
"Top 3 predicted labels: ['Node.js' 'RESTful APIs' 'JavaScript']\n",
|
||
"Design a user-friendly dashboard layout with interactive charts and graphs.\n",
|
||
"Top 3 predicted labels: ['R language' 'jQuery' 'Data Analysis']\n",
|
||
"Implement authentication and authorization using JWT and bcrypt.\n",
|
||
"Top 3 predicted labels: ['API Integration' '.NET' 'PHP']\n",
|
||
"Create a database schema for storing employee data and performance metrics.\n",
|
||
"Top 3 predicted labels: ['SQL' 'PostgreSQL' 'Java']\n",
|
||
"Design a responsive user interface with a modern and clean aesthetic.\n",
|
||
"Top 3 predicted labels: ['HTML/CSS' 'Adobe Creative Suite' 'C++']\n",
|
||
"Implement data visualization using a charting library like D3.js.\n",
|
||
"Top 3 predicted labels: ['C++' 'JavaScript' 'ReactJS']\n",
|
||
"Set up a MongoDB database for storing and querying analytics data.\n",
|
||
"Top 3 predicted labels: ['MongoDB' 'SQL' 'Azure']\n",
|
||
"Create wireframes for the employee profile page displaying key performance indicators.\n",
|
||
"Top 3 predicted labels: ['jQuery' 'Go' 'HTML/CSS']\n",
|
||
"Implement CRUD operations for managing employee data using REST APIs.\n",
|
||
"Top 3 predicted labels: ['RESTful APIs' 'API Integration' 'Linux/Unix']\n",
|
||
"Design a visually appealing landing page with clear call-to-action buttons.\n",
|
||
"Top 3 predicted labels: ['HTML/CSS' 'Bootstrap' 'Microsoft Office Suite']\n",
|
||
"Implement user authentication using Firebase Authentication.\n",
|
||
"Top 3 predicted labels: ['Firebase' 'ReactJS' 'Ruby']\n",
|
||
"Set up a Next.js project with server-side rendering for improved performance.\n",
|
||
"Top 3 predicted labels: ['TypeScript' 'SQL' 'jQuery']\n",
|
||
"Design a mobile-friendly layout for seamless viewing on different devices.\n",
|
||
"Top 3 predicted labels: ['Bootstrap' 'jQuery' 'Java']\n",
|
||
"Implement a search functionality for easily finding employee records.\n",
|
||
"Top 3 predicted labels: ['Elasticsearch' 'Objective-C' 'Java']\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"for x in sample:\n",
|
||
" sample_text = x\n",
|
||
"\n",
|
||
" # Vectorize \n",
|
||
" vectorized_text = word_vectorizer.transform([sample_text]) \n",
|
||
"\n",
|
||
" binary_predictions = svm_model.predict(vectorized_text)\n",
|
||
"\n",
|
||
" decision_function_scores = svm_model.decision_function(vectorized_text)\n",
|
||
"\n",
|
||
" # Get the top 3 predicted labels based on highest decision function scores\n",
|
||
" top_4_indices = decision_function_scores.argsort()[0][-3:][::-1]\n",
|
||
" top_4_labels = encoder.inverse_transform(top_4_indices)\n",
|
||
"\n",
|
||
" print(x)\n",
|
||
" print(\"Top 3 predicted labels:\", top_4_labels)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "638ba4a7",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3 (ipykernel)",
|
||
"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": "3.10.9"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|