{ "cells": [ { "cell_type": "markdown", "metadata": { "colab_type": "text", "id": "view-in-github" }, "source": [ "\"Open" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "kD4VfQr4h0P1" }, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "markdown", "metadata": { "id": "t3UVcbHDsi6U" }, "source": [ "# DATASET RESUME 100" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "F5Og0ulylvhU", "outputId": "ff37410f-bb93-44ea-a56a-6cb5b2806d1f" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df_resume\",\n \"rows\": 166,\n \"fields\": [\n {\n \"column\": \"category\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 25,\n \"samples\": [\n \"Civil Engineer\",\n \"DevOps Engineer\",\n \"Data Science\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_data\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 166,\n \"samples\": [\n \"key competency multi operation management\\u00e2 people management customer service email mi vendor client service management\\u00e2 cross functional coordination\\u00e2 banking financial services\\u00e2 transaction monitoring atm operation prepaid card operation pre issuance post issuance po operation job profile skill effective communicator excellent relationship building interpersonal skill strong analytical problem solving organizational ability extensive experience managing operation demonstrated leadership quality organisational skill tenure managing customer centric operation ensuring customer satisfaction achieving service quality norm analyzing operational problem customer complaint take preventive corrective action resolve receive respond key customer inquiry effective manner provide relevant timely information deft steering banking back end operation analyzing risk managing delinquency dexterity across applying technique maximizing recovery minimizing credit loss analyzed identified training need team member developing organizing conducting training program manage bottom quartile team improve performance preparing maintaining daily mi report evaluate performance efficiency process relate various vertical measuring performance process term efficiency effectiveness matrix ensuring adherence sla major activity define process field service monitored necessary check executed controlled also measured vendor sla analyzing tat vendor client sla provided u per company procedure handling ensuring vendor payment issue sorted payment processed quarterly basis appropriately plan execute skill operation accordance department policy procedure manage relationship business team software development team service achieve project objective different software worked till ctl prime axis bank credit card insight po machine technical operation amex mid tid generation atos venture infotek ticket management system tata communication private service ltd atm noc operation branch portal yalamanchili software export ltd prepaid card sbi bank zaggle prepaid ocean service ltd zaggle prepaid ocean service pvt ltd oct till date designation manager operation payment industry prepaid card inr education detail commerce mumbai mumbai university operation manager service manager operation payment industry prepaid card inr ftc skill detail operation experience seventy three month satisfaction experience forty eight month training experience twenty four month noc experience twenty three month point sale experience detail company zaggle prepaid ocean service pvt ltd description card operation company yalamanchili software export ltd description operation pvt ltd designation service manager operation payment industry prepaid card inr ftc key contribution result oriented business professional planning executing managing process improving efficiency operation team building detailing process information determine effective result operation ensuring pin generation sla maintained chargeback case raised perfect timeframe managing email customer service properly ensuring email replied properly also ensuring transaction monitoring properly managed assisting banker sbi associated bank bcp plan getting executed system help dr pr plan vice versa business requirement expertise maintaining highest level quality operation ensuring adherence quality parameter procedure per stringent norm lead manage supervise execution external audit engagement responsible presenting finding developing quality report senior management client coach mentor team member perform higher level giving opportunity providing timely continuous feedback working staff improve communication time management decision making organization analytical skill providing solution service client premise aforesaid count team member also ensuring end end process pr dr per client requirement pr dr dr pr interacting internal external stakeholder determining process gap designing conducting training program enhance operational efficiency retain talent providing optimum opportunity personal professional growth company credit card description ensured highest standard customer satisfaction quality service developing new policy procedure improve based customer feedback resolving customer query via correspondence inbound call email channel strength team member company ag transact technology limited description key contribution lead spoc bank company tata communication payment solution ltd description make atm operational within tat analyzing issue technical non technical also interacting internal external stakeholder company vertex customer solution india private ltd description key contribution build positive working relationship team member client keeping management informed kyc document collection con current audit progress responding timely management inquiry understanding business conducting self professionally company financial inclusion network operation limited description key contribution po operation cascading adherence process strictly followed team member training reduce downtime managing stock edc terminal managing deployment terminal multiple team would worked multiple terminal make model managing inward outward qc application installed po machine company venture infotek private ltd description key contribution po operation company axis bank ltd customer service description foi smart designation team leader executive email phone banking correspondence unit snail mail\",\n \"skill set hadoop map reduce hdfs hive sqoop java duration role hadoop developer rplus offer quick simple powerful cloud based solution demand sense accurately predict demand product market combine enterprise external data predict demand accurately us social conversation sentiment derive demand identifies significant driver sale horde factor selects best suited model multiple forecasting model product responsibility involved deploying product customer gathering requirement algorithm optimization backend product load transform large datasets structured semi structured responsible manage data coming different source application supported map reduce program running cluster involved creating hive table loading data writing hive query run internally map reduce detail hadoop developer hadoop developer braindatawire skill detail apache hadoop hdfs experience forty nine month apache hadoop sqoop experience forty nine month hadoop experience forty nine month hadoop experience forty nine month hadoop distributed file system experience detail company braindatawire description technical skill programming core java map reduce scala hadoop tool hdfs spark map reduce sqoop hive hbase database mysql oracle scripting shell scripting ide eclipse operating system linux centos window source control git github\",\n \"skill area exposure modeling tool bizagi m visio prototyping tool indigo studio documentation m office m word m excel m power point testing proficiency smoke sanity integration functional acceptance ui methodology implemented waterfall agile scrum database sql testing tool hpqc business exposure education detail bachelor computer engineering computer engineering thadomal shahani engineering college diploma computer engineering ulhasnagar institute technology secondary school certificate ulhasnagar new english high school senior business analyst rpa senior business analyst rpa hexaware technology skill detail documentation experience forty seven month testing experience twenty nine month integration experience twenty five month integrator experience twenty five month prototype experience detail company hexaware technology description working rpa business analyst company bbh brown brother harriman co description private bank provides commercial banking investment management brokerage trust service private company individual also performs merger advisory foreign exchange custody service commercial banking corporate financing service responsibility performed automation assessment various process identified process candidate rpa conducting assessment involves initial understanding existing system technology process usage tool feasibility tool automation tool along automation roi analysis preparing automation potential sheet describes step process volume frequency transaction aht taken sme perform process depending step could automated automation potential manual effort saved calculated calculating complexity process considered automation depending factor number bot number automation tool license determined implementing proof concept poc validate feasibility executing selected critical use case conducting poc help identify financial operational benefit provide recommendation regarding actual need complete automation gathering business requirement conducting detailed interview business user stakeholder subject matter expert sme preparing business requirement document converted business requirement functional requirement specification constructing prototype early toward design acceptable customer feasible assisting designing test plan test scenario test case integration regression user acceptance testing uat improve overall quality automation participating regularly walkthroughs review meeting project manager qa engineer development team regularly interacting offshore onshore development team company fadv first advantage description criminal background check company delivers global solution ranging employment screening background check following process covered email process research process review process responsibility requirement gathering conducting interview brainstorming session stakeholder develop decision model execute rule per use case specification test validate decision model document test data maintain enhance decision model change regulation per use case specification responsible performing business research make business growth developing clear understanding existing business function process effectively communicate onsite client query suggestion update giving suggestion enhance current process identifying area process improvement flagging potential problem early stage preparing powerpoint presentation document business meeting using information gathered write detailed report highlighting risk issue could impact project delivery able work accurately develop maintain documentation internal team training client end user operation work efficiently team member across team mentor train junior team member company clinical testing lab work diagnostic testing description iqvia provides service customer includes clinical testing lab work diagnostic testing clinical trial customer need pay iqvia aging detail invoice generated following process covered tracking payment automated real time metric reporting dashboard past due notification ar statement credit rebill responsibility conducting meeting client key stakeholder gather requirement analyze finalize formal sign offs approver gather perform analysis business requirement translating business requirement business requirement document brd functional requirement document frd facilitating meeting appropriate subject matter expert business technology team coordinating business user community execution user acceptance test well tracking issue working collaborating coordinating offshore onsite team member fulfill ba responsibility project initiation post implementation reviewing test script business user well technology team execute test script expected result system integration test sit user acceptance test uat coordinating conducting production acceptance testing pat business user creating flow diagram structure chart type system process representation managing change requirement baseline change control process utilizing standard method design testing tool throughout project development life cycle work closely operational functional team operation management personnel various technology team facilitate shared understanding requirement priority across area company eduavenir solution description project inventory management application allows user manage inventory detail different warehouse different product located various location help extract good procured sold returned customer generates automated invoicesalong withcustomized report also managescustomer complaint resolution system implementation along automated mi monthly basis sale forecastingis also developed mi system streamlining process warehousing dispatch along online proof delivery management system pod documentation generated responsibility participate requirement gathering discussion client understand flow business process analyze requirement determine core process develop process documentation ensure stay date conjunction going change participate process flow analysis preparing brd sr coordinating developer designer operation team various nuance project communicate stakeholder requirement requirement enhancement implementation finally deliver within estimated timeframe support uat reviewing test case manage version control document software build coordinate stakeholder uat sign coordinate internally production movement till golive stage application provide demo training internal end user using powerpoint presentation resolving project functional technical issue uat prioritizing production bug resolving within estimated timeframe preparing project status report production bug status stakeholder promoting networking online trading platform designing query sheet obtaining comparison quote various vendor development product code material code inventory management master data management company capgemini head office description type mobile device testing duration follet application take electronic request user book requires particular follet store detailed information book include name book price date transaction party involved sent follet store user create request one book given date request processed user get mail date provided book responsibility understanding need business requirement preparing brd sr eliciting requirement client smes understanding dependency module system preparation test plan unit level integration level preparation execution test case defect tracking issue resolution risk monitoring status tracking reporting follow preparation test completion report company capgemini head office description company capgemini head office description humana health care insurance project deal supplying various medicine citizen per doctor reference patient insurance policy application keep track medicine user consumed past generates patient history citizen given drug doctor reference doctor information also linked patient history responsibility understanding requirement getting clarification client involved writing test case based test scenario execute ensuring test coverage using requirement traceability matrix rtm preparation test completion report company capgemini head office description testing trend wqr world quality report application allows user take survey different method technology used testing user choose answer type question three different category user facility search view export data excel also user get daily weekly report email new trend testing implemented around globe testing trend wqr app available android io platform responsibility understanding requirement getting clarification client writing test case based test scenario executed performing different type testing functional integration system uat defect resolution maintenance application\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"text_length\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 256,\n \"min\": 14,\n \"max\": 1411,\n \"num_unique_values\": 144,\n \"samples\": [\n 353,\n 78,\n 442\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df_resume" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
categoryclean_datatext_length
0Data Scienceskill programming language python panda numpy ...502
1Data Scienceeducation detail uit rgpv data scientist data ...123
2Data Sciencearea interest deep learning control system des...190
3Data Scienceskill python sap hana tableau sap hana sql sap...722
4Data Scienceeducation detail mca ymcaust faridabad haryana...53
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " category clean_data \\\n", "0 Data Science skill programming language python panda numpy ... \n", "1 Data Science education detail uit rgpv data scientist data ... \n", "2 Data Science area interest deep learning control system des... \n", "3 Data Science skill python sap hana tableau sap hana sql sap... \n", "4 Data Science education detail mca ymcaust faridabad haryana... \n", "\n", " text_length \n", "0 502 \n", "1 123 \n", "2 190 \n", "3 722 \n", "4 53 " ] }, "execution_count": 384, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_resume = pd.read_csv(\"/content/drive/MyDrive/Dataset/Compfest16_AIC/dataset_resume.csv\")\n", "df_resume.drop(columns=['Resume'], inplace=True)\n", "df_resume.rename(columns={'Category': 'category'}, inplace=True)\n", "df_resume.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "2GzDd1jHrpum" }, "outputs": [], "source": [ "df_resume['category'] = df_resume['category'].replace('Web Designing', 'UI/UX Designer')\n", "df_resume['category'] = df_resume['category'].replace('Database', 'database administrator')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "yvk6b-Vz--U4" }, "outputs": [], "source": [ "df_resume['category'] = df_resume['category'].str.lower()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "EWF5ENAb_B7-" }, "outputs": [], "source": [ "# FILTER BY AVAILABLE ROLE\n", "df_resume = df_resume[df_resume['category'].\n", " isin(['java developer', 'data science', 'software developer',\n", " 'systems administrator', 'project manager', 'sales',\n", " 'accountant', 'business development', 'hr',\n", " 'consultant', 'finance', 'chef', 'security analyst',\n", " 'dotnet developer', 'devops engineer', 'automation testing',\n", " 'ui/ux designer', 'web developer', 'business analyst',\n", " ])]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 398 }, "id": "Vsl_cHNkmfym", "outputId": "cb5d2bc3-11bd-417a-d630-0c0ca2a88201" }, "outputs": [ { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
count
category
java developer13
data science10
hr10
automation testing7
devops engineer7
dotnet developer7
business analyst6
sales5
ui/ux designer4

" ], "text/plain": [ "category\n", "java developer 13\n", "data science 10\n", "hr 10\n", "automation testing 7\n", "devops engineer 7\n", "dotnet developer 7\n", "business analyst 6\n", "sales 5\n", "ui/ux designer 4\n", "Name: count, dtype: int64" ] }, "execution_count": 388, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_resume['category'].value_counts()" ] }, { "cell_type": "markdown", "metadata": { "id": "at562JBVEPzc" }, "source": [ "# DATASET RESUME HUGGINGFACE 30K" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "h7odnnVuEPUv", "outputId": "56acc576-99b4-4721-883c-e89aca702d5c" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df_resumehug\",\n \"rows\": 31566,\n \"fields\": [\n {\n \"column\": \"category\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 52,\n \"samples\": [\n \"database administrator\",\n \"public relations\",\n \"systems administrator\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_data\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 31566,\n \"samples\": [\n \"software developer span lsoftwarespan span ldeveloperspan software developer icon technology inc charlotte nc work experience object oriented design modeling programming testing core java j2ee technology experience phase software development life cycle including project development scratch experienced complete project lifecycle using sdlc technique uml use case functional design document expertise object oriented programming using core java j2ee related technology proficiency developing secure web application serverside development using spring rest web service aop orm hibernate jdbc strut jsp servlets java bean javascript xml html java bean oracle soap web service various design pattern comprehensive knowledge physical logical data modeling performance tuning hand experience database including oracle db2 mysql experience environment requiring direct customer interaction requirement gathering design development support phase involved testing phase like unit testing integration testing performance testing including application profiling user acceptance testing strong analytical skill ability quickly understand client business need experience using continuous integration tool like jenkins knowledge amazon web service ec2 s3 experience memory leak detection jvm gc tuning experience working weblogic tomcat jboss experienced eclipse spring tool suite selfmotivated proven ability work independently team excellent team player quick learner selfstarter effective communication motivation organizational skill combined attention detail work experience software developer icon technology inc charlotte nc present rulo creating unique experience mortgage refinance purchase user us realtime pricing technology realtime processing technology crm system user experience significantly increase payouts couple impact well first rulo get offer wide range borrower allows user sort skip filtering step inside lendingtree go directly pricing engine way brings material increase customer satisfaction second rulo help reducing phone call increasing capacity lender massively spring boot application scratch spring mongo connection included idsrv4 oauth token validation enabled authentication rest apis designed rule engine evaluate complex expression expression tree incorporated kafka application transform mongo object relational table column used spring ioc injecting bean reduced coupling class implemented data access tier using dao asynchronous computation java completablefuture reading xml file multiple thread using sax parser used aop module handle transaction management service application identified fixed memory leak caused bug code involved deploying managing production setup aws service used aws service including ec2 vpc application deployment transforming requirement stipulation environment java spring rest service spring mvccorejpa sts svn aws ec2 s3 angular j html cs javascript security group vpc production deployment caching jms linux redhat jvm memory management design architectural pattern tdd concurrency agile maven bitbucket lead developer persistent system pune maharashtra project title cu loan platform mycb project creating loan platform aggregator web traffic originator direct personal loan application participation loan platform open multiple credit union platform single simple loan offered common term participating cu creditkyc check done using call credit service round robin cu allocation various filter agreement sending signing using adobe echosign api loan account creation disbursement using mambu apis role responsibility developed spring boot application scratch hibernate mysql created rest apis backend application integration application third party service mambu adobe echosign api call credit service involved architectural design api management using api gateway information security token based authentication role based authorization implemented design pattern command builder j2ee design pattern deployed application aws load balancer aws elastic ip white listed thirdparty apis ec2 vpc junit framework unit testing identification documentation technical depth issue prioritizing sprint transforming requirement stipulation environment core java spring rest service spring mvccorejpa aws ec2 s3 angular j html cs javascript security group vpc production deployment caching jms linux redhat jvm memory management design architectural pattern tdd concurrency agile maven project gdpr trunomi work location pune role lead developer consent management data sharing platform connects financial institution customer capturing customer consent use personal data financial institution provides secure messaging document sharing prove regulatory compliance general data protection regulation gdpr role responsibility developed nodejs back end application tpb eba part trunomi platform cassandra created rest apis application unit testing mocha implemented information security feature using hybrid encryption digital signing verification enable secure communication cfa customer front end application tpb trunomi platform backend application eba enterprise back end application multipart data environment nodejs cassandra git jira linux rest service individual contributor developer ibm india pvt ltd pune maharashtra india project title direct debit dispute barclays british multinational banking financial service company headquartered london universal bank operation retail wholesale investment banking well wealth management mortgage lending credit card direct debit dispute module added existing customer support banking application raise dispute direct debit barclays customer design application mca based architecture role responsibility implemented multithreaded solution complex computation implemented design pattern command builder j2ee design pattern involved agile project describing story listing task design application flow design development spring mvc based web application direct debit dispute identified fixed memory leak caused bug code responsible performing code review analysing risk project schedule unit testing junit framework environnent java web service log4j websphere application server tdd concurrency agile maven project bnp paribas role senior developer work location pune project title bmrc credit rick reporting system bmrc data warehouse store data credit rating credit risk different legal entity organisation across globe core technology involved plsql role responsibility converting high level design low level design wrote stored procedure using oracle plsql aggregation engine basel ii family low level design creation coding performance tuning stored procedure created unit test matrix performed unit test environment oracle g tdd project ibm software lab role java developer work location pune project title jazz service management security service security service make use single sign ltpa token work across websphere nonwebsphere application registry service shared data repository providing index application installed resource manage intended support loosely coupled integration open service lifecycle collaboration oslc expose functionality oslc service provider role responsibility incorporated cobertura running unit test case build developed ssodebug tool find problem failure encountered single sign responsible sign module single sign prototype developed oauth websphere application server tai based solution implemented command design pattern writing cli backend application wrote ddt case unit testing setup deploying product solarisredhataix platform identified deadlock issue code fixed adhering locking sequence environment java web service websphere application server linux aix tdd agile project ups united parcel service java developer work location pune project title open account marketing rate discount mrd application allows user apply rate change promo discount existing account open new account promo discount web seller account module allows web seller open online account without involving third party agent role responsibility designing developing new mrd module integrating existing application designed developed web seller account module integrated existing application requirement gathering client impact analysis project planning person estimation prepare design document design develop jsp page writing action business logic class web service oracle ejb java developer patni computer system ltd mumbai maharashtra india project title odin project related development odin application used configure celerra na device various na service like iscsi cifs nfs ui code involved multithreading role responsibility requirement analysis estimation design coding discus issue ar client resolving outofmemoryerror ui getting blocked writing strut action business logic class celerra feature like iscsi nfs cifs provisioning etc environment java struts13 web service project hitachi role java developer work location mumbai project title collaboration portal groupmax provides collaboration portal built around crossfunctionality security ubiquity globalization facilitating rich collaboration rapid knowledge acquisition beyond individual organizational framework help create virtual workplace collaboration enabling organization community bring together variety knowledge create new insight solve problem also enhanced security functionality built compliance mind applies electronic forum mobile device promote realtime communication knowledge sharing beyond barrier organization time place key bringing speed value business role responsibility requirement gathering client impact analysis interacting client clarify query regarding functionality risk analysis module term time line expected dependency module looking multithreaded solution given scenario coding code review environment core java strut web service spring hibernate oracle ejb project ge aviation u role java developer work location bangalore project title customer web center cwc goal project rebuild application initial provisioning using jsf framework portlet integrated portal based jboss portal framework initial provisioning application allows customer calculate spare part configuration based need allow place order part role responsibility requirement gathering client impact analysis interacting client clarify query regarding functionality coding code review developed dao class interact stored procedure back end developed package procedure interaction database test case creation unit testing various module environment java strut web service spring hibernate oracle ejb java15 jboss strut eclipse33 plsql developer education post graduate diploma information technology information technology iit kharagpur skill eclipse j2ee java hibernate spring jaxb jms jsp servlets strut application server git groovy nodejs jenkins svn xml mvc rest service soap\",\n \"full stack software developer full stack software span ldeveloperspan full stack software developer asoftio llc boca raton fl work experience full stack software developer asoftio llc miami fl present charge relational database design technology infrastructure implementation develop apis ruby rail backend consumed vuejs reactjs depending project scope implement bitcoin litecoin stripe payment gateway cloud mobile ecosystem practice agile methodology project sprint collaboration tool like jira trello others implement circleci cicd project led full stack developer cryptostudio llc created saas platform company sold online using stripe payment gateway crypto trading course developed tool called swap coin connected several crypto exchange create remote random order bitcoin litecoin payment method developed auto trading algorithm operate crypto exchange developed apps api ruby rail running mysql database redis queue system user platform made reactjs web front end developer bushido lab llc helped team structure new apps architecture mostly front end using react main framework backend certain apps use ruby rail case firebase project needed fast mvp ruby rail backend developer clever code sa bogot co colombia leader development team created several platform company client online advertising platform measure traffic click client website also developed ecommerce creator like shopify made laravel latin america using laravel time found many limitation hence reason moving ruby rail much reliable framework education wyncode academy fl b psychologist pontificia universidad bogot skill javascript reactjs redux php laravel ruby rail ruby rail scripting mysql nginx html5 bash linux wordpress jquery node react react node jquery nodejs link additional information skill ruby rail javascript ruby html5 css3 nodejs reactjs vuejs redux scripting linux mysql nginx npm yarn php laravel wordpress\",\n \"web developer uxui designer span lwebspan span ldeveloperspan uxui designer web designer demonstrated history working uxui edison nj experienced web designer demonstrated history working user experience information technology education industry skilled sketch cascading style sheet cs html wireframing ui prototyping strong designing professional master degree focused computer science authorized work u employer work experience web developer uxui designer academy belleville nj present created washington academy official website based wordpress initiated user experience research design client implemented website portal district parent teacher implemented designing skill technical knowledge research delivery full stack developer finslide technology corp new york ny efficiently shared skill design functionality finslide mobile webbased module ux ui web developer desktop creator successfully worked user experience user interface client desktop creator applying knowledge web development education master computer science monroe college new rochelle bachelor computer application university skill user experience sketch wireframe html css3 ux adobe ui user interface link assessment graphic design highly proficient measure candidate ability create visual medium effectively communicate information concept full result basic word processing microsoft word expert measure candidate knowledge basic microsoft word technique word processing including use tool format edit text full result indeed assessment provides skill test indicative license certification continued development professional field\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"text_length\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 543,\n \"min\": 1,\n \"max\": 8930,\n \"num_unique_values\": 2594,\n \"samples\": [\n 741,\n 2301,\n 1925\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df_resumehug" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
categoryclean_datatext_length
0accountantresult oriented organized bilingual accounting...550
1accountantflexible accountant adapts seamlessly constant...865
2accountanthighly analytical detail oriented professional...699
3accountantanalysis prepare auction sale journal finalize...308
4accountantexperience accounting profession bachelor degr...482
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " category clean_data text_length\n", "0 accountant result oriented organized bilingual accounting... 550\n", "1 accountant flexible accountant adapts seamlessly constant... 865\n", "2 accountant highly analytical detail oriented professional... 699\n", "3 accountant analysis prepare auction sale journal finalize... 308\n", "4 accountant experience accounting profession bachelor degr... 482" ] }, "execution_count": 389, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_resumehug = pd.read_csv(\"/content/drive/MyDrive/Dataset/Compfest16_AIC/resume30k_noner.csv\")\n", "df_resumehug = df_resumehug.drop(columns=['Unnamed: 0'])\n", "df_resumehug.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "WO2j_WjJEchX", "outputId": "f1ca5b2e-e89d-450e-a13d-c381fb2001ed" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 31566 entries, 0 to 31565\n", "Data columns (total 3 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 category 31566 non-null object\n", " 1 clean_data 31566 non-null object\n", " 2 text_length 31566 non-null int64 \n", "dtypes: int64(1), object(2)\n", "memory usage: 740.0+ KB\n" ] } ], "source": [ "df_resumehug.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "sZ_RWsh8EeAe" }, "outputs": [], "source": [ "df_resumehug['category'] = df_resumehug['category'].str.lower()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "PacAHJHkEiP0", "outputId": "dbd4817b-7cbb-40fb-9f11-fa67f8c3f41c" }, "outputs": [ { "data": { "text/plain": [ "52" ] }, "execution_count": 392, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_resumehug['category'].value_counts().count()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "EDGNusMUErqp" }, "outputs": [], "source": [ "df_resumehug = df_resumehug.drop_duplicates(subset='clean_data', keep='first')\n", "df_resumehug = df_resumehug.dropna(subset=['clean_data'])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "V0l_HNakEuQ3" }, "outputs": [], "source": [ "# FILTER BY AVAILABLE ROLE\n", "df_resumehug = df_resumehug[df_resumehug['category'].\n", " isin(['java developer', 'data science', 'software developer',\n", " 'systems administrator', 'project manager', 'sales',\n", " 'accountant', 'business development', 'hr',\n", " 'consultant', 'finance', 'chef', 'security analyst',\n", " 'dotnet developer', 'devops engineer', 'automation testing',\n", " 'ui/ux designer', 'web developer', 'business analyst', 'database administrator'\n", " ])]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "P0zbMQGrEy1_", "outputId": "ec3d96e2-5b6c-4743-9c63-cdc169e89a9a" }, "outputs": [ { "data": { "text/plain": [ "19" ] }, "execution_count": 395, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_resumehug['category'].value_counts().count()" ] }, { "cell_type": "markdown", "metadata": { "id": "SoOpLTYrsfpW" }, "source": [ "# DATASET JOB DESCRIPTION DATA SCIENCE 10K" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "Hqrspodbl05N", "outputId": "a60581d6-2f3b-4445-9024-66fe91bbbfed" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df_jobds\",\n \"rows\": 7738,\n \"fields\": [\n {\n \"column\": \"category\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 1,\n \"samples\": [\n \"data science\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_data\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 7218,\n \"samples\": [\n \"title data scientist location houston tx duration month job description year experience working supervised unsupervised machine learning year performing anomaly detection year programming python year working data visualization ability communicate finding experience data wrangling statistic advance splunk knowledge implementing data science model within splunk note strong d resource background cyber security good experience machine learning specified algorithm\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df_jobds" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
categoryclean_data
0data sciencefarmer join team diverse professional farmer a...
1data scienceimmediate opening sharp data scientist strong ...
2data sciencecandidate following background skill character...
3data scienceblackrock blackrock help investor build better...
4data scienceseeking extraordinary data scientist charlotte...
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " category clean_data\n", "0 data science farmer join team diverse professional farmer a...\n", "1 data science immediate opening sharp data scientist strong ...\n", "2 data science candidate following background skill character...\n", "3 data science blackrock blackrock help investor build better...\n", "4 data science seeking extraordinary data scientist charlotte..." ] }, "execution_count": 396, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_jobds = pd.read_csv(\"/content/drive/MyDrive/Dataset/Compfest16_AIC/output_dsjob.csv\")\n", "df_jobds.drop(columns=['job_description'], inplace=True)\n", "df_jobds.rename(columns={'job_title': 'category'}, inplace=True)\n", "df_jobds['category'] = 'data science'\n", "df_jobds.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 147 }, "id": "BsVEIB2dl9JC", "outputId": "654d49d7-7f57-433f-e00c-17b914a69687" }, "outputs": [ { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
count
category
data science7738

" ], "text/plain": [ "category\n", "data science 7738\n", "Name: count, dtype: int64" ] }, "execution_count": 397, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_jobds['category'].value_counts()" ] }, { "cell_type": "markdown", "metadata": { "id": "m1muGpmlsoK6" }, "source": [ "# DATASET JOB DESCRIPTION 30K" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "fyLlhgg2ms_X", "outputId": "81cdd10d-6cb1-4ab5-aa6c-5a39a7d9a2a3" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df_joball\",\n \"rows\": 4988,\n \"fields\": [\n {\n \"column\": \"category\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 4116,\n \"samples\": [\n \"Head of Business Process (Hospitality - Cisarua)\",\n \"Head of HR Strategy & Development\",\n \"Content Creator Copywriter Specialist\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_data\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 4985,\n \"samples\": [\n \"accountant accounting tax finance expertise experience managing finance retail company proficient using microsoft excel accounting software willing work semarang central java en ko rio one leading jewelry company semarang cv sentosa dik known kom bunga tanjung opening limited opportunity outstanding accountant join accounting tax supervisor placed semarang central java toko ma bunga tanjung believe best service client satisfaction important want provide world class service always working synergistically achieve common goal want work also learn together school life waiting cv requirement general accounting tax staff profession also intended looking position accounting tax finance accounting supervisor accounting tax supervisor finance supervisor accounting supervisor tax supervisor minimum education bachelor age twenty five thirty five year least three year experience accounting tax finance proficient using microsoft office powerpoint excel word outlook especially microsoft excel proficient using accounting system software experience working accounting tax retail company pleasant personality work quickly pay attention detail responsibility responsible bookkeeping company financial transaction offline store online store accounting function invoice receivables payable financial report control function budgeting general ledger reconciliation data quality connection posting accounting system monitor bank account reconciliation treasurer function cashier petty cash bank receipt payment create financial report manage appropriate tax transaction applicable provision vat pph twenty one pph twenty five corporate pph benefit full job permanent full time employment status fun family like working atmosphere thr meet criterion action send cv photo last salary february seventeen 2022allcvs handled strictly confidentially selected candidate contacted\",\n \"responsibility responsible collection effort customer arrears installment payment potentially risky company qualification minimum two year experience financial institution retail banking credit card coordinator strong analytical strategic skill field collection able collaborate third party related authority minimum associate degree graduate ac driving license motorbike like field work placement jakarta east bekasi regency\",\n \"duty responsibility greet customer friendly manner provide input customer interest drink need explain menu requested customer prepare serve coffee drink according recipe improve reputation coffee shop continuing maintain quality dish qualification age twenty thirty year receive education important thing experienced high work ethic minimum one year experience experience barista neat polite appearance\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df_joball" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
categoryclean_data
0PROCUREMENT & EXIM SUPERVISORprocurement exim supervisor requirement 1 leas...
1Staff Adminqualification open age minimum education high ...
2Motion Graphic Designerrequirement bachelor degree equivalent design ...
3Asisten Associate Managercrave freedom work get comfort zone faster sig...
4Staff Design Developmentjob responsibility responsible process develop...
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " category \\\n", "0 PROCUREMENT & EXIM SUPERVISOR \n", "1 Staff Admin \n", "2 Motion Graphic Designer \n", "3 Asisten Associate Manager \n", "4 Staff Design Development \n", "\n", " clean_data \n", "0 procurement exim supervisor requirement 1 leas... \n", "1 qualification open age minimum education high ... \n", "2 requirement bachelor degree equivalent design ... \n", "3 crave freedom work get comfort zone faster sig... \n", "4 job responsibility responsible process develop... " ] }, "execution_count": 398, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_joball = pd.read_csv(\"/content/drive/MyDrive/Dataset/Compfest16_AIC/combined_df.csv\")\n", "df_joball.drop(columns=['id', 'location', 'salary_currency', 'career_level', 'experience_level', 'education_level', 'employment_type',\n", " 'job_function', 'job_benefits', 'company_process_time', 'company_size', 'company_industry', 'job_description', 'salary'], inplace=True)\n", "df_joball.rename(columns={'job_title': 'category'}, inplace=True)\n", "df_joball.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "kaN4Rko0og9E" }, "outputs": [], "source": [ "category_counts = df_joball['category'].value_counts()\n", "\n", "categories_to_keep = category_counts[category_counts > 1].index\n", "\n", "df_joball = df_joball[df_joball['category'].isin(categories_to_keep)]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "vJV1_v6eLmnw", "outputId": "d44d6e3b-69bd-45c0-b639-5fd60ebfbb5b" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 1229 entries, 1 to 4983\n", "Data columns (total 2 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 category 1229 non-null object\n", " 1 clean_data 1229 non-null object\n", "dtypes: object(2)\n", "memory usage: 28.8+ KB\n" ] } ], "source": [ "df_joball.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "QXN9P8qgphwX", "outputId": "b585d077-fc96-4396-d774-86b887104bdf" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":13: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace(values_to_replace, 'Sales')\n" ] } ], "source": [ "# REPLACE SALES\n", "values_to_replace = ['Sales Executive', 'Sales', 'Sales Engineer', 'Sales Manager',\n", " 'Sales Marketing', 'Sales Supervisor', 'SALES EXECUTIVE', 'SALES ENGINEER',\n", " 'SALES', 'Sales Project', 'Salesman', 'Sales Representative', 'SALES MANAGER',\n", " 'Sales Staff', 'SALES SUPERVISOR', 'Area Sales Manager', 'Sales Staff',\n", " 'Admin Sales', 'Area Sales Supervisor', 'SALES MARKETING', 'Direct Sales',\n", " 'Sales Admin', 'Sales Associate', 'Sales & Marketing Manager', 'Sales Motoris',\n", " 'Sales Bahan Bangunan', 'Sales HORECA', 'Sales Assistant Manager', 'SALES TAKING ORDER',\n", " 'Sales Executive (Jakarta)', 'Sales Consultant', 'Sales Administration', 'Sales Canvas',\n", " 'Sales Specialist', 'Sales Marketing Executive', 'Sales Officer', 'Sales Trainer'\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'Sales')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "mSiCTHz-YKoA", "outputId": "08c47370-179a-4efa-f734-4932882c5cbc" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":8: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace(values_to_replace, 'Accounting')\n" ] } ], "source": [ "# REPLACE ACCOUNTING\n", "values_to_replace = ['Senior Staff Accounting', 'Staff Accounting & Tax', 'Staff Accounting', 'STAFF ACCOUNTING',\n", " 'Finance & Accounting Staff', 'ACCOUNTING', 'Accounting Staff', 'Accounting',\n", " 'Finance & Accounting', 'Finance Accounting Manager', 'Accounting Officer', 'Finance & Accounting Supervisor', 'Accounting Supervisor',\n", " 'Accounting and Tax Staff', 'ACCOUNTING STAFF', 'Senior Accounting', 'FINANCE & ACCOUNTING STAFF',\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'Accounting')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "XPYucx_9Ztb6", "outputId": "b698d34b-3cf1-4fa3-841e-2e78a06aa106" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":10: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace(values_to_replace, 'Marketing')\n" ] } ], "source": [ "# REPLACE MARKETING\n", "values_to_replace = ['Marketing', 'Marketing Executive', 'Digital Marketing', 'Marketing Manager',\n", " 'Digital Marketing Officer', 'Marketing Communication Manager', 'Marketing Officer', 'Digital Marketing Specialist',\n", " 'Staff Marketing', 'MARKETING', 'DIGITAL MARKETING', 'Head of Marketing', 'TELEMARKETING',\n", " 'Senior Marketing Executive', 'STAFF MARKETING', 'Telemarketing', 'Marketing Coordinator',\n", " 'Sales Marketing Executive', 'Online Marketing', 'Marketing Communication Specialist', 'MARKETING SUPPORT',\n", " 'Digital Marketing Manager', 'Assistant Marketing Manager', 'Marketing Supervisor', 'Marketing Staff',\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'Marketing')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "B9_5hoeeeRHF", "outputId": "23b79b2c-fe27-4a75-a1e6-663cecd07e4a" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":5: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace(values_to_replace, 'software developer')\n" ] } ], "source": [ "# REPLACE SOFTWARE DEVELOPER\n", "values_to_replace = ['Software Developer', 'Senior Software Engineer', 'Software Engineer'\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'software developer')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "zh7-X11febM8", "outputId": "d46faf20-5e6f-4aed-8719-7e84b8891dfa" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":1: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace('Software Quality Assurance (Automation)', 'Automation Testing')\n", ":2: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace('.NET Developer', 'DotNet Developer')\n", ":3: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace('Data Scientist', 'data science')\n", ":4: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace('Data Analyst', 'data science')\n", ":5: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace('Accounting', 'accountant')\n", ":6: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace('System Administrator', 'systems administrator')\n" ] } ], "source": [ "df_joball['category'] = df_joball['category'].replace('Software Quality Assurance (Automation)', 'Automation Testing')\n", "df_joball['category'] = df_joball['category'].replace('.NET Developer', 'DotNet Developer')\n", "df_joball['category'] = df_joball['category'].replace('Data Scientist', 'data science')\n", "df_joball['category'] = df_joball['category'].replace('Data Analyst', 'data science')\n", "df_joball['category'] = df_joball['category'].replace('Accounting', 'accountant')\n", "df_joball['category'] = df_joball['category'].replace('System Administrator', 'systems administrator')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "RTIN6cBUeyV6", "outputId": "99f6b710-8221-4341-d359-35abe4df4085" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":6: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace(values_to_replace, 'hr')\n" ] } ], "source": [ "# REPLACE HR\n", "values_to_replace = ['HRD Staff', 'HR Supervisor', 'HR Staff', 'HRD',\n", " 'HR Manager', 'HR & GA Staff', 'HRD & GA Manager', 'HR MANAGER', 'HRD Manager'\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'hr')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "NtsUD5GvfygQ", "outputId": "8654d54d-bb5a-444a-a8cf-02b1c64d5bde" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":6: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace(values_to_replace, 'web developer')\n" ] } ], "source": [ "# REPLACE WEB DEVELOPER\n", "values_to_replace = ['Web Developer', 'Front End Developer', 'Frontend Developer', 'Front-end Developer', 'Web Programmer',\n", " 'FULLSTACK DEVELOPER', 'Full Stack Developer', 'Back End Developer', 'Backend Engineer', 'Backend Developer'\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'web developer')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ppJU3FkOiNHv", "outputId": "0ad1fb9a-dd80-4970-f163-aa865220bf05" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":5: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace(values_to_replace, 'project manager')\n" ] } ], "source": [ "# REPLACE PROJECT MANAGER\n", "values_to_replace = ['Project Manager (MEP)', 'PROJECT MANAGER', 'Assistant Project Manager', 'IT Project Manager', 'Project Manager',\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'project manager')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "dje-WAxCpWta", "outputId": "d04bffd3-490b-4cc6-d034-29d376cf9936" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":5: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " df_joball['category'] = df_joball['category'].replace(values_to_replace, 'business development')\n" ] } ], "source": [ "values_to_replace = ['Business Development Officer', 'Business Development Manager', 'BUSINESS DEVELOPMENT MANAGER', 'Business Development'\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'business development')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "nu4fWVzzpfyu" }, "outputs": [], "source": [ "values_to_replace = ['Chef de Partie', 'Chef', 'Head Chef', 'Cook', 'COOK', 'Cook Helper'\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'chef')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "GiQ7ddeApocU" }, "outputs": [], "source": [ "values_to_replace = ['Finance, Accounting & Tax Manager', 'Finance Accounting Supervisor', 'Finance Officer', 'STAFF FINANCE', 'Staff Finance & Accounting',\n", " 'Finance Accounting Staff', 'FINANCE STAFF', 'Finance Supervisor', 'Staff Finance', 'Finance', 'Finance Staff'\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'finance')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "Z540fxwgp2SP" }, "outputs": [], "source": [ "\n", "values_to_replace = ['Tax Consultant', 'Senior Recruitment Consultant'\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'consultant')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "IlMZ9Ksap9dv" }, "outputs": [], "source": [ "values_to_replace = ['IT Business Analyst', 'Business Analyst','Senior IT Business Analys'\n", " ]\n", "\n", "df_joball['category'] = df_joball['category'].replace(values_to_replace, 'business analyst')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "ggpSu0U--1JH" }, "outputs": [], "source": [ "df_joball['category'] = df_joball['category'].str.lower()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "B9gPAkb3qCls" }, "outputs": [], "source": [ "# FILTER BY AVAILABLE ROLE\n", "df_joball = df_joball[df_joball['category'].\n", " isin(['java developer', 'data science', 'software developer',\n", " 'systems administrator', 'project manager', 'sales',\n", " 'accountant', 'business development', 'hr',\n", " 'consultant', 'finance', 'chef', 'security analyst',\n", " 'dotnet developer', 'devops engineer', 'automation testing',\n", " 'ui/ux designer', 'web developer', 'business analyst',\n", " ])]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ch0ccJ9O-gIp", "outputId": "329ec2c6-0a7e-4952-fa1e-92d45a6f2dd8" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 458 entries, 15 to 4981\n", "Data columns (total 2 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 category 458 non-null object\n", " 1 clean_data 458 non-null object\n", "dtypes: object(2)\n", "memory usage: 10.7+ KB\n" ] } ], "source": [ "df_joball.info()" ] }, { "cell_type": "markdown", "metadata": { "id": "HsGd7NQZvFyh" }, "source": [ "# DATASET IT JOBS 10K" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "XXl5A_Ept7if", "outputId": "86faa44e-cdf0-43fe-86de-114c18785d12" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df_job\",\n \"rows\": 9376,\n \"fields\": [\n {\n \"column\": \"category\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 25,\n \"samples\": [\n \"Machine Learning\",\n \"Technology Integration\",\n \"Data Scientist\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_data\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 9327,\n \"samples\": [\n \"bachelor degree computer science related technical discipline equivalent combination education technical certification training work experience active t clearance five eight year directly related experience system administration window server operating system o two thousand eight two thousand twelve two thousand sixteen window desktop o seven ten window active directory ad group policy object gpo administrative experience hand experience exchange sharepoint m wsus vmware data server backup experience knowledge linux operating system\",\n \"job summary working direct supervision provides routine day today operation administrative support business unit large department assist coordination budget process improvement control specialized software function enabling department meet objective effective efficient manner essential duty responsibility analyzes monthly department budget report maintain expense control prepares commentary explanation variance management review assist system administration specialized software utilized business group support operation research resolve routine support issue follows ensure open issue resolved assist preparing user reference material troubleshoots resolve simple inquiry request internal external client review monitor department process procedure identify opportunity improve service delivery internal external customer may network external contact research recommend best practice coordinate budget preparation research collect input multiple internal external resource compiles variety operating financial statistical information needed respond management request coordinate work department may add commentary complete analysis report proposal assist communication best practice policy procedure initiative support operation help facilitate process improvement engaging appropriate resource issue identification resolution assist developing project plan cost including personnel fiscal requirement achieve defined objective may provide periodic update relative project resource fiscal plan performs duty assigned supervisory responsibility formal supervisory responsibility position provides informal assistance technical guidance training coworkers may lead project team plan supervise assignment lower level employee qualification perform job successfully individual must able perform essential duty satisfactorily requirement listed representative knowledge skill ability required reasonable accommodation may made enable individual disability perform essential function education experience bachelor degree babs equivalent four year college university plus minimum two year related work experience include budgeting finance business analytics equivalent combination education experience work experience related specific department business unit function preferred certificate license none communication skill excellent written verbal communication skill strong organizational analytical skill ability provide efficient timely reliable courteous service customer ability effectively present information financial knowledge requires knowledge financial term principle ability calculate intermediate figure percentage discount commission conduct basic financial analysis reasoning ability ability comprehend analyze interpret document ability solve problem involving several option situation requires intermediate analytical quantitative skill skill ability advanced proficiency microsoft office suite spreadsheet skill set include advanced function graphic pivottables scope responsibility decision made understanding procedure company policy achieve set result deadline responsible setting project deadline error judgment may cause short term impact coworkers supervisor\",\n \"science technology mission sixty year lawrence livermore national laboratory llnl applied science technology make world safer place seeking highly qualified scientist engineer join interdisciplinary team system analyst supporting program across global security principal directorate chemical biological explosive security nuclear threat reduction intelligence program energy infrastructure cybersecurity apply combination technical depth breadth critical thinking modeling simulation analysis understand multidomain problem area provide decision insight communicate option tradeoff facilitates integration new technology support customer mission position programmatically global security system analysis group administratively report payroll supervisor hiring organization position filled either thesis two s three level depending qualification additional job responsibility outlined assigned selected higher level essential duty provide solution requiring advanced analysis creative use innovation method problem intermediate complexity collaborating scientist researcher across variety technical discipline create analytical framework evaluate competing characteristic determine solution effectively meet customer stakeholder objective provide decision insight stakeholder moderately complex problem area develop evaluate apply physical computational simulation gain insight fairly complex system partner llnl scientist engineer bring research result practical use llnl global security program communicate technical concept intermediate complexity stakeholder concise effective way perform duty assigned addition thesis three level manage multiple parallel task priority customer stakeholder ensure deadline met lead various complex project leverage team member skill complete complex project task mentor staff assist recruiting effort serve primary technical point contact sponsor stakeholder participate development new program business qualification m engineering physical computer science related field equivalent combination education related experience comprehensive record technical achievement demonstrated ability approach hard problem enthusiasm creativity flexibility change focus necessary comprehensive analytical problem solving decision making skill develop creative solution moderately complex problem proficient verbal written interpersonal communication skill necessary effectively collaborate multidisciplinary team environment communicate technical information document work prepare present successful proposal high quality research paper ability travel offsite including potentially internationally sponsor customer interaction addition thesis three level significant experience leading system analysis project advanced analytical problem solving decision making skill develop creative solution complex problem demonstrated ability work independently effectively manage advanced concurrent technical task competing priority implement advanced research concept multidisciplinary team environment commitment deadline important project success desired qualification phd engineering physical computer science expertise one following area cybersecurity modeling simulation risk analysis data analytics chemical biological security explosive intelligence analysis radiological nuclear security energy system infrastructure protection expert knowledge substantial experience project manager principal investigator project competing priority loosely defined deliverable high visibility significant experience working department homeland security department energy intelligence community relevant government sponsor preemployment drug test external applicant selected position required pas post offer preemployment drug test security clearance position requires department energy eq level clearance selected initiate federal background investigation determine meet eligibility requirement access classified information matter additional q cleared employee subject random drug testing q level clearance requires u citizenship hold multiple citizenship u another country may required renounce non u citizenship doel q clearance processed granted note career indefinite position lab employee external candidate may considered position u lawrence livermore national laboratory llnl located san francisco bay area eastbay premier applied science laboratory part national nuclear security administration nnsa within department energy doell nls mission strengthening national security developing applying cutting edge science technology engineering respond vision quality integrity technical excellence scientific issue national importance laboratory current annual budget one eight billion employing approximately six five hundred employee llnl affirmative action equal opportunity employer qualified applicant receive consideration employment without regard race color religion marital status national origin ancestry sex sexual orientation gender identity disability medical condition protected veteran status age citizenship characteristic protected law\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df_job" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
categoryclean_data
0Data Scientistjob description junior data scientist ibm work...
1Data Scientistoverall summary data scientist data science so...
2Data Scientistteam data science team newly formed applied re...
3Data Scientistneed junior data scientist ny area remote succ...
4Data Scientistwant help guide core business spot using insig...
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " category clean_data\n", "0 Data Scientist job description junior data scientist ibm work...\n", "1 Data Scientist overall summary data scientist data science so...\n", "2 Data Scientist team data science team newly formed applied re...\n", "3 Data Scientist need junior data scientist ny area remote succ...\n", "4 Data Scientist want help guide core business spot using insig..." ] }, "execution_count": 417, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_job = pd.read_csv(\"/content/drive/MyDrive/Dataset/Compfest16_AIC/it job full.csv\")\n", "df_job.drop(columns=['ID', 'Job Title', 'Description'], inplace=True)\n", "df_job.rename(columns={'Query': 'category'}, inplace=True)\n", "df_job.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "C-JCQ9hLxwEP", "outputId": "a0599023-af9e-4d03-ee2d-2cd190406e2f" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 9376 entries, 0 to 9375\n", "Data columns (total 2 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 category 9376 non-null object\n", " 1 clean_data 9376 non-null object\n", "dtypes: object(2)\n", "memory usage: 146.6+ KB\n" ] } ], "source": [ "df_job.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "zuTDmbOzxyUq", "outputId": "3755f693-8b68-41ca-d7ac-d38c25813973" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "category 49\n", "clean_data 49\n", "dtype: int64\n" ] } ], "source": [ "train_duplicates = df_job[df_job['clean_data'].duplicated()].count()\n", "print(train_duplicates)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "_Qx55NOp2nRc" }, "outputs": [], "source": [ "df_job = df_job.drop_duplicates(subset='clean_data', keep='first')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "CtMf82b88XXE" }, "outputs": [], "source": [ "# Ensure you're working with a copy of the DataFrame to avoid the warning\n", "df_job = df_job.copy()\n", "\n", "# Perform the replacements using .loc\n", "df_job.loc[df_job['category'] == 'IT Systems Administrator', 'category'] = 'systems administrator'\n", "df_job.loc[df_job['category'] == 'Database Administrator', 'category'] = 'database administrator'\n", "df_job.loc[df_job['category'] == 'Data Scientist', 'category'] = 'data science'\n", "df_job.loc[df_job['category'] == 'Data Analyst', 'category'] = 'data science'\n", "df_job.loc[df_job['category'] == 'Information Security Analyst', 'category'] = 'security analyst'\n", "df_job.loc[df_job['category'].isin(['Business Intelligence Analyst', 'Business Analyst']), 'category'] = 'business analyst'\n", "df_job.loc[df_job['category'] == 'Full Stack Developer', 'category'] = 'web developer'" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "6oVhgPVV9RCu" }, "outputs": [], "source": [ "# FILTER BY AVAILABLE ROLE\n", "df_job = df_job[df_job['category'].isin(['data science', 'business analyst', 'database administrator', 'systems administrator', 'security analyst', 'web developer'])]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "VrHkyHlS2wR7", "outputId": "295ec92c-be85-418b-8db6-d0e4613d292f" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 3103 entries, 0 to 9023\n", "Data columns (total 2 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 category 3103 non-null object\n", " 1 clean_data 3103 non-null object\n", "dtypes: object(2)\n", "memory usage: 72.7+ KB\n" ] } ], "source": [ "df_job.info()" ] }, { "cell_type": "markdown", "metadata": { "id": "vxQdxyLMAEAT" }, "source": [ "# MERGE DATASET JOB DESCRIPTION" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "cjyasnSO220k", "outputId": "2a1114da-478d-4a2f-b198-46eba9c570f3" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 3561 entries, 0 to 3560\n", "Data columns (total 2 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 category 3561 non-null object\n", " 1 clean_data 3561 non-null object\n", "dtypes: object(2)\n", "memory usage: 55.8+ KB\n" ] } ], "source": [ "df_job = pd.concat([df_job, df_joball], axis=0, ignore_index=True)\n", "df_job.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "9EdoEC19DINP", "outputId": "0bda06d0-8c26-4625-abb9-64ca40aec202" }, "outputs": [ { "data": { "text/plain": [ "20" ] }, "execution_count": 425, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_job['category'].value_counts().count()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "2STQ-MtaCeAJ", "outputId": "a351eaba-0525-4f56-e54e-2282123e8db1" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "category 0\n", "clean_data 0\n", "dtype: int64\n" ] } ], "source": [ "train_duplicates = df_job[df_job['clean_data'].duplicated()].count()\n", "print(train_duplicates)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "zYugEf8-DGv5" }, "outputs": [], "source": [ "df_job = df_job.drop_duplicates(subset='clean_data', keep='first')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "SbmttzbsDL8r", "outputId": "864997f2-faf5-4105-975b-3e2bc935a3d9" }, "outputs": [ { "data": { "text/plain": [ "20" ] }, "execution_count": 428, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_job['category'].value_counts().count()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "m-1Pb-gKDX7i", "outputId": "29985fab-d318-4752-8981-fae886def20f" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 3561 entries, 0 to 3560\n", "Data columns (total 2 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 category 3561 non-null object\n", " 1 clean_data 3561 non-null object\n", "dtypes: object(2)\n", "memory usage: 55.8+ KB\n" ] } ], "source": [ "df_job.info()" ] }, { "cell_type": "markdown", "metadata": { "id": "LAfwoBsVBpAc" }, "source": [ "# MERGE DATASET RESUME" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "UuPEBYRwBk-I", "outputId": "9fa783c3-b564-4560-9178-39b262375103" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 25318 entries, 0 to 25317\n", "Data columns (total 3 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 category 25318 non-null object\n", " 1 clean_data 25318 non-null object\n", " 2 text_length 25318 non-null int64 \n", "dtypes: int64(1), object(2)\n", "memory usage: 593.5+ KB\n" ] } ], "source": [ "df_resume = pd.concat([df_resume, df_resumehug], axis=0, ignore_index=True)\n", "df_resume.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yxnWI6yDdpsx", "outputId": "69f0868e-bb50-4dd2-ea42-cf4d2070c21c" }, "outputs": [ { "data": { "text/plain": [ "20" ] }, "execution_count": 431, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_resume['category'].value_counts().count()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 178 }, "id": "LSsjbuDGdwMF", "outputId": "cb614b66-ccb6-4e31-b3a8-9498b264a1d0" }, "outputs": [ { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
0
category4
clean_data4
text_length4

" ], "text/plain": [ "category 4\n", "clean_data 4\n", "text_length 4\n", "dtype: int64" ] }, "execution_count": 432, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_resume[df_resume['clean_data'].duplicated()].count()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "zSViWWzudzEJ" }, "outputs": [], "source": [ "df_resume = df_resume.drop_duplicates(subset='clean_data', keep='first')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Ej8i98zzd2iY", "outputId": "a00bbcfb-f8e7-4a3f-a0b8-5dc28792ca78" }, "outputs": [ { "data": { "text/plain": [ "20" ] }, "execution_count": 434, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_resume['category'].value_counts().count()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "5mTz8iiud6fV", "outputId": "5d97106c-ee18-4e96-b30a-7aa2e889b03e" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 25314 entries, 0 to 25317\n", "Data columns (total 2 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 category 25314 non-null object\n", " 1 clean_data 25314 non-null object\n", "dtypes: object(2)\n", "memory usage: 593.3+ KB\n" ] } ], "source": [ "df_resume = df_resume.drop(columns=['text_length'])\n", "df_resume.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 175 }, "id": "_5HscermkCa_", "outputId": "d30e9c4d-1a64-43bc-a745-a7bcda1dc510" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df_resume\",\n \"rows\": 4,\n \"fields\": [\n {\n \"column\": \"category\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 4,\n \"samples\": [\n 20,\n \"5804\",\n \"25314\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_data\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"25314\",\n \"skill programming language python panda numpy scipy scikit learn matplotlib sql java javascript jquery machine learning regression svm na\\u00e3 bayes knn random forest decision tree boosting technique cluster analysis word embedding sentiment analysis natural language processing dimensionality reduction topic modelling lda nmf pca neural net database visualization mysql sqlserver cassandra hbase elasticsearch d3 j dc j plotly kibana matplotlib ggplot tableau others regular expression html cs angular logstash kafka python flask git docker computer vision open cv understanding deep detail data science assurance associate data science assurance associate ernst young llp skill detail javascript experience twenty four month jquery experience twenty four month python experience detail company ernst young llp description fraud investigation dispute service assurance technology assisted review tar technology assisted review assist accelerating review process run analytics generate report core member team helped developing automated review platform tool scratch assisting discovery domain tool implement predictive coding topic modelling automating review resulting reduced labor cost time spent lawyer review understand end end flow solution research development classification model predictive analysis mining information present text data worked analyzing output precision monitoring entire tool tar assist predictive coding topic modelling evidence following ey standard developed classifier model order identify red flag fraud related issue tool technology python scikit learn tfidf word2vec doc2vec cosine similarity na\\u00e3 bayes lda nmf topic modelling vader text blob sentiment analysis matplot lib tableau dashboard reporting multiple data science analytic project usa client text analytics motor vehicle customer review data received customer feedback survey data past one year performed sentiment positive negative neutral time series analysis customer comment across category created heat map term survey category based frequency word extracted positive negative word across survey category plotted word cloud created customized tableau dashboard effective reporting visualization chatbot developed user friendly chatbot one product handle simple question hour operation reservation option chat bot serf entire product related question giving overview tool via qa platform also give recommendation response user question build chain relevant answer intelligence build pipeline question per user requirement asks relevant recommended question tool technology python natural language processing nltk spacy topic modelling sentiment analysis word embedding scikit learn javascript jquery sqlserver information governance organization make informed decision information store integrated information governance portfolio synthesizes intelligence across unstructured data source facilitates action ensure organization best positioned counter information risk scan data multiple source format parse different file format extract meta data information push result indexing elastic search created customized interactive dashboard using kibana preforming rot analysis data give information data help identify content either redundant outdated trivial preforming full text search analysis elastic search predefined method tag pii personally identifiable information social security number address name etc frequently targeted cyber attack tool technology python flask elastic search kibana fraud analytic platform fraud analytics investigative platform review red flag case fap fraud analytics investigative platform inbuilt case manager suite analytics various erp system used client interrogate accounting system identifying anomaly indicator fraud running advanced analytics tool technology html javascript sqlserver jquery cs bootstrap node j d3 j dc j\",\n \"1\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
categoryclean_data
count2531425314
unique2025314
topsoftware developerskill programming language python panda numpy ...
freq58041
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " category clean_data\n", "count 25314 25314\n", "unique 20 25314\n", "top software developer skill programming language python panda numpy ...\n", "freq 5804 1" ] }, "execution_count": 436, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_resume.describe()" ] }, { "cell_type": "markdown", "metadata": { "id": "8ESVu_4gd_-y" }, "source": [ "# Merge training dataset" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "NTcgkyOyrc7u", "outputId": "71c8569a-bcdd-454d-c3cc-50f224b2ee2e" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 452 entries, 0 to 451\n", "Series name: category\n", "Non-Null Count Dtype \n", "-------------- ----- \n", "452 non-null object\n", "dtypes: object(1)\n", "memory usage: 3.7+ KB\n", "None\n", "\n", "RangeIndex: 637 entries, 0 to 636\n", "Series name: category\n", "Non-Null Count Dtype \n", "-------------- ----- \n", "637 non-null object\n", "dtypes: object(1)\n", "memory usage: 5.1+ KB\n", "None\n" ] } ], "source": [ "def sample_or_all(group):\n", " return group.head(40)\n", "\n", "# Apply the function to each group\n", "df_jd = df_job.groupby('category').apply(sample_or_all).reset_index(drop=True)\n", "\n", "print(df_jd['category'].info())\n", "\n", "# Apply the function to each group\n", "df_res = df_resume.groupby('category').apply(sample_or_all).reset_index(drop=True)\n", "\n", "print(df_res['category'].info())" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "_d97s5ePt5NF", "outputId": "4001fd0b-dc23-4c73-888b-8b0b105a9f0b" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df_label1\",\n \"rows\": 15718,\n \"fields\": [\n {\n \"column\": \"clean_cv\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 637,\n \"samples\": [\n \"participated intra college cricket competition various sport event group dance college cultural programme education detail msc computer science pune pune university bsc computer science pune pune university hsc semi english pune maharashatra board ssc semi english pune maharashatra board dot net developer dot net developer skill detail html cs sql experience six month javascript experience le one year month sql two thousand twelve experience le one year detail company description\",\n \"network administrator span lnetworkspan span ladministratorspan greer sc work experience network administrator department education spartanburg sc present implemented local area network lan wide area network wan intranet extranets data network maintained network availability multiple networking environment administering cisco campusbased switching environment fiberbased copperbased ethernet connectivity 1gig 10gig installs manages maintains cisco switching component support campus wan distributed core architecture work cisco chassisbased system internet circuit termination equipment advanced cisco management tool managed cisco prime infrastructure analyze network health workflow access information security requirement performing router switch administration interface configuration switching protocol experience network router switch strong cisco switch router configuration experience workd knowledge tcpip dns acls arp radius ipv6 dhcp intrusion prevention authentication isp circuit connection developed execute test plan check infrastructure system performance performed network modeling analysis defined diagram design business technology initiative enforced policy standardizing system network technician u department state dc enterprise work changed password unlocked account need added device new softwareapplications need troubleshoot application freezing printer working hardware actively troubleshoot level issue transferred call appropriate technician assigned ticket filed issue sorted ticket answered field need supportedcomputer network operating system o include program record version linux microsoft windowsserver io alcatel xosaos designed installed maintained repaireddata communication link fiberoptic tactical fiberoptic cabling analyzedand evaluated system output designand manipulateddatabase information produce nonroutine reportsweekly aviation logistics specialist united state marine corp jacksonville nc deployed 26th meu deployed al assad worked buying team product ordered proactively minimize stock situation plan truckload stock transfer well order inventory maintain healthy product level evaluating buying report sale trend tracked managed adjustment 3pl hmi database reconcile change well investigate resolve discrepancy kept 3pl web portal updated change respond alert timely manner processed invoice 3pl ensure accurate timely resolution maintained regular proactive communication 3pl team participated buying meeting prepared question information skus need reviewed discussed based inventory analysis prepared analysis reporting overall statistic offered continuous improvement idea overall process needed used forklift microsoft office managed designated group packup kit aviation asset well group designated packup kit support aircraft squadron recommend approved asset stocking packup kit recommend consumable item inclusion commutated various customersrepresentatives via telephone email naval message rectify discrepancy ordered stocked required repairable consumables approved increase decrease loaded stock item record sir navy enterprise resource planning nerp database master record file mrf nalcomis database ensured picking ticket pulled delivered timely manner ensured complete order entered automated system determined problem may affectdelay material availability initiate corrective action conducted onload onboard offload inventory cycle count maintained local carcasstracking program accurately track account part material education bachelor bachelor science cybersecurity purdue university global west lafayette present associate associate degree diesel technology applied service management wyo techblairsville blairsville pa military service branch united state marine corp rank corporal certificationslicenses epa refrigerant recovery recycling certification core type present epa refrigerant recovery recycling certification present certified vsat installer basic vsat theory course introduction vsat frequency band satellite orbit vsat link terminology vsat latency rain fade sun outage solar transit event adaptive coding modulation acm linear polarization circular polarization decibel db dc voltage rf safety vsat glossary term tool equipment documentation hand tool cable software test equipment adaptor comms spare consumables ppe documentation checklist indoor equipment equipment rack ups scpc modem comtech paradise datacom tdma outdoor equipment low noise block lnb upconverter buc rf feed assembly antenna sat dish antenna offset antenna mount nonpenetrating mount rf coax ntype connector termination ftype connector termination power grounding stabilized autoaquire antenna stabilized antenna theory acu configuration sea tel antenna intellian spacetrack antenna remote site site survey arrival install location jha take work area dish alignment dish pointing elevation azimuth polarization remote commissioning compression point 1db point test cross polarization xpol voip data site documentation fault dish pointing dish movement low rx signal tx power problem slow data poor voice crosspol issue certified fiber optic technician certified premise cabling technician cpct\",\n \"cpa candidate strong financial accounting audit experience knowledge internal control enterprise risk management gl pl b reconciliation work paper cost cash control ap ar different accounting software participated coordination financial planning budget management function monitored analyzed operating result budget managed preparation official report actual revenue transfer expense financial outlook forecast collaborated department manager corporate staff develop business plan created guide financial control planning procedure exceptional communication interpersonal skill adept forming strong working relationship diverse internal external business partner account receivable payable payroll corporate expense analysis tax proficiency bookkeeping reporting journal entry account reconciliation entrusted process high responsibility task work independently demonstrated professionalism communicating department manager client supplier interacted wide variety personality developing business plan preparing report supervised role mapping workflow delegated task oversaw work coworkers enhanced leadership teamwork team coordination ability strong quantitative technical accounting skill independently driven accomplish immediate assigned goal long term company objective highlight analytical reasoning financial statement analysis strength regulatory reporting compliance testing knowledge understands foreign tax reporting budget forecasting expertise account reconciliation expert peoplesoft knowledge great plain familiarity complex problem solving excellent managerial technique strong organizational skill sec call reporting proficiency general ledger accounting expert customer relation superior research skill flexible team player advanced computer proficiency pc mac effective time management accomplishment formally recognized excellence achieved financial analysis budgeting forecasting experience volunteer accountant company name city state federal compliance review preparation corporation insurance partnership private foundation tax return coordinate fixed asset accountant necessary information correct tax depreciation calculation review tax depreciation calculation schedule accuracy analyze accrual account deductibility pertaining provision tax return assist completion tax footnote statement identify reportable transaction disclosure consolidated tax return prepare tax filing new entity dissolution liquidation assist audit request research implementation tax consequence participate implementation new provision fixed asset erp system accountant company name city state responsible various general accounting duty including account payable banking check request special project needed processed account payable including purchase order entry invoice approval entry follow vendor aging reporting processed check various credit assisted end close financial reporting performed reconciliation bank account including reconciliation deposit account receivable maintaining accounting record preparing account management information small business accountancy advising client business transaction merger acquisition corporate finance advising client area business improvement dealing insolvency detecting preventing fraud forensic accounting managing junior colleague accountant manager company name city state performed periodic budgeting modeling project cash requirement prepared financial regulatory report required law regulation addition opening office ajman sharjah prepared annual expense forecast including necessary recommended action required manage cost achieve budget executed account receivable reporting enhancement reconciliation procedure order integrate quickbooks accounting software vision software managed accounting operation accounting close account reporting reconciliation received recorded banked cash check voucher well reconciled record bank transaction developed online invoicing procedure several customer order streamline account receivable process reduced invoice turn performed complex general accounting function including preparation journal entry account analysis balance sheet reconciliation education master business administration accounting keller graduate school management city state master science accounting financial management keller graduate school management city state u certificate essential bookkeeping computerized accounting technology holding ny driving license type skill proficient microsoft office suite access quickbooks turbo tax vision accounting software peach tree dac easy sage peoplesoft advance microsoft excel\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_jd\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 452,\n \"samples\": [\n \"design deliver solu bi sale partner mp expert sale academy program foundation continuous development program analyze day today need training sale team manage new solu bi sale partner mp orientation product training create training module solu bi sale partner mp stay date current market trend changing demand sale environment maintaining existing solu bi sale partner mp expert achieve target beyond target requirement bachelor degree human resource business administration marketing relevant field proven two year experience sale trainer similar role preferable ecommerce banking multi finance insurance mlm industry strong data excel formula hand experience elearning platform solid communication presentation ability ability design effective sale training program great interpersonal\",\n \"applicant position preferred experience finance accounting field breve tab experience using microsoft dynamic nav sap program self motivated personnel manage knowledge fast learner able work independently following qualification job summary responsible account transaction ensuring business target within area reached preparing documentation relating account payable account receivable tax bank account payable handle daily bookkeeping invoice payable bank payment voucher make sure ap balance correct prepare payment schedule based cash availability due date invoice communicate local vendor balance payable payment detail account receivable prepare bank receipt payment received fixed asset maintain fixed asset register update data regularly case correction disposal transfer asset tax calculate prepare tax payment tax article twenty three twenty six four two twenty five liaise tax officer external auditor bank prepare monthly bank reconciliation general accounting handle bookkeeping posting accrual depreciation entry amortization expense monthly basis others checking employee monthly claim handle petty cash transaction monitor cash advance ad hoc k task finance accounting manager requirement university graduate bachelor degree accounting major fresh graduate welcome 2 year experience finance accounting field breve tab preferred preferable experience using microsoft dynamic nav sap program strong skill microsoft office excel advance powerpoint word proficient english language important age maximum twenty seven year old\",\n \"benefit competitive salary medical dental vision insurance four hundred one k retirement saving plan life insurance tuition assistance wellness reimbursement travel insurance paid holiday vacation cybersecurity analyst role within information technology cybersecurity group support company cybersecurity service cybersecurity analyst protect confidentiality integrity availability central hudson information technical environment also support enterprise security goal objective responsibility perform security risk assessment system implementation project ensure proper security control configuration implemented testing effectiveness understand analyze existing network security architecture security best practice provide recommendation ensure alignment internal policy monitor analyze security alert including trend root cause analysis detect respond mitigate information security related vulnerability incident evaluate system specific vulnerability scan work various department remediate high risk item assist responding cybersecurity incident including investigating documenting incident according incident response plan coordinate external consultant security assessment including developing implementing action plan address finding perform duty required assigned may include risk compliance assignment qualification required associate degree computer information system computer science cybersecurity related field study least three year experience information cybersecurity technical support lieu degree least five year experience information cybersecurity technical support demonstrated understanding network topology architecture protocol addressing scheme across multiple platform knowledge demonstrated ability operate window based linux based security tool well developed written verbal communication presentation skill planning organizational skill proven interpersonal facilitation negotiation problem resolution skill must able work minimal supervision work well pressure must able adapt variety assignment preferred bachelor degree computer information system computer science information security information assurance management information system one following certification scism security caspcisspcsslporgiac experience following highly desirable network management understanding packet dump data parsing system log basic scripting language siem please go click search career opportunity button follow direction submit application upload resume desired position application sent via email u mail accepted phone call agency please reply held strict confidence qualified applicant receive consideration employment discriminated basis race color religion sex sexual orientation gender identity national origin age disability protected veteran status central hudson gas electric corporation take affirmative action support policy employ advance employment individual minority woman protected veteran individual disability v evra federal contractor\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"label\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 1,\n \"max\": 1,\n \"num_unique_values\": 1,\n \"samples\": [\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df_label1" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
clean_cvclean_jdlabel
0result oriented organized bilingual accounting...minimum education requirement bachelor degree ...1
1result oriented organized bilingual accounting...hiring talented candidate join accounting team...1
2result oriented organized bilingual accounting...duty proficient working excel skilled working ...1
3result oriented organized bilingual accounting...job description responsible supervising checki...1
4result oriented organized bilingual accounting...qualification one bachelor degree finance acco...1
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " clean_cv \\\n", "0 result oriented organized bilingual accounting... \n", "1 result oriented organized bilingual accounting... \n", "2 result oriented organized bilingual accounting... \n", "3 result oriented organized bilingual accounting... \n", "4 result oriented organized bilingual accounting... \n", "\n", " clean_jd label \n", "0 minimum education requirement bachelor degree ... 1 \n", "1 hiring talented candidate join accounting team... 1 \n", "2 duty proficient working excel skilled working ... 1 \n", "3 job description responsible supervising checki... 1 \n", "4 qualification one bachelor degree finance acco... 1 " ] }, "execution_count": 490, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Rename columns for clarity\n", "df_jd1 = df_jd.rename(columns={'clean_data': 'clean_jd'})\n", "df_cv1 = df_res.rename(columns={'clean_data': 'clean_cv'})\n", "\n", "# Create all possible pairs of job descriptions and CVs\n", "df_pairs1 = pd.merge(df_cv1.assign(key=1), df_jd1.assign(key=1), on='key').drop('key', axis=1)\n", "\n", "# Filter pairs where categories match\n", "df_pairs1 = df_pairs1[df_pairs1['category_x'] == df_pairs1['category_y']]\n", "\n", "# Assign labels\n", "df_pairs1['label'] = 1\n", "\n", "# Rename columns for clarity\n", "df_pairs1 = df_pairs1.rename(columns={'category_x': 'category_cv', 'category_y': 'category_jd'})\n", "\n", "# Select the desired columns\n", "df_label1 = df_pairs1[['clean_cv', 'clean_jd', 'label']]\n", "\n", "df_label1.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "znc72rJFx-jk", "outputId": "e704f0ed-e968-46d4-dfce-26e441ee4309" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 15718 entries, 0 to 287923\n", "Data columns (total 3 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 clean_cv 15718 non-null object\n", " 1 clean_jd 15718 non-null object\n", " 2 label 15718 non-null int64 \n", "dtypes: int64(1), object(2)\n", "memory usage: 491.2+ KB\n" ] } ], "source": [ "df_label1.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "j80Lj-Idv-7i", "outputId": "4330206e-da46-4727-c904-9b1d81b7e784" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 119 entries, 0 to 118\n", "Series name: category\n", "Non-Null Count Dtype \n", "-------------- ----- \n", "119 non-null object\n", "dtypes: object(1)\n", "memory usage: 1.1+ KB\n", "None\n", "\n", "RangeIndex: 137 entries, 0 to 136\n", "Series name: category\n", "Non-Null Count Dtype \n", "-------------- ----- \n", "137 non-null object\n", "dtypes: object(1)\n", "memory usage: 1.2+ KB\n", "None\n" ] } ], "source": [ "def sample_or_all(group):\n", " return group.head(7)\n", "\n", "# Apply the function to each group\n", "df_jd = df_job.groupby('category').apply(sample_or_all).reset_index(drop=True)\n", "\n", "print(df_jd['category'].info())\n", "\n", "# Apply the function to each group\n", "df_res = df_resume.groupby('category').apply(sample_or_all).reset_index(drop=True)\n", "\n", "print(df_res['category'].info())" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "1T6ms0zkxkRt", "outputId": "bf799a25-9ae6-40eb-88e7-689f1e8834c1" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df_label0\",\n \"rows\": 15485,\n \"fields\": [\n {\n \"column\": \"clean_cv\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 137,\n \"samples\": [\n \"java developer span span ldeveloperspan java developer starmount life baton rouge la work experience java developer starmount life baton rouge la present description starmount life insurance company part unum group offer consumer driven insurance solution group dental vision product customized approach valuable coverage option promote physical financial wellness help member protect planning responsibility involved phase software development life cycle sdlc including analysis design development testing project used spring boot create standalone application used eclipse integrated development environment coding debugging testing application module involved developing presentation layer application module using angular js2 xhtml html5 jquery ajax cs designed developed microservices business component using spring boot knowledge creation typescript reusable component service consume rest apis using component based architecture provided angular implemented spring boot service combination angular front end form microservice oriented application angular j used parse json file using rest web service configured based microservices spring boot used objectrelational mapping tool hibernate jpa achieve object database table persistency developed hibernate pojo class hibernate configuration file hibernate mapping file configured swaggerui registered micro service eureka server monitor service health check boot admin console analyze fix issue related rest web service application response implemented backend service using springboot worked developing rest service expose processed data service experience working nosql mongo db apache cassandra implemented spring security spring transaction application worked swagger rest json test data postman testing web service documentation web api experienced framework application like spring core spring aop mvc batch spring security spring boot integration micro service existing system architecture involved configuration spring framework hibernate mapping tool configured mq queue topic publish message topic consume published message worked docker deploy microservices modern container increase isolation experience spring ribbon kafka broker service handle heavy traffic used spring core annotation dependency injection used apache camel integrate spring framework developed communication different application using mq series jms spring integration configured monitored numerous cassandra nosql instance deployment micro service via aws beanstalk lambda worked daos pull data source database converted json format published kafka stream implemented continuous delivery pipeline docker jenkins github aws amis extensively followed test driven development implement application business logic work flow process integration application module followed pair programming analysis design development integration testing deploy application used xml xsd xpath jaxb message transformation mapping extensively followed agile scrum methodology xp implement application module configured used hudson jenkins tool continues integration build deploy application used building deploying web application websphere configuring dependency plugins resource wrote junit test case line application code performed validation environment javaj2ee jsp springboot hibernate soap rest jaxrs jms mq series sql plsql jaxb xml html5 cs javascript jquery ajax json angularjs eclipse jboss maven nexus aws db2 kafka cassandra micro service autosys uml agile xp jenkins github stash jira junit log4j soapui unix shell scripting java developer att california description att inc american multinational conglomerate holding company world largest telecommunication company second largest provider mobile telephone service largest provider fixed telephone service united state att communication responsibility implemented business layer using core java spring bean using dependency injection spring annotation implemented micro service using spring boot spring cloud microservices enabled discovery using eureka server used s3 bucket manage document management rds host database experience nosql database like cassandra mongo db created customized amis based already existing aws ec2 instance using create image functionality hence using snapshot disaster recovery optimized full text search function connecting nosql db like mongodb elastic search implemented mongodb database concept locking transaction index replication used rabbit mq queue implementation multithreaded synchronization process using jms queue consumption request used micro service architecture bootbased service interacting combination rest mq leveraging aws build test deploy micro service involved design development ui component using framework angularjs javascript html cs bootstrap experienced using kafka distributed publishersubscriber messaging system involved implementation enterprise integration web service legacy system using soap rest added security soap w security experience working kafka camel used spring security authentication authorization extensively set jenkins server build job provide automated build based polling git source control system consumed rest based micro service rest template based restful apis used docker possible production development environment fast possible interactive use responsible continuous integration ci continuous delivery cd process implementation using jenkins along linux shell script automate routine job created web service using spring rest controller return json frontend developed serverside service using java spring web service soap restful wsdl jaxb jaxrpc used soap ui tool testing web service connectivity environment java j2ee servletfilters jsp jstl springboot microservices spring security angular j cassandra javascript html cs bootstrap rest pivotal cloud foundry aws ec2 s3 eureka rabbit mq kafka soap restful nosql mongo db elastic search sts junit jenkins log4j jira docker git java developer bbva compass plano tx description bbva compass banking list largest bank united state part project role develop web application meet mortgage need client loan deposit multi loan deposit teller referral responsibility involved gathering analyzing business requirement converting technical specification developed class diagram sequence diagram part module design documentation agile delivery software using practice short iteration scrum involved developing distributed transactional secure portable application based java technology using ejb technology implemented presentation layer using spring framework developed javascript clientside validation used strut framework develop application based mvc design pattern developed user interface using jstl custom tag library htmlxhtml javascript cs used jdbc database connectivity sql server java api including jdbc jaxp jdom query patent data database transfer data various format soap used protocol send request response form xml message wsdl used expose web service using apache axis used j2ee design pattern like service locator data access object factory pattern mvc singleton pattern created consumed soaprestful web service restful web service used retrieve update data populated implemented persistence layer using hibernate use pojos represent persistence database table pojos serialized java class would business process implemented hibernate using spring framework created session factory dao hibernate transaction implemented using framework refactored code migrate hibernate2x version hibernate3 ie moved xml mapping annotation created ldap service user authentication authorization involve junit testing debugging bug fixing worked multithreading participated discussion business expert understand business requirement mold technical requirement toward development designed uml diagram using rational rose built functionality front end jsps take data model xml using xslt convert xsl html prepared test case integration testing used java message service jms reliable asynchronous exchange important information loan teller application designed developed message driven bean consumed message java message queue deployed component development environment system test environment uat environment used simple maven project archetype project developing application provided jar file ui application use test driven development approach used involved writing many unit integration test case environment java javascript hibernate strut jstl custom tag library html xhtml cs jdbc jaxp jdom plsql jms junit rational rose eclipse ide svn mysqljboss application server education bachelor\",\n \"outbound sale career overview call center representative versed customer support high call volume environment superior computer skill telephone etiquette core strength exceptional communication skill microsoft outlook word excel m window proficient adherence high customer service skilled call center operation standard adheres customer service procedure customer focused customer service award quick learner accomplishment customer service award quick learner work experience outbound sale company name city state answered average call per day addressing customer inquiry solving problem providing new product information described product customer accurately explained detail care merchandise politely assisted customer via telephone answered product question date knowledge sale store promotion ensured superior customer experience addressing customer concern demonstrating empathy resolving problem spot built long term customer relationship advised customer purchase promotion routinely answered customer question regarding merchandise pricing effectively managed high volume inbound outbound customer call evaluated consumer report basis managed customer call effectively efficiently complex fast paced challenging call center environment resolved service pricing technical problem customer asking clear specific question receptionist company name city state scheduled appointment registered patient distributed sample pharmaceutical prescribed professionally courteously verified appointment time patient adeptly managed multi line phone system pleasantly greeted patient verified patient eligibility claim status insurance agency prepared patient chart accurately neatly clinic diligently filed followed third party claim coordinated luncheon pharmaceutical representative researched cpt icd coding discrepancy compliance reimbursement accuracy resourcefully used various coding book procedure manual line encoders precisely evaluated verified benefit eligibility updated patient financial information guarantee accuracy treated patient family visitor peer staff provider pleasant courteous manner provider rep company name city state assisted maintenance medical chart electronic medical record filing op report test result home care form meticulously identified rectified inconsistency deficiency discrepancy medical documentation prepared patient chart accurately neatly clinic prepared patient chart pre admission consent form necessary researched question concern provider provided detailed response updated patient financial information guarantee accuracy organized department accordance administrative guideline order provide specified nursing service meet legal organizational medical staff guideline participated facility survey inspection made authorized governmental agency confirmed accurate completion form report admission transfer discharge resident initiated audit process evaluate thoroughness documentation maintenance facility standard cole manage vision twinsburg oh effectively managed high volume inbound outbound customer call accurately documented researched resolved customer service issue managed customer call effectively efficiently complex fast paced challenging call center environment managed high call volume tact professionalism educational background high school diploma north marion high high school diploma general north marion high school mannington wv diploma webster college city state diploma paralegal webster college fairmont wv office webster college city state degree office technology webster college fairmont wv diploma medical brown mackie college city state diploma medical office brown mackie college akron oh skill pricing sale inbound outbound audit documentation filing inspection maintenance medical record basis receptionist customer inquiry sale sale telephone benefit claim coding cpt icd icd icd9 coding icd coding multi line multi line phone multi line phone system phone system customer service retail sale award call center representative customer support etiquette excel microsoft outlook operation outlook word paralegal\",\n \"education detail tech electronics instrumentation engineering jaunpur uttar pradesh vbs purvanchal university automation tester automation tester tech mahindra skill detail company detail company tech mahindra description mumbai present project contribution tech mahindra project title payment gateway jio money role automation tester responsibility analyzing manual test case create automation script working redwood tool automation maintained regression pack per project requirement performed api testing created automation script api testing enhancing framework support cross functionality testing execute test case evaluate test result manual automated testing maintaining script per requirement adding new automated test improve automated test coverage functional regression performed automation testing analyzing test result report defect bug tracking system drive issue resolution preparation test data different test condition ensure coverage business rule performed sanity ad hoc regression testing participated defect triage meeting developer validate severity bug responsible tracking bug life cycle worked development team ensure testing issue resolved project description jio money jio payment gateway provides facility merchant user enable pay jio money feature include purchase bill payment load money short cash purchase pay merchant pay user etc inscripts project title cometchat role automation tester responsibility created automation framework bug report using page object data driven framework automated email test script handling qa ticket coordinate development team project description cometchat chat solution site app help grow customer base exponentially drastically increase time spent user cometchat several useful feature like one one chat group chat audio video call screen sharing game real time chat translation mobile apps desktop messenger project title web tracker role sr software tester responsibility creation test scenario test script test case execution test case ad hoc manual testing regression testing automation testing test script using tool selenium webdriver project description accomplishment web tracker aim provide time sheet facility customer release contains following feature related employee time tracking task assignment tracker submission reminder approval notification hayaan infotech project title real estate agent website role sr software tester responsibility creation test scenario test case execution test case smoke testing black box testing ad hoc manual testing regression testing project description project web page graphical html representation neighborhood made different type house apartment several sale people around country responsible selling house apartment web site web site help user purchase request estate property project title commerce website role software tester responsibility creation test scenario test case execution test case ad hoc manual testing smoke testing black box testing regression testing project description project includes order processing invoice generated printing packaging slip order payment return material authorization label sheet printing order processing application big main entity involved order processing customer sale person admin project title enquiry invoice system role software tester responsibility creation test scenario test case execution test case smoke testing black box testing ad hoc manual testing regression testing project description application browser based application reduce investment hardware software proposed system contains following module offer database management reporting various activity company application comprise following module inquiry estimation quotation negotiation purchase order system delivery system mi report company inscripts pvt ltd description company haayan infotech pvt ltd description\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_jd\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 119,\n \"samples\": [\n \"ensure recruitment selection process required company usermanager making monthly report monthly annual recruitment update op regulation regarding recruitment selection process liaise third party headhunter outsourcing university college regarding recruitment certain level hiring process assist new hire board handle payroll process attendance time calculation liaise hr coordinator develop effective efficient hr system including performance appraisal kpi translation requirement candidate must posse least bachelor degree psychology human resource management mandarin fluency oral written least two year working experience related field required position required skill psychological test scoring interview labor law kpi preferably staff non management non supervisor specialized human resource equivalent willing business travel recruitment certified hr staff recruitment selection staff\",\n \"job working closely cto drive product vision prioritize roadmap based market opportunity manage data driven prioritization ensure timely execution engage closely drive collaboration cross functional team engineer designer business develop improvement solution support growth product responsibility lead product development process vybe score product set product roadmap spring goal prioritize backlog gain deep understanding influencers user need user research client feedback partner closely engineering operation business team solve practical challenge rapidly produce multiple concept prototype industry standard tool setup success metric communicate key stakeholder requirement two four year full time work experience product management onab2c consumer facing product bsc computer science engineering similar field plus hand experience managing stage product lifecycle extensively used data user research improve product\",\n \"detailed description minimum qualification please refer website duty description detailed description duty description please refer website additional comment starting salary fifty six six hundred four zero resume evaluated determine whether candidate proceed interview phase process\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"label\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 0,\n \"num_unique_values\": 1,\n \"samples\": [\n 0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df_label0" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
clean_cvclean_jdlabel
7result oriented organized bilingual accounting...requirement candidate must posse least bachelo...0
8result oriented organized bilingual accounting...develop test plan mind map test script test da...0
9result oriented organized bilingual accounting...junior business planning analyst gucci new yor...0
10result oriented organized bilingual accounting...analyzes make recommendation revenue cycle bus...0
11result oriented organized bilingual accounting...detailed description minimum qualification ple...0
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " clean_cv \\\n", "7 result oriented organized bilingual accounting... \n", "8 result oriented organized bilingual accounting... \n", "9 result oriented organized bilingual accounting... \n", "10 result oriented organized bilingual accounting... \n", "11 result oriented organized bilingual accounting... \n", "\n", " clean_jd label \n", "7 requirement candidate must posse least bachelo... 0 \n", "8 develop test plan mind map test script test da... 0 \n", "9 junior business planning analyst gucci new yor... 0 \n", "10 analyzes make recommendation revenue cycle bus... 0 \n", "11 detailed description minimum qualification ple... 0 " ] }, "execution_count": 486, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Rename columns for clarity\n", "df_jd2 = df_jd.rename(columns={'clean_data': 'clean_jd'})\n", "df_cv2 = df_res.rename(columns={'clean_data': 'clean_cv'})\n", "\n", "# Create all possible pairs of job descriptions and CVs\n", "df_pairs2 = pd.merge(df_cv2.assign(key=1), df_jd2.assign(key=1), on='key').drop('key', axis=1)\n", "\n", "# Filter pairs where categories match\n", "df_pairs2 = df_pairs2[df_pairs2['category_x'] != df_pairs2['category_y']]\n", "\n", "# Assign labels\n", "df_pairs2['label'] = 0\n", "\n", "# Rename columns for clarity\n", "df_pairs2 = df_pairs2.rename(columns={'category_x': 'category_cv', 'category_y': 'category_jd'})\n", "\n", "# Select the desired columns\n", "df_label0 = df_pairs2[['clean_cv', 'clean_jd', 'label']]\n", "\n", "df_label0.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "caRYiBhLxsIE", "outputId": "43844153-00de-47ad-c775-673fd0bb3cf7" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 15485 entries, 7 to 16295\n", "Data columns (total 3 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 clean_cv 15485 non-null object\n", " 1 clean_jd 15485 non-null object\n", " 2 label 15485 non-null int64 \n", "dtypes: int64(1), object(2)\n", "memory usage: 483.9+ KB\n" ] } ], "source": [ "df_label0.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "b5lud2i2xuoZ", "outputId": "d8f02819-586d-4e24-8783-a108586fd372" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df\",\n \"rows\": 31203,\n \"fields\": [\n {\n \"column\": \"clean_cv\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 637,\n \"samples\": [\n \"participated intra college cricket competition various sport event group dance college cultural programme education detail msc computer science pune pune university bsc computer science pune pune university hsc semi english pune maharashatra board ssc semi english pune maharashatra board dot net developer dot net developer skill detail html cs sql experience six month javascript experience le one year month sql two thousand twelve experience le one year detail company description\",\n \"network administrator span lnetworkspan span ladministratorspan greer sc work experience network administrator department education spartanburg sc present implemented local area network lan wide area network wan intranet extranets data network maintained network availability multiple networking environment administering cisco campusbased switching environment fiberbased copperbased ethernet connectivity 1gig 10gig installs manages maintains cisco switching component support campus wan distributed core architecture work cisco chassisbased system internet circuit termination equipment advanced cisco management tool managed cisco prime infrastructure analyze network health workflow access information security requirement performing router switch administration interface configuration switching protocol experience network router switch strong cisco switch router configuration experience workd knowledge tcpip dns acls arp radius ipv6 dhcp intrusion prevention authentication isp circuit connection developed execute test plan check infrastructure system performance performed network modeling analysis defined diagram design business technology initiative enforced policy standardizing system network technician u department state dc enterprise work changed password unlocked account need added device new softwareapplications need troubleshoot application freezing printer working hardware actively troubleshoot level issue transferred call appropriate technician assigned ticket filed issue sorted ticket answered field need supportedcomputer network operating system o include program record version linux microsoft windowsserver io alcatel xosaos designed installed maintained repaireddata communication link fiberoptic tactical fiberoptic cabling analyzedand evaluated system output designand manipulateddatabase information produce nonroutine reportsweekly aviation logistics specialist united state marine corp jacksonville nc deployed 26th meu deployed al assad worked buying team product ordered proactively minimize stock situation plan truckload stock transfer well order inventory maintain healthy product level evaluating buying report sale trend tracked managed adjustment 3pl hmi database reconcile change well investigate resolve discrepancy kept 3pl web portal updated change respond alert timely manner processed invoice 3pl ensure accurate timely resolution maintained regular proactive communication 3pl team participated buying meeting prepared question information skus need reviewed discussed based inventory analysis prepared analysis reporting overall statistic offered continuous improvement idea overall process needed used forklift microsoft office managed designated group packup kit aviation asset well group designated packup kit support aircraft squadron recommend approved asset stocking packup kit recommend consumable item inclusion commutated various customersrepresentatives via telephone email naval message rectify discrepancy ordered stocked required repairable consumables approved increase decrease loaded stock item record sir navy enterprise resource planning nerp database master record file mrf nalcomis database ensured picking ticket pulled delivered timely manner ensured complete order entered automated system determined problem may affectdelay material availability initiate corrective action conducted onload onboard offload inventory cycle count maintained local carcasstracking program accurately track account part material education bachelor bachelor science cybersecurity purdue university global west lafayette present associate associate degree diesel technology applied service management wyo techblairsville blairsville pa military service branch united state marine corp rank corporal certificationslicenses epa refrigerant recovery recycling certification core type present epa refrigerant recovery recycling certification present certified vsat installer basic vsat theory course introduction vsat frequency band satellite orbit vsat link terminology vsat latency rain fade sun outage solar transit event adaptive coding modulation acm linear polarization circular polarization decibel db dc voltage rf safety vsat glossary term tool equipment documentation hand tool cable software test equipment adaptor comms spare consumables ppe documentation checklist indoor equipment equipment rack ups scpc modem comtech paradise datacom tdma outdoor equipment low noise block lnb upconverter buc rf feed assembly antenna sat dish antenna offset antenna mount nonpenetrating mount rf coax ntype connector termination ftype connector termination power grounding stabilized autoaquire antenna stabilized antenna theory acu configuration sea tel antenna intellian spacetrack antenna remote site site survey arrival install location jha take work area dish alignment dish pointing elevation azimuth polarization remote commissioning compression point 1db point test cross polarization xpol voip data site documentation fault dish pointing dish movement low rx signal tx power problem slow data poor voice crosspol issue certified fiber optic technician certified premise cabling technician cpct\",\n \"cpa candidate strong financial accounting audit experience knowledge internal control enterprise risk management gl pl b reconciliation work paper cost cash control ap ar different accounting software participated coordination financial planning budget management function monitored analyzed operating result budget managed preparation official report actual revenue transfer expense financial outlook forecast collaborated department manager corporate staff develop business plan created guide financial control planning procedure exceptional communication interpersonal skill adept forming strong working relationship diverse internal external business partner account receivable payable payroll corporate expense analysis tax proficiency bookkeeping reporting journal entry account reconciliation entrusted process high responsibility task work independently demonstrated professionalism communicating department manager client supplier interacted wide variety personality developing business plan preparing report supervised role mapping workflow delegated task oversaw work coworkers enhanced leadership teamwork team coordination ability strong quantitative technical accounting skill independently driven accomplish immediate assigned goal long term company objective highlight analytical reasoning financial statement analysis strength regulatory reporting compliance testing knowledge understands foreign tax reporting budget forecasting expertise account reconciliation expert peoplesoft knowledge great plain familiarity complex problem solving excellent managerial technique strong organizational skill sec call reporting proficiency general ledger accounting expert customer relation superior research skill flexible team player advanced computer proficiency pc mac effective time management accomplishment formally recognized excellence achieved financial analysis budgeting forecasting experience volunteer accountant company name city state federal compliance review preparation corporation insurance partnership private foundation tax return coordinate fixed asset accountant necessary information correct tax depreciation calculation review tax depreciation calculation schedule accuracy analyze accrual account deductibility pertaining provision tax return assist completion tax footnote statement identify reportable transaction disclosure consolidated tax return prepare tax filing new entity dissolution liquidation assist audit request research implementation tax consequence participate implementation new provision fixed asset erp system accountant company name city state responsible various general accounting duty including account payable banking check request special project needed processed account payable including purchase order entry invoice approval entry follow vendor aging reporting processed check various credit assisted end close financial reporting performed reconciliation bank account including reconciliation deposit account receivable maintaining accounting record preparing account management information small business accountancy advising client business transaction merger acquisition corporate finance advising client area business improvement dealing insolvency detecting preventing fraud forensic accounting managing junior colleague accountant manager company name city state performed periodic budgeting modeling project cash requirement prepared financial regulatory report required law regulation addition opening office ajman sharjah prepared annual expense forecast including necessary recommended action required manage cost achieve budget executed account receivable reporting enhancement reconciliation procedure order integrate quickbooks accounting software vision software managed accounting operation accounting close account reporting reconciliation received recorded banked cash check voucher well reconciled record bank transaction developed online invoicing procedure several customer order streamline account receivable process reduced invoice turn performed complex general accounting function including preparation journal entry account analysis balance sheet reconciliation education master business administration accounting keller graduate school management city state master science accounting financial management keller graduate school management city state u certificate essential bookkeeping computerized accounting technology holding ny driving license type skill proficient microsoft office suite access quickbooks turbo tax vision accounting software peach tree dac easy sage peoplesoft advance microsoft excel\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_jd\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 452,\n \"samples\": [\n \"design deliver solu bi sale partner mp expert sale academy program foundation continuous development program analyze day today need training sale team manage new solu bi sale partner mp orientation product training create training module solu bi sale partner mp stay date current market trend changing demand sale environment maintaining existing solu bi sale partner mp expert achieve target beyond target requirement bachelor degree human resource business administration marketing relevant field proven two year experience sale trainer similar role preferable ecommerce banking multi finance insurance mlm industry strong data excel formula hand experience elearning platform solid communication presentation ability ability design effective sale training program great interpersonal\",\n \"applicant position preferred experience finance accounting field breve tab experience using microsoft dynamic nav sap program self motivated personnel manage knowledge fast learner able work independently following qualification job summary responsible account transaction ensuring business target within area reached preparing documentation relating account payable account receivable tax bank account payable handle daily bookkeeping invoice payable bank payment voucher make sure ap balance correct prepare payment schedule based cash availability due date invoice communicate local vendor balance payable payment detail account receivable prepare bank receipt payment received fixed asset maintain fixed asset register update data regularly case correction disposal transfer asset tax calculate prepare tax payment tax article twenty three twenty six four two twenty five liaise tax officer external auditor bank prepare monthly bank reconciliation general accounting handle bookkeeping posting accrual depreciation entry amortization expense monthly basis others checking employee monthly claim handle petty cash transaction monitor cash advance ad hoc k task finance accounting manager requirement university graduate bachelor degree accounting major fresh graduate welcome 2 year experience finance accounting field breve tab preferred preferable experience using microsoft dynamic nav sap program strong skill microsoft office excel advance powerpoint word proficient english language important age maximum twenty seven year old\",\n \"benefit competitive salary medical dental vision insurance four hundred one k retirement saving plan life insurance tuition assistance wellness reimbursement travel insurance paid holiday vacation cybersecurity analyst role within information technology cybersecurity group support company cybersecurity service cybersecurity analyst protect confidentiality integrity availability central hudson information technical environment also support enterprise security goal objective responsibility perform security risk assessment system implementation project ensure proper security control configuration implemented testing effectiveness understand analyze existing network security architecture security best practice provide recommendation ensure alignment internal policy monitor analyze security alert including trend root cause analysis detect respond mitigate information security related vulnerability incident evaluate system specific vulnerability scan work various department remediate high risk item assist responding cybersecurity incident including investigating documenting incident according incident response plan coordinate external consultant security assessment including developing implementing action plan address finding perform duty required assigned may include risk compliance assignment qualification required associate degree computer information system computer science cybersecurity related field study least three year experience information cybersecurity technical support lieu degree least five year experience information cybersecurity technical support demonstrated understanding network topology architecture protocol addressing scheme across multiple platform knowledge demonstrated ability operate window based linux based security tool well developed written verbal communication presentation skill planning organizational skill proven interpersonal facilitation negotiation problem resolution skill must able work minimal supervision work well pressure must able adapt variety assignment preferred bachelor degree computer information system computer science information security information assurance management information system one following certification scism security caspcisspcsslporgiac experience following highly desirable network management understanding packet dump data parsing system log basic scripting language siem please go click search career opportunity button follow direction submit application upload resume desired position application sent via email u mail accepted phone call agency please reply held strict confidence qualified applicant receive consideration employment discriminated basis race color religion sex sexual orientation gender identity national origin age disability protected veteran status central hudson gas electric corporation take affirmative action support policy employ advance employment individual minority woman protected veteran individual disability v evra federal contractor\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"label\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 1,\n \"num_unique_values\": 2,\n \"samples\": [\n 0,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
clean_cvclean_jdlabel
0result oriented organized bilingual accounting...minimum education requirement bachelor degree ...1
1result oriented organized bilingual accounting...hiring talented candidate join accounting team...1
2result oriented organized bilingual accounting...duty proficient working excel skilled working ...1
3result oriented organized bilingual accounting...job description responsible supervising checki...1
4result oriented organized bilingual accounting...qualification one bachelor degree finance acco...1
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " clean_cv \\\n", "0 result oriented organized bilingual accounting... \n", "1 result oriented organized bilingual accounting... \n", "2 result oriented organized bilingual accounting... \n", "3 result oriented organized bilingual accounting... \n", "4 result oriented organized bilingual accounting... \n", "\n", " clean_jd label \n", "0 minimum education requirement bachelor degree ... 1 \n", "1 hiring talented candidate join accounting team... 1 \n", "2 duty proficient working excel skilled working ... 1 \n", "3 job description responsible supervising checki... 1 \n", "4 qualification one bachelor degree finance acco... 1 " ] }, "execution_count": 492, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.concat([df_label1, df_label0], axis=0, ignore_index=True)\n", "df.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "OsRyJW4dyOpg", "outputId": "04b7c791-8a21-4233-fb7c-9456565305c2" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 31203 entries, 0 to 31202\n", "Data columns (total 3 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 clean_cv 31203 non-null object\n", " 1 clean_jd 31203 non-null object\n", " 2 label 31203 non-null int64 \n", "dtypes: int64(1), object(2)\n", "memory usage: 731.4+ KB\n" ] } ], "source": [ "df.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 178 }, "id": "z1WRGkqMyPkz", "outputId": "cfc7980d-d7f2-409f-f0de-019e3bd2620d" }, "outputs": [ { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
count
label
115718
015485

" ], "text/plain": [ "label\n", "1 15718\n", "0 15485\n", "Name: count, dtype: int64" ] }, "execution_count": 494, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df['label'].value_counts()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "NJXX9fIxySWp" }, "outputs": [], "source": [ "df.to_csv(\"/content/drive/MyDrive/Dataset/Compfest16_AIC/data_supervised.csv\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "0TK9vf9eykJ5" }, "outputs": [], "source": [] } ], "metadata": { "colab": { "authorship_tag": "ABX9TyPTRlP+VT+7KWR18Msj2Hig", "include_colab_link": true, "mount_file_id": "1fkiLuMgXUvkJzbGbXxBuFX4ZiNoyuHL4", "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python" } }, "nbformat": 4, "nbformat_minor": 0 }