Reduce the number of keywords and phrases from the file named hard_skills.txt. The goal here is try to reduce them to minimal numbers, right now there are too many and most are irrelevant and...

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.feature_extraction.text import CountVectorizer"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Every feature:\n",
"['10', '2003', '2008', '3d', '5g', '60', '66', 'aap', 'abm', 'aca', 'academia', 'acceptance', 'accepted', 'access', 'account', 'accountability', 'accountancy', 'accounting', 'accounts', 'accuracy', 'accurate', 'achievement', 'acquisition', 'acquisitions', 'acrobat', 'act', 'activations', 'active', 'activities', 'actuators', 'acumen', 'ad', 'ada', 'adjudication', 'admin', 'administration', 'administrative', 'administrator', 'admissions', 'adobe', 'adoption', 'ads', 'adult', 'advanced', 'advertisement', 'advertising', 'advice', 'advisory', 'advocacy', 'adwords', 'aed', 'aerospace', 'affairs', 'affiliate', 'affinity', 'agencies', 'agency', 'agile', 'agreements', 'aid', 'air', 'airport', 'ajax', 'algebra', 'algorithms', 'alliance', 'allocation', 'alt', 'alteryx', 'ami', 'aml', 'amplifiers', 'analyses', 'analysis', 'analytical', 'analytics', 'analyze', 'analyzing', 'anatomy', 'android', 'angular', 'annual', 'ansible', 'answer', 'answering', 'ansys', 'anti', 'antivirus', 'aop', 'apac', 'apache', 'api', 'apis', 'app', 'application', 'applications', 'appointments', 'appraisal', 'appraisals', 'apps', 'aptitude', 'arabic', 'arbitration', 'archicad', 'architect', 'architectural', 'architecture', 'architectures', 'area', 'ariba', 'arrangements', 'arts', 'as400', 'asana', 'aseptic', 'asian', 'asic', 'asp', 'assemblies', 'assembly', 'assessment', 'assessments', 'asset', 'assets', 'assurance', 'assure', 'atg', 'ats', 'attribution', 'audience', 'audiences', 'audio', 'audit', 'auditing', 'audits', 'autocad', 'automated', 'automation', 'avaya', 'aviation', 'avionics', 'awareness', 'azure', 'b2b', 'b2c', 'backbone', 'backup', 'baking', 'balance', 'balancer', 'bank', 'banking', 'banner', 'base', 'basecamp', 'bash', 'basic', 'behavioral', 'belt', 'benchmark', 'benchmarking', 'benefit', 'best', 'beverage', 'bgp', 'bi', 'big', 'bilingual', 'billing', 'bing', 'biological', 'black', 'blackberry', 'board', 'boarding', 'bom', 'bomgar', 'bookkeeping', 'books', 'brand', 'branding', 'briefs', 'broadcast', 'browsers', 'budget', 'budgeting', 'budgets', 'build', 'building', 'business', 'buying', 'cac', 'cad', 'cadence', 'cae', 'calculations', 'calculus', 'calendar', 'calibration', 'california', 'calling', 'calls', 'cam', 'campaign', 'campaigns', 'cantonese', 'capabilities', 'capacity', 'capital', 'cardiology', 'cardiovascular', 'cards', 'care', 'career', 'cas', 'case', 'cases', 'cash', 'catalyst', 'category', 'catering', 'cause', 'cc', 'ccie', 'ccna', 'ccnp', 'cctv', 'cdn', 'center', 'centos', 'certificate', 'certification', 'certified', 'cfa', 'chain', 'change', 'channel', 'channels', 'checkpoint', 'chemical', 'chemicals', 'chemistry', 'child', 'chinese', 'chrome', 'circuit', 'circuits', 'cis', 'cisa', 'cisco', 'cism', 'cissp', 'citrix', 'civil', 'claims', 'clearance', 'clerical', 'client', 'clients', 'climate', 'clinical', 'close', 'closeout', 'closing', 'cloud', 'cm', 'cma', 'cms', 'coaching', 'cobit', 'cobol', 'coding', 'cognos', 'cold', 'collaboration', 'collection', 'com', 'commerce', 'commercial', 'commercialization', 'communication', 'communications', 'community', 'company', 'compensation', 'competitive', 'complaints', 'complex', 'compliance', 'comptia', 'computation', 'computer', 'computing', 'concept', 'concepts', 'concierge', 'conditions', 'conduct', 'conducting', 'configuration', 'conflicts', 'construction', 'consultative', 'consulting', 'consumer', 'consumers', 'contact', 'content', 'continuity', 'continuous', 'contract', 'contracts', 'control', 'controls', 'conversion', 'coordinate', 'coordination', 'copy', 'copyediting', 'copying', 'copywriting', 'core', 'corporate', 'correspondence', 'cost', 'costing', 'counsel', 'counseling', 'cpc', 'cpg', 'cpt', 'crb', 'create', 'creation', 'creative', 'credentialing', 'credit', 'crime', 'criminal', 'crisis', 'critical', 'crm', 'cross', 'crystal', 'csc', 'csp', 'css', 'cubes', 'cucm', 'curation', 'curriculum', 'custom', 'customer', 'customers', 'cut', 'cybersecurity', 'cycle', 'czech', 'daily', 'data', 'database', 'databases', 'datacenter', 'datasets', 'db', 'dba', 'deadlines', 'dealer', 'debt', 'debug', 'debugging', 'decision', 'delegate', 'delivery', 'demand', 'department', 'departmental', 'deployment', 'deposits', 'depreciation', 'derivatives', 'design', 'desk', 'desktop', 'detection', 'develop', 'development', 'device', 'devices', 'dexterity', 'dfm', 'dfmea', 'dhcp', 'diagnostics', 'dictation', 'digital', 'diligence', 'diploma', 'direct', 'directing', 'direction', 'directory', 'disaster', 'disbursement', 'discipline', 'display', 'distributed', 'distribution', 'divestitures', 'django', 'dns', 'dnv', 'docker', 'docs', 'document', 'documentation', 'documenting', 'documents', 'drafting', 'drainage', 'drawings', 'drive', 'driven', 'drivers', 'driving', 'dss', 'dutch', 'duties', 'dynamic', 'dynamics', 'dynamodb', 'east', 'ebitda', 'ebs', 'ec2', 'ecommerce', 'econometrics', 'economic', 'economics', 'edit', 'editing', 'editorial', 'edp', 'educating', 'education', 'educational', 'effective', 'effectiveness', 'effects', 'ehs', 'elearning', 'electrical', 'electronic', 'electronics', 'electrophysiology', 'ellucian', 'email', 'emails', 'embedded', 'emc', 'emea', 'emergency', 'emerging', 'employee', 'employees', 'employment', 'emr', 'enablement', 'end', 'energy', 'enforcement', 'engagement', 'engine', 'engineer', 'engineering', 'english', 'enhancements', 'ensure', 'enterprise', 'entity', 'entomology', 'entrepreneurship', 'entries', 'entry', 'environment', 'environmental', 'enzyme', 'epc', 'equipment', 'equity', 'erp', 'escalation', 'escalations', 'essbase', 'established', 'estate', 'estimates', 'ethernet', 'etl', 'european', 'evaluate', 'evaluation', 'evaluations', 'event', 'events', 'examination', 'excel', 'excellence', 'excellent', 'exchange', 'execute', 'executive', 'expenditure', 'expense', 'expenses', 'experience', 'experimenting', 'experiments', 'expertise', 'explorer', 'exports', 'expression', 'external', 'faa', 'fabrication', 'facebook', 'facilitation', 'facilities', 'facility', 'facing', 'facsimile', 'facts', 'fan', 'fashion', 'fda', 'feasibility', 'feature', 'features', 'federal', 'fema', 'fha', 'field', 'file', 'files', 'filing', 'filings', 'film', 'filtration', 'final', 'finance', 'financial', 'financials', 'financing', 'firefox', 'firewall', 'firewalls', 'firmware', 'fitness', 'fixed', 'flash', 'flex', 'flexible', 'flow', 'flowcharts', 'flows', 'flsa', 'fluid', 'fmea', 'fmla', 'focus', 'follow', 'food', 'force', 'forecasting', 'forecasts', 'foreign', 'forklift', 'formal', 'formulation', 'framework', 'frameworks', 'framing', 'fraud', 'freebsd', 'french', 'friendly', 'ftp', 'ftth', 'fulfillment', 'functionality', 'functions', 'fund', 'fundraising', 'fx', 'gaap', 'game', 'games', 'gap', 'gas', 'gather', 'gathering', 'gcp', 'ge', 'general', 'generally', 'generation', 'genetics', 'german', 'gimp', 'git', 'github', 'gl', 'global', 'gmail', 'goals', 'good', 'google', 'governance', 'government', 'gps', 'grant', 'graphic', 'graphics', 'grassroots', 'greek', 'greets', 'group', 'grow', 'growth', 'gsk', 'guard', 'guest', 'guidance', 'guide', 'guidelines', 'h1b', 'haccp', 'hadoop', 'hand', 'handling', 'hardware', 'hazard', 'hazardous', 'hcm', 'hcpcs', 'health', 'healthcare', 'heat', 'hedge', 'help', 'helpdesk', 'high', 'higher', 'hipaa', 'hippa', 'hire', 'hiring', 'hive', 'hoc', 'home', 'hootsuite', 'hospice', 'hospital', 'hospitality', 'hospitals', 'hotel', 'hotels', 'hr', 'hris', 'hse', 'html', 'html5', 'hubspot', 'hud', 'human', 'humanitarian', 'hungarian', 'hvac', 'hyperion', 'ibm', 'icd', 'ideation', 'identify', 'identity', 'ifrs', 'iis', 'imagery', 'imaging', 'immigration', 'immunology', 'implement', 'implementation', 'improvement', 'improvements', 'ims', 'inbound', 'incident', 'income', 'indesign', 'indicators', 'indonesian', 'industry', 'infection', 'informal', 'informatica', 'information', 'infrastructure', 'initiatives', 'innovation', 'innovations', 'inquiry', 'inside', 'insights', 'instagram', 'installation', 'institutional', 'instructional', 'instrumentation', 'insurance', 'integrated', 'integration', 'integrity', 'intellectual', 'intelligence', 'interaction', 'interactive', 'intercompany', 'interface', 'internal', 'international', 'internet', 'internship', 'interpret', 'intervention', 'interviewing', 'interviews', 'intranet', 'intrusion', 'inventory', 'investigate', 'investigation', 'investigations', 'investing', 'investment', 'investors', 'invision', 'invoices', 'invoicing', 'involvement', 'ios', 'ip', 'ipad', 'iphone', 'ipsec', 'ipv4', 'ipv6', 'iso', 'issue', 'issues', 'italian', 'itil', 'itsm', 'japanese', 'java', 'javascript', 'jira', 'job', 'journal', 'journalism', 'jquery', 'js', 'juniper', 'justice', 'kaizen', 'kanban', 'keeping', 'key', 'keyboard', 'keyboarding', 'kindle', 'knockout', 'knowledge', 'korean', 'kyc', 'l3', 'labor', 'lan', 'landing', 'language', 'languages', 'large', 'launch', 'launches', 'law', 'laws', 'leadership', 'leads', 'lean', 'learning', 'lease', 'ledger', 'legal', 'legislation', 'lending', 'levels', 'license', 'licensing', 'life', 'lifecycle', 'lighting', 'line', 'lingual', 'linux', 'lisp', 'lists', 'litigation', 'lms', 'load', 'loan', 'local', 'logistics', 'look', 'loss', 'lotus', 'ltv', 'lua', 'lync', 'mac', 'machine', 'machining', 'macos', 'macros', 'magento', 'mail', 'mailchimp', 'maintain', 'maintaining', 'maintains', 'maintenance', 'make', 'making', 'manage', 'management', 'manager', 'managers', 'managing', 'mandarin', 'manual', 'manufacturing', 'mapping', 'market', 'marketing', 'marketo', 'markets', 'mason', 'mat', 'material', 'materials', 'math', 'mathematics', 'matlab', 'matrix', 'mcdst', 'mcse', 'mdm', 'measures', 'mechanical', 'mechanics', 'mechatronics', 'media', 'medical', 'medicare', 'medicine', 'meditech', 'meet', 'meeting', 'meets', 'mental', 'mentorship', 'merchandising', 'merger', 'mergers', 'messaging', 'metadata', 'methodologies', 'methodology', 'methods', 'metrics', 'microelectronics', 'microsoft', 'mid', 'middle', 'middleware', 'migration', 'military', 'mining', 'minitab', 'minutes', 'mis', 'mitigation', 'mobile', 'mobilization', 'model', 'modeling', 'modelling', 'models', 'mongodb', 'monitoring', 'month', 'monthly', 'mortgage', 'motion', 'mpa', 'mpls', 'mrd', 'mrp', 'ms', 'msa', 'msd', 'msha', 'multi', 'multilingual', 'multimedia', 'mutual', 'myhr', 'mysql', 'nas', 'national', 'natural', 'ncarb', 'nebosh', 'needs', 'negotiate', 'negotiation', 'net', 'netbackup', 'netsuite', 'network', 'networking', 'networks', 'neurology', 'new', 'newsletter', 'newspapers', 'nexus', 'nginx', 'node', 'non', 'nosql', 'notary', 'notes', 'nt', 'numeracy', 'numerical', 'nursing', 'object', 'objectives', 'objects', 'oee', 'office', 'offline', 'oil', 'oils', 'omniture', 'oms', 'oncology', 'online', 'oo', 'op', 'open', 'openstack', 'operating', 'operational', 'operations', 'opportunities', 'optimization', 'oracle', 'oral', 'order', 'ordering', 'orders', 'ordinator', 'organisational', 'organization', 'organizational', 'organizing', 'orientation', 'oriented', 'orm', 'os', 'osha', 'osi', 'osp', 'ott', 'outbound', 'outlets', 'outlook', 'outreach', 'outside', 'outsourcing', 'oxley', 'pace', 'pages', 'papers', 'parking', 'partner', 'partnering', 'partners', 'partnership', 'partnerships', 'party', 'patent', 'patient', 'patterns', 'payable', 'payment', 'payments', 'payroll', 'pci', 'peer', 'peoplesoft', 'performance', 'performing', 'perl', 'personal', 'personnel', 'petrochemical', 'petty', 'pharmaceutical', 'pharmacies', 'pharmacovigilance', 'pharmacy', 'phone', 'phones', 'photography', 'photoshop', 'php', 'phr', 'physical', 'physics', 'physiology', 'pinterest', 'pipedrive', 'piping', 'pivot', 'pl', 'plan', 'planning', 'plans', 'plant', 'platform', 'platforms', 'plc', 'pleadings', 'plsql', 'plumbing', 'pmi', 'pmp', 'policies', 'policy', 'polish', 'portfolio', 'portuguese', 'positioning', 'post', 'postgres', 'postgresql', 'postman', 'power', 'powerpoint', 'powershell', 'ppc', 'ppe', 'ppt', 'pr', 'practice', 'practices', 'pre', 'predictive', 'preferred', 'preparation', 'prepare', 'preparing', 'presales', 'presence', 'presentation', 'presentations', 'preventative', 'preventive', 'pricing', 'principal', 'principles', 'print', 'printed', 'prioritization', 'privacy', 'private', 'pro', 'problem', 'problems', 'procedure', 'procedures', 'process', 'processes', 'processing', 'procurement', 'product', 'production', 'products', 'professional', 'profiling', 'profit', 'program', 'programing', 'programme', 'programmer', 'programming', 'programs', 'progress', 'progressive', 'project', 'projections', 'projects', 'promotional', 'proofread', 'property', 'proposal', 'proposals', 'proposition', 'prospecting', 'protective', 'protocols', 'prototype', 'prototyping', 'provide', 'provides', 'providing', 'proxy', 'psychology', 'public', 'publication', 'publications', 'publishing', 'puppet', 'purchase', 'purchasing', 'python', 'qa', 'qc', 'qsr', 'qualitative', 'quality', 'quantitative', 'quarterly', 'query', 'quick', 'quickbooks', 'rabbitmq', 'radiology', 'radius', 'rails', 'rally', 'rapid', 'rate', 'raw', 'rdbms', 'rds', 'react', 'real', 'receipts', 'receivable', 'receivables', 'recognition', 'reconcile', 'reconciliation', 'reconciliations', 'record', 'recordkeeping', 'records', 'recovery', 'recruit', 'recruiting', 'recruitment', 'redhat', 'redshift', 'reduction', 'refactoring', 'referral', 'regional', 'regulation', 'regulations', 'regulatory', 'reimbursement', 'relation', 'relational', 'relations', 'relationship', 'relationships', 'release', 'relic', 'remarketing', 'remote', 'repairs', 'report', 'reporting', 'reports', 'requests', 'requirement', 'requirements', 'research', 'researching', 'residential', 'resolving', 'resource', 'resources', 'respa', 'respiratory', 'response', 'responsive', 'restful', 'restructuring', 'results', 'retail', 'retention', 'return', 'returns', 'revenue', 'review', 'reviews', 'rewards', 'rfi', 'rfis', 'rfp', 'rfps', 'rfq', 'rfqs', 'rhce', 'rich', 'rights', 'risk', 'risks', 'rma', 'roadmap', 'roi', 'romanian', 'root', 'router', 'routers', 'routine', 'routing', 'rstp', 'ruby', 'rules', 'russian', 's3', 'saas', 'sabre', 'safeguarding', 'safety', 'sales', 'salesforce', 'sample', 'sap', 'sarbanes', 'sas', 'satellite', 'scada', 'scale', 'scaled', 'sccm', 'scenario', 'schedules', 'scheduling', 'scheme', 'school', 'sci', 'science', 'sciences', 'scorm', 'scrap', 'screening', 'scripting', 'scrum', 'sdlc', 'search', 'sec', 'secrecy', 'secretarial', 'security', 'segment', 'segmentation', 'sell', 'selling', 'sem', 'semiconductor', 'senior', 'sensitive', 'sensitivity', 'seo', 'sequencing', 'series', 'server', 'servers', 'service', 'servicenow', 'services', 'servicing', 'sets', 'shared', 'sharepoint', 'sharing', 'sheet', 'shell', 'shopping', 'shows', 'sigma', 'simulink', 'site', 'sitecore', 'skill', 'skills', 'skype', 'sla', 'small', 'smartphones', 'smb', 'sme', 'sms', 'smt', 'smtp', 'soa', 'soap', 'social', 'sociology', 'software', 'soldering', 'solidworks', 'solutions', 'sops', 'source', 'sources', 'sourcing', 'southern', 'sow', 'sox', 'speaking', 'special', 'specification', 'specifications', 'specs', 'speech', 'spelling', 'spending', 'sphr', 'spiceworks', 'splunk', 'sports', 'spreadsheets', 'spss', 'sql', 'ssas', 'ssis', 'ssl', 'ssrs', 'staff', 'staffing', 'stakeholder', 'stakeholders', 'standard', 'standardization', 'standards', 'start', 'startup', 'state', 'statement', 'statements', 'static', 'statistical', 'statistics', 'status', 'statutory', 'storage', 'store', 'stories', 'storm', 'storytelling', 'strategic', 'strategies', 'strategy', 'streams', 'strong', 'structure', 'structured', 'structures', 'studies', 'style', 'sub', 'subcontractor', 'subsystems', 'subversion', 'success', 'suite', 'supervising', 'supervisory', 'supplier', 'suppliers', 'supplies', 'supply', 'support', 'survey', 'swedish', 'swift', 'switches', 'switching', 'syndicated', 'synthesis', 'sys', 'systems', 'tableau', 'tables', 'tablets', 'tactical', 'talent', 'target', 'targets', 'tasks', 'tax', 'taxonomy', 'tcl', 'tcp', 'tcpdump', 'tdd', 'teaching', 'team', 'technical', 'technique', 'techniques', 'technologies', 'technology', 'telecom', 'telecommunications', 'telemarketing', 'telephone', 'terminology', 'terraform', 'territory', 'test', 'testing', 'tfs', 'thai', 'therapeutic', 'therapy', 'thermodynamics', 'thinker', 'thinking', 'time', 'timekeeping', 'title', 'tomcat', 'tools', 'tracking', 'trade', 'tradeshow', 'trading', 'train', 'training', 'transactional', 'transactions', 'transcription', 'transfer', 'transformation', 'transition', 'translate', 'transport', 'transportation', 'travel', 'treatment', 'trello', 'trend', 'trends', 'trial', 'troubleshoot', 'troubleshooting', 'tuning', 'tv', 'twitter', 'typing', 'uat', 'ubuntu', 'ui', 'underwriting', 'unit', 'unity', 'unix', 'ups', 'upsell', 'urban', 'usability', 'use', 'user', 'ux', 'v3', 'valid', 'value', 'variance', 'variances', 'vba', 'vehicle', 'vendor', 'vendors', 'verbal', 'version', 'vertical', 'video', 'vii', 'virtualization', 'virus', 'visio', 'visual', 'visualization', 'visuals', 'vlans', 'vlookup', 'vmware', 'voip', 'volume', 'vpn', 'wan', 'warehouse', 'warehousing', 'wastewater', 'water', 'waterfall', 'wealth', 'web', 'webinars', 'website', 'websphere', 'white', 'whmis', 'windows', 'wins', 'wireframes', 'wireframing', 'wireshark', 'wiring', 'word', 'wordpress', 'work', 'workday', 'workers', 'workflow', 'workflows', 'workforce', 'workstation', 'worth', 'wpm', 'write', 'writer', 'writing', 'xamarin', 'xml', 'xp', 'youtube', 'zendesk', 'zoom']\n",
"\n",
"Every 3rd feature:\n",
"['10', '3d', '66', 'aca', 'accepted', 'accountability', 'accounts', 'achievement', 'acrobat', 'active', 'acumen', 'adjudication', 'administrative', 'adobe', 'adult', 'advertising', 'advocacy', 'aerospace', 'affinity', 'agile', 'air', 'algebra', 'allocation', 'ami', 'analyses', 'analytics', 'anatomy', 'annual', 'answering', 'antivirus', 'apache', 'app', 'appointments', 'apps', 'arbitration', 'architectural', 'area', 'arts', 'aseptic', 'asp', 'assessment', 'assets', 'atg', 'audience', 'audit', 'autocad', 'avaya', 'awareness', 'b2c', 'baking', 'bank', 'base', 'basic', 'benchmark', 'best', 'bi', 'billing', 'black', 'boarding', 'bookkeeping', 'branding', 'browsers', 'budgets', 'business', 'cad', 'calculations', 'calibration', 'calls', 'campaigns', 'capacity', 'cardiovascular', 'career', 'cases', 'category', 'cc', 'ccnp', 'center', 'certification', 'chain', 'channels', 'chemicals', 'chinese', 'circuits', 'cisco', 'citrix', 'clearance', 'clients', 'close', 'cloud', 'cms', 'cobol', 'cold', 'com', 'commercialization', 'community', 'competitive', 'compliance', 'computer', 'concepts', 'conduct', 'conflicts', 'consulting', 'contact', 'continuous', 'control', 'coordinate', 'copyediting', 'core', 'cost', 'counseling', 'cpt', 'creation', 'credit', 'crisis', 'cross', 'csp', 'cucm', 'custom', 'cut', 'czech', 'database', 'datasets', 'deadlines', 'debug', 'delegate', 'department', 'deposits', 'design', 'detection', 'device', 'dfm', 'diagnostics', 'diligence', 'directing', 'disaster', 'display', 'divestitures', 'dnv', 'document', 'documents', 'drawings', 'drivers', 'dutch', 'dynamics', 'ebitda', 'ecommerce', 'economics', 'editorial', 'education', 'effectiveness', 'elearning', 'electronics', 'email', 'emc', 'emerging', 'employment', 'end', 'engagement', 'engineering', 'ensure', 'entomology', 'entry', 'enzyme', 'equity', 'escalations', 'estate', 'etl', 'evaluation', 'events', 'excellence', 'execute', 'expense', 'experimenting', 'explorer', 'external', 'facebook', 'facility', 'facts', 'fda', 'features', 'fha', 'files', 'film', 'finance', 'financing', 'firewalls', 'fixed', 'flexible', 'flows', 'fmea', 'follow', 'forecasting', 'forklift', 'framework', 'fraud', 'friendly', 'fulfillment', 'fund', 'gaap', 'gap', 'gathering', 'general', 'genetics', 'git', 'global', 'good', 'government', 'graphic', 'greek', 'grow', 'guard', 'guide', 'haccp', 'handling', 'hazardous', 'health', 'hedge', 'high', 'hippa', 'hive', 'hootsuite', 'hospitality', 'hotels', 'hse', 'hubspot', 'humanitarian', 'hyperion', 'ideation', 'ifrs', 'imaging', 'implement', 'improvements', 'incident', 'indicators', 'infection', 'information', 'innovation', 'inside', 'installation', 'instrumentation', 'integration', 'intelligence', 'intercompany', 'international', 'interpret', 'interviews', 'inventory', 'investigations', 'investors', 'invoicing', 'ip', 'ipsec', 'iso', 'italian', 'japanese', 'jira', 'journalism', 'juniper', 'kanban', 'keyboard', 'knockout', 'kyc', 'lan', 'languages', 'launches', 'leadership', 'learning', 'legal', 'levels', 'life', 'line', 'lisp', 'lms', 'local', 'loss', 'lua', 'machine', 'macros', 'mailchimp', 'maintains', 'making', 'manager', 'mandarin', 'mapping', 'marketo', 'mat', 'math', 'matrix', 'mdm', 'mechanics', 'medical', 'meditech', 'meets', 'merchandising', 'messaging', 'methodology', 'microelectronics', 'middle', 'military', 'minutes', 'mobile', 'modeling', 'mongodb', 'monthly', 'mpa', 'mrp', 'msd', 'multilingual', 'myhr', 'national', 'nebosh', 'negotiation', 'netsuite', 'networks', 'newsletter', 'nginx', 'nosql', 'nt', 'nursing', 'objects', 'offline', 'omniture', 'online', 'open', 'operational', 'optimization', 'order', 'ordinator', 'organizational', 'oriented', 'osha', 'ott', 'outlook', 'outsourcing', 'pages', 'partner', 'partnership', 'patent', 'payable', 'payroll', 'peoplesoft', 'perl', 'petrochemical', 'pharmacies', 'phone', 'photoshop', 'physical', 'pinterest', 'pivot', 'planning', 'platform', 'pleadings', 'pmi', 'policy', 'portuguese', 'postgres', 'power', 'ppc', 'pr', 'pre', 'preparation', 'presales', 'presentations', 'pricing', 'print', 'privacy', 'problem', 'procedures', 'processing', 'production', 'profiling', 'programing', 'programming', 'progressive', 'projects', 'property', 'proposition', 'protocols', 'provide', 'proxy', 'publication', 'puppet', 'python', 'qsr', 'quantitative', 'quick', 'radiology', 'rally', 'raw', 'react', 'receivable', 'reconcile', 'record', 'recovery', 'recruitment', 'reduction', 'regional', 'regulatory', 'relational', 'relationships', 'remarketing', 'report', 'requests', 'research', 'resolving', 'respa', 'responsive', 'results', 'return', 'review', 'rfi', 'rfps', 'rhce', 'risk', 'roadmap', 'root', 'routine', 'ruby', 's3', 'safeguarding', 'salesforce', 'sarbanes', 'scada', 'sccm', 'scheduling', 'sci', 'scorm', 'scripting', 'search', 'secretarial', 'segmentation', 'sem', 'sensitive', 'sequencing', 'servers', 'services', 'shared', 'sheet', 'shows', 'site', 'skills', 'small', 'sme', 'smtp', 'social', 'soldering', 'sops', 'sourcing', 'sox', 'specification', 'speech', 'sphr', 'sports', 'sql', 'ssl', 'staffing', 'standard', 'start', 'statement', 'statistical', 'statutory', 'stories', 'strategic', 'streams', 'structured', 'style', 'subsystems', 'suite', 'supplier', 'supply', 'swedish', 'switching', 'sys', 'tables', 'talent', 'tasks', 'tcl', 'tdd', 'technical', 'technologies', 'telecommunications', 'terminology', 'test', 'thai', 'thermodynamics', 'time', 'tomcat', 'trade', 'train', 'transactions', 'transformation', 'transport', 'treatment', 'trends', 'troubleshooting', 'twitter', 'ubuntu', 'unit', 'ups', 'usability', 'ux', 'value', 'vba', 'vendors', 'vertical', 'virtualization', 'visual', 'vlans', 'voip', 'wan', 'wastewater', 'wealth', 'website', 'whmis', 'wireframes', 'wiring', 'work', 'workflow', 'workstation', 'write', 'xamarin', 'youtube']\n"
]
}
],
"source": [
"f = open(\"hardskills.txt\", \"r\")\n",
"content = f.read()\n",
"content_list = content.split(\" \")\n",
"count_vec = CountVectorizer(stop_words=\"english\", analyzer='word', \n",
" ngram_range=(1, 1), max_df=1.0, min_df=1, max_features=None)\n",
"\n",
"# Transforms the data into a bag of words\n",
"count_train = count_vec.fit(content_list)\n",
"bag_of_words = count_vec.transform(content_list)\n",
"\n",
"# Print the first 10 features of the count_vec\n",
"print(\"Every feature:\\n{}\".format(count_vec.get_feature_names()))\n",
"print(\"\\nEvery 3rd feature:\\n{}\".format(count_vec.get_feature_names()[::3]))"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Vocabulary size: 1566\n",
"Vocabulary content:\n",
" {'budgeting': 185, 'cissp': 251, 'process': 1102, 'management': 842, 'accounts': 18, 'payable': 1014, 'positioning': 1063, 'seo': 1298, 'teaching': 1432, 'presentations': 1086, 'electrical': 451, 'reporting': 1204, '10': 0, 'key': 776, 'customer': 352, 'handling': 639, 'sql': 1359, 'server': 1301, 'clinical': 260, 'knowledge': 781, 'microsoft': 889, 'dynamics': 429, 'hotels': 666, 'hotel': 665, 'legal': 801, 'integrated': 719, 'communications': 281, 'publishing': 1142, 'costing': 325, 'desktop': 383, 'support': 1408, 'public': 1139, 'administration': 35, 'sensitivity': 1297, 'analysis': 73, 'capital': 208, 'spending': 1352, 'project': 1120, 'planning': 1047, 'foreign': 575, 'exchange': 509, 'operating': 971, 'scheduling': 1272, 'architecture': 106, 'variances': 1505, 'high': 651, 'volume': 1525, 'csc': 344, 'phone': 1032, 'calls': 201, 'development': 386, 'activities': 28, 'proofread': 1124, 'retail': 1222, 'meet': 874, 'quality': 1151, 'standards': 1370, 'legislation': 802, 'regulatory': 1191, 'test': 1446, 'plans': 1048, 'insights': 712, 'trade': 1461, 'shows': 1314, 'cpg': 329, 'balance': 148, 'sheet': 1311, 'reconciliations': 1175, 'reconcile': 1173, 'bank': 150, 'experience': 515, 'higher': 652, 'education': 444, 'delivery': 373, 'itil': 760, 'certification': 231, 'business': 189, 'operations': 973, 'lighting': 809, 'database': 360, 'processing': 1104, 'payments': 1016, 'partnerships': 1009, 'work': 1548, 'streams': 1389, 'invoicing': 747, 'strategic': 1386, 'sales': 1259, 'talent': 1422, 'financial': 550, 'forecasts': 574, 'ifrs': 684, 'agile': 57, 'budget': 184, 'product': 1106, 'features': 537, 'journalism': 768, 'develop': 385, 'advertisement': 44, 'transactions': 1467, 'marketing': 851, 'annual': 81, 'income': 697, 'tax': 1426, 'return': 1224, 'engagement': 471, 'performance': 1021, 'measures': 865, 'technical': 1434, 'skills': 1320, 'fluid': 566, 'accounting': 17, 'strategy': 1388, 'linux': 812, 'governance': 617, 'market': 850, 'segment': 1289, 'reconciliation': 1174, 'variance': 1504, 'life': 807, 'cycle': 356, 'billing': 168, 'contracts': 311, 'program': 1112, 'analytics': 75, 'value': 1503, 'proposition': 1128, 'visio': 1517, 'invoices': 746, 'safety': 1258, 'recruiting': 1181, 'distribution': 407, 'prospecting': 1129, 'wins': 1541, 'email': 456, 'employee': 463, 'services': 1305, 'account': 14, 'initiatives': 707, 'regulation': 1189, 'autocad': 135, 'erp': 490, 'systems': 1417, 'intelligence': 723, 'requirements': 1208, 'certificate': 230, 'achievement': 21, 'oncology': 965, 'expenditure': 512, 'entrepreneurship': 481, 'retention': 1223, 'company': 283, 'credit': 336, 'cards': 211, 'documentation': 415, 'digital': 395, 'content': 307, 'negotiation': 933, 'chinese': 243, 'revenue': 1226, 'recognition': 1172, 'mobile': 900, 'solutions': 1337, 'online': 966, 'web': 1534, 'application': 94, 'portuguese': 1062, 'launches': 792, 'success': 1400, 'usability': 1497, 'outside': 998, 'hyperion': 678, 'client': 257, 'relationships': 1197, 'mid': 890, 'advertising': 45, 'control': 312, 'smb': 1325, 'military': 894, 'metrics': 887, 'excel': 506, 'presales': 1083, 'analytical': 74, 'administrative': 36, 'category': 219, 'pivot': 1044, 'tables': 1419, 'service': 1303, 'orientation': 986, 'receivable': 1170, 'food': 571, 'professional': 1109, 'growth': 628, 'insurance': 718, 'claims': 254, 'information': 705, 'msd': 918, 'computer': 291, 'science': 1276, 'jira': 765, 'processes': 1103, 'network': 937, 'publication': 1140, 'research': 1209, 'methods': 886, 'ibm': 679, 'video': 1513, 'enterprise': 478, 'software': 1334, 'applications': 95, 'telecommunications': 1440, 'plan': 1046, 'events': 504, 'issues': 758, 'hospital': 662, 'peoplesoft': 1020, 'financials': 551, 'commercial': 278, 'editing': 440, 'channel': 236, 'banking': 151, 'sox': 1344, 'middleware': 892, 'tv': 1484, 'water': 1531, 'treatment': 1476, 'concierge': 295, 'petrochemical': 1026, 'cisco': 249, 'collaboration': 274, 'standard': 1368, 'procedures': 1101, 'field': 541, 'installation': 714, 'ecommerce': 435, 'consumer': 304, 'brand': 179, 'osp': 992, 'statutory': 1380, 'laws': 794, 'european': 499, 'indicators': 699, 'inventory': 738, 'change': 235, 'follow': 570, 'guidance': 632, 'industry': 701, 'trends': 1479, 'regional': 1188, 'alliance': 65, 'gap': 597, 'audit': 132, 'voip': 1524, 'federal': 538, 'regulations': 1190, 'feasibility': 535, 'studies': 1394, 'cma': 266, 'disbursement': 403, 'integration': 720, 'status': 1379, 'reports': 1205, 'forecasting': 573, 'quickbooks': 1156, 'mutual': 923, 'fund': 591, 'lean': 797, 'security': 1288, 'compliance': 288, 'audits': 134, 'segmentation': 1290, 'policies': 1058, 'media': 869, 'resource': 1213, 'allocation': 66, 'social': 1332, 'immigration': 688, 'backbone': 145, 'scripting': 1281, 'windows': 1540, 'cash': 217, 'presentation': 1085, 'design': 381, 'storytelling': 1385, 'basic': 156, 'office': 959, 'equipment': 488, 'campaigns': 204, 'coaching': 268, 'internal': 728, 'migration': 893, 'outbound': 994, 'rfi': 1230, 'saas': 1255, 'managing': 845, 'clients': 258, 'internship': 731, 'telecom': 1439, 'proposal': 1126, 'strong': 1390, 'organisational': 982, 'vlookup': 1522, 'contract': 310, 'territory': 1445, 'scheme': 1273, 'twitter': 1485, 'purchasing': 1145, 'skype': 1321, 'facebook': 525, 'issue': 757, 'driving': 424, 'record': 1176, 'fulfillment': 588, 'chrome': 244, 'personnel': 1025, 'photography': 1034, 'end': 468, 'cas': 214, 'non': 947, 'profit': 1111, 'user': 1499, 'interface': 727, 'access': 13, 'lifecycle': 808, 'infrastructure': 706, 'drafting': 418, 'counsel': 326, 'skill': 1319, 'relationship': 1196, 'building': 188, 'recruitment': 1182, 'omniture': 963, 'channels': 237, 'word': 1546, 'standardization': 1369, 'medical': 870, 'device': 387, 'workflows': 1552, 'accountancy': 16, 'ensure': 477, 'accuracy': 19, 'deposits': 378, 'sell': 1291, 'sem': 1293, 'sla': 1322, 'economics': 438, 'license': 805, 'architectural': 105, 'merchandising': 879, 'materials': 857, 'purchase': 1144, 'orders': 980, 'human': 674, 'resources': 1214, 'protocols': 1131, 'interpret': 732, 'data': 359, 'roi': 1243, 'calculations': 195, 'functions': 590, 'cost': 324, 'asic': 116, 'records': 1178, 'gsk': 629, 'center': 228, 'asset': 122, 'electronics': 453, 'aerospace': 51, 'graphic': 621, 'metadata': 883, 'preparation': 1080, 'trial': 1480, 'aop': 88, 'mysql': 925, 'general': 603, 'international': 729, 'travel': 1475, 'bi': 165, 'lingual': 811, 'progressive': 1119, 'training': 1465, 'upsell': 1495, 'workforce': 1553, 'grant': 620, 'chemical': 239, 'engineering': 474, 'ledger': 800, 'writing': 1559, 'executive': 511, 'team': 1433, 'continuous': 309, 'improvement': 692, 'supply': 1407, 'chain': 234, 'diagnostics': 393, 'sharepoint': 1309, 'ms': 916, 'loss': 822, 'statements': 1375, 'staffing': 1365, 'ccna': 224, 'logistics': 820, 'clerical': 256, 'duties': 427, 'architect': 104, 'procurement': 1105, 'principles': 1091, 'finance': 549, 'pricing': 1089, 'java': 763, 'mortgage': 910, 'escalation': 491, 'oriented': 987, 'marketo': 852, 'mandarin': 846, 'coding': 271, 'plant': 1049, 'acquisition': 22, 'b2b': 143, 'maintenance': 838, 'publications': 1141, 'global': 612, 'methodology': 885, 'complex': 287, 'projects': 1122, 'cdn': 227, 'quick': 1155, 'books': 178, 'branding': 180, 'manage': 841, 'demand': 374, 'consulting': 303, 'strategies': 1387, 'hiring': 656, 'modeling': 903, 'line': 810, 'cloud': 264, 'computing': 292, 'firewall': 554, 'rds': 1166, 'budgets': 186, 'sciences': 1277, 'health': 645, 'sarbanes': 1263, 'oxley': 1000, 'meeting': 875, 'deadlines': 366, 'transcription': 1468, 'production': 1107, 'problems': 1099, 'focus': 569, 'filing': 544, 'trading': 1463, 'investigation': 740, 'spreadsheets': 1357, 'monthly': 909, 'computation': 290, 'aed': 50, 'b2c': 144, 'southern': 1342, 'california': 199, 'sports': 1356, 'goals': 614, 'intranet': 736, 'debug': 369, 'sources': 1340, 'google': 616, 'negotiate': 932, 'community': 282, 'outreach': 997, 'statement': 1374, 'conversion': 314, 'divestitures': 408, 'therapeutic': 1450, 'catering': 220, 'inside': 711, 's3': 1254, 'entry': 483, 'zendesk': 1564, 'terminology': 1443, 'fmla': 568, 'dictation': 394, 'macros': 831, 'rfq': 1234, 'store': 1382, 'qa': 1147, 'facing': 529, 'scrap': 1279, 'auditing': 133, 'direct': 398, 'raw': 1164, 'depreciation': 379, 'fema': 539, 'ccie': 223, 'dnv': 411, 'portfolio': 1061, 'operational': 972, 'ppt': 1073, 'flow': 562, 'startup': 1372, 'html': 670, 'cardiovascular': 210, 'direction': 400, 'soa': 1330, 'minutes': 897, 'fitness': 557, 'technologies': 1437, 'hardware': 640, 'semiconductor': 1294, 'creative': 334, 'loan': 818, 'servicing': 1306, 'specifications': 1348, 'fixed': 558, 'assets': 123, 'suite': 1401, 'competitive': 285, 'commerce': 277, 'counseling': 327, 'adoption': 40, 'advanced': 43, 'trend': 1478, 'employment': 465, 'researching': 1210, 'vendors': 1509, 'environment': 484, 'mentorship': 878, 'powerpoint': 1069, 'editorial': 441, 'government': 618, 'new': 941, 'gaap': 594, 'relations': 1195, 'emergency': 461, 'pre': 1077, 'salesforce': 1260, 'com': 276, 'consumers': 305, 'advocacy': 48, 'corporate': 322, 'big': 166, 'real': 1168, 'estate': 495, 'transportation': 1474, 'small': 1323, 'risk': 1239, 'receipts': 1169, 'matrix': 861, 'policy': 1059, 'making': 840, 'lending': 803, 'filtration': 547, 'controls': 313, 'recruit': 1180, 'stakeholders': 1367, 'partnership': 1008, 'practices': 1076, 'techniques': 1436, 'advisory': 47, 'youtube': 1563, 'technology': 1438, 'intercompany': 726, 'licensing': 806, 'incident': 696, 'response': 1217, 'correspondence': 323, 'communication': 280, 'methodologies': 884, 'leads': 796, 'english': 475, 'investigate': 739, 'air': 60, 'force': 572, 'organization': 983, 'emerging': 462, 'math': 858, 'dynamodb': 430, 'hadoop': 637, 'payroll': 1017, 'bookkeeping': 177, 'programming': 1116, 'hospitality': 663, 'networking': 938, 'time': 1455, 'selling': 1292, 'programs': 1117, 'base': 153, 'fabrication': 524, 'healthcare': 646, 'financing': 552, 'investigations': 741, 'hospitals': 664, 'petty': 1027, 'facts': 531, 'ethernet': 497, 'outlook': 996, 'scenario': 1270, 'oracle': 976, 'sourcing': 1341, 'infection': 702, 'facilitation': 526, 'netsuite': 936, 'troubleshooting': 1482, 'patient': 1012, 'use': 1498, 'cases': 216, 'pipedrive': 1042, 'distributed': 406, 'microelectronics': 888, 'beverage': 163, 'testing': 1447, 'manufacturing': 848, 'escalations': 492, 'gather': 599, 'acquisitions': 23, 'investing': 742, 'ec2': 434, 'cisa': 248, 'flows': 564, 'journal': 767, 'entries': 482, 'rfps': 1233, 'vendor': 1508, 'troubleshoot': 1481, 'rfp': 1232, 'awareness': 141, 'affairs': 52, 'fashion': 533, 'conditions': 296, 'litigation': 815, 'generally': 604, 'accepted': 12, 'helpdesk': 650, 'databases': 361, 'crm': 341, 'cybersecurity': 355, 'sap': 1262, 'school': 1274, 'diploma': 397, 'complaints': 286, 'webinars': 1535, 'white': 1538, 'papers': 1003, 'law': 793, 'enforcement': 470, 'keeping': 775, 'apac': 89, 'gl': 611, 'hcm': 643, 'evaluate': 500, 'special': 1346, 'returns': 1225, 'clearance': 255, 'ftp': 586, 'nas': 926, 'maintain': 835, 'interviewing': 734, 'anti': 86, 'virus': 1516, 'ellucian': 455, 'banner': 152, 'sys': 1416, 'admin': 34, 'monitoring': 907, 'tools': 1459, 'dns': 410, 'bilingual': 167, 'pr': 1074, 'active': 27, 'directory': 401, 'hazardous': 642, 'established': 494, '2003': 1, 'flsa': 565, 'medicare': 871, 'critical': 340, 'care': 212, 'dss': 425, 'verbal': 1510, 'disaster': 402, 'recovery': 1179, 'dba': 365, 'programmer': 1115, 'language': 788, 'departmental': 376, 'citrix': 252, 'speaking': 1345, 'physical': 1038, 'therapy': 1451, 'mcdst': 862, 'redhat': 1183, 'prepare': 1081, 'hcpcs': 644, 'driven': 422, 'inquiry': 710, 'physiology': 1040, 'vpn': 1526, 'rhce': 1236, 'configuration': 299, 'procedure': 1100, 'construction': 301, 'languages': 789, 'economic': 437, 'rstp': 1250, 'appointments': 96, 'ipad': 751, 'examination': 505, 'agencies': 55, 'ordinator': 981, 'mitigation': 899, 'answering': 84, 'phones': 1033, 'gathering': 600, 'comptia': 289, 'provide': 1134, 'analyze': 76, 'problem': 1098, 'supplier': 1404, 'needs': 931, 'assessments': 121, 'adult': 42, 'learning': 798, 'os': 989, 'iphone': 752, 'cms': 267, 'radius': 1159, 'openstack': 970, 'products': 1108, 'tcp': 1429, 'ip': 750, 'l3': 784, 'hospice': 661, 'copying': 319, 'lan': 786, 'wan': 1527, 'greets': 625, 'load': 817, 'balancer': 149, 'datacenter': 362, 'facility': 528, '2008': 2, 'soldering': 1335, 'supervising': 1402, 'external': 522, 'audiences': 130, 'levels': 804, 'perl': 1023, 'electronic': 452, 'ssl': 1362, 'as400': 112, 'statistical': 1377, 'cpt': 330, 'schedules': 1271, 'audio': 131, 'enhancements': 476, 'vmware': 1523, 'sensitive': 1296, 'virtualization': 1515, 'statistics': 1378, 'apache': 90, 'shared': 1308, 'elearning': 450, 'cognos': 272, 'emr': 466, 'nginx': 945, 'aviation': 139, 'pci': 1018, 'arrangements': 110, 'netbackup': 935, 'certified': 232, 'document': 414, 'epc': 487, 'tracking': 1460, 'expenses': 514, 'hse': 669, 'switching': 1413, 'dhcp': 392, 'timekeeping': 1456, 'prototype': 1132, 'centos': 229, 'bash': 155, 'acceptance': 11, 'bgp': 164, 'workstation': 1554, 'child': 242, 'sociology': 1333, 'credentialing': 335, 'nursing': 954, 'interaction': 724, 'formulation': 578, 'survey': 1409, 'privacy': 1095, 'state': 1373, 'capacity': 207, 'bomgar': 176, 'faa': 523, 'lms': 816, 'mental': 877, 'calendar': 197, 'antivirus': 87, 'organizational': 984, 'structure': 1391, 'tcl': 1428, 'sms': 1327, 'medicine': 872, 'debugging': 370, 'hippa': 654, 'receivables': 1171, 'requirement': 1207, 'specification': 1347, 'inbound': 695, 'implementation': 691, 'ami': 69, 'report': 1203, 'etl': 498, 'maintaining': 836, 'files': 543, 'continuity': 308, 'engineer': 473, 'sccm': 1269, 'lotus': 823, 'notes': 950, 'customers': 353, 'guard': 630, 'french': 584, 'asp': 117, 'reimbursement': 1192, 'requests': 1206, 'checkpoint': 238, 'tcpdump': 1430, 'xp': 1562, 'osha': 990, 'accurate': 20, 'criminal': 338, 'justice': 772, 'remote': 1201, 'pace': 1001, 'documenting': 416, 'answer': 83, 'urban': 1496, 'smtp': 1329, 'sec': 1285, 'subcontractor': 1397, 'adjudication': 33, 'lync': 826, 'tuning': 1483, 'freebsd': 583, 'avionics': 140, 'solidworks': 1336, 'ordering': 979, 'supplies': 1406, 'hris': 668, 'informatica': 704, 'adobe': 39, 'acrobat': 24, 'avaya': 138, 'coordinate': 315, 'delegate': 372, 'tasks': 1425, 'postman': 1067, 'cctv': 226, 'hr': 667, 'file': 542, 'mdm': 864, 'warehouse': 1528, 'translate': 1472, 'home': 659, 'admissions': 38, 'personal': 1024, 'protective': 1130, 'improvements': 693, 'firewalls': 555, '60': 5, 'wpm': 1556, 'typing': 1486, 'staff': 1364, 'roadmap': 1242, 'backup': 146, 'unix': 1493, 'effectiveness': 447, 'circuits': 246, 'mpa': 912, 'keyboard': 777, 'workers': 1550, 'compensation': 284, 'datasets': 363, 'safeguarding': 1257, 'instructional': 716, 'splunk': 1355, 'genetics': 606, 'tactical': 1421, 'boarding': 174, 'group': 626, 'preparing': 1082, 'rdbms': 1165, 'excellence': 507, 'postgres': 1065, 'partners': 1007, 'environmental': 485, 'appraisals': 98, 'macos': 830, 'assembly': 119, 'forklift': 576, 'event': 503, 'coordination': 316, 'terraform': 1444, 'ansys': 85, 'ruby': 1251, 'flash': 559, 'cpc': 328, 'functionality': 589, 'iis': 685, 'secretarial': 1287, 'trello': 1477, 'psychology': 1138, 'release': 1198, 'transactional': 1466, 'myhr': 924, 'open': 969, 'source': 1339, 'help': 649, 'desk': 382, 'pleadings': 1053, 'hipaa': 653, 'assurance': 124, 'cis': 247, 'drawings': 420, 'practice': 1075, 'emea': 460, 'ccnp': 225, 'vlans': 1521, 'directing': 399, 'lists': 814, 'tomcat': 1458, 'results': 1221, 'manual': 847, 'dexterity': 389, 'scorm': 1278, 'notary': 949, 'party': 1010, 'nt': 951, 'ansible': 82, 'icd': 680, 'cm': 265, 'spelling': 1351, 'job': 766, 'anatomy': 78, 'curriculum': 350, 'recordkeeping': 1177, 'routing': 1249, 'cardiology': 209, 'evaluations': 502, 'mpls': 913, 'hire': 655, 'db': 364, 'wireshark': 1544, 'senior': 1295, 'managers': 844, 'switches': 1412, 'imaging': 687, 'case': 215, 'informal': 703, 'juniper': 771, 'router': 1246, 'diligence': 396, 'aid': 59, 'css': 346, 'aap': 7, 'transport': 1473, 'behavioral': 157, 'routers': 1247,...