[2024-04-14] lab 4, 5

lab/data/.gitignore

@@ -0,0 +1,2 @@
+corpus/
+NIPS Papers/

lab/data/lda_topics.txt

@@ -0,0 +1,10 @@
+(0, '0.006*"learning" + 0.005*"model" + 0.005*"data" + 0.004*"function" + 0.004*"set" + 0.004*"using" + 0.004*"number" + 0.004*"neural" + 0.004*"one" + 0.003*"error"')
+(1, '0.008*"learning" + 0.006*"data" + 0.005*"model" + 0.005*"set" + 0.004*"algorithm" + 0.004*"time" + 0.004*"one" + 0.004*"two" + 0.003*"used" + 0.003*"figure"')
+(2, '0.007*"data" + 0.005*"model" + 0.005*"set" + 0.005*"learning" + 0.004*"one" + 0.004*"algorithm" + 0.004*"time" + 0.003*"using" + 0.003*"figure" + 0.003*"training"')
+(3, '0.006*"data" + 0.005*"model" + 0.004*"learning" + 0.004*"two" + 0.004*"algorithm" + 0.004*"using" + 0.004*"function" + 0.004*"set" + 0.003*"number" + 0.003*"given"')
+(4, '0.006*"learning" + 0.005*"data" + 0.005*"model" + 0.005*"set" + 0.004*"algorithm" + 0.004*"time" + 0.004*"using" + 0.004*"two" + 0.004*"function" + 0.003*"one"')
+(5, '0.008*"learning" + 0.006*"data" + 0.005*"algorithm" + 0.004*"model" + 0.004*"two" + 0.004*"function" + 0.004*"number" + 0.003*"figure" + 0.003*"time" + 0.003*"set"')
+(6, '0.007*"learning" + 0.006*"model" + 0.005*"data" + 0.005*"algorithm" + 0.004*"function" + 0.004*"set" + 0.003*"time" + 0.003*"one" + 0.003*"based" + 0.003*"number"')
+(7, '0.007*"learning" + 0.005*"set" + 0.005*"data" + 0.005*"model" + 0.004*"algorithm" + 0.004*"function" + 0.004*"using" + 0.004*"number" + 0.004*"log" + 0.004*"figure"')
+(8, '0.005*"learning" + 0.005*"set" + 0.005*"algorithm" + 0.004*"model" + 0.004*"function" + 0.004*"data" + 0.004*"one" + 0.004*"time" + 0.003*"using" + 0.003*"given"')
+(9, '0.007*"data" + 0.006*"model" + 0.005*"learning" + 0.005*"algorithm" + 0.004*"two" + 0.003*"number" + 0.003*"time" + 0.003*"set" + 0.003*"function" + 0.003*"used"')

lab/data/top_nouns.txt

@@ -0,0 +1,100 @@
+project victims support visit mediation
+exhibition cooperation year meeting films
+exhibition cooperation year meeting films
+solution occupation settlement problem resolutions
+residence citizens permit security citizen
+residence citizens permit security citizen
+support measures countries farmers member
+data services infrastructure development project
+data services infrastructure development project
+photographs service scans materials films
+photographs service scans materials films
+insurance ZUS contributions benefits administration
+project archaeology research conservation history
+project archaeology research conservation history
+cases % coronavirus countries disease
+% year case cases coronavirus
+ship tug speed accident course
+ship tug speed accident course
+work scientists research science telomerase
+work scientists research science telomerase
+film media part time efforts
+film media part time efforts
+insurance ZUS contributions benefits administration
+use care stewardship resistance antibiotics
+services administration state information e
+services administration state information e
+coronavirus research measures outbreak member
+residence card foreigner work permit
+security e threats policy gas
+security e threats policy gas
+paper 15th reader file date
+paper 15th reader file date
+costs implementation management tasks expenditures
+food cooperation products market agri
+costs implementation management tasks expenditures
+costs implementation management tasks expenditures
+artist work painting paintings time
+artist work painting paintings time
+Home » rights representatives discrimination
+Home » rights representatives discrimination
+command documentation alias files directory
+water basis land status item
+water basis land status item
+% contract contracts . No
+food cooperation products market agri
+% contract contracts . No
+market level services age companies
+market level services age companies
+projects innovation R&D development companies
+projects innovation R&D development companies
+contracts contract % item procedures
+contracts contract % item procedures
+room A office information B
+room A office information B
+advantage production country countries goods
+measles vaccine disease person people
+advantage production country countries goods
+card residence permission business stamp
+card residence permission business stamp
+w % gospodarczego polityki publicznych
+system banks stability risk sector
+camps people concentration policy resistance
+camps people concentration policy resistance
+safety aviation management requirements entity
+safety aviation management requirements entity
+research call philosophy information project
+vaccination pertussis cancer risk disease
+research call philosophy information project
+energy gas % oil countries
+energy gas % oil countries
+cooperation meeting talks forces defence
+project education information coronavirus funding
+food education project measures assistance
+infection disease symptoms fever humans
+energy audit costs use management
+countries % development benefits funds
+years minister year rector persons
+water food fish times year
+land water population data age
+land water population data age
+market labour crisis unemployment countries
+market labour crisis unemployment countries
+accelerator research - operation model
+accelerator research - operation model
+energy policy power development objectives
+priest hand country wedding church
+eggs breakfast food products meat
+eggs breakfast food products meat
+water fish times food year
+honey production bread time taste
+honey production bread time taste
+data job portal vacancies Decision
+data job portal vacancies Decision
+food quality products apples farmers
+food quality products apples farmers
+visa activities child B-1 institution
+visa activities child B-1 institution
+- co preparations operation preparation
+- co preparations operation preparation
+project victims support visit mediation

lab/data/top_nouns_tfidf.txt

@@ -0,0 +1,100 @@
+approval total lawyers priorities judges
+agriculture support guests offers author
+agriculture support guests offers author
+homeland invasion address prisoners sources
+identity positions elaboration issues terms
+identity positions elaboration issues terms
+distancing lenders mechanism check part
+IT Realization Services resolutions bases
+IT Realization Services resolutions bases
+occupation scans browser Service processes
+occupation scans browser Service processes
+am war month Insurance centralisation
+conservation zu provisions basin record
+conservation zu provisions basin record
+culture city abscesses aeronautics disruptors
+infection Recommendations man evening occurrence
+course hull STATE classifier certificate
+course hull STATE classifier certificate
+cooling work culture part laboratory
+cooling work culture part laboratory
+culture reverse advisor documentary service
+culture reverse advisor documentary service
+am war month Insurance centralisation
+pressure ability entry prescribers costs
+economies management role disk stakeholders
+economies management role disk stakeholders
+traders fears carriers illness distancing
+activity employment foreigners Visa graduate
+defense forecast quarter factors opportunity
+defense forecast quarter factors opportunity
+case author screen announcement typefaces
+case author screen announcement typefaces
+revenue office premises o proposals
+storage completion efforts Meeting crisis
+office Types premises protection days
+revenue office premises o proposals
+pictures splashing dobrze viewer culture
+pictures splashing dobrze viewer culture
+creation origin discrimination interest institutions
+creation origin discrimination interest institutions
+names contexts calculator program descriptor
+periods standards total name property
+periods standards total name property
+Art days liability authorities services
+storage completion efforts Meeting crisis
+Art days liability authorities services
+skills provision country economies science
+skills provision country economies science
+Project possibilities cancer members therapies
+Project possibilities cancer members therapies
+price auction actions telecommunications appointment
+price auction actions telecommunications appointment
+records coffee authorisation line times
+records coffee authorisation line times
+example manner source essence identification
+defences vaccines days spread body
+example manner source essence identification
+servants employees Possession insurance examinations
+servants employees Possession insurance examinations
+systemowe dopiero system latach popytem
+efficiency problems uncertainty improvement Risk
+uprising borders rights security campaign
+uprising borders rights security campaign
+part audits Responsibilities services authority
+protection competence version occurrence requisition
+Requirements members methodology data database
+whoop substitute cause exposure course
+Requirements members methodology data database
+erent decisions SOURCES spectrum economies
+erent decisions SOURCES spectrum economies
+invitation effects help armament round
+area teaching tax time travel
+time Recommendation participants guarantees work
+toxin mechanisms attacks Babies therapies
+production replacement control SMEs audit
+significance net ground participants levels
+functioning consultation interest expert procedures
+thing mercury eggs municipality lunch
+agriculture R result development prices
+agriculture R result development prices
+reflection basis sources points results
+reflection basis sources points results
+leaders reach author features publications
+leaders reach author features publications
+consumption Improvement bodies level need
+money delirium advice house couple
+work thanks BEgINNINg range funds
+work thanks BEgINNINg range funds
+option eggs dinner wine quantities
+seeds mead event maples approach
+seeds mead event maples approach
+case complaints consultation Employers actions
+case complaints consultation Employers actions
+activity fruit indications zation rice
+activity fruit indications zation rice
+building work premises Food child
+building work premises Food child
+virtue works culture sectors others
+virtue works culture sectors others
+approval total lawyers priorities judges