Upload 15 files

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/_20news_df_output_doc_topic_CTM.csv filter=lfs diff=lfs merge=lfs -text
+data/_20news_df_output_doc_topic_LDA.csv filter=lfs diff=lfs merge=lfs -text
+data/_20news_df_output_doc_topic_NMF.csv filter=lfs diff=lfs merge=lfs -text
+data/_20news_df_output_doc_topic_Top2Vec.csv filter=lfs diff=lfs merge=lfs -text
+data/sample_text.csv filter=lfs diff=lfs merge=lfs -text

data/_20news_df_output_clusterId_label_words.csv

@@ -0,0 +1,22 @@
+id_cluster,label_class,list_topic_words
+-1,#,"['ax', 'line', 'subject', 'organization', 'one', 'would', 'writes', 'article', 'posting', 'university', 'like', 'host', 'get', 'nntp', 'know', 'max', 'time', 'system', 'people', 'use']"
+0,talk.politics.mideast,"['israel', 'israeli', 'arab', 'jew', 'palestinian', 'jewish', 'people', 'right', 'peace', 'writes', 'war', 'article', 'would', 'state', 'jake', 'policy', 'civilian', 'one', 'subject', 'country']"
+1,rec.sport.baseball,"['game', 'player', 'baseball', 'year', 'pitcher', 'hit', 'team', 'hitter', 'run', 'writes', 'article', 'line', 'pitch', 'ball', 'clutch', 'organization', 'subject', 'last', 'season', 'base']"
+2,rec.motorcycles,"['bike', 'dod', 'dog', 'motorcycle', 'ride', 'helmet', 'riding', 'line', 'organization', 'rider', 'writes', 'subject', 'article', 'tire', 'countersteering', 'one', 'like', 'bmw', 'advice', 'posting']"
+3,comp.os.ms-windows.misc,"['window', 'do', 'mouse', 'microsoft', 'file', 'line', 'nt', 'subject', 'application', 'system', 'organization', 'pc', 'win', 'user', 'software', 'manager', 'com', 'program', 'run', 'use']"
+4,talk.politics.guns,"['president', 'stephanopoulos', 'mr', 'fbi', 'fire', 'think', 'myers', 'batf', 'people', 'would', 'koresh', 'atf', 'going', 'waco', 'know', 'said', 'compound', 'writes', 'gas', 'child']"
+5,rec.sport.hockey,"['team', 'game', 'hockey', 'player', 'nhl', 'blue', 'goal', 'pit', 'det', 'gm', 'play', 'leaf', 'playoff', 'league', 'chi', 'wing', 'win', 'bos', 'season', 'tor']"
+6,soc.religion.christian,"['god', 'jesus', 'church', 'sin', 'christian', 'christ', 'bible', 'mary', 'hell', 'law', 'faith', 'one', 'heaven', 'catholic', 'say', 'would', 'people', 'believe', 'eternal', 'subject']"
+7,comp.sys.ibm.pc.hardware,"['drive', 'scsi', 'ide', 'mb', 'disk', 'controller', 'bus', 'hard', 'pc', 'system', 'floppy', 'do', 'mac', 'line', 'bit', 'subject', 'organization', 'meg', 'card', 'problem']"
+8,sci.crypt,"['key', 'encryption', 'clipper', 'chip', 'escrow', 'government', 'phone', 'algorithm', 'de', 'system', 'security', 'nsa', 'bit', 'would', 'public', 'use', 'line', 'encrypted', 'crypto', 'law']"
+9,talk.politics.misc,"['homosexual', 'gay', 'cramer', 'homosexuality', 'sex', 'sexual', 'clayton', 'men', 'people', 'marriage', 'christian', 'study', 'sin', 'god', 'male', 'writes', 'article', 'one', 'would', 'love']"
+10,rec.autos,"['car', 'dealer', 'engine', 'ford', 'price', 'writes', 'saturn', 'subject', 'line', 'organization', 'article', 'diesel', 'mustang', 'auto', 'would', 'like', 'new', 'automatic', 'transmission', 'university']"
+11,sci.med,"['candida', 'patient', 'vitamin', 'gordon', 'doctor', 'yeast', 'geb', 'disease', 'bank', 'infection', 'quack', 'treatment', 'pain', 'kidney', 'physician', 'stone', 'medical', 'diet', 'migraine', 'bloom']"
+12,alt.atheism,"['god', 'atheist', 'belief', 'atheism', 'christian', 'believe', 'truth', 'faith', 'absolute', 'say', 'religion', 'existence', 'people', 'one', 'reason', 'exist', 'jesus', 'would', 'think', 'evidence']"
+13,talk.politics.guns,"['gun', 'firearm', 'weapon', 'right', 'militia', 'people', 'handgun', 'amendment', 'crime', 'control', 'state', 'would', 'criminal', 'arm', 'one', 'well', 'law', 'revolver', 'police', 'like']"
+14,comp.sys.mac.hardware,"['monitor', 'video', 'vga', 'line', 'color', 'screen', 'computer', 'subject', 'resolution', 'organization', 'horizontal', 'apple', 'problem', 'mac', 'atari', 'sync', 'university', 'nec', 'mode', 'power']"
+15,comp.graphics,"['jpeg', 'image', 'color', 'gif', 'file', 'bit', 'format', 'program', 'display', 'version', 'viewer', 'pixel', 'quality', 'convert', 'jfif', 'colormap', 'colour', 'use', 'graphic', 'window']"
+16,sci.space,"['space', 'mission', 'orbit', 'hst', 'nasa', 'shuttle', 'probe', 'satellite', 'earth', 'data', 'spacecraft', 'lunar', 'baalke', 'solar', 'image', 'propulsion', 'jupiter', 'mar', 'launch', 'planetary']"
+17,misc.forsale,"['sound', 'audio', 'amp', 'stereo', 'channel', 'speaker', 'sale', 'line', 'voltage', 'relay', 'subject', 'organization', 'midi', 'input', 'cd', 'output', 'switch', 'amplifier', 'circuit', 'signal']"
+18,comp.os.ms-windows.misc,"['printer', 'print', 'deskjet', 'hp', 'laser', 'ink', 'bubblejet', 'bj', 'printing', 'canon', 'driver', 'line', 'subject', 'organization', 'postscript', 'cartridge', 'page', 'university', 'paper', 'problem']"
+19,talk.politics.mideast,"['armenian', 'turkish', 'armenia', 'turk', 'turkey', 'greek', 'argic', 'serdar', 'muslim', 'soviet', 'azeri', 'people', 'genocide', 'serum', 'russian', 'village', 'greece', 'istanbul', 'tartar', 'azerbaijan']"

data/_20news_df_output_doc_topic_CTM.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04dc9cd291442e9836d3e2d5836c27034a4a9cd2230b4269a26964c254a75a70
+size 10527298

data/_20news_df_output_doc_topic_CTM_LIST.csv

@@ -0,0 +1,21 @@
+id_cluster,label_class,list_topic_words
+0,sci.space,"['health', 'patient', 'medical', 'space', 'disease', 'study', 'year', 'treatment', 'drug', 'april']"
+1,misc.forsale,"['notice', 'passed', 'suggested', 'higher', 'dark', 'background', 'larger', 'choice', 'requirement', 'discus']"
+2,comp.windows.x,"['pub', 'ftp', 'edu', 'format', 'archive', 'image', 'graphic', 'version', 'faq', 'site']"
+3,talk.politics.guns,"['atf', 'fire', 'waco', 'fbi', 'disclaimer', 'koresh', 'gas', 'survivor', 'reserve', 'bank']"
+4,talk.politics.mideast,"['people', 'right', 'article', 'atheism', 'homosexual', 'would', 'israel', 'writes', 'one', 'argument']"
+5,soc.religion.christian,"['trouble', 'suggested', 'notice', 'avoid', 'count', 'choice', 'higher', 'consideration', 'changed', 'passed']"
+6,rec.autos,"['car', 'engine', 'bike', 'dod', 'ride', 'mile', 'auto', 'oil', 'ford', 'motorcycle']"
+7,talk.politics.mideast,"['soviet', 'turkish', 'armenia', 'turk', 'armenian', 'genocide', 'muslim', 'soldier', 'people', 'russian']"
+8,soc.religion.christian,"['jesus', 'god', 'church', 'one', 'bible', 'christ', 'scripture', 'spirit', 'passage', 'sin']"
+9,comp.os.ms-windows.misc,"['max', 'mi', 'md', 'window', 'pl', 'tm', 'ex', 'id', 'ah', 'mb']"
+10,alt.atheism,"['objective', 'morality', 'moral', 'god', 'christianity', 'exist', 'faith', 'writes', 'christian', 'atheist']"
+11,comp.windows.x,"['window', 'application', 'manager', 'font', 'help', 'thanks', 'screen', 'mouse', 'motif', 'graphic']"
+12,comp.sys.ibm.pc.hardware,"['card', 'board', 'monitor', 'video', 'thanks', 'port', 'offer', 'driver', 'modem', 'drive']"
+13,rec.sport.hockey,"['red', 'boston', 'leaf', 'fan', 'playoff', 'blue', 'lost', 'baseball', 'game', 'ranger']"
+14,talk.politics.guns,"['would', 'think', 'people', 'president', 'know', 'going', 'get', 'time', 'fbi', 'right']"
+15,comp.sys.ibm.pc.hardware,"['scsi', 'drive', 'ide', 'bus', 'disk', 'controller', 'mac', 'problem', 'card', 'mb']"
+16,sci.crypt,"['chip', 'encryption', 'clipper', 'escrow', 'wiretap', 'crypto', 'key', 'secret', 'secure', 'nsa']"
+17,misc.forsale,"['ac', 'sale', 'shipping', 'email', 'looking', 'distribution', 'asking', 'usa', 'express', 'nntp']"
+18,misc.forsale,"['nntp', 'posting', 'host', 'distribution', 'usa', 'sale', 'offer', 'interested', 'ca', 'ohio']"
+19,rec.sport.hockey,"['year', 'game', 'player', 'team', 'appears', 'season', 'hockey', 'league', 'play', 'st']"

data/_20news_df_output_doc_topic_LDA.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b87675ff2422b7c0411266320a5cca316bed5c102427b06610fdb35eec5ceac
+size 13063689

data/_20news_df_output_doc_topic_LDA_LIST.csv

@@ -0,0 +1,21 @@
+id_cluster,label_class,list_topic_words
+0,soc.religion.christian,"['god', 'line', 'output', 'lord', 'christ', 'would', 'book', 'problem', 'subject', 'organization']"
+1,comp.sys.mac.hardware,"['drive', 'system', 'disk', 'mac', 'hard', 'problem', 'get', 'scsi', 'also', 'card']"
+2,comp.graphics,"['graphic', 'file', 'pub', 'mail', 'ray', 'send', 'edu', 'object', 'archive', 'output']"
+3,comp.os.ms-windows.misc,"['max', 'pl', 'tm', 'mb', 'mr', 'mi', 'ex', 'ah', 'au', 'de']"
+4,sci.electronics,"['one', 'use', 'get', 'two', 'see', 'also', 'new', 'time', 'first', 'year']"
+5,comp.graphics,"['image', 'gif', 'color', 'format', 'quality', 'software', 'pixel', 'free', 'tool', 'version']"
+6,comp.windows.x,"['available', 'ftp', 'edu', 'pub', 'version', 'format', 'graphic', 'package', 'source', 'contact']"
+7,sci.space,"['system', 'data', 'drive', 'disk', 'support', 'feature', 'software', 'space', 'user', 'rom']"
+8,comp.windows.x,"['data', 'image', 'available', 'also', 'information', 'sun', 'based', 'set', 'tool', 'motif']"
+9,rec.sport.hockey,"['would', 'know', 'writes', 'article', 'think', 'line', 'organization', 'subject', 'year', 'like']"
+10,sci.crypt,"['state', 'law', 'use', 'information', 'question', 'new', 'american', 'must', 'example', 'may']"
+11,soc.religion.christian,"['jesus', 'said', 'people', 'say', 'know', 'one', 'armenian', 'day', 'lord', 'come']"
+12,comp.graphics,"['file', 'image', 'program', 'gif', 'format', 'gun', 'color', 'output', 'section', 'may']"
+13,misc.forsale,"['line', 'organization', 'subject', 'writes', 'article', 'host', 'nntp', 'people', 'world', 'university']"
+14,alt.atheism,"['god', 'atheist', 'atheism', 'religion', 'religious', 'christian', 'belief', 'many', 'believe', 'one']"
+15,comp.windows.x,"['mail', 'computer', 'internet', 'server', 'anonymous', 'posting', 'system', 'user', 'privacy', 'information']"
+16,comp.os.ms-windows.misc,"['pl', 'md', 'sc', 'ah', 'id', 'wa', 'mr', 'st', 'gif', 'tm']"
+17,comp.os.ms-windows.misc,"['do', 'window', 'file', 'microsoft', 'program', 'mouse', 'output', 'font', 'version', 'server']"
+18,comp.graphics,"['bit', 'use', 'color', 'window', 'driver', 'mac', 'program', 'version', 'scsi', 'hardware']"
+19,talk.politics.guns,"['people', 'would', 'one', 'think', 'make', 'president', 'know', 'mr', 'well', 'even']"

data/_20news_df_output_doc_topic_NMF.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33a5baa539dcdc12d23c65bec27d9aa26473e1b8bae3629a2384f2a4b120cee
+size 13068868

data/_20news_df_output_doc_topic_NMF_LIST.csv

@@ -0,0 +1,21 @@
+id_cluster,label_class,list_topic_words
+0,soc.religion.christian,"['god', 'line', 'output', 'lord', 'christ', 'would', 'book', 'problem', 'subject', 'organization']"
+1,comp.sys.mac.hardware,"['drive', 'system', 'disk', 'mac', 'hard', 'problem', 'get', 'scsi', 'also', 'card']"
+2,comp.graphics,"['graphic', 'file', 'pub', 'mail', 'ray', 'send', 'edu', 'object', 'archive', 'output']"
+3,comp.os.ms-windows.misc,"['max', 'pl', 'tm', 'mb', 'mr', 'mi', 'ex', 'ah', 'au', 'de']"
+4,sci.electronics,"['one', 'use', 'get', 'two', 'see', 'also', 'new', 'time', 'first', 'year']"
+5,comp.graphics,"['image', 'gif', 'color', 'format', 'quality', 'software', 'pixel', 'free', 'tool', 'version']"
+6,comp.windows.x,"['available', 'ftp', 'edu', 'pub', 'version', 'format', 'graphic', 'package', 'source', 'contact']"
+7,sci.space,"['system', 'data', 'drive', 'disk', 'support', 'feature', 'software', 'space', 'user', 'rom']"
+8,comp.windows.x,"['data', 'image', 'available', 'also', 'information', 'sun', 'based', 'set', 'tool', 'motif']"
+9,rec.sport.hockey,"['would', 'know', 'writes', 'article', 'think', 'line', 'organization', 'subject', 'year', 'like']"
+10,sci.crypt,"['state', 'law', 'use', 'information', 'question', 'new', 'american', 'must', 'example', 'may']"
+11,soc.religion.christian,"['jesus', 'said', 'people', 'say', 'know', 'one', 'armenian', 'day', 'lord', 'come']"
+12,comp.graphics,"['file', 'image', 'program', 'gif', 'format', 'gun', 'color', 'output', 'section', 'may']"
+13,misc.forsale,"['line', 'organization', 'subject', 'writes', 'article', 'host', 'nntp', 'people', 'world', 'university']"
+14,alt.atheism,"['god', 'atheist', 'atheism', 'religion', 'religious', 'christian', 'belief', 'many', 'believe', 'one']"
+15,comp.windows.x,"['mail', 'computer', 'internet', 'server', 'anonymous', 'posting', 'system', 'user', 'privacy', 'information']"
+16,comp.os.ms-windows.misc,"['pl', 'md', 'sc', 'ah', 'id', 'wa', 'mr', 'st', 'gif', 'tm']"
+17,comp.os.ms-windows.misc,"['do', 'window', 'file', 'microsoft', 'program', 'mouse', 'output', 'font', 'version', 'server']"
+18,comp.graphics,"['bit', 'use', 'color', 'window', 'driver', 'mac', 'program', 'version', 'scsi', 'hardware']"
+19,talk.politics.guns,"['people', 'would', 'one', 'think', 'make', 'president', 'know', 'mr', 'well', 'even']"

data/_20news_df_output_doc_topic_Top2Vec.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838c4667500d7d544ef1f6732d5c4017371618ce92573790953c7d53c4a210d6
+size 21296146

data/_20news_df_output_doc_topic_Top2Vec_LIST.csv

@@ -0,0 +1,21 @@
+id_cluster,label_class,list_topic_words
+0,soc.religion.christian,"['bible', 'god', 'jesus', 'religion', 'scripture', 'christianity', 'christ', 'atheist', 'prophet', 'christian', 'religious', 'church', 'muslim', 'theist', 'quran', 'verse', 'doctrine', 'gospel', 'belief', 'holy', 'testament', 'psalm', 'islam', 'apostle', 'faith', 'believer', 'theology', 'heresy', 'congregation', 'atheism', 'interpretation', 'disciple', 'revelation', 'catholic', 'armenian', 'salvation', 'truth', 'corinthian', 'khomeini', 'baptism', 'sin', 'persecution', 'teaching', 'turkish', 'passage', 'hebrew', 'biblical', 'isaiah']"
+1,comp.windows.x,"['window', 'olwmxterm', 'open', 'windows', 'default', 's', 'pointer', 'menu', 'intrinsics', 'client', 'xdm', 'widget', 'openwin', 'bitmap', 'colormap', 'xlib', 'ncd', 'screen', 'file', 'server', 'icon', 'manager', 'display', 'application', 'directory', 'button', 'config', 'default', 'ini', 'pixmap', 'openlook', 'font', 'sunos', 'paste', 'exit', 'sparc', 'mwm', 'console', 'xaw', 'ctrl', 'twm', 'xpert', 'ndet', 'running', 'program', 'args', 'mouse', 'fprintf', 'motif', 'contrib', 'exe']"
+2,comp.sys.mac.hardware,"['apple', 'sale', 'shipping', 'powerbook', 'coprocessor', 'lc', 'iii', 'price', 'simm', 'brand', 'offer', 'iis', 'ifp', 'ui', 'cic', 'entris', 'nubus', 'mac', 'for', 'sale', 'slot', 'vram', 'printer', 'simm', 'selling', 'quadra', 'bought', 'sell', 'upgrade', 'monitor', 'adapter', 'cartridge', 'duo', 'external', 'purchased', 'lc', 'plus', 'asking', 'buying', 'sony', 'portable', 'interested', 'buyer', 'dpi', 'ethernet', 'obo', 'codram', 'deskjet', 'laserjet', 'modem', 'mhz', 'hanover']"
+3,talk.politics.misc,"['gun', 'firearm', 'criminal', 'handgun', 'crime', 'nra', 'constitutional', 'democrat', 'homicide', 'politician', 'abiding', 'cramer', 'clayton', 'brady', 'liberal', 'homosexual', 'amendment', 'rkb', 'federal', 'voter', 'clinton', 'constitution', 'economic', 'social', 'shotgun', 'bang', 'government', 'tax', 'opti', 'link', 'veal', 'gay', 'liberty', 'abuse', 'citizen', 'atheist', 'legal', 'self', 'violent', 'minority', 'petaluma', 'privacy', 'drug', 'majority', 'cipriani', 'enforce', 'election', 'freedom', 'heterosexual', 'jail', 'health']"
+4,rec.sport.hockey,"['playoff', 'hockey', 'bruin', 'nhl', 'goalie', 'bure', 'goaltender', 'mogilny', 'blackhawks', 'islander', 'lafontaine', 'potvin', 'canadien', 'lemieux', 'powerplay', 'quebec', 'gilmour', 'canuck', 'penguin', 'whaler', 'elanne', 'defenseman', 'puck', 'shanahan', 'overtime', 'yzerman', 'chhabra', 'fuhr', 'habs', 'recchi', 'barrasso', 'gretzky', 'cup', 'stanley', 'domi', 'oderstrom', 'adirondack', 'oiler', 'sabre', 'probert', 'chelios', 'messier', 'rauser', 'flyer', 'isle', 'skate', 'edmonton', 'tournament', 'dineen', 'devil']"
+5,sci.electronics,"['championship', 'mail', 'hockey', 'email', 'sweden', 'nhl', 'canada', 'please', 'hello', 'reply', 'internet', 'motorcycle', 'histaff', 'an', 'space', 'tournament', 'subject', 'appreciate', 'finland', 'posciqw', 'sale', 'playoff', 'thanks', 'university', 'appreciated', 'posting', 'carnegie', 'xj', 'mailing', 'fax', 'send', 'honda', 'engineering', 'computer', 'news', 'cmu', 'moa', 'computing', 'thanks', 'yr', 'usa', 'advance', 'hv', 'net', 'news', 'post', 'ua', 'phone']"
+6,sci.electronics,"['amp', 'circuit', 'voltage', 'capacitor', 'amplifier', 'transistor', 'signal', 'receiver', 'ohm', 'transmitter', 'frequency', 'radio', 'antenna', 'shack', 'transformer', 'volt', 'tube', 'audio', 'stereo', 'khz', 'metal', 'resistor', 'watt', 'pulse', 'grounding', 'meter', 'electronics', 'light', 'detector', 'analog', 'filter', 'connector', 'satellite', 'orbit', 'relay', 'conductor', 'noise', 'dtm', 'edinttl', 'wiring', 'gfcioorttvvc', 'radar', 'lamp', 'diameter', 'orbiting', 'switch', 'sensor']"
+7,comp.sys.ibm.pc.hardware,"['ide', 'controller', 'vlb', 'scsi', 'motherboard', 'bus', 'drive', 'eisa', 'isa', 'vga', 'vram', 'max', 'tores', 'di', 'card', 'dma', 'vesa', 'floppy', 'mhz', 'seagate', 'dram', 'meg', 'mf', 'mhdd', 'adapter', 'bios', 'chipset', 'pen', 'evati', 'simm', 'slot', 'ram', 'mb', 'jumpers', 'simms', 'orchid', 'board', 'adaptec', 'nubus', 'dx', 'monitor', 'ultra', 'vga', 'cache', 'hard', 'apple', 'benchmark', 'hd', 'trident', 'toshiba', 'brand']"
+8,rec.sport.baseball,"['pitching', 'goaltender', 'season', 'defenseman', 'pitcher', 'innings', 'and', 'berg', 'obp', 'playoff', 'rbi', 'scored', 'goalie', 'player', 'team', 'batter', 'batting', 'bullpen', 'nhl', 'whaler', 'alomar', 'shutout', 'rookie', 'recchi', 'gretzky', 'baerga', 'fielder', 'soderstrom', 'mattingly', 'blackhawks', 'hitter', 'game', 'dodger', 'puck', 'orioles', 'nichols', 'hockey', 'sox', 'tampa', 'winfield', 'potvin', 'talent', 'sherri', 'clemens', 'sanderson', 'score', 'yzerman', 'career', 'pitched', 'gilmour', 'winning']"
+9,alt.atheism,"['atheist', 'morality', 'theist', 'livesey', 'dwyer', 'atheism', 'bob', 'be', 'mozumder', 'beauchaine', 'solntze', 'morals', 'schneider', 'kmr', 'bilw', 'pdo', 'kc', 'forum', 'benedikt', 'jaeger', 'allan', 'agnostic', 'cook', 'amung', 'amotto', 'islam', 'theism', 'religion', 'keith', 'rosenau', 'evolution', 'mathew', 'rushdie', 'conner', 'objective', 'darice', 'rus', 'news', 'gregg', 'khomeini', 'punisher', 'sandvik', 'objectively', 'halat', 'exist', 'specie', 'immoral', 'heal', 'taq', 'quran', 'mantis', 'subjective', 'believer', 'belief', 'islam']"
+10,misc.forsale,"['membership', 'conference', 'campus', 'siggraph', 'registration', 'hotel', 'tour', 'proceeding', 'information', 'acm', 'servicemail', 'cryptology', 'dinner', 'june', 'students', 'suite', 'electronic', 'participant', 'attend', 'july', 'thursday', 'address', 'avenue', 'interested', 'space', 'project', 'ticket', 'publication', 'tutorial', 'bethesda', 'monday', 'sponsor', 'hill', 'payment', 'offer', 'airport', 'director', 'meeting', 'bulletin', 'weekend', 'participation', 'letter', 'association', 'county', 'fee', 'email', 'newsletter', 'motorcycle', 'schedule']"
+11,talk.politics.guns,"['fbi', 'atf', 'davidian', 'koresh', 'compound', 'batf', 'waco', 'bdf', 'fire', 'ranch', 'survivor', 'dividian', 'raid', 'grenade', 'tear', 'warrant', 'cnn', 'reno', 'tank', 'armored', 'cult', 'burn', 'agent', 'suicide', 'knock', 'tavares', 'follower', 'jmd', 'stove', 'investigation', 'cdt', 'paranoid', 'janet', 'fed', 'burned', 'inside', 'knocking', 'branch', 'arras', 'assault', 'burning', 'gas', 'started', 'hostage', 'roby', 'building', 'stratus', 'flee', 'happened', 'davidian']"
+12,rec.motorcycles,"['riding', 'e', 'green', 'motorcycle', 'dod', 'countersteering', 'biker', 'bikers', 'bikes', 'squid', 'ride', 'helmet', 'cousineau', 'drinking', 'cookson', 'rider', 'infant', 'en', 'pet', 'karr', 'pette', 'far', 'jacket', 'mjs', 'blaine', 'puck', 'newbie', 'bgardner', 'pillion', 'playoffs', 'kate', 'coach', 'lean', 'levine', 'balcony', 'drunk', 'boom', 'hockey', 'mamma', 'infield', 'jody', 'harley', 'keeper', 'sorenson', 'sabre', 'nhl', 'azerbaijan', 'iran', 'ckspeedy', 'cruiser', 'wheelie', 'slyuda', 'ama']"
+13,comp.graphics,"['graphical', 'programming', 'borland', 'gui', 'application', 'motif', 'framework', 'toolkit', 'api', 'builder', 'window', 'interactive', 'interface', 'package', 'library', 'polygon', 'processing', 'tool', 'programmer', 'oriented', 'graphic', 'toolkit', 'microsoft', 'openlook', 'functionality', 'turbo', 'graph', 'modeling', 'routine', 'compiler', 'widget', 'intrinsics', 'drawing', 'osf', 'architecture', 'platform', 'pc', 'networking', 'apps', 'operating', 'fortran', 'looking', 'vertex', 'spline', 'phigs', 'manual', 'unix', 'feature', 'simulation', 'workstation']"
+14,sci.crypt,"['clipper', 'escrow', 'encryption', 'scheme', 'escrowed', 'nsa', 'chip', 'crypto', 'secure', 'key', 'algorithm', 'encrypted', 'sternlight', 'hellman', 'strnlght', 'wiretap', 'classified', 'decrypt', 'strnlght', 'c', 'excepted', 'p', 'metzger', 'denning', 'secret', 'encrypt', 'plaintext', 'metzger', 'enforcement', 'd', 'sidorothy', 'f', 'ed', 'omission', 'tapped', 'laissez', 'decryption', 'tap', 'device', 'security', 'ensure', 'ciphertext', 'toal', 'serial', 'qualcomm', 'cryptography', 'cryptosystem', 'approval', 'trust', 'agency', 'spook', 'communication', 'gtoal']"
+15,sci.space,"['orbit', 'prb', 'shuttle', 'spacecraft', 'mission', 'satellite', 'nsmca', 'solar', 'henry', 'launch', 'payload', 'landing', 'flyby', 'zoology', 'orbital', 'orbiter', 'manned', 'ut', 'zoos', 'st', 'galileo', 'lunar', 'nasa', 'pluto', 'space', 'servicing', 'digex', 'moon', 'mccall', 'propulsion', 'astronaut', 'orbiting', 'flight', 'spencer', 'baalke', 'jsc', 'comet', 'trajectory', 'venus', 'funding', 'ssft', 'titan', 'telescope', 'aircraft', 'earth', 'asteroid', 'kipling', 'jbh', 'design', 'shafer', 'magellan']"
+16,rec.autos,"['toyota', 'brake', 'sedan', 'car', 'civic', 'torque', 'ford', 'shifter', 'wagon', 'engine', 'chevy', 'mustang', 'nissan', 'cruiser', 'rear', 'tire', 'wheel', 'integra', 'jeep', 'liter', 'honda', 'taurus', 'suspension', 'gear', 'dealer', 'mazda', 'clutch', 'sho', 'accord', 'steering', 'braking', 'rotor', 'opel', 'eliot', 'vehicle', 'motorcycle', 'motor', 'shifting', 'camaro', 'convertible', 'dodge', 'bike', 'valve', 'porsche', 'nhl', 'mpg', 'seat', 'saturn', 'mile', 'highway']"
+17,rec.motorcycles,"['temperature', 'heat', 'oil', 'drain', 'cooling', 'fuel', 'bike', 'battery', 'thermal', 'water', 'dry', 'liquid', 'gas', 'spray', 'behan', 'na', 'steam', 'exhaust', 'pump', 'cleaning', 'discharge', 'solvent', 'wood', 'bolt', 'dir', 'toxygencylinder', 'cold', 'valve', 'atmosphere', 'diesel', 'bottle', 'wax', 'surface', 'motorcycle', 'warm', 'removing', 'metal', 'cement', 'tower', 'concrete', 'tire', 'emission', 'cool', 'hot', 'tear', 'diameter', 'electricity', 'boom', 'air', 'vacuum']"
+18,talk.politics.mideast,"['israeli', 'israel', 'arab', 'palestinian', 'livni', 'gaza', 'palestine', 'zionist', 'and', 'it', 'clock', 'beyer', 'jake', 'occupied', 'shostack', 'hamas', 'kaufman', 'davidsson', 'jew', 'terrorism', 'jerusalem', 'gazans', 'lebanese', 'cprin', 'hern', 'leman', 'ahezbollah', 'cwr', 'ushai', 'hela', 'propaganda', 'oac', 'lebanon', 'reserve', 'redundancy', 'amoss', 'syrians', 'syria', 'ghetto', 'guday', 'jewish', 'irgun', 'peace', 'jordan', 'eliat', 'territory', 'plo', 'iraq', 'occupation', 'orion']"
+19,sci.med,"['disease', 'patient', 'doctor', 'physician', 'diagnosis', 'treatment', 'infection', 'vaginal', 'candida', 'vitamin', 'therapy', 'sinus', 'diagnosed', 'medication', 'chronic', 'chastity', 'syndrome', 'symptoms', 'yeast', 'pregnancy', 'tissue', 'clinical', 'medical', 'diet', 'systemic', 'rind', 'intellect', 'shameful', 'bacteria', 'disorder', 'nerve', 'antibiotic', 'lyme', 'gordon', 'surgery', 'medicine', 'illness', 'liver', 'cure', 'pain', 'quack', 'banschbach', 'dietary', 'kidney', 'migraine', 'dose', 'placebo']"

data/_20news_df_output_topic_word_CTM.csv

@@ -0,0 +1,41 @@
+run_id,method,method_specific_params,dataset,num_given_topics,reduced,topic_num,topic_size,topic_words,word_scores,num_detected_topics,num_final_topics,duration_secs,diversity_unique,diversity_inv_rbo,coherence_npmi,coherence_v,rand_index
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,0,732,"['health', 'patient', 'medical', 'space', 'disease', 'study', 'year', 'treatment', 'drug', 'april']","[0.12383451 0.11521751 0.11353351 0.1077095  0.09458103 0.092962
+ 0.09117454 0.08762824 0.08683101 0.08652814]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,1,756,"['notice', 'passed', 'suggested', 'higher', 'dark', 'background', 'larger', 'choice', 'requirement', 'discus']","[0.10493658 0.10426784 0.10232636 0.10052309 0.09887514 0.09880958
+ 0.0980336  0.09770604 0.09764653 0.09687528]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,2,518,"['pub', 'ftp', 'edu', 'format', 'archive', 'image', 'graphic', 'version', 'faq', 'site']","[0.11425608 0.11422319 0.11114949 0.1088886  0.10393708 0.09187336
+ 0.09019504 0.08906046 0.08828697 0.08812961]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,3,1323,"['atf', 'fire', 'waco', 'fbi', 'disclaimer', 'koresh', 'gas', 'survivor', 'reserve', 'bank']","[0.11390629 0.10463645 0.10274681 0.10265718 0.10119981 0.10058824
+ 0.09597317 0.0939759  0.0926476  0.09166859]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,4,478,"['people', 'right', 'article', 'atheism', 'homosexual', 'would', 'israel', 'writes', 'one', 'argument']","[0.12244946 0.10862308 0.10516351 0.10412805 0.10212132 0.10055386
+ 0.095933   0.09209377 0.08563491 0.08329905]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,5,704,"['trouble', 'suggested', 'notice', 'avoid', 'count', 'choice', 'higher', 'consideration', 'changed', 'passed']","[0.10687547 0.1035945  0.10281763 0.10066567 0.09871156 0.09862704
+ 0.09789448 0.09716429 0.09714134 0.09650805]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,6,1061,"['car', 'engine', 'bike', 'dod', 'ride', 'mile', 'auto', 'oil', 'ford', 'motorcycle']","[0.12913983 0.11862411 0.11026718 0.09704107 0.09644363 0.09473452
+ 0.0923589  0.09197619 0.08799469 0.08141985]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,7,518,"['soviet', 'turkish', 'armenia', 'turk', 'armenian', 'genocide', 'muslim', 'soldier', 'people', 'russian']","[0.10896654 0.10893553 0.10683964 0.10593498 0.10491596 0.10097778
+ 0.10019729 0.09013389 0.08842223 0.08467618]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,8,564,"['jesus', 'god', 'church', 'one', 'bible', 'christ', 'scripture', 'spirit', 'passage', 'sin']","[0.11491191 0.11250298 0.11043111 0.10765673 0.1024358  0.09674171
+ 0.09472436 0.08755608 0.08664075 0.0863985 ]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,9,396,"['max', 'mi', 'md', 'window', 'pl', 'tm', 'ex', 'id', 'ah', 'mb']","[0.13491088 0.10957684 0.10768988 0.1076818  0.10544891 0.09252201
+ 0.08989577 0.08594737 0.08437467 0.08195181]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,10,708,"['objective', 'morality', 'moral', 'god', 'christianity', 'exist', 'faith', 'writes', 'christian', 'atheist']","[0.109519   0.10796002 0.10678478 0.1035361  0.10269511 0.09694914
+ 0.09588029 0.0944791  0.0914978  0.09069863]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,11,876,"['window', 'application', 'manager', 'font', 'help', 'thanks', 'screen', 'mouse', 'motif', 'graphic']","[0.13398996 0.1091726  0.10379196 0.10361101 0.10081472 0.09725458
+ 0.0934235  0.08959287 0.08454128 0.08380754]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,12,1038,"['card', 'board', 'monitor', 'video', 'thanks', 'port', 'offer', 'driver', 'modem', 'drive']","[0.11984834 0.1134081  0.10677309 0.09944587 0.0985932  0.0959444
+ 0.09349772 0.09153173 0.09102782 0.0899297 ]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,13,808,"['red', 'boston', 'leaf', 'fan', 'playoff', 'blue', 'lost', 'baseball', 'game', 'ranger']","[0.10695428 0.10541338 0.10267578 0.10250854 0.09960378 0.09924651
+ 0.09874782 0.09704522 0.09397282 0.09383183]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,14,731,"['would', 'think', 'people', 'president', 'know', 'going', 'get', 'time', 'fbi', 'right']","[0.13352683 0.1260272  0.11690333 0.10108264 0.10049071 0.08579428
+ 0.08460232 0.08453774 0.08370963 0.08332541]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,15,713,"['scsi', 'drive', 'ide', 'bus', 'disk', 'controller', 'mac', 'problem', 'card', 'mb']","[0.12090454 0.11668422 0.11019469 0.10720176 0.09680493 0.09506889
+ 0.09220924 0.08808973 0.08799659 0.08484541]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,16,811,"['chip', 'encryption', 'clipper', 'escrow', 'wiretap', 'crypto', 'key', 'secret', 'secure', 'nsa']","[0.11366736 0.10840231 0.10831383 0.09918499 0.09748073 0.09735812
+ 0.09556631 0.09536911 0.09293538 0.09172186]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,17,835,"['ac', 'sale', 'shipping', 'email', 'looking', 'distribution', 'asking', 'usa', 'express', 'nntp']","[0.10743178 0.10743141 0.10255697 0.10167028 0.09907106 0.09891009
+ 0.09625679 0.09599011 0.09570176 0.09497967]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,18,800,"['nntp', 'posting', 'host', 'distribution', 'usa', 'sale', 'offer', 'interested', 'ca', 'ohio']","[0.13477376 0.13057682 0.12034003 0.10569087 0.10016396 0.08343355
+ 0.08232912 0.08194834 0.08051746 0.08022609]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716
+1687106817,ctm,"{'num_epochs': 100, 'lr': 0.002, 'batch_size': 64}",20news,20,False,19,706,"['year', 'game', 'player', 'team', 'appears', 'season', 'hockey', 'league', 'play', 'st']","[0.12629244 0.11492042 0.1056929  0.10263036 0.09683751 0.09508488
+ 0.0916804  0.08949064 0.08876076 0.08860979]",20,20,1869.52,0.87,0.9912969946869549,0.11664103691784058,0.6771646204844821,0.9191184609366716

data/_20news_df_output_topic_word_LDA.csv

@@ -0,0 +1,41 @@
+run_id,method,method_specific_params,dataset,num_given_topics,reduced,topic_num,topic_size,topic_words,word_scores,num_detected_topics,num_final_topics,duration_secs,diversity_unique,diversity_inv_rbo,coherence_npmi,coherence_v,rand_index
+1687099886,lda,{'alpha': 0.1},20news,20,False,0,1983,"['people', 'would', 'think', 'writes', 'one', 'article', 'say', 'like', 'even', 'right']","[0.15944211 0.15224469 0.12663063 0.09782166 0.08654518 0.08315944
+ 0.08102202 0.07570259 0.06934862 0.06808303]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,1,1392,"['game', 'line', 'subject', 'organization', 'hockey', 'pittsburgh', 'jason', 'sale', 'bike', 'one']","[0.15864137 0.15104766 0.1412904  0.14096186 0.09204587 0.06773349
+ 0.06546046 0.06349892 0.06315827 0.05616174]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,2,1088,"['key', 'file', 'line', 'subject', 'organization', 'user', 'program', 'command', 'copy', 'system']","[0.24934617 0.14403053 0.09751268 0.07934412 0.07487413 0.07465485
+ 0.07421384 0.07272138 0.06740832 0.06589408]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,3,74,"['power', 'ray', 'supply', 'second', 'period', 'speed', 'physical', 'led', 'detroit', 'drive']","[0.36320662 0.11131906 0.0865567  0.07299744 0.07110922 0.06680124
+ 0.0601517  0.05910192 0.05901084 0.0497453 ]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,4,1463,"['chip', 'card', 'line', 'bus', 'driver', 'board', 'system', 'subject', 'bi', 'port']","[0.25674582 0.14665987 0.09656386 0.08028611 0.0772783  0.07018365
+ 0.07017458 0.0688495  0.06784467 0.06541362]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,5,139,"['mr', 'bd', 'line', 'organization', 'subject', 'la', 'georgia', 'jim', 'tv', 'bb']","[0.40496555 0.08192329 0.07686187 0.07221673 0.07185741 0.06734095
+ 0.06571998 0.06564764 0.04696385 0.0465027 ]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,6,633,"['god', 'one', 'jesus', 'christian', 'people', 'child', 'said', 'say', 'men', 'day']","[0.20740458 0.13620628 0.12195267 0.09815736 0.09672838 0.09088862
+ 0.07117718 0.06802055 0.05513892 0.05432544]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,7,1454,"['arab', 'would', 'right', 'clinton', 'get', 'police', 'one', 'know', 'war', 'russian']","[0.12601893 0.12368312 0.10284469 0.10216503 0.09605458 0.0910842
+ 0.09088893 0.0896497  0.08962572 0.08798514]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,8,969,"['system', 'year', 'time', 'problem', 'would', 'water', 'two', 'one', 'season', 'get']","[0.1390074  0.13774833 0.12779438 0.09163507 0.08726825 0.0860028
+ 0.08587282 0.08329464 0.08109743 0.08027877]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,9,1941,"['organization', 'line', 'subject', 'university', 'posting', 'host', 'nntp', 'edu', 'article', 'writes']","[0.13164079 0.12725668 0.12707195 0.11136677 0.10630848 0.09919478
+ 0.09862357 0.07071686 0.06533524 0.06248491]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,10,789,"['one', 'fbi', 'may', 'people', 'use', 'many', 'christian', 'question', 'also', 'evidence']","[0.17698498 0.12187716 0.10865493 0.09114419 0.08722291 0.0852498
+ 0.08284143 0.08273355 0.08256708 0.08072395]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,11,710,"['space', 'program', 'mission', 'system', 'page', 'file', 'available', 'package', 'information', 'also']","[0.1585192  0.14749347 0.09407386 0.08963598 0.08897515 0.08795281
+ 0.08662158 0.08649572 0.08510548 0.07512669]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,12,463,"['group', 'weapon', 'would', 'state', 'american', 'law', 'new', 'article', 'organization', 'day']","[0.11562134 0.11349647 0.10780852 0.10352351 0.1024464  0.09807958
+ 0.0907825  0.0898603  0.08921809 0.08916336]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,13,97,"['muslim', 'max', 'tm', 'pl', 'religion', 'islam', 'tin', 'newsreader', 'ex', 'version']","[0.20428702 0.1473811  0.09972491 0.09721643 0.09494188 0.09063093
+ 0.07441587 0.07242449 0.06325752 0.05571985]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,14,2438,"['line', 'subject', 'organization', 'posting', 'host', 'nntp', 'writes', 'article', 'problem', 'one']","[0.16525298 0.14868902 0.13808452 0.0916653  0.08841628 0.08717743
+ 0.08092585 0.07759399 0.06161902 0.06057569]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,15,470,"['government', 'gas', 'would', 'warrant', 'right', 'sex', 'line', 'encryption', 'subject', 'tank']","[0.19382758 0.13207996 0.11948839 0.10724095 0.08666767 0.08636794
+ 0.07251114 0.07062805 0.06617918 0.06500917]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,16,103,"['st', 'frank', 'man', 'ed', 'armed', 'survivor', 'new', 'line', 'subject', 'spirit']","[0.12606965 0.11788099 0.10643179 0.10502937 0.09843564 0.09841796
+ 0.09526637 0.09022573 0.08191948 0.08032307]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,17,788,"['subject', 'line', 'organization', 'god', 'writes', 'would', 'greek', 'article', 'jew', 'know']","[0.11895489 0.11156828 0.10866257 0.10448369 0.10438665 0.102501
+ 0.09522998 0.09161492 0.09004647 0.07255147]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,18,1158,"['writes', 'article', 'apr', 'line', 'brian', 'subject', 'organization', 'israel', 'insurance', 'good']","[0.18839596 0.17242719 0.09725275 0.08833881 0.08613019 0.08504379
+ 0.08398097 0.07830536 0.06050047 0.05962449]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256
+1687099886,lda,{'alpha': 0.1},20news,20,False,19,694,"['line', 'organization', 'subject', 'university', 'host', 'posting', 'nntp', 'western', 'usa', 'ohio']","[0.11497776 0.11235808 0.1098053  0.10738717 0.09731661 0.0971822
+ 0.09494393 0.09386095 0.08933801 0.08282992]",20,20,199.09,0.635,0.9018807954953008,0.06993716674819705,0.5295167193987539,0.8930608444752256

data/_20news_df_output_topic_word_NMF.csv

@@ -0,0 +1,41 @@
+run_id,method,method_specific_params,dataset,num_given_topics,reduced,topic_num,topic_size,topic_words,word_scores,num_detected_topics,num_final_topics,duration_secs,diversity_unique,diversity_inv_rbo,coherence_npmi,coherence_v,rand_index
+1687106317,nmf,{},20news,20,False,0,361,"['god', 'line', 'output', 'lord', 'christ', 'would', 'book', 'problem', 'subject', 'organization']","[0.34979106 0.12350973 0.0947608  0.09453389 0.07471375 0.05836609
+ 0.05477346 0.05082214 0.05022724 0.04850186]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,1,1066,"['drive', 'system', 'disk', 'mac', 'hard', 'problem', 'get', 'scsi', 'also', 'card']","[0.19116262 0.15926939 0.12734865 0.11779287 0.08843095 0.07085378
+ 0.06267696 0.06198804 0.06154982 0.0589269 ]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,2,44,"['graphic', 'file', 'pub', 'mail', 'ray', 'send', 'edu', 'object', 'archive', 'output']","[0.18261122 0.17998113 0.1156435  0.0977497  0.09352912 0.08524382
+ 0.0849599  0.05835556 0.0533657  0.04856034]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,3,34,"['max', 'pl', 'tm', 'mb', 'mr', 'mi', 'ex', 'ah', 'au', 'de']","[0.81594648 0.06553909 0.04312668 0.02029965 0.01533819 0.01430676
+ 0.01005241 0.006095   0.00528083 0.0040149 ]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,4,1270,"['one', 'use', 'get', 'two', 'see', 'also', 'new', 'time', 'first', 'year']","[0.23971018 0.09956428 0.09932129 0.09751522 0.08508889 0.08494885
+ 0.07695754 0.07451225 0.07415631 0.06822519]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,5,53,"['image', 'gif', 'color', 'format', 'quality', 'software', 'pixel', 'free', 'tool', 'version']","[0.45527478 0.1064173  0.09178239 0.08095739 0.05727959 0.04782921
+ 0.04337543 0.04194787 0.03787981 0.03725623]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,6,49,"['available', 'ftp', 'edu', 'pub', 'version', 'format', 'graphic', 'package', 'source', 'contact']","[0.16663209 0.14746206 0.14448388 0.10769796 0.10278298 0.08357541
+ 0.0707831  0.06603169 0.05688584 0.053665  ]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,7,62,"['system', 'data', 'drive', 'disk', 'support', 'feature', 'software', 'space', 'user', 'rom']","[0.20376969 0.1854125  0.11060066 0.09022935 0.08683401 0.08307478
+ 0.0710087  0.05707783 0.05616885 0.05582363]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,8,134,"['data', 'image', 'available', 'also', 'information', 'sun', 'based', 'set', 'tool', 'motif']","[0.17411892 0.16602923 0.09961587 0.09704964 0.08925781 0.08008402
+ 0.07975093 0.07610741 0.07116763 0.06681855]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,9,4899,"['would', 'know', 'writes', 'article', 'think', 'line', 'organization', 'subject', 'year', 'like']","[0.14483345 0.11344227 0.11183915 0.11130367 0.10084824 0.09255977
+ 0.0924911  0.08888184 0.07933589 0.06446461]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,10,303,"['state', 'law', 'use', 'information', 'question', 'new', 'american', 'must', 'example', 'may']","[0.13702646 0.11159397 0.11068197 0.10648077 0.1030514  0.1015426
+ 0.08623879 0.08187689 0.08137951 0.08012766]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,11,209,"['jesus', 'said', 'people', 'say', 'know', 'one', 'armenian', 'day', 'lord', 'come']","[0.15556769 0.15193523 0.13980515 0.12600016 0.09142169 0.07601694
+ 0.07501137 0.06542825 0.06164289 0.05717063]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,12,128,"['file', 'image', 'program', 'gif', 'format', 'gun', 'color', 'output', 'section', 'may']","[0.40080525 0.11953442 0.10542488 0.0751564  0.0649226  0.05394245
+ 0.05294286 0.04787489 0.04281177 0.03658447]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,13,7652,"['line', 'organization', 'subject', 'writes', 'article', 'host', 'nntp', 'people', 'world', 'university']","[0.15852053 0.14480727 0.14317839 0.11433758 0.10727352 0.0804632
+ 0.07618727 0.06295255 0.0575845  0.0546952 ]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,14,90,"['god', 'atheist', 'atheism', 'religion', 'religious', 'christian', 'belief', 'many', 'believe', 'one']","[0.22380489 0.18513454 0.09868232 0.09665265 0.07770896 0.07635449
+ 0.07468084 0.06507333 0.06193238 0.03997562]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,15,219,"['mail', 'computer', 'internet', 'server', 'anonymous', 'posting', 'system', 'user', 'privacy', 'information']","[0.12141562 0.10778277 0.10736879 0.10597809 0.10154666 0.09926864
+ 0.09909393 0.09225525 0.08398684 0.0813034 ]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,16,37,"['pl', 'md', 'sc', 'ah', 'id', 'wa', 'mr', 'st', 'gif', 'tm']","[0.17065527 0.13395293 0.10855263 0.10596626 0.09627617 0.09583026
+ 0.09455009 0.07227479 0.06647285 0.05546874]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,17,749,"['do', 'window', 'file', 'microsoft', 'program', 'mouse', 'output', 'font', 'version', 'server']","[0.35849979 0.21097385 0.07707617 0.06976072 0.05095114 0.04960919
+ 0.04793472 0.0451268  0.04512359 0.04494403]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,18,319,"['bit', 'use', 'color', 'window', 'driver', 'mac', 'program', 'version', 'scsi', 'hardware']","[0.2273714  0.12952355 0.10517634 0.09524074 0.08628512 0.0836056
+ 0.08155865 0.06488489 0.06451468 0.06183903]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955
+1687106317,nmf,{},20news,20,False,19,1168,"['people', 'would', 'one', 'think', 'make', 'president', 'know', 'mr', 'well', 'even']","[0.17643617 0.14980483 0.14105327 0.10093348 0.07604843 0.07378741
+ 0.07171568 0.07168691 0.06959962 0.06893418]",20,20,367.93,0.645,0.9608968291743609,0.10370885185486564,0.6470614670550731,0.7350220371300955

data/_20news_df_output_topic_word_Top2Vec.csv

@@ -0,0 +1,305 @@
+run_id,method,method_specific_params,dataset,num_given_topics,reduced,topic_num,topic_size,topic_words,word_scores,num_detected_topics,num_final_topics,duration_secs
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,0,1616,"['bible' 'god' 'jesus' 'religion' 'scripture' 'christianity' 'christ'
+ 'atheist' 'prophet' 'christian' 'religious' 'church' 'muslim' 'theist'
+ 'qur' 'verse' 'doctrine' 'gospel' 'belief' 'holy' 'testament' 'psalm'
+ 'islam' 'apostle' 'faith' 'believer' 'theology' 'clh' 'heresy' 'quran'
+ 'congregation' 'atheism' 'interpretation' 'disciple' 'revelation'
+ 'catholic' 'armenian' 'salvation' 'truth' 'corinthian' 'khomeini'
+ 'baptism' 'sin' 'persecution' 'teaching' 'turkish' 'passage' 'hebrew'
+ 'biblical' 'isaiah']","[0.44676337 0.44158506 0.4414148  0.4250672  0.42309386 0.41805178
+ 0.4160752  0.4154315  0.41115087 0.4075917  0.3984454  0.3958729
+ 0.3906172  0.39005995 0.38813427 0.38569444 0.38469318 0.37988603
+ 0.37768558 0.37669003 0.374072   0.37036234 0.36953464 0.36884975
+ 0.36864585 0.3683077  0.36524647 0.3640772  0.3627922  0.35627204
+ 0.35473567 0.3525921  0.35250074 0.350264   0.34985965 0.34982705
+ 0.34791228 0.34752375 0.34076905 0.34058702 0.3389619  0.33720076
+ 0.33691663 0.33592725 0.33553275 0.3345945  0.33261788 0.3306961
+ 0.3291487  0.3282006 ]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,1,1433,"['window' 'olwm' 'xterm' 'openwindows' 'xdefaults' 'pointer' 'menu'
+ 'intrinsics' 'client' 'xdm' 'widget' 'openwin' 'bitmap' 'colormap' 'xlib'
+ 'ncd' 'screen' 'file' 'server' 'icon' 'manager' 'display' 'application'
+ 'directory' 'button' 'config' 'default' 'ini' 'pixmap' 'openlook' 'font'
+ 'sunos' 'paste' 'exit' 'sparc' 'mwm' 'console' 'xaw' 'ctrl' 'twm' 'xpert'
+ 'ndet' 'running' 'program' 'args' 'mouse' 'fprintf' 'motif' 'contrib'
+ 'exe']","[0.4715806  0.40489066 0.38360178 0.38229018 0.38183886 0.36847085
+ 0.36512193 0.36083105 0.35867202 0.35434687 0.3492447  0.34910566
+ 0.3489738  0.3475267  0.34732035 0.34555644 0.3450095  0.34349802
+ 0.3393754  0.33892933 0.33685613 0.3360705  0.3314531  0.33126542
+ 0.32636884 0.32313222 0.31982037 0.31860113 0.31551248 0.3133896
+ 0.30953708 0.30911303 0.30873692 0.30854362 0.3078321  0.30708423
+ 0.30538025 0.3053298  0.303819   0.30295336 0.30166018 0.30153474
+ 0.30145884 0.3011434  0.29960972 0.29814076 0.2973088  0.29728878
+ 0.29679278 0.2967768 ]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,2,1352,"['apple' 'sale' 'shipping' 'powerbook' 'coprocessor' 'lciii' 'price'
+ 'simm' 'brand' 'offer' 'iisi' 'fpu' 'iici' 'centris' 'nubus' 'mac'
+ 'forsale' 'slot' 'vram' 'printer' 'simms' 'selling' 'quadra' 'bought'
+ 'sell' 'upgrade' 'monitor' 'adapter' 'cartridge' 'duo' 'external'
+ 'purchased' 'lc' 'plus' 'asking' 'buying' 'sony' 'portable' 'interested'
+ 'buyer' 'dpi' 'ethernet' 'obo' 'cod' 'ram' 'deskjet' 'laserjet' 'modem'
+ 'mhz' 'hanover']","[0.42084357 0.3996125  0.3828575  0.3738153  0.35114548 0.3508577
+ 0.35029182 0.34458438 0.34436062 0.34023166 0.3397068  0.33833215
+ 0.33543992 0.33508453 0.3297907  0.3284306  0.3256174  0.32163784
+ 0.31535777 0.313064   0.31085122 0.3099688  0.3077851  0.30697435
+ 0.30588296 0.30419356 0.3019396  0.2984153  0.29826868 0.29718032
+ 0.29222956 0.28986603 0.28650752 0.28592142 0.28544748 0.2840621
+ 0.28394428 0.28078222 0.2798127  0.27918035 0.27807266 0.27502447
+ 0.27429968 0.27302492 0.27251047 0.27248186 0.27171037 0.2713627
+ 0.27132747 0.27121824]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,3,1339,"['gun' 'firearm' 'criminal' 'handgun' 'crime' 'nra' 'constitutional'
+ 'democrat' 'homicide' 'politician' 'abiding' 'cramer' 'clayton' 'brady'
+ 'liberal' 'homosexual' 'amendment' 'rkba' 'federal' 'voter' 'clinton'
+ 'constitution' 'economic' 'social' 'shotgun' 'ban' 'government' 'tax'
+ 'optilink' 'veal' 'gay' 'liberty' 'abuse' 'citizen' 'atheist' 'legal'
+ 'self' 'violent' 'minority' 'petaluma' 'privacy' 'drug' 'majority'
+ 'cipriani' 'enforce' 'election' 'freedom' 'heterosexual' 'jail' 'health']","[0.38347796 0.3787889  0.3679612  0.36430764 0.3554895  0.3511525
+ 0.34857452 0.34014687 0.33959094 0.3372019  0.33454198 0.32582545
+ 0.31983513 0.3168776  0.31487548 0.31218153 0.31092322 0.3103757
+ 0.30537516 0.30387998 0.30337164 0.30098853 0.298684   0.2978992
+ 0.29771733 0.29765505 0.29524988 0.29269737 0.2911522  0.28939897
+ 0.28611898 0.28418207 0.27660564 0.2763301  0.27374923 0.272509
+ 0.2718676  0.27084577 0.26999676 0.26828033 0.26778233 0.26767984
+ 0.26732287 0.2665463  0.2658036  0.26460105 0.26452196 0.26405072
+ 0.26368138 0.26102233]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,4,1119,"['playoff' 'hockey' 'bruin' 'nhl' 'goalie' 'bure' 'goaltender' 'mogilny'
+ 'blackhawks' 'islander' 'lafontaine' 'potvin' 'canadiens' 'lemieux'
+ 'powerplay' 'quebec' 'gilmour' 'canuck' 'penguin' 'whaler' 'selanne'
+ 'defenseman' 'puck' 'shanahan' 'overtime' 'yzerman' 'dchhabra' 'fuhr'
+ 'habs' 'recchi' 'barrasso' 'gretzky' 'cup' 'stanley' 'domi' 'soderstrom'
+ 'adirondack' 'oiler' 'sabre' 'probert' 'chelios' 'messier' 'rauser'
+ 'flyer' 'isle' 'skate' 'edmonton' 'tournament' 'dineen' 'devil']","[0.46590942 0.44713598 0.4239912  0.42257857 0.4217516  0.4191884
+ 0.4092419  0.40255633 0.39616874 0.3945594  0.38332573 0.38262597
+ 0.3762384  0.37487462 0.3743045  0.37386978 0.373065   0.36891234
+ 0.36809236 0.36592788 0.36473086 0.36453372 0.3636976  0.359594
+ 0.35779458 0.3555419  0.35410357 0.35251305 0.3486529  0.34727
+ 0.3464234  0.34516758 0.34137625 0.34075826 0.33696085 0.33651152
+ 0.33625218 0.33311346 0.3329189  0.33219948 0.32794854 0.32602125
+ 0.32478017 0.3216294  0.32005927 0.3147339  0.31425625 0.31333056
+ 0.3040147  0.30185115]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,5,1073,"['championship' 'mail' 'hockey' 'email' 'sweden' 'nhl' 'canada' 'please'
+ 'hello' 'reply' 'internet' 'motorcycle' 'hi' 'staffan' 'space'
+ 'tournament' 'se' 'subject' 'appreciate' 'finland' 'po' 'sci' 'qw' 'sale'
+ 'playoff' 'thanks' 'university' 'appreciated' 'posting' 'carnegie' 'xj'
+ 'mailing' 'fax' 'send' 'honda' 'engineering' 'computer' 'news' 'cmu'
+ 'moa' 'computing' 'thanx' 'yr' 'usa' 'advance' 'hv' 'netnews' 'post' 'ua'
+ 'phone']","[0.3630246  0.34161925 0.3414568  0.32976812 0.3128215  0.30187768
+ 0.2970038  0.29541144 0.29449564 0.29026005 0.2864499  0.2802989
+ 0.28006414 0.27813578 0.27792534 0.27719298 0.2759723  0.27250564
+ 0.27171326 0.27121776 0.27089795 0.27072582 0.27053788 0.26927954
+ 0.26886922 0.26859212 0.26837417 0.2671209  0.26608652 0.2652242
+ 0.26476553 0.26268485 0.26216033 0.26212424 0.25979197 0.259427
+ 0.25906652 0.25888425 0.25841695 0.25806126 0.25669473 0.25627166
+ 0.25586653 0.2556815  0.25503826 0.25497687 0.25455207 0.2544282
+ 0.25436395 0.25297272]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,6,917,"['amp' 'circuit' 'voltage' 'capacitor' 'amplifier' 'transistor' 'signal'
+ 'receiver' 'ohm' 'transmitter' 'frequency' 'radio' 'antenna' 'shack'
+ 'transformer' 'volt' 'tube' 'audio' 'stereo' 'khz' 'metal' 'resistor'
+ 'watt' 'pulse' 'grounding' 'meter' 'electronics' 'light' 'detector'
+ 'analog' 'filter' 'connector' 'satellite' 'orbit' 'relay' 'conductor'
+ 'noise' 'dtmedin' 'ttl' 'wiring' 'gfci' 'oort' 'tv' 'vcr' 'radar' 'lamp'
+ 'diameter' 'orbiting' 'switch' 'sensor']","[0.47413015 0.4708779  0.45542216 0.3937438  0.39038676 0.3839948
+ 0.38005072 0.37083778 0.36485273 0.35683596 0.35484332 0.34855273
+ 0.34549275 0.34522355 0.3375527  0.329933   0.32977253 0.32121888
+ 0.31858146 0.31828302 0.31616575 0.31540495 0.3126575  0.311877
+ 0.3112969  0.31016406 0.3101191  0.30984265 0.3096066  0.30437598
+ 0.30111343 0.29882246 0.2985236  0.29597062 0.2935729  0.29238188
+ 0.29194543 0.291157   0.28724945 0.28360963 0.28211528 0.28207964
+ 0.28027534 0.27832478 0.2776957  0.27767122 0.27725393 0.2759151
+ 0.27582926 0.27270424]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,7,907,"['ide' 'controller' 'vlb' 'scsi' 'motherboard' 'bus' 'drive' 'eisa' 'isa'
+ 'svga' 'vram' 'maxtor' 'esdi' 'card' 'dma' 'vesa' 'floppy' 'mhz'
+ 'seagate' 'dram' 'meg' 'mfm' 'hdd' 'adapter' 'bios' 'chipset' 'penev'
+ 'ati' 'simm' 'slot' 'ram' 'mb' 'jumper' 'simms' 'orchid' 'board'
+ 'adaptec' 'nubus' 'dx' 'monitor' 'ultra' 'vga' 'cache' 'hard' 'apple'
+ 'benchmark' 'hd' 'trident' 'toshiba' 'brand']","[0.51592463 0.45202082 0.43783426 0.43552488 0.42594004 0.4070964
+ 0.3885573  0.38779846 0.38645172 0.3809911  0.3721417  0.369662
+ 0.3677196  0.36494362 0.35803476 0.3537441  0.3507664  0.3488544
+ 0.34600908 0.3442523  0.3434435  0.34212285 0.33911508 0.32981914
+ 0.32907662 0.32285517 0.3209666  0.3203686  0.3188119  0.31582078
+ 0.3149792  0.30925786 0.30752766 0.30566144 0.3021134  0.30166447
+ 0.2938785  0.29251978 0.29103965 0.28887713 0.2865978  0.2865807
+ 0.285491   0.28390944 0.28378698 0.2835799  0.28333062 0.28302824
+ 0.28207874 0.28105193]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,8,863,"['pitching' 'goaltender' 'season' 'defenseman' 'pitcher' 'inning'
+ 'sandberg' 'obp' 'playoff' 'rbi' 'scored' 'goalie' 'player' 'team'
+ 'batter' 'batting' 'bullpen' 'nhl' 'whaler' 'alomar' 'shutout' 'rookie'
+ 'recchi' 'gretzky' 'baerga' 'fielder' 'soderstrom' 'mattingly'
+ 'blackhawks' 'hitter' 'game' 'dodger' 'puck' 'oriole' 'snichols' 'hockey'
+ 'sox' 'tampa' 'winfield' 'potvin' 'talent' 'sherri' 'clemens' 'sanderson'
+ 'score' 'yzerman' 'career' 'pitched' 'gilmour' 'winning']","[0.38014483 0.3789016  0.37256125 0.36911368 0.353766   0.3475885
+ 0.3414901  0.33900553 0.33893228 0.33813792 0.33412263 0.33359426
+ 0.33340466 0.32941717 0.3285423  0.32582566 0.32435375 0.32421935
+ 0.3235423  0.32162356 0.3206997  0.31891322 0.3174274  0.31570834
+ 0.3127724  0.31258675 0.30754888 0.30717647 0.30560625 0.30555865
+ 0.30293164 0.30011946 0.29883778 0.295937   0.29524797 0.29420918
+ 0.2931141  0.29203683 0.2913671  0.29120994 0.29103744 0.2905165
+ 0.28822783 0.28763106 0.28509793 0.28462318 0.283857   0.28375292
+ 0.28373525 0.28345263]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,9,860,"['atheist' 'morality' 'theist' 'livesey' 'dwyer' 'atheism' 'bobbe'
+ 'mozumder' 'beauchaine' 'solntze' 'moral' 'schneider' 'kmr' 'bil' 'wpd'
+ 'okcforum' 'benedikt' 'jaeger' 'allan' 'agnostic' 'cookamunga' 'motto'
+ 'islamic' 'theism' 'religion' 'keith' 'rosenau' 'evolution' 'mathew'
+ 'rushdie' 'conner' 'objective' 'darice' 'rusnews' 'gregg' 'khomeini'
+ 'punisher' 'sandvik' 'objectively' 'halat' 'exist' 'specie' 'immoral'
+ 'healta' 'quran' 'mantis' 'subjective' 'believer' 'belief' 'islam']","[0.50602657 0.44531634 0.43936396 0.42137936 0.41620952 0.40997714
+ 0.4004252  0.39174497 0.39160943 0.38147688 0.37546414 0.36531267
+ 0.3594244  0.3445725  0.3362559  0.33301878 0.32759196 0.3252498
+ 0.31651446 0.3143277  0.31357464 0.30626386 0.3033719  0.30169833
+ 0.30109283 0.30084568 0.2945159  0.29261556 0.29168844 0.29025084
+ 0.28797036 0.28596056 0.28305757 0.28301924 0.28264028 0.28140482
+ 0.27835423 0.27604178 0.27072585 0.2643424  0.25929388 0.25921416
+ 0.256099   0.25507405 0.25278842 0.25175795 0.25021374 0.24655274
+ 0.24615248 0.24575195]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,10,832,"['membership' 'conference' 'campus' 'siggraph' 'registration' 'hotel'
+ 'tour' 'proceeding' 'information' 'acm' 'service' 'mail' 'cryptology'
+ 'dinner' 'june' 'student' 'suite' 'electronic' 'participant' 'attend'
+ 'july' 'thursday' 'address' 'avenue' 'interested' 'space' 'project'
+ 'ticket' 'publication' 'tutorial' 'bethesda' 'monday' 'sponsor' 'hill'
+ 'payment' 'offer' 'airport' 'director' 'meeting' 'bulletin' 'weekend'
+ 'participation' 'letter' 'association' 'county' 'fee' 'email'
+ 'newsletter' 'motorcycle' 'schedule']","[0.37641203 0.37549758 0.3680211  0.3671983  0.3637733  0.34958172
+ 0.3426261  0.3379334  0.32778293 0.32679507 0.3247376  0.3163039
+ 0.31118208 0.3098779  0.30920613 0.30706063 0.30275297 0.30152684
+ 0.30137172 0.30098063 0.29588354 0.2929973  0.29049584 0.29006344
+ 0.28908098 0.28858015 0.28830767 0.28723055 0.28255087 0.28237736
+ 0.2820445  0.28091612 0.27746138 0.2772538  0.27671865 0.2765438
+ 0.2757618  0.27530587 0.2751091  0.27469456 0.27454117 0.27440792
+ 0.2739563  0.27242443 0.2705129  0.26944393 0.26797917 0.26713628
+ 0.26711327 0.26683828]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,11,776,"['fbi' 'atf' 'davidians' 'koresh' 'compound' 'batf' 'waco' 'bd' 'fire'
+ 'ranch' 'survivor' 'dividian' 'raid' 'grenade' 'tear' 'warrant' 'cnn'
+ 'reno' 'tank' 'armored' 'cult' 'burn' 'agent' 'suicide' 'knock' 'tavares'
+ 'follower' 'jmd' 'stove' 'investigation' 'cdt' 'paranoid' 'janet' 'fed'
+ 'burned' 'inside' 'knocking' 'branch' 'arras' 'assault' 'burning' 'gas'
+ 'started' 'hostage' 'roby' 'building' 'stratus' 'flee' 'happened'
+ 'davidian']","[0.5663208  0.5527084  0.54346037 0.52827954 0.5163899  0.5084876
+ 0.49466527 0.48884875 0.4885131  0.45129156 0.44314212 0.42619407
+ 0.42141107 0.41937637 0.3949927  0.39384326 0.37510183 0.37389514
+ 0.37186143 0.3610953  0.35808873 0.3538611  0.34679633 0.34508017
+ 0.3363666  0.3325144  0.33024508 0.3277991  0.32340246 0.32110196
+ 0.32067192 0.3200016  0.31780922 0.3147901  0.31345642 0.31323874
+ 0.3103191  0.31015503 0.30978537 0.3096369  0.30926692 0.3066926
+ 0.30661058 0.29615265 0.2940686  0.29287642 0.29033172 0.2900957
+ 0.28810024 0.28578383]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,12,772,"['riding' 'egreen' 'motorcycle' 'dod' 'countersteering' 'biker' 'bikers'
+ 'bike' 'squid' 'ride' 'helmet' 'cousineau' 'drinking' 'cookson' 'rider'
+ 'infante' 'npet' 'karr' 'pettefar' 'jacket' 'mjs' 'blaine' 'puck'
+ 'newbie' 'bgardner' 'pillion' 'playoff' 'skate' 'coach' 'lean' 'levine'
+ 'balcony' 'drunk' 'boom' 'hockey' 'mamma' 'infield' 'jody' 'harley'
+ 'keeper' 'sorenson' 'sabre' 'nhl' 'azerbaijani' 'ranck' 'speedy'
+ 'cruiser' 'wheelies' 'lyuda' 'ama']","[0.41461077 0.39282525 0.37715077 0.36484554 0.35063148 0.33479384
+ 0.33462274 0.33298865 0.3319907  0.32893145 0.32492083 0.3105444
+ 0.28028214 0.27274084 0.27210125 0.26896492 0.26730326 0.26370856
+ 0.2634203  0.26052043 0.25942084 0.2590174  0.2586859  0.2586578
+ 0.2524207  0.2488463  0.24796811 0.24651901 0.24457517 0.23809463
+ 0.23794222 0.23766775 0.2366336  0.23643237 0.23621374 0.23604974
+ 0.23476706 0.23243055 0.23103555 0.23098774 0.22998813 0.22980058
+ 0.22714046 0.22572297 0.22559911 0.22516048 0.22514091 0.22425602
+ 0.22397438 0.22318973]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,13,748,"['graphical' 'programming' 'borland' 'gui' 'application' 'motif'
+ 'framework' 'toolkit' 'api' 'builder' 'window' 'interactive' 'interface'
+ 'package' 'library' 'polygon' 'processing' 'tool' 'programmer' 'oriented'
+ 'graphic' 'toolkits' 'microsoft' 'openlook' 'functionality' 'turbo'
+ 'graph' 'modeling' 'routine' 'compiler' 'widget' 'intrinsics' 'drawing'
+ 'osf' 'architecture' 'platform' 'pc' 'networking' 'apps' 'operating'
+ 'fortran' 'looking' 'vertex' 'spline' 'phigs' 'manual' 'unix' 'feature'
+ 'simulation' 'workstation']","[0.4384119  0.3882578  0.38631064 0.38347492 0.38143724 0.37813997
+ 0.36548048 0.35531527 0.35095713 0.3509377  0.34626365 0.3449847
+ 0.34453845 0.34367275 0.3410035  0.34039888 0.33888048 0.32572466
+ 0.3247982  0.32260007 0.31918436 0.31766117 0.31704426 0.31185216
+ 0.3096385  0.30828592 0.3052628  0.30463484 0.30449712 0.30253798
+ 0.29837552 0.29726636 0.29659134 0.29610744 0.2947264  0.29455125
+ 0.29407462 0.29384118 0.29348552 0.29250127 0.29200053 0.29100662
+ 0.29074687 0.29074043 0.2904779  0.2890798  0.28778    0.28479168
+ 0.28445467 0.28393763]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,14,747,"['clipper' 'escrow' 'encryption' 'scheme' 'escrowed' 'nsa' 'chip' 'crypto'
+ 'secure' 'key' 'algorithm' 'encrypted' 'sternlight' 'hellman' 'strnlght'
+ 'wiretap' 'classified' 'decrypt' 'strnlghtc' 'excepted' 'pmetzger'
+ 'denning' 'secret' 'encrypt' 'plaintext' 'metzger' 'enforcement' 'dsi'
+ 'dorothy' 'fed' 'omission' 'tapped' 'laissez' 'decryption' 'tap' 'device'
+ 'security' 'ensure' 'ciphertext' 'toal' 'serial' 'qualcomm'
+ 'cryptography' 'cryptosystem' 'approval' 'trust' 'agency' 'spook'
+ 'communication' 'gtoal']","[0.53622144 0.51438415 0.47407508 0.45463344 0.4485225  0.44310796
+ 0.44174838 0.44148    0.44016623 0.43232006 0.42186934 0.41818953
+ 0.40332472 0.39804906 0.39571035 0.38707638 0.38706988 0.38338387
+ 0.3833515  0.3805896  0.3804127  0.3762514  0.37518197 0.36292812
+ 0.3523016  0.3512108  0.3474918  0.34463465 0.3440556  0.34328783
+ 0.3383907  0.3301744  0.3297775  0.32963568 0.32737336 0.3259146
+ 0.3229884  0.31992412 0.3190465  0.31714386 0.31693232 0.3151013
+ 0.31495202 0.31394005 0.3099162  0.30657524 0.3045889  0.30456156
+ 0.30431086 0.3039512 ]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,15,737,"['orbit' 'prb' 'shuttle' 'spacecraft' 'mission' 'satellite' 'nsmca'
+ 'solar' 'henry' 'launch' 'payload' 'landing' 'flyby' 'zoology' 'orbital'
+ 'orbiter' 'manned' 'utzoo' 'ssto' 'galileo' 'lunar' 'nasa' 'pluto'
+ 'space' 'servicing' 'digex' 'moon' 'mccall' 'propulsion' 'astronaut'
+ 'orbiting' 'flight' 'spencer' 'baalke' 'jsc' 'comet' 'trajectory' 'venus'
+ 'funding' 'ssf' 'titan' 'telescope' 'aircraft' 'earth' 'asteroid'
+ 'kipling' 'jbh' 'design' 'shafer' 'magellan']","[0.47373086 0.46202362 0.45533887 0.43171287 0.412343   0.410465
+ 0.40169445 0.4012512  0.39061272 0.38869444 0.38783133 0.3872778
+ 0.3864897  0.38422304 0.37999982 0.37800846 0.37716657 0.37500364
+ 0.3725879  0.3695118  0.36791682 0.3657704  0.36366093 0.36269274
+ 0.35963058 0.3475752  0.34491754 0.34488463 0.34403253 0.34377724
+ 0.3408779  0.33478466 0.333887   0.32768953 0.3273967  0.32607034
+ 0.32421684 0.3228647  0.3126804  0.31172872 0.3100717  0.3100507
+ 0.31001002 0.30487514 0.30258626 0.3010378  0.29808497 0.29804218
+ 0.29652447 0.2953205 ]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,16,697,"['toyota' 'brake' 'sedan' 'car' 'civic' 'torque' 'ford' 'shifter' 'wagon'
+ 'engine' 'chevy' 'mustang' 'nissan' 'cruiser' 'rear' 'tire' 'wheel'
+ 'integra' 'jeep' 'liter' 'honda' 'taurus' 'suspension' 'gear' 'dealer'
+ 'mazda' 'clutch' 'sho' 'accord' 'steering' 'braking' 'rotor' 'opel'
+ 'eliot' 'vehicle' 'motorcycle' 'motor' 'shifting' 'camaro' 'convertible'
+ 'dodge' 'bike' 'valve' 'porsche' 'nhl' 'mpg' 'seat' 'saturn' 'mile'
+ 'highway']","[0.39571    0.37745798 0.37729716 0.36061507 0.360043   0.35976624
+ 0.35714692 0.35585535 0.355524   0.35510963 0.35412773 0.34132427
+ 0.34061238 0.33668256 0.3362129  0.3349996  0.33462238 0.32848147
+ 0.32835317 0.32521552 0.32297438 0.31911826 0.31077892 0.3047754
+ 0.30159217 0.2923528  0.29225302 0.29082403 0.2903491  0.29028058
+ 0.28864217 0.2883463  0.2877421  0.28653866 0.28255364 0.28221753
+ 0.27619636 0.27617338 0.2761493  0.27520862 0.27492434 0.27293944
+ 0.27141443 0.26931706 0.2665119  0.26613706 0.26508605 0.26388812
+ 0.2630334  0.26206416]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,17,694,"['temperature' 'heat' 'oil' 'drain' 'cooling' 'fuel' 'bike' 'battery'
+ 'thermal' 'water' 'dry' 'liquid' 'gas' 'spray' 'behanna' 'steam'
+ 'exhaust' 'pump' 'cleaning' 'discharge' 'solvent' 'wood' 'bolt' 'dirt'
+ 'oxygen' 'cylinder' 'cold' 'valve' 'atmosphere' 'diesel' 'bottle' 'wax'
+ 'surface' 'motorcycle' 'warm' 'removing' 'metal' 'cement' 'tower'
+ 'concrete' 'tire' 'emission' 'cool' 'hot' 'tear' 'diameter' 'electricity'
+ 'boom' 'air' 'vacuum']","[0.38994113 0.37223655 0.3659422  0.36278605 0.35352123 0.35129756
+ 0.3472059  0.34584868 0.3258671  0.32109696 0.3128299  0.3064231
+ 0.3031057  0.30245066 0.30225492 0.29960772 0.29874486 0.29400587
+ 0.28933424 0.28888935 0.288783   0.28770658 0.28001165 0.27997652
+ 0.2772094  0.27563    0.27516425 0.27506196 0.27488017 0.2657459
+ 0.26499617 0.26479498 0.26456675 0.264168   0.26409522 0.26169625
+ 0.2612601  0.25858256 0.25794652 0.25648054 0.25529054 0.2537981
+ 0.2520281  0.2506379  0.25042093 0.24887553 0.2476764  0.24741241
+ 0.24695235 0.2457898 ]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,18,686,"['israeli' 'israel' 'arab' 'palestinian' 'livni' 'gaza' 'palestine'
+ 'zionist' 'andi' 'tclock' 'beyer' 'jake' 'occupied' 'shostack' 'hamas'
+ 'kaufman' 'davidsson' 'jew' 'terrorism' 'jerusalem' 'gazans' 'lebanese'
+ 'cpr' 'in' 'hernlem' 'ana' 'hezbollah' 'cwru' 'shai' 'hela' 'propaganda'
+ 'oac' 'lebanon' 'reserve' 'redundancy' 'amos' 'syrian' 'syria' 'ghetto'
+ 'guday' 'jewish' 'irgun' 'peace' 'jordan' 'elia' 'territory' 'plo' 'iraq'
+ 'occupation' 'orion']","[0.5798781  0.4864083  0.47888124 0.4376715  0.4304331  0.4260963
+ 0.42182434 0.41124582 0.40849674 0.4030689  0.40131482 0.3953199
+ 0.39427945 0.39251405 0.3896283  0.38426933 0.37792894 0.37311408
+ 0.37026602 0.3690432  0.36581022 0.36551306 0.36441153 0.36347967
+ 0.3634483  0.3600469  0.35887873 0.35557127 0.35184813 0.3517988
+ 0.34519568 0.34395516 0.3436267  0.34030044 0.33586282 0.33550203
+ 0.32902315 0.32690272 0.32504597 0.31950957 0.3143857  0.31242925
+ 0.30857286 0.30692795 0.30610973 0.30222043 0.30131567 0.29541656
+ 0.29520452 0.2933391 ]",236,20,1337.527
+1687099717,top2vec,"{'doc2vec_speed': 'learn', 'min_count': 50, 'embedding_model': 'doc2vec', 'umap_args': {'n_neighbors': 15, 'n_components': 5, 'metric': 'cosine', 'random_state': 42}, 'hdbscan_args': {'min_cluster_size': 15, 'metric': 'euclidean', 'cluster_selection_method': 'eom'}}",20news,20,True,19,678,"['disease' 'patient' 'doctor' 'physician' 'diagnosis' 'treatment'
+ 'infection' 'jxp' 'geb' 'vaginal' 'candida' 'vitamin' 'therapy' 'sinus'
+ 'diagnosed' 'medication' 'chronic' 'chastity' 'syndrome' 'symptom'
+ 'skepticism' 'yeast' 'pregnancy' 'tissue' 'clinical' 'medical' 'diet'
+ 'systemic' 'rind' 'intellect' 'shameful' 'bacteria' 'disorder' 'nerve'
+ 'antibiotic' 'lyme' 'gordon' 'surgery' 'medicine' 'illness' 'liver'
+ 'cure' 'pain' 'quack' 'banschbach' 'dietary' 'kidney' 'migraine' 'dose'
+ 'placebo']","[0.51703024 0.5059259  0.49075317 0.47384253 0.46913362 0.46782446
+ 0.45764387 0.4515015  0.44527012 0.43146837 0.42805362 0.4274508
+ 0.42565894 0.4239667  0.42124498 0.4210152  0.41872454 0.4175253
+ 0.4121551  0.41190648 0.4063744  0.40461332 0.4000011  0.39615753
+ 0.3931234  0.39151937 0.39004126 0.3890183  0.3871621  0.38580507
+ 0.38531238 0.38243055 0.38105106 0.38043314 0.37947708 0.37777084
+ 0.37690628 0.37274668 0.3680032  0.3603353  0.3598597  0.35893765
+ 0.35835528 0.35703662 0.34972584 0.3469156  0.34666422 0.3463875
+ 0.34193394 0.3419305 ]",236,20,1337.527

data/sample_text-old.csv

@@ -0,0 +1,385 @@
+id_category,category,data
+0,alt.atheism,"
+
+Ideologies also split, giving more to disagree upon, and may also lead
+to intolerance.  So do you also oppose all ideologies?
+
+I don't think your argument is an argument against religion at all, but
+just points out the weaknesses of human nature.
+
+
+I would like a reference if you have got one, for this is news to me.
+
+
+One must approach the Qur'an with intelligence.  Any thinking approach
+to the Qur'an cannot but interpret the above verse and others like it
+that women and men are spiritual equals.
+
+I think that the above verse does clearly imply that women have
+souls.  Does it make any sense for something without a soul to be
+forgiven?  Or to have a great reward (understood to be in the
+after-life)?  I think the usual answer would be no -- in which case, the
+part saying ""For them has God prepared forgiveness and a great reward""
+says they have souls.  
+
+(If it makes sense to say that things without souls can be forgiven, then 
+I have no idea _what_ a soul is.)
+
+As for your saying that the quote above may not be given a high priority
+in all interpretations, any thinking approach to the Qur'an has to give
+all verses of the Qur'an equal priority.  That is because, according to
+Muslim belief, the _whole_ Qur'an is the revelation of God -- in fact,
+denying the truth of any part of the Qur'an is sufficient to be
+considered a disbeliever in Islam.
+
+
+Look, any approach to the Qur'an must be done with intelligence and
+thought.  It is in this fashion that one can try to understand the
+Quran's message.  In a book of finite length, it cannot explicitly
+answer every question you want to put to it, but through its teachings
+it can guide you.  I think, however, that women are the spiritual equals
+of men is clearly and unambiguously implied in the above verse, and that
+since women can clearly be ""forgiven"" and ""rewarded"" they _must_ have
+souls (from the above verse).
+
+Let's try to understand what the Qur'an is trying to teach, rather than
+try to see how many ways it can be misinterpreted by ignoring this
+passage or that passage.  The misinterpretations of the Qur'an based on
+ignoring this verse or that verse are infinite, but the interpretations 
+fully consistent are more limited.  Let's try to discuss these
+interpretations consistent with the text rather than how people can
+ignore this bit or that bit, for that is just showing how people can try
+to twist Islam for their own ends -- something I do not deny -- but
+provides no reflection on the true teachings of Islam whatsoever."
+1,comp.graphics,"Does ANYONE out there in Net-land have any information on the Cobra 2.20 
+card?  The sticker on the end of the card reads
+        Model: Cobra 1-B-1
+        Bios:  Cobra v2.20
+
+I Havn't been able to find anything about it from anyone!  If you have 
+any information on how to get a hold of the company which produces the 
+card or know where any drivers are for it, PLEASE let me know!
+
+As far as I can tell, it's a CGA card that is taking up 2 of my 16-bit 
+ISA slots but when I enable the test patterns, it displays much more than 
+the usualy 4 CGA colors... At least 16 from what I can count.. Thanks!
+
+              .------------------------------------------.
+              : Internet: [email protected]          :
+              :           [email protected]  :
+              :           [email protected]    :
+              :           [email protected]             :
+              : UUCP    : apple.com!tsoft!bbs.mirage     :
+              `------------------------------------------'"
+2,comp.os.ms-windows.misc,"
+
+Two things that annoyed me about the PC Magazine review:
+
+1.  Their benchmarking technique is seriously flawed, as was clearly shown
+    by the Graphite and #9GXE's ""cheating"".  Can't they just admit that
+    their benchmark is to easy to optimize for and/or cheat on?  WinTach
+    is much harder to beat...
+
+2.  The big ""cheat"" that Hercules/IIT used was overlappipping BitBlit and
+    PolyLine optimization, and Hercules sent them a new driver which didn't
+    do this -- but produced almost identical scores.  Yet, the only thing
+    PC Magazine says is that scores are not ""legitimate"" -- couldn't they
+    at least make some comment about its real-world performance?
+
+I'm not so much going by WinBench for performance, but, rather, by Steve
+Gibson's results, which are more real-world based (like using Micrografx
+
+    ""Despite these documented cheats, I have to say that in real-world
+     applications the Hercules Graphite adapter actually draws faster than
+     any other display adapter in the industry.   [...]  Even though it's
+     just a modest ISA bus card, it outperformed every local bus adapter I
+     have, including the Stealth 24 VLB, the Fahrenheit 1280VA/VLB, the
+     ATI VLB Mach32 and even the Weitek P9000-based Diamond Viper VLB.""
+
+This kind of praise is enough for me to be interested in it, bogus WinBench
+or not!  :)
+
+
+I already returned the ATI GU+.  My dealer had sold eight of them, and 
+seven were returned to him.  I'm now (temporarily) back to running an
+original ATI GU, until I get my Graphite.  And, yes, the GU is faster in
+my 16 MB system than the GU+, especially in bitmap handling (that's where
+you use BitBlits).
+
+Hercules has a promotion available for VARs and software developers: you
+can buy one Graphite or Graphite VLB for 50% off list to try it out.  At
+just $199 for Graphite or $249 for the VLB version I decided it was worth
+trying (I'm supposed to get the VLB board within two weeks).  I'll post
+my impressions when I get it...
+"
+3,comp.sys.ibm.pc.hardware,"Hi.  I am trying to set up a Conner 3184 and a Quantum 80AT drive.  I have
+the conner set to the master, and the quantum set to the slave (doesn't work
+the other way around).  I am able to access both drives if I boot from a 
+floppy, but the drives will not boot themselves.  I am running MSDOS 6, and
+have the Conner partitioned as Primary Dos, and is formatted with system
+files.  I have tried all different types of setups, and even changed IDE
+controller cards.  If I boot from a floppy, everything works great (except
+the booting part :)).  The system doesn't report an error message or anything,
+just hangs there.  Does anyone have any suggestions, or has somebody else
+run into a similar problem?  I was thinking that I might have to update the bios
+on one of the drives (is this possible?).  Any suggestions/answers would be
+greatly appreciated.  Please reply to:"
+4,comp.sys.mac.hardware,"	In certain Apple 13"" RGB monitors there has been a problem with
+	the HIGH VOLTAGE CAPASITOR. Apple knows about this problem and is
+	replacing the cap at no cost if it falls into the bad batch that
+	they got from their supplier. Your local repair shop should know about
+	REPAIR EXTENSION 3L0218.
+"
+5,comp.windows.x,"
+Have you gotten an answer yet?  Using your variables, this is what I would do:
+	xterm -T ""$HOST - $LOGNAME"" -n ""$HOST""
+"
+6,misc.forsale,"
+
+COD is fine until the buyer opens the box to find they paid 150.00
+for a brick. Or if it the seller allows for a personal check to be used
+on a COD it's fine till a stop payment is made. There are few methods
+to protect both buyer and seller in any sort of transaction. Even with
+merchants and customers there are problems...stolen credit cards, 
+chargebacks, no return policies and getting the wrong item, etc.
+
+About the only protection available to to do business with someone you
+trust....someone who has been around for a while.
+
+Jeff
+
+
+________________________________________________________________________"
+7,rec.autos,"From article <[email protected]>, by [email protected] (Eric Lorenzo):
+
+--Let me put it like this.  The only similarity between the three models
+  is the ""300"", or 3-liter engine displacement.  Actually, the SC300 (the
+  coupe) and the GS300 (the funky-looking new sedan) share the same 3.0
+  liter inline-six, and the ES300 (popular small sedan) uses 3.0 V6 shared
+  with the Camry.  The SC300 is a luxury/sports coupe, the GS300 is the new
+  luxury sedan, and the ES300 is the base executive sedan.  All three look
+  completely different.
+
+--Aamir Qazi
+-- "
+8,rec.motorcycles,"Now, I am jumping into the middle of this thread so I may not know
+what y'all been talking about, but I have a few comments:
+
+
+There are a number of other factors that are very important, the three
+biggest being air velocity, air momentum and shock waves.
+Velocity stacks have been used for years and are now being used inside
+of stock airboxes on a number of bikes.  At a tuned engine rpm, the
+stacks can greatly increase the speed, and thus momentum of the air
+rushing in.
+Air momentum is critical in getting good air intake: the momentum of
+the air stack outside the combustion chamber will force its way inside
+long after the piston has begun its compressive up-stroke.
+Shock waves are used to induce air intake and to prevent fresh air from
+escaping out the exzhaust ports.  Shock waves are the product of expansion
+chambers or any other means of presenting a 'wall' (opening or closing)
+to the air in motion.  Beyond this I am lost in the mystery of how they
+design for shock waves."
+9,rec.sport.baseball,"
+Maybe it's just me, but the combination of those *young* faces peeking out
+from under oversized aqua helmets screams ""Little League"" in every fibre of
+my being...
+"
+10,rec.sport.hockey,"........
+
+It looks like the Edmonton Oilers just decided to take a European
+vacation this spring...
+
+Ranford, Tugnutt, Benning, Manson, Smith, Buchberger, and Corson
+are playing for Canada.
+
+Podein and Weight are playing for the US.
+
+Is Kravchuk playing for the Russians...I know he had nagging
+injuries late in the season.
+
+Podein is an interesting case...because he was eligible to
+play in Cape Breton in the AHL playoffs like Kovalev, Zubov,
+and Andersson...obviously Sather and Pocklington are not
+the total scrooges everyone makes them out to be...certainly
+in this case they've massively outclassed Paramount and the
+New York Rangers."
+11,sci.crypt,"Gee, I guess they should also have such a repository for house keys,
+car keys, safety deposit keys, ... :-(
+
+rdl"
+12,sci.electronics,"Doesn't Motorola AMCU have something on the BBS yet? (512-891-3733)
+"
+13,sci.med,"[reply to [email protected] (Keith Stewart)]
+ 
+ 
+It would help if you (and anyone else asking for medical information on
+some subject) could ask specific questions, as no one is likely to type
+in a textbook chapter covering all aspects of the subject.  If you are
+looking for a comprehensive review, ask your local hospital librarian.
+Most are happy to help with a request of this sort.
+ 
+Briefly, this is a condition in which patients who have significant
+residual weakness from childhood polio notice progression of the
+weakness as they get older.  One theory is that the remaining motor
+neurons have to work harder and so die sooner."
+14,sci.space,"
+Any lunar satellite needs fuel to do regular orbit corrections, and when
+its fuel runs out it will crash within months.  The orbits of the Apollo
+motherships changed noticeably during lunar missions lasting only a few
+days.  It is *possible* that there are stable orbits here and there --
+the Moon's gravitational field is poorly mapped -- but we know of none.
+
+Perturbations from Sun and Earth are relatively minor issues at low
+altitudes.  The big problem is that the Moon's own gravitational field
+is quite lumpy due to the irregular distribution of mass within the Moon."
+15,soc.religion.christian,"I wrote in response to [email protected] (Darius_Lecointe):
+
+
+Was Paul a God too? Is an interpretation of the words of Paul of higher
+priority than the direct word of Jesus in Matt5:14-19? Paul begins
+Romans 14 with ""If someone is weak in the faith ..."" Do you count
+yourself as one who is weak in the faith?
+
+
+Yes, but what does the Bible have to say? What did Jesus say? Paul
+closes Romans 14 with, ""On the other hand, the person with doubts about
+something who eats it anyway is guilty, because he isn't acting on his
+faith, and any failure to act on faith is a sin."" Gaus, ISBN:0-933999-99-2
+Have you read the Ten Commandments which are a portion of the Law? Have
+you read Jesus' word in Matt5:14-19? Is there any doubt in your mind
+about what is right and what is sin (Greek hamartia = missing the mark)?
+
+
+Whereas, the Ten Commandments and Jesus' words in Matt5:14-19 are fairly
+clear, are they not?
+
+
+Matt5:14-19 doesn't answer your question?
+
+
+Breaking bread - roughly synonymous with eating.
+
+
+How do you unite this concept of yours with the Ten Commandments and
+Jesus's word in Matt5:14-19?
+
+
+Or, they assumed that the Ten Commandments and Jesus' word in
+Matt5:14-19 actually stood for something? Perhaps they were ""strong in
+the faith?""
+
+---------------------------
+
+[No, I don't believe that Paul can overrule God.  However Paul was
+writing for a largely Gentile audience.  The Law was regarded by Jews
+at the time (and now) as binding on Jews, but not on Gentiles.  There
+are rules that were binding on all human beings (the so-called Noachic
+laws), but they are quite minimal.  The issue that the Church had to
+face after Jesus' death was what to do about Gentiles who wanted to
+follow Christ.  The decision not to impose the Law on them didn't say
+that the Law was abolished.  It simply acknowledged that fact that it
+didn't apply to Gentiles.  Thus there is no contradiction with Mat 5.
+As far as I can tell, both Paul and other Jewish Christians did
+continue to participate in Jewish worship on the Sabbath.  Thus they
+continued to obey the Law.  The issue was (and is) with Gentile
+Christians, who are not covered by the Law (or at least not by the
+ceremonial aspects of it).
+
+Jesus dealt mostly with Jews.  I think we can reasonably assume that
+Mat 5 was directed to a Jewish audience.  He did interact with
+Gentiles a few times (e.g. the centurion whose slave was healed and a
+couple of others).  The terms used to describe the centurion (see Luke
+7) suggest that he was a ""God-fearer"", i.e. a Gentile who followed
+God, but had not adopted the whole Jewish Law.  He was commended by
+Jewish elders as a worthy person, and Jesus accepted him as such.
+This seems to me to indicate that Jesus accepted the prevailing view
+that Gentiles need not accept the Law.
+
+However there's more involved if you want to compare Jesus and Paul on
+the Law.  In order to get a full picture of the role of the Law, we
+have to come to grips with Paul's apparent rejection of the Law, and
+how that relates to Jesus' commendation of the Law.  At least as I
+read Paul, he says that the Law serves a purpose that has been in a
+certain sense superceded.  Again, this issue isn't one of the
+abolition of the Law.  In the middle of his discussion, Paul notes
+that he might be understood this way, and assures us that that's not
+what he intends to say.  Rather, he sees the Law as primarily being
+present to convict people of their sinfulness.  But ultimately it's an
+impossible standard, and one that has been superceded by Christ.
+Paul's comments are not the world's clearest here, and not everyone
+agrees with my reading.  But the interesting thing to notice is that
+even this radical position does not entail an abolition of the Law.
+It still remains as an uncompromising standard, from which not an iota
+or dot may be removed.  For its purpose of convicting of sin, it's
+important that it not be relaxed.  However for Christians, it's not
+the end -- ultimately we live in faith, not Law.
+
+While the theoretical categories they use are rather different, in the
+end I think Jesus and Paul come to a rather similar conclusion.  The
+quoted passage from Mat 5 should be taken in the context of the rest
+of the Sermon on the Mount, where Jesus shows us how he interprets the
+Law.  The ""not an iota or dot"" would suggest a rather literal reading,
+but in fact that's not Jesus' approach.  Jesus' interpretations
+emphasize the intent of the Law, and stay away from the ceremonial
+details.  Indeed he is well known for taking a rather free attitude
+towards the Sabbath and kosher laws.  Some scholars claim that Mat
+5:17-20 needs to be taken in the context of 1st Cent. Jewish
+discussions.  Jesus accuses his opponents of caring about giving a
+tenth of even the most minor herbs, but neglecting the things that
+really matter: justice, mercy and faith, and caring about how cups and
+plates are cleaned, but not about the fact that inside the people who
+use them are full of extortion and rapacity.  (Mat 23:23-25) This, and
+the discussion later in Mat 5, suggest that Jesus has a very specific
+view of the Law in mind, and that when he talks about maintaining the
+Law in its full strength, he is thinking of these aspects of it.
+Paul's conclusion is similar.  While he talks about the Law being
+superceded, all of the specific examples he gives involve the
+""ceremonial law"", such as circumcision and the Sabbath.  He is quite
+concerned about maintaining moral standards.
+
+The net result of this is that when Paul talks about the Law being
+superceded, and Jesus talks about the Law being maintained, I believe
+they are talking about different aspects of the Law.  Paul is
+embroiled in arguments about circumcision.  As is natural in letters
+responding to specific situations, he's looking at the aspect of the
+Law that is currently causing trouble: the Law as specifically Jewish
+ceremonies.  He certainly does not intend to abolish divine standards
+of conduct.  On the other hand, when Jesus commends the Law, he seems
+to be talking the Law in its broadest implications for morals and
+human relationships, and deemphasizing those aspects that were later
+to give Paul so much trouble.
+
+It's unfortunate that people use the same terms in different ways, but
+we should be familiar with that from current conflicts.  Look at the
+way terms like ""family values"" take on special meaning from the
+current context.  Imagine some poor historian of the future trying to
+figure out why ""family values"" should be used as a code word for
+opposition to homosexuality in one specific period in the U.S.  I
+think Law had taken on a similar role in the arguments Paul was
+involved in.  Paul was clearly not rejecting all of the Jewish values
+that go along with the term ""Law"", any more than people who concerned
+about the ""family values"" movement are really opposed to family
+values."
+16,talk.politics.guns,"
+That's a revisionist account of what happened.  Gritz was well-aware
+of Duke's presence on the ticket.  Given that Gritz is not at all shy
+about associating and promoting other white supremacists (such as the
+Christian Identity movement or Willis Carto), whatever reasons Gritz
+had to leave the ticket had nothing to do with Duke's presence.
+
+
+I believe Chip Berlet has a Populist Party newsletter from the time with
+a photo of Gritz happily shaking hands with Duke."
+17,talk.politics.mideast,"
+						      ^^^^^^^^^^^^^^^"
+18,talk.politics.misc,"
+And the reason that the Soviet Union couldn't achieve the ideal of pure
+communism was the hostility of surrounding capitalist nations...Uh huh.
+Somehow, this all sounds familiar.  Once again, utopian dreams are 
+confronted by the real world...
+"
+19,talk.religion.misc,"
+
+Paradise and salvation are not the same thing.  Salvation is better.  Refer
+to John 14:2."

data/sample_text.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c16fa77b26c7c6686dbdafccbe792b41b797d336af9e87f534133248a25ca7
+size 12440444