fscore_metadata_deep = [] fscore_metadata_deep.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.060887512899896801, 0.53679522497704313, 0.54368577133796669, 0.68557476976628118, 0.83591692404756834, 0.97823658019042592, 0.97823658019042592, 0.98547506229584403, 0.98642542686424783, 0.98642542686424783, 0.98672117036812568, 0.98672443696525403, 0.98672770354132078, 0.98675383539166284, 0.98676036814364698, 0.98694341933508456, 0.9871195398224385, 0.9871195398224385, 0.9871260678596403, 0.9871358597576696, 0.98719134360388872, 0.98721092468655647, 0.98721092468655647, 0.98722724167708509, 0.98722724167708509, 0.98824438292667216, 0.98824438292667216, 0.98824763971016649, 0.98824763971016649, 0.98824763971016649, 0.98846755840639133, 0.9931177029573719, 0.99182118559223631, 0.99182118559223631, 0.99199503647487375, 0.99008394426635515, 0.99388475984975633, 0.99378294320902405, 0.99378294320902405, 0.99378294320902405, 0.99378294320902405, 0.99378294320902405, 0.99378294320902405, 0.99378294320902405, 0.99379259202434367, 0.99379259202434367, 0.99379259202434367, 0.99379902446508595, 0.99387620733960202, 0.99387620733960202, 0.99387620733960202]) fscore_metadata_deep.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.035596284520915157, 0.52152385934755807, 0.53502848653426949, 0.67834664200708961, 0.83898634619476298, 0.84015134817427084, 0.96875153106719059, 0.96152949556433331, 0.97656578154762874, 0.97656578154762874, 0.97634781023561035, 0.97658910791151388, 0.97658910791151388, 0.97658910791151388, 0.97660576894900153, 0.9776609724047306, 0.97766762293215725, 0.97767094816342326, 0.97767094816342326, 0.97767094816342326, 0.97767094816342326, 0.96460720799639144, 0.97545174588173955, 0.97825655895173802, 0.97837433780753347, 0.97837433780753347, 0.97837588394342767, 0.97841749999187522, 0.97869976282530291, 0.97870626076220801, 0.98886394194581873, 0.98887369927786795, 0.98888345642160524, 0.98891844684553698, 0.98891844684553698, 0.98891844684553698, 0.98891844684553698, 0.98891844684553698, 0.9889282038085434, 0.9889282038085434, 0.98951672790749257, 0.98951672790749257, 0.98951672790749257, 0.98951672790749257, 0.98959501898097402, 0.98933825183319102, 0.98933825183319102, 0.98933825183319102, 0.98933825183319102, 0.99015261837707458, 0.99403423607562591]) fscore_metadata_deep.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.10817186183656277, 0.56393858971957922, 0.57668228780284814, 0.71308939837902696, 0.87921056747572124, 0.97679461170169601, 0.98254447801275591, 0.98364300255275139, 0.97730195741350723, 0.98448617827682927, 0.99132525485670309, 0.99132525485670309, 0.99134493325981854, 0.99134493325981854, 0.97467504497428226, 0.99003203189749778, 0.99146005509641866, 0.99146651632701432, 0.99147620801768188, 0.99124955575406548, 0.99159324769654988, 0.99203822676001319, 0.99203822676001319, 0.99204145489250373, 0.99204468300431703, 0.99209310220041702, 0.99209310220041702, 0.99209310220041702, 0.99209632998142572, 0.99212900994601105, 0.99213869204486871, 0.9922355028032237, 0.9922419561925071, 0.99252582351980889, 0.99344615709391926, 0.99344615709391926, 0.9934209895062065, 0.99368173330263732, 0.99404516469290893, 0.99404516469290893, 0.99404516469290893, 0.99405802613957095, 0.99406445673957455, 0.99406445673957455, 0.99406445673957455, 0.99421248581883259, 0.99421248581883259, 0.99394705993209209, 0.99395670033282868, 0.99395670033282868, 0.99400114993930877]) fscore_metadata_deep.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.052600586379386222, 0.50531945973885883, 0.55113856663021732, 0.68633747684334845, 0.722155795775278, 0.86721250036036546, 0.97403021321599692, 0.97403021321599692, 0.97403021321599692, 0.97403021321599692, 0.97403021321599692, 0.97403021321599692, 0.97403356215134629, 0.974338223776954, 0.97441519752276728, 0.97441887782403847, 0.97442858308181746, 0.97442858308181746, 0.97450922176944432, 0.97450922176944432, 0.97451591328037068, 0.97451591328037068, 0.98476744186046494, 0.98476744186046494, 0.94722403320444881, 0.97798139735544942, 0.98519066175497272, 0.98519066175497272, 0.98613319742856131, 0.98860605124541878, 0.9886093056181221, 0.98861801172299746, 0.98870041955162025, 0.98925975947006239, 0.98928576022225934, 0.98928576022225934, 0.98941669667198195, 0.98947842160250743, 0.9894881669549116, 0.9894881669549116, 0.9894881669549116, 0.98949141536394292, 0.98949141536394292, 0.98949141536394292, 0.98949141536394292, 0.98949141536394292, 0.98949141536394292, 0.98949141536394292, 0.98949141536394292, 0.98824180028744413, 0.98824180028744413]) fscore_metadata_deep.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.076222068534986628, 0.53931638167147822, 0.58825423228610529, 0.72276163143215166, 0.85909481544605648, 0.85949207037318021, 0.9657050000982853, 0.97414741294620266, 0.96913666019304523, 0.97656578154762874, 0.97656578154762874, 0.97657244633152829, 0.97657244633152829, 0.97657911102862394, 0.97658244334462097, 0.97658910791151388, 0.97673237510784106, 0.97673237510784106, 0.97673237510784106, 0.9769521955792223, 0.97695885533129578, 0.97695885533129578, 0.97695885533129578, 0.97727509371095378, 0.97728507700166911, 0.9772852248212851, 0.97728367105246028, 0.97732500821557677, 0.97726755193525094, 0.98746203667024146, 0.98746203667024146, 0.98746203667024146, 0.98746203667024146, 0.98746203667024146, 0.97840788514886934, 0.98761631838232933, 0.98761631838232933, 0.98771141138433394, 0.98773748953435958, 0.98658876387161476, 0.98658876387161476, 0.98658876387161476, 0.98814122373300373, 0.98805573347323561, 0.98805899051800172, 0.98816689950877823, 0.98816689950877823, 0.98816689950877823, 0.98816689950877823, 0.98818318477816514, 0.98819946952334359]) average_metadata_deep = list(np.mean(np.matrix(fscore_metadata_deep), axis=0).A1) fscore_metadata_only = [] fscore_metadata_only.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.26769677760169047, 0.64959398767163834, 0.81498155537152761, 0.87640262765282273, 0.90739650466118638, 0.9103778912887962, 0.92383590849648889, 0.92723503109934302, 0.92753967188129505, 0.9626215480357837, 0.9626215480357837, 0.96202408639487957, 0.96261891256786314, 0.96261891256786314, 0.95140962500484749, 0.95076654140854777, 0.96393651785598033, 0.96393651785598033, 0.96629031526717057, 0.96569379446051873, 0.96569379446051873, 0.96569379446051873, 0.96661551510913413, 0.96723403979603073, 0.97340949507625385, 0.97323317850723379, 0.97281614591624888, 0.97279722482971875, 0.9729450586569317, 0.97680704733877399, 0.97698131798322385, 0.97739645852991042, 0.97740123985163274, 0.97714324580808343, 0.97775159726312921, 0.97799056692337316, 0.9782683974278068, 0.97831272270642722, 0.97834248135874069, 0.97886587423139071, 0.97895428602876677, 0.97895428602876677, 0.97895428602876677, 0.97895428602876677, 0.97897425438724273, 0.97912699954666138, 0.97918703820026809, 0.97914723862812136, 0.98731867764772385, 0.98734144688450554, 0.98733672990806109]) fscore_metadata_only.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.36445574539779008, 0.70752894570255864, 0.81823611090374315, 0.89289364425664242, 0.91399914932151527, 0.97569315394335832, 0.98013681588020696, 0.98013681588020696, 0.97914561915982101, 0.97914575378368518, 0.98196197250003203, 0.98662806153333704, 0.98663122157453065, 0.98750336620458823, 0.98643209160980017, 0.98643209160980017, 0.9864353372912944, 0.98884211804789801, 0.98896848458113162, 0.98654754275037226, 0.98893132820865237, 0.98893132820865237, 0.98900726562524965, 0.98705516070995636, 0.98631184278847228, 0.98708336521051687, 0.98904391378230938, 0.98904391378230938, 0.98907592551186629, 0.98943172781189825, 0.98978640826279563, 0.98978640826279563, 0.98988628856470828, 0.98988628856470828, 0.99005067201041519, 0.99026517895032395, 0.98962800470613743, 0.99018184486868166, 0.99031226666156114, 0.99031226666156114, 0.99013342876131072, 0.99031408929438525, 0.99034591154784868, 0.99037816495122, 0.99138065933644814, 0.99140047963162248, 0.99141014178055953, 0.99141014178055953, 0.99141014178055953, 0.99141014178055953, 0.99144442067007521]) fscore_metadata_only.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.29053599704995553, 0.67302584221892003, 0.85378517925969022, 0.93056462840891851, 0.9621509095567512, 0.96727747856846935, 0.98121759145513554, 0.98121759145513554, 0.9235388897026513, 0.96915693489041754, 0.9806289000051569, 0.98059438361948104, 0.98256740453041025, 0.98027490900196634, 0.98255483870967741, 0.98255483870967741, 0.98234931774130596, 0.98006865776324981, 0.98228393429513028, 0.98228721603276214, 0.98228721603276214, 0.98228721603276214, 0.98232839517320114, 0.98259261168827827, 0.9845375913124873, 0.98453125753896131, 0.98476892784062398, 0.98477526463112508, 0.98477526463112508, 0.98308111302381751, 0.98315711037167419, 0.98317099323886148, 0.9831807864804214, 0.98326949564480337, 0.98345552830600524, 0.98423610821090912, 0.98424263451585858, 0.98427852769407698, 0.98457713999409036, 0.98465214417157232, 0.98487066861883843, 0.98478034060448461, 0.98491449191148372, 0.98513929901142638, 0.98517743426458504, 0.98520924678859623, 0.98520924678859623, 0.98614301640797941, 0.98619196319570268, 0.98682536214187477, 0.98686235513730436]) fscore_metadata_only.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.32861372869953964, 0.68871425543674747, 0.8509717964215755, 0.94197874409092441, 0.95988119792096371, 0.9768880895257821, 0.97032308965802683, 0.97032308965802683, 0.97691505283686331, 0.97818910938326054, 0.98115856171440341, 0.98115856171440341, 0.98115856171440341, 0.98115856171440341, 0.98115856171440341, 0.98423332110611295, 0.98423332110611295, 0.98423332110611295, 0.98423658951744453, 0.98410768171611318, 0.98409185226172358, 0.98401924895616877, 0.98415200689770543, 0.98387708771455951, 0.98428302141703705, 0.98429568629973929, 0.98409329191028427, 0.98410911675505652, 0.98412177699732095, 0.98412177699732095, 0.98412177699732095, 0.98123262502765574, 0.9836138289255455, 0.98389191830855494, 0.98389243619668598, 0.98365037701478819, 0.98365353723575144, 0.98276997612920436, 0.98318998212931186, 0.98329955124972279, 0.98329955124972279, 0.98329955124972279, 0.98345937093588931, 0.98395732224019727, 0.98413126458700528, 0.98413126458700528, 0.98613506508522264, 0.98668646183805886, 0.98668646183805886, 0.98687871485943779, 0.98688196985712506]) fscore_metadata_only.append([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.36798217794210925, 0.70972529130211437, 0.80980026470942124, 0.89981052364685443, 0.95666614668642602, 0.95973370557285509, 0.96691012561957468, 0.96691012561957468, 0.96924992564946422, 0.97031505982024557, 0.97031505982024557, 0.96923664945068944, 0.97417778515214504, 0.98242771805604423, 0.98196138129440702, 0.98238175446748377, 0.98212700574892586, 0.98212700574892586, 0.98212700574892586, 0.98223744306976224, 0.98162675474814198, 0.98163003964298723, 0.98163660936910313, 0.98194137480439436, 0.98193527155168236, 0.98147127192770356, 0.98205196028463959, 0.98206803116078778, 0.98247697480944118, 0.98139797250471406, 0.98384056712404555, 0.9845088238228733, 0.98484141565925842, 0.98484468212444742, 0.98626166151947647, 0.98665655897261273, 0.98590163934426223, 0.9856561791611067, 0.98545609992061123, 0.98586486086727243, 0.98662867727453984, 0.98662867727453984, 0.98691782386186344, 0.98695274552063572, 0.98695600425900132, 0.98719057833750878, 0.98820548438545031, 0.98819655896415237, 0.98819655896415237, 0.98808804433073194, 0.99156002398662879]) average_metadata_only = list(np.mean(np.matrix(fscore_metadata_only), axis=0).A1) ranges = [label_potential, label_potential, label_potential, label_potential, label_potential] list = [average_metadata_no_svd_unigram, average_metadata_no_svd_bigram, average_metadata_only, average_metadata_no_svd_absolute_potential, average_metadata_deep] names = ["Unigrams", "Unigrams + Bigrams", "Metadata", "Unigrams + Metadata", "LSTM + Metadata"] plot_list_latex(ranges, list, names, "Address", x_max=350) plot_list(ranges, list, names, "Address", x_max=350)
0.16233354470513636, 0.16228209191759113, 0.16579292267365664,
0.1654485049833887, 0.17009966777408639, 0.17118020728853225,
0.18194791295041027, 0.18142392482833394, 0.18365871294287778,
0.19781110660721524, 0.20032573289902281, 0.20640865584685808,
0.20770519262981579, 0.1947798987144527, 0.19398797595190381,
0.19492868462757529, 0.1945902301170771, 0.19272291083566576,
0.19334135579622944, 0.19365079365079366, 0.19564356435643565,
0.19839999999999999, 0.19879759519038073, 0.19959758551307846,
0.20321285140562251, 0.20429671665991081, 0.20711974110032361,
0.21160971593248251, 0.21902017291066284, 0.22691511387163563,
0.22764900662251655, 0.2308015107007973, 0.23238255033557048,
0.23337515683814306, 0.23613445378151257, 0.23761544920235092,
0.23642439431913112, 0.23993358239933582, 0.24173985780008367,
0.2443133951137321, 0.24776500638569607, 0.24734381640458988,
0.24659863945578234, 0.2519148936170213, 0.2544529262086514,
0.2592274678111588, 0.25933877200515243, 0.2653862941946748,
0.26625659050966605, 0.26802299867315349, 0.2723666813574262,
0.27925892453682782, 0.28065395095367845, 0.28221415607985484
])
average_naive_bayes = list(np.mean(np.matrix(fscore_naive_bayes), axis=0).A1)
ranges = [label_potential, label_potential, label_potential]
list = [
average_metadata_no_svd_absolute_potential, average_linear_svm,
average_naive_bayes
]
names = ["XGBoost", "Linear SVM", "Naive Bayes"]
plot_list_latex(ranges, list, names, "Hospital", x_max=800)
0.66522593320235757, 0.66522593320235757, 0.66607652208124324,
0.61769653470898278, 0.68254671035154513, 0.68254671035154513,
0.68277999114652499, 0.63510101010101006, 0.67976534127944865,
0.51007347712728135, 0.51244195737587805, 0.51491738975395218,
0.68243875070132787
])
fscore_naive_bayes.append([
0.25861779048259631, 0.45229485396383873, 0.58935820076796486,
0.64990987382335264, 0.65609228550829124, 0.71113581619418198,
0.62645168564663423, 0.58755957472809484, 0.60305619059078341,
0.59076315139540625, 0.61255779995132631, 0.64267530664198114,
0.61202185792349728, 0.61287897769982458, 0.6149155126413417,
0.61907177276185643, 0.61646507998439337, 0.45941384072425961,
0.46768860835587622, 0.450046685340803, 0.45199135535659152,
0.45380225204380692, 0.46361268576681475, 0.47214121258633923,
0.49029714978775019, 0.55380159304851562, 0.549833164079501,
0.55483123279733448, 0.56278669724770636, 0.56440483036227718,
0.6722159162567789
])
average_naive_bayes = list(np.mean(np.matrix(fscore_naive_bayes), axis=0).A1)
ranges = [label_potential, label_potential, label_potential]
list = [
average_metadata_no_svd_absolute_potential, average_linear_svm,
average_naive_bayes
]
names = ["XGBoost", "Linear SVM", "Naive Bayes"]
plot_list_latex(ranges, list, names, "Flights", x_max=200)
#plot_list(ranges, list, names)
0.97571913223194207, 0.97572039460857585, 0.97393137445676858,
0.9742729814409985, 0.97902300983185497, 0.97900419141775752,
0.97934547191674926, 0.97934547191674926, 0.97775154494200833,
0.97633685785986624, 0.97645673735989036, 0.98082281804388227,
0.98103290014010336, 0.98218754030697786, 0.98224390369727899,
0.98539603721582414, 0.98590453408440559, 0.98623748460199989,
0.98727090197693579, 0.98727090197693579, 0.98738323621117385,
0.98738641336525346, 0.98753950222370979, 0.98790226575118567,
0.98790226575118567, 0.98790838947984827, 0.98776206336181227,
0.98802144682384896, 0.98808558297609395, 0.98832872639278158,
0.9884158702577468, 0.9884158702577468
])
average_metadata_only = list(
np.mean(np.matrix(fscore_metadata_only), axis=0).A1)
ranges = [
label_potential, label_potential, label_potential, label_potential,
label_potential
]
list = [
average_metadata_no_svd_unigram, average_metadata_no_svd_bigram,
average_metadata_only, average_metadata_no_svd_absolute_potential,
average_metadata_deep
]
names = [
"Unigrams", "Bigrams", "Metadata", "Unigrams + Metadata", "LSTM + Metadata"
]
plot_list_latex(ranges, list, names, "BlackOak", x_max=350)
plot_list(ranges, list, names, "BlackOak", x_max=350)