############################################################################### ## POPULATION IN THE WORLD ############################################################################### #DBPEDIA PREFIX xsd: PREFIX rdfs: PREFIX rdf: PREFIX dbr: PREFIX wd: prefix dbo: prefix wdt: SELECT ?digit (COUNT(*) AS ?count)WHERE {{SELECT (SUBSTR(STR(?number * 1.0),1,1) AS ?digit)WHERE {SELECT ?subject ?number WHERE { ?subject dbo:populationTotal ?number . FILTER(?number >= 0.0)}}}FILTER (?digit IN ('1', '2', '3','4', '5', '6','7', '8', '9'))}GROUP BY ?digit #digit present_facts true_distribution GBL_distribution missing_facts 1 97567.0 0.29983712354025815 0.30588218180197874 6799.273844569107 2 60384.0 0.18556853103872156 0.176976613090914 0.0 3 40747.0 0.12522126613398893 0.12470068056949121 1800.575998869339 4 31031.0 0.09536263060848187 0.09623321003235653 1803.542672645097 5 25939.0 0.0797141979102643 0.0783105484956022 780.3731294274367 6 21114.0 0.06488629379225569 0.06598854248378452 1401.1339476358044 7 18108.0 0.05564843269821758 0.05699790808419435 1339.5508466643405 8 16210.0 0.04981561155500922 0.05014971253171137 900.9627912205178 9 14300.0 0.0439459127228027 0.044760602909967036 972.2113894619051 N = 325400.0 R = 325400 alpha = -0.019969956443524894 MAD = 0.0023369228726594113 WLS = 6.39213736387723E-4 prevalence = 15.999999994350308 missing numbers = 15797.62462049356 missing facts = 15797.62462049356 representativeness = 0.9536994882714529 all = 341197 Compliance with BL: CLOSE #WIKIDATA PREFIX xsd: PREFIX rdfs: PREFIX rdf: PREFIX dbr: PREFIX wd: prefix dbo: prefix wdt: SELECT ?digit (COUNT(*) AS ?count)WHERE {{SELECT (SUBSTR(STR(?number * 1.0),1,1) AS ?digit)WHERE {SELECT ?subject ?number WHERE { ?subject wdt:P1082 ?number . FILTER(?number >= 0.0)}}}FILTER (?digit IN ('1', '2', '3','4', '5', '6','7', '8', '9'))}GROUP BY ?digit #digit present_facts true_distribution GBL_distribution missing_facts 1 103659.0 0.2930115809379514 0.29776602249859324 5932.184766734004 2 63410.0 0.17924024298204205 0.1754781939883285 1173.806501960964 3 45264.0 0.1279471748673577 0.12508765279908363 773.8385515970294 4 34258.0 0.09683665421982017 0.09736067389191544 1575.0729341459664 5 29358.0 0.08298588635020959 0.07976750052589308 0.0 6 24100.0 0.06812316441992136 0.06759582654115409 778.2807849297787 7 20584.0 0.0581845318016457 0.058667996210432824 1008.4407984526479 8 17646.0 0.04987972445452001 0.05183671104911236 1432.222997420442 9 15492.0 0.043791039966532025 0.04643942249548681 1599.7799433861292 N = 353771.0 R = 353771 alpha = 0.013501945347976373 MAD = 0.002303843281126978 WLS = 5.876242098222398E-4 prevalence = 10.876800963309707 missing numbers = 14273.627278626955 missing facts = 14273.627278626955 representativeness = 0.9612176724758404 all = 368044 Compliance with BL: CLOSE #YAGO PREFIX xsd: PREFIX rdfs: PREFIX rdf: PREFIX dbr: PREFIX wd: prefix dbo: prefix wdt: SELECT ?digit (COUNT(*) AS ?count)WHERE {{SELECT (SUBSTR(STR(?number * 1.0),1,1) AS ?digit)WHERE {SELECT ?subject ?number WHERE { ?subject ?number . FILTER(?number >= 0.0)}}}FILTER (?digit IN ('1', '2', '3','4', '5', '6','7', '8', '9'))}GROUP BY ?digit #digit present_facts true_distribution GBL_distribution missing_facts 1 111800.0 0.2953008079831589 0.3083969239986854 18599.64265180791 2 75020.0 0.19815265308494256 0.17742331779358303 0.0 3 46739.0 0.12345317052168929 0.12456957973929624 5932.82458460371 4 35115.0 0.09275033875070325 0.09587930932974256 5425.701613333462 5 29834.0 0.07880146963657926 0.07785971872427659 3087.468109906382 6 24476.0 0.06464921803395167 0.06549500428180652 3217.2890350832567 7 21238.0 0.05609658819272208 0.05648782175339747 2646.777044188191 8 18329.0 0.04841295625691699 0.04963659945977985 2658.8709167469024 9 16046.0 0.04238279753933602 0.04425172491943234 2664.9814242008397 N = 378597.0 R = 378597 alpha = -0.03027375594789349 MAD = 0.004815796934147156 WLS = 0.0032242879239349743 prevalence = 18.04619593531349 missing numbers = 44233.55537987064 missing facts = 44233.55537987064 representativeness = 0.8953870414115856 all = 422830 Compliance with BL: CLOSE ############################################################################### ## POPULATION IN FRANCE ############################################################################### #DBPEDIA PREFIX xsd: PREFIX rdfs: PREFIX rdf: PREFIX dbr: PREFIX wd: prefix dbo: prefix wdt: SELECT ?digit (COUNT(*) AS ?count)WHERE {{SELECT (SUBSTR(STR(?number * 1.0),1,1) AS ?digit)WHERE {SELECT ?subject ?number WHERE {?subject dbo:country dbr:France. ?subject dbo:populationTotal ?number . FILTER(?number >= 0.0)}}}FILTER (?digit IN ('1', '2', '3','4', '5', '6','7', '8', '9'))}GROUP BY ?digit #digit present_facts true_distribution GBL_distribution missing_facts 1 11380.0 0.30489765298467475 0.30877673578969467 500.0502380408743 2 6820.0 0.18272425249169436 0.17749006849397936 8.852973877976183 3 4726.0 0.1266209409495231 0.12454932589567652 65.98099225500391 4 3431.0 0.09192476690601221 0.09582567611896527 255.85109477582364 5 2993.0 0.08018969027971279 0.07779165506045535 0.0 6 2464.0 0.06601650412603151 0.06542064610205092 53.03082588062216 7 2094.0 0.056103311542171255 0.05641108085419149 76.39173244717995 8 1776.0 0.0475833244025292 0.0495594895858116 130.77974668438515 9 1640.0 0.04393955631765084 0.04417532209917482 59.62625091442942 N = 37324.0 R = 37324 alpha = -0.03182732988925161 MAD = 0.002288820509955463 WLS = 5.574308724927195E-4 prevalence = 8.079364949946388 missing numbers = 1150.5638548762945 missing facts = 1150.5638548762945 representativeness = 0.9700954672490596 all = 38474 Compliance with BL: CLOSE #WIKIDATA PREFIX xsd: PREFIX rdfs: PREFIX rdf: PREFIX dbr: PREFIX wd: prefix dbo: prefix wdt: SELECT ?digit (COUNT(*) AS ?count)WHERE {{SELECT (SUBSTR(STR(?number * 1.0),1,1) AS ?digit)WHERE {SELECT ?subject ?number WHERE {?subject wdt:P17 wd:Q142. ?subject wdt:P1082 ?number . FILTER(?number >= 0.0)}}}FILTER (?digit IN ('1', '2', '3','4', '5', '6','7', '8', '9'))}GROUP BY ?digit #digit present_facts true_distribution GBL_distribution missing_facts 1 12071.0 0.30241763747964423 0.3095747154631687 761.3058363065193 2 7363.0 0.18446699235876238 0.17762969952806104 -9.094947017729282E-13 3 5159.0 0.1292496555179757 0.12450638751808278 1.9642629093195865 4 3776.0 0.09460102718276338 0.09571283926315446 191.43133252486314 5 3166.0 0.07931855192283603 0.0776486779340603 52.64652784692316 6 2617.0 0.06556432418890142 0.0652645766503121 88.30817286179217 7 2188.0 0.05481648503069022 0.056250104161662685 143.64565409228726 8 1906.0 0.0477514718777402 0.04939781226573098 141.60855126661477 9 1669.0 0.04181385444068646 0.044015187215766895 155.49119899847892 N = 39915.0 R = 39915 alpha = -0.035089134641951084 MAD = 0.003011151635102064 WLS = 8.610531469758153E-4 prevalence = 9.123851640967086 missing numbers = 1536.4015368067994 missing facts = 1536.4015368067994 representativeness = 0.962934871202303 all = 41451 Compliance with BL: CLOSE #YAGO PREFIX xsd: PREFIX rdfs: PREFIX rdf: PREFIX dbr: PREFIX wd: prefix dbo: prefix wdt: SELECT ?digit (COUNT(*) AS ?count)WHERE {{SELECT (SUBSTR(STR(?number * 1.0),1,1) AS ?digit)WHERE {SELECT ?subject ?number WHERE {?subject + . ?subject ?number . FILTER(?number >= 0.0)}}}FILTER (?digit IN ('1', '2', '3','4', '5', '6','7', '8', '9'))}GROUP BY ?digit #digit present_facts true_distribution GBL_distribution missing_facts 1 61572.0 0.2909224924873845 0.3006475135510568 7721.027111065094 2 40569.0 0.1916850938368203 0.17602014929587545 0.0 3 25973.0 0.12272022830791329 0.12495665747519659 2826.922380420554 4 19978.0 0.0943943603409499 0.0969630173612466 2369.967929036342 5 17447.0 0.08243559940277069 0.07924992329038608 818.4664868132204 6 13917.0 0.06575664795600158 0.06702266047771285 1530.335568099339 7 13345.0 0.06305399633346563 0.058070859529942814 39.13079237999227 8 9681.0 0.04574190621987866 0.051232294230776465 2126.9830801340704 9 9162.0 0.04328967511481544 0.04583692478780636 1402.4621320639344 N = 211644.0 R = 211644 alpha = 0.0015792903539290682 MAD = 0.005296390545967174 WLS = 0.0031262749943079446 prevalence = 14.301904732047493 missing numbers = 18835.295480012544 missing facts = 18835.295480012544 representativeness = 0.9182777114934128 all = 230479 Compliance with BL: CLOSE ############################################################################### ## POPULATION IN YEMEN ############################################################################### #DBPEDIA PREFIX xsd: PREFIX rdfs: PREFIX rdf: PREFIX dbr: PREFIX wd: prefix dbo: prefix wdt: SELECT ?digit (COUNT(*) AS ?count)WHERE {{SELECT (SUBSTR(STR(?number * 1.0),1,1) AS ?digit)WHERE {SELECT ?subject ?number WHERE {?subject dbo:country dbr:Yemen. ?subject dbo:populationTotal ?number . FILTER(?number >= 0.0)}}}FILTER (?digit IN ('1', '2', '3','4', '5', '6','7', '8', '9'))}GROUP BY ?digit #digit present_facts true_distribution GBL_distribution missing_facts 1 104.0 0.2751322751322751 0.2710582750235829 19.580846215353105 2 59.0 0.15608465608465608 0.16991831762155718 18.469132707106013 3 44.0 0.1164021164021164 0.12594839845764177 13.422374061480546 4 46.0 0.12169312169312169 0.10089492856649303 0.0 5 38.0 0.10052910052910052 0.08457505803331941 0.5594471873654072 6 27.0 0.07142857142857142 0.07304293517490282 6.301723543331491 7 26.0 0.06878306878306878 0.06443281259134741 3.376197806103491 8 18.0 0.047619047619047616 0.05774311452740601 8.326231714512446 9 16.0 0.042328042328042326 0.0523861600037495 7.883889848679214 N = 378.0 R = 378 alpha = 0.12634435673398456 MAD = 0.010039220427294094 WLS = 0.01324344945582918 prevalence = 4.418753132333526 missing numbers = 77.91984308393171 missing facts = 77.91984308393171 representativeness = 0.8290931086550949 all = 455 Compliance with BL: ACCEPTABLE #WIKIDATA PREFIX xsd: PREFIX rdfs: PREFIX rdf: PREFIX dbr: PREFIX wd: prefix dbo: prefix wdt: SELECT ?digit (COUNT(*) AS ?count)WHERE {{SELECT (SUBSTR(STR(?number * 1.0),1,1) AS ?digit)WHERE {SELECT ?subject ?number WHERE {?subject wdt:P17 wd:Q805. ?subject wdt:P1082 ?number . FILTER(?number >= 0.0)}}}FILTER (?digit IN ('1', '2', '3','4', '5', '6','7', '8', '9'))}GROUP BY ?digit #digit present_facts true_distribution GBL_distribution missing_facts 1 8965.0 0.26448548501298086 0.28675140702726587 1983.593067562113 2 6617.0 0.19521477460467312 0.1733039166393928 0.0 3 4606.0 0.135886240264338 0.12552161929969047 186.6011772388174 4 3491.0 0.1029915034222327 0.09885264218410691 283.34016504825877 5 2869.0 0.08464125560538116 0.08174851443091359 252.27925599576065 6 2253.0 0.06646801982534813 0.06981266304458171 412.5507868712166 7 1932.0 0.056997875855558176 0.060994245796860955 396.8505664740933 8 1659.0 0.048943828180316264 0.05420447990301604 410.6072568548602 9 1504.0 0.04437101722917158 0.04881051167417164 359.6575676477187 N = 33896.0 R = 33896 alpha = 0.05950287269657288 MAD = 0.00873490696500471 WLS = 0.006967029389598474 prevalence = 9.123851640967086 missing numbers = 4285.4798436928395 missing facts = 4285.4798436928395 representativeness = 0.8877602476059934 all = 38181 Compliance with BL: CLOSE #YAGO PREFIX xsd: PREFIX rdfs: PREFIX rdf: PREFIX dbr: PREFIX wd: prefix dbo: prefix wdt: SELECT ?digit (COUNT(*) AS ?count)WHERE {{SELECT (SUBSTR(STR(?number * 1.0),1,1) AS ?digit)WHERE {SELECT ?subject ?number WHERE {?subject + . ?subject ?number . FILTER(?number >= 0.0)}}}FILTER (?digit IN ('1', '2', '3','4', '5', '6','7', '8', '9'))}GROUP BY ?digit #digit present_facts true_distribution GBL_distribution missing_facts 1 47.0 0.27167630057803466 0.2215507281730079 19.381672745980453 2 19.0 0.10982658959537572 0.15685808083291214 27.998273827752215 3 18.0 0.10404624277456648 0.12561322810665473 19.636600292420255 4 10.0 0.057803468208092484 0.10653909798633909 21.921554018357483 5 28.0 0.16184971098265896 0.09345079947868368 0.0 6 13.0 0.07514450867052024 0.08380615684037142 12.110244156505665 7 20.0 0.11560693641618497 0.07634738115975362 2.8754241204830038 8 9.0 0.05202312138728324 0.0703737178186327 12.08557775764329 9 9.0 0.05202312138728324 0.06546080960364474 10.61355792702599 N = 173.0 R = 173 alpha = 0.350467269585839 MAD = 0.03506311981454076 WLS = 0.130128978959553 prevalence = 8.795867787439267 missing numbers = 126.62290484616835 missing facts = 126.62290484616835 representativeness = 0.5773924396361527 all = 299 Compliance with BL: NON