Implementation of a K Means Clustering algorithm to classify documents by language

Blog post here

This implementation of K Means Clustering will try to classify the text you enter in textareas by language

Set the K value of the number of different languages you want it to recognize

K:

Click + to add a textarea or click on the side to select some sample text
Some text example to feed the algorithm
Click to add them
ROMA - Eros Ramazzotti festeggia lunedì 28 ottobre il suo cinquantesimo compleanno e lo fa nel modo migliore per un cantante: proprio lunedì uscirà un nuovo singolo, "Io prima di te", prodotto e arrangiato da Babydaddy (vero nome Scott Hoffman, componente degli Scissor Sisters e produttore di Pet Shop Boys e Blondie). E il 19 novembre sarà pubblicata una special edition di "Noi due", il suo ultimo album di inediti che ha venduto 700 mila copie tra Italia, Svizzera, Germania, Francia, Spagna, Russia, Austria, Belgio, Repubblica Ceca, Ungheria, Romania e Venezuela. Lui intanto ha chiuso trionfalmente la tranche americana del "Noi World Tour 2013" con il concerto del 24 a Miami, poi sarà in Australia a novembre per apporre il sigillo conclusivo al nutrito giro di date che ha toccato, oltre all'Italia, l'Europa e l'America Latina. Dopo trent'anni di carriera c'è sicuramente di che essere soddisfatti. La sua esplosione risale infatti al Sanremo 1984 quando dopo aver vinto nella sezione Voci Nuove con "Terra promessa" si ritrova proiettato in classifica anche in Europa poco più che ventenne. Da lì è cominciata una carriera che ha fatto di Eros Ramazzotti uno dei cantanti pop europei, non inglesi, di maggior successo nel mondo.
Sebastian Vettel, almost inevitably, won his fourth straight Formula One world championship here in Delhi and, as if to banish his few remaining doubters, he did so with one of the most devastating drives of his career. It was Vettel's 10th win of the season and his sixth in as many races. He joins only three other drivers as quadruple winners but, at 26, he is significantly younger than Michael Schumacher (32), Alain Prost (38) and Juan Manuel Fangio (45) were when they achieved the feat. Only Vettel, Schumacher and and Fangio have won four championships in successive seasons. Only the mixed-tyre strategies and the possibility of heavy traffic was expected to deny pole-sitter Vettel victory. Starting on the softer tyre, the champion was always going to pit earlier than the four drivers in the top 10 – including team-mate Mark Webber – who had chosen the harder, medium tyre. But Vettel confounded everyone by pitting early, at the end of the second lap, and then carving his way through the traffic with some imperious driving. It was to Vettel's great advantage that Webber, his most serious rival at the Buddh International circuit, made a bad start, colliding with first Kimi Raikkonen and then Fernando Alonso at the start of the opening lap. It got worse for the Australian. At the two-thirds stage of the race he dropped out with alternator trouble, his third retirement of the season. He threw his gloves into the car as he walked away from the vehicle. By then, though, the race and the championship was already virtually over. By the time Vettel and Webber had made their second stops at the halfway point the champion was already a decisive dozen seconds ahead of his team-mate. Even without Webber's collection of misfortunes, Vettel would surely have won. He did not actually lead every lap, which he had done in the previous two races here, but, cutting through the field from almost the back – he was 17th after his first stop – he was more dominant than ever. To make it a double, Red Bull clinched the constructors' title as well. Happy days in Milton Keynes and in Heppenheim, Germany. Nico Rosberg (Mercedes), who was half a minute behind, and Romain Grosjean (Lotus) completed the podium positions but there was only one Formula One show in town. "Brilliant drive, you did it in style and joined the greats," said Red Bull team principal Christian Horner. He was speaking for all of us.
ROMA - Usa Twitter Renato Brunetta per scavare la linea oltre la quale, per i falchi del Pdl, il governo Letta cade. "O il premier cambia la legge di stabilità ed evita decadenza Berlusconi, o larghe intese finite". Nonostante il sintetico linguaggio di Twitter il messaggio del capogruppo Pdl alla Camera è chiarissimo e pone un aut-aut non solo agli alleati avversari del Pd ma anche e soprattutto ai "ministeriali" del suo partito. Mara Carfagna rincara la dose. "La legge di stabilità e la legge Severino - dice - sono la cartina di tornasole dell'effettivo peso specifico che la delegazione del Pdl esercita sul governo. La prima, purtroppo, presenta più ombre che luci e colpisce in larga parte il nostro elettorato di riferimento, tasse sulla casa e Iva docet, la seconda potrebbe e dovrebbe essere corretta dal Cdm nell'aspetto relativo alla sua retroattività, invece il tema non figura affatto in agenda". "I soli proclami davanti a telecamere e taccuini - conclude - purtroppo non bastano, bisogna avere il coraggio di non essere subalterni ad alcuna logica rinunciataria e incidere sulle scelte, per il bene del Paese e per il futuro del nostro movimento". Stessi toni dalla senatrice Anna Maria Bernini. "È singolare che i nostri ministri del Pdl trovino occasione, nel loro consueto profluvio di interviste, per esprimere tante perplessità e distinguo sul rilancio di Forza Italia, ma dimentichino di chiarire la loro posizione su questioni che non sono irrilevanti". "In politica parlano i fatti - prosegue - non le parole. E sulla decadenza di Berlusconi finora i ministri, oltre alle parole, non hanno sviluppato in Cdm alcuna iniziativa per chiarire definitivamente la non retroattività della legge Severino". E sono proprio queste polemiche, che Epifani chiama "fibrillazioni", che secondo il ministro Graziano Delrio "fanno male all'Italia". "Questo continuo stato di incertezza - ha aggiunto - non fa bene alle nostre imprese e alla legge finanziaria. E' chiaro che il governo fa quello che riesce a fare nelle condizioni date". Per questo secondo il ministro "è necessario un chiarimento con il Pdl una volta che avranno risolto i loro problemi interni".
A host of foreign state-owned rail operators will be vying against Sir Richard Branson's Virgin Rail to run the last major route in public hands after the government launched the contest to reprivatise the east coast mainline franchise. The service is run by Directly Operated Railways, the government-owned company that took over in 2009 after National Express said it could not afford the payments under a £1.4bn contract. As the privatisation process got under way, the transport secretary, Patrick McLoughlin, said: "We want to see a revitalised east coast railway, one that both rekindles the spirit of competition for customers on this great route to Scotland and competes with the west coast on speed, quality and customer service." The Department for Transport said a strong private sector partner would deliver a "world-class railway for passengers and best value for the taxpayer". However, Labour and the unions have strongly criticised the government for pushing the east coast line back into private hands, with DOR on course to return around £1bn in premiums and profits to the state over its five-year tenure. The east coast company will be sold to a private operator with rights to run trains on the London-Edinburgh line for eight to nine years, with a possible extension. The terms of the franchise will encourage the next operator to retain the current brand. In line with the process for all European state contracts, the franchise was advertised to the private sector in the Official Journal of the European Union on Friday. Eurostar and Keolis, both owned by the French state railway SNCF, have already said they will join forces in the race for the line. Arriva, owned by Deutsche Bahn, is likely to be joining them. A shortlist of bidders will be announced in January. An award is due to be made by next October, for the new operator to take over in February 2015, before the next general election. Labour has indicated it would keep the line in public hands. The coalition prioritised the reletting of the east coast line while granting direct awards to privately owned Virgin, FirstGroup and National Express to run other services until as late as 2017, after the rail franchising programme was thrown into disarray by the bungled reletting of the west coast contract last year. The east coast competition is likely to reignite the rivalry behind the west coast debacle, which saw FirstGroup awarded the rights to the London-Glasgow route run by Virgin, only for the government to scrap the competition under a legal challenge from Branson's firm. Mary Creagh, Labour's shadow transport secretary, said the east coast move showed the government had learned nothing from the west coast franchising fiasco. She said: "David Cameron should tackle his government's cost of living crisis and cap rail fare rises for struggling commuters, instead of obsessing about handing East Coast over to the private sector." Labour has suggested that the state-owned DOR should be allowed to bid for future franchises.National Express has ruled itself out of the running.
Soll das Bundeswirtschaftsministerium auf den neuen Brief antworten, der vom Verband der Automobilindustrie (VDA) gekommen ist? Nein, das sei "nicht erforderlich", findet die Ministerialbeamtin. Denn es handle sich um einen Appell, "dem wir versucht haben, weitgehend nachzukommen", notiert sie auf dem Schreiben der Autolobbyisten. Und überhaupt: Man sei mit den Interessenvertretern der Autoindustrie "auf Arbeitsebene ständig in Kontakt". Diese und andere Briefwechsel zwischen VDA und Ministerien, die ZEIT ONLINE vorliegen, offenbaren ein bisher nicht gekanntes Ausmaß von Lobbyismus. Dabei geht es um den Entwurf für die Verordnung, die die Kennzeichnung des Energieverbrauchs von Neuwagen regeln soll. Auch in dem Brief, auf den die Beamtin nicht antworten will, nimmt der VDA Stellung dazu. Zu sagen, dass das Wirtschaftsministerium den Lobbyisten weitgehend entgegenkam, ist untertrieben. Der Automobilverband hat beim Entwurf sogar die Abstimmung zwischen den Ministerien übernommen. Eigentlich sollte das sogenannte Energielabel den Käufern von Autos zeigen, wie effizient das Fahrzeug beim Kraftstoffverbrauch und wie sparsam es beim Ausstoß von Kohlendioxid (CO2) ist. Umweltverbände halten die inzwischen eingeführte, verpflichtende Einstufung der Pkw in Effizienzklassen jedoch für irreführend, da schwere Pkws bevorzugt werden. Angesichts der massiven Einflussnahme der Autoindustrie überrascht das nicht. Insbesondere zu Beginn des neuen Kennzeichnungssystems, schreibt die VDA-Geschäftsführung im April 2010 an drei Ministerien, "sollte sichergestellt werden, dass alle Hersteller ihre Top-Produkte auch in den vordersten Rängen wiederfinden". Die Vorgaben für die beste Effizienzklasse sollten deshalb spürbar gesenkt werden.
NSA-Spezialisten in Frankfurt und Berlin Das Magazin beruft sich bei den Enthüllungen auf interne Dokumente von Whistleblower Edward Snowden. Aus einem Papier gehe hervor, dass für die NSA an über 80 Standorten weltweit ein Special Collection Service (SCS) zumeist in Botschaften und Konsulaten im Einsatz ist. Darunter befinde sich eines in Frankfurt am Main und eines in Berlin. Beide deutschen Stützpunkte seien mit aktiven Mitarbeitern besetzt. Die Einheit sei imstande, Mikrowellen und Millimeterwellen und verschlüsselte Kommunikation abzufangen. Seit einigen Jahren spezialisierten sich die SCS-Agenten zunehmend auf Einsätze im Internet, schreibt der Spiegel weiter. 2002 sei die Handynummer der heutigen Bundeskanzlerin in eine Liste der NSA aufgenommen worden, die den Schluss zulasse, dass sie Ziele der SCS-Agenten definiere. Als nach dem Anschlägen vom 11. September klar wurde, dass einige der Terroristen in Deutschland gelebt hatten, trauten die US-Amerikaner den Deutschen nicht mehr. Zudem waren sich Deutschland und die USA im Vorgehen gegen den Irak uneins. Die Bild am Sonntag berichtete, dass auch der damalige Bundeskanzler Gerhard Schröder (SPD) abgehört worden sei. Zudem sei Barack Obama in die Überwachung Merkels eingeweiht gewesen. Das geht laut Spiegel aus den Unterlagen jedoch nicht eindeutig hervor.
ILS FONT LA TRONCHE, TIRENT LA LANGUE, sont mal peignés, et l'un d'eux menace de balancer une "poopbomb" ("bombe de caca"). Loin des chatons-mignons, les nouveaux héros du business félin sur le Web sont du genre mal lunés et s'appellent Grumpy Cat, Colonel Meow ou Lil Bub. Produits croisés de la culture Internet, qui fabrique les stars virtuelles à coup de clics, et de la passion très anglo-saxonne pour les boules de fourrure griffues, ils ont envahi médias et boutiques en ligne. Venus des Etats-Unis, ils semblent partager une certaine posture : un cocktail de mauvais caractère et d'air blasé. Ces anti-lol cats ont aussi en commun des parcours à la Dickens revu par Hollywood. Grumpy Cat, de son vrai nom Tardar Sauce (elle était orangée à la naissance, et la petite fille qui a choisi son nom balbutie en orthographe), a ainsi grandi dans une famille pauvre de l'Arizona, chez Tabatha Bundesen, mère célibataire et serveuse. La carrière de ce chat à la mine perpétuellement dépitée a démarré par hasard, avec une photo postée sur Twitter par le frère de Tabatha. De vidéos sur YouTube en likes sur Facebook, ce croisé de siamois atteint de nanisme est devenu une vedette. Sa première vidéo, datée de 2012, frôle la barre des 17 millions de "vues". Grumpy Cat pose aujourd'hui en couverture du numéro spécial business du New York Magazine, et sa carrière est gérée par un agent assisté d'un avocat. Grâce à eux, elle est désormais égérie Friskies (parce qu'elle vaut bien sa gamelle de croquettes) et affiche son minois sur des tee-shirts, des peluches, et bientôt une boisson au café. Son livre est sur la liste des best-sellers du New York Times, et les droits d'un film sont en négociation. Ces "self-made-cats" sont devenus de petites entreprises florissantes capitalisant sur le succès spontané : la "marque" Grumpy Cat a déjà rapporté plus d'un million de dollars (source : New York Magazine).
Georges Ibrahim Abdallah a entamé, vendredi 25 octobre, sa trentième année de détention dans les prisons françaises. Une demi-vie derrière les barreaux qui fait de ce militant libanais pro-palestinien de 62 ans, condamné pour "complicité d'assassinats", "le plus vieux prisonnier politique d'Europe", selon les mots de son avocat, Jean-Louis Chalanset. Un prisonnier politique, Georges Ibrahim Abdallah ? De l'avis de l'ensemble des acteurs interrogés sur ce dossier, le destin de cet ancien combattant marxiste chrétien se joue davantage à l'Elysée que dans les palais de justice. Face à ce qu'elle considère comme un "régime d'exception", la Ligue des droits de l'homme appelle samedi à un rassemblement à Lannemezan, dans les Hautes-Pyrénées, où il est incarcéré. Le 23 octobre, 14 élus – députés, sénateurs, maires et conseillers régionaux – ont adressé une lettre ouverte au président de la République demandant qu'il soit libéré et puisse rejoindre le Liban, "quelles que soient les pressions étrangères". ASSASSINATS CIBLÉS Ancien membre du Front populaire de libération de la Palestine (FPLP), Georges Ibrahim Abdallah est le dernier souvenir que conservent les prisons françaises de la vague terroriste des années 1980. Son histoire personnelle est indissociable de celle du Liban, alors en pleine guerre civile et envahi par l'armée israélienne lors de l'opération "Paix en Galilée", en juin 1982. Cette même année, quelques mois avant l'attentat de la rue des Rosiers, deux diplomates – Charles R. Ray, l'attaché militaire américain à Paris, et Yacov Barsimentov, deuxième conseiller à l'ambassade d'Israël – sont tués d'une balle dans la tête à Paris. La Fraction armée révolutionnaire libanaise (FARL), un mouvement marxiste pro-palestinien créé trois ans plus tôt par Georges Ibrahim Abdallah, revendique les deux assassinats. Arrêté le 25 octobre 1984, il est condamné en février 1987 à la réclusion à perpétuité pour "complicité d'assassinats", reconnu coupable d'avoir commandité ces exécutions.
Click on a textarea after the algorithm has run to see the letter frequencies of the text