You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by pw...@apache.org on 2013/09/25 02:14:46 UTC
svn commit: r2978 [7/12] - in
/dev/incubator/spark/spark-0.8.0-incubating-rc6-docs: ./ css/ img/ js/
js/vendor/
Added: dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/js/vendor/modernizr-2.6.1-respond-1.1.0.min.js
==============================================================================
--- dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/js/vendor/modernizr-2.6.1-respond-1.1.0.min.js (added)
+++ dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/js/vendor/modernizr-2.6.1-respond-1.1.0.min.js Wed Sep 25 00:14:43 2013
@@ -0,0 +1,11 @@
+/* Modernizr 2.6.1 (Custom Build) | MIT & BSD
+ * Build: http://modernizr.com/download/#-fontface-backgroundsize-borderimage-borderradius-boxshadow-flexbox-hsla-multiplebgs-opacity-rgba-textshadow-cssanimations-csscolumns-generatedcontent-cssgradients-cssreflections-csstransforms-csstransforms3d-csstransitions-applicationcache-canvas-canvastext-draganddrop-hashchange-history-audio-video-indexeddb-input-inputtypes-localstorage-postmessage-sessionstorage-websockets-websqldatabase-webworkers-geolocation-inlinesvg-smil-svg-svgclippaths-touch-webgl-shiv-mq-cssclasses-addtest-prefixed-teststyles-testprop-testallprops-hasevent-prefixes-domprefixes-load
+ */
+;window.Modernizr=function(a,b,c){function D(a){j.cssText=a}function E(a,b){return D(n.join(a+";")+(b||""))}function F(a,b){return typeof a===b}function G(a,b){return!!~(""+a).indexOf(b)}function H(a,b){for(var d in a){var e=a[d];if(!G(e,"-")&&j[e]!==c)return b=="pfx"?e:!0}return!1}function I(a,b,d){for(var e in a){var f=b[a[e]];if(f!==c)return d===!1?a[e]:F(f,"function")?f.bind(d||b):f}return!1}function J(a,b,c){var d=a.charAt(0).toUpperCase()+a.slice(1),e=(a+" "+p.join(d+" ")+d).split(" ");return F(b,"string")||F(b,"undefined")?H(e,b):(e=(a+" "+q.join(d+" ")+d).split(" "),I(e,b,c))}function K(){e.input=function(c){for(var d=0,e=c.length;d<e;d++)u[c[d]]=c[d]in k;return u.list&&(u.list=!!b.createElement("datalist")&&!!a.HTMLDataListElement),u}("autocomplete autofocus list placeholder max min multiple pattern required step".split(" ")),e.inputtypes=function(a){for(var d=0,e,f,h,i=a.length;d<i;d++)k.setAttribute("type",f=a[d]),e=k.type!=="text",e&&(k.value=l,k.style.cssText="position:
absolute;visibility:hidden;",/^range$/.test(f)&&k.style.WebkitAppearance!==c?(g.appendChild(k),h=b.defaultView,e=h.getComputedStyle&&h.getComputedStyle(k,null).WebkitAppearance!=="textfield"&&k.offsetHeight!==0,g.removeChild(k)):/^(search|tel)$/.test(f)||(/^(url|email)$/.test(f)?e=k.checkValidity&&k.checkValidity()===!1:e=k.value!=l)),t[a[d]]=!!e;return t}("search tel url email datetime date month week time datetime-local number range color".split(" "))}var d="2.6.1",e={},f=!0,g=b.documentElement,h="modernizr",i=b.createElement(h),j=i.style,k=b.createElement("input"),l=":)",m={}.toString,n=" -webkit- -moz- -o- -ms- ".split(" "),o="Webkit Moz O ms",p=o.split(" "),q=o.toLowerCase().split(" "),r={svg:"http://www.w3.org/2000/svg"},s={},t={},u={},v=[],w=v.slice,x,y=function(a,c,d,e){var f,i,j,k=b.createElement("div"),l=b.body,m=l?l:b.createElement("body");if(parseInt(d,10))while(d--)j=b.createElement("div"),j.id=e?e[d]:h+(d+1),k.appendChild(j);return f=["­",'<style id="s',h,'">',a,"
</style>"].join(""),k.id=h,(l?k:m).innerHTML+=f,m.appendChild(k),l||(m.style.background="",g.appendChild(m)),i=c(k,a),l?k.parentNode.removeChild(k):m.parentNode.removeChild(m),!!i},z=function(b){var c=a.matchMedia||a.msMatchMedia;if(c)return c(b).matches;var d;return y("@media "+b+" { #"+h+" { position: absolute; } }",function(b){d=(a.getComputedStyle?getComputedStyle(b,null):b.currentStyle)["position"]=="absolute"}),d},A=function(){function d(d,e){e=e||b.createElement(a[d]||"div"),d="on"+d;var f=d in e;return f||(e.setAttribute||(e=b.createElement("div")),e.setAttribute&&e.removeAttribute&&(e.setAttribute(d,""),f=F(e[d],"function"),F(e[d],"undefined")||(e[d]=c),e.removeAttribute(d))),e=null,f}var a={select:"input",change:"input",submit:"form",reset:"form",error:"img",load:"img",abort:"img"};return d}(),B={}.hasOwnProperty,C;!F(B,"undefined")&&!F(B.call,"undefined")?C=function(a,b){return B.call(a,b)}:C=function(a,b){return b in a&&F(a.constructor.prototype[b],"undefined")},Function
.prototype.bind||(Function.prototype.bind=function(b){var c=this;if(typeof c!="function")throw new TypeError;var d=w.call(arguments,1),e=function(){if(this instanceof e){var a=function(){};a.prototype=c.prototype;var f=new a,g=c.apply(f,d.concat(w.call(arguments)));return Object(g)===g?g:f}return c.apply(b,d.concat(w.call(arguments)))};return e}),s.flexbox=function(){return J("flexWrap")},s.canvas=function(){var a=b.createElement("canvas");return!!a.getContext&&!!a.getContext("2d")},s.canvastext=function(){return!!e.canvas&&!!F(b.createElement("canvas").getContext("2d").fillText,"function")},s.webgl=function(){return!!a.WebGLRenderingContext},s.touch=function(){var c;return"ontouchstart"in a||a.DocumentTouch&&b instanceof DocumentTouch?c=!0:y(["@media (",n.join("touch-enabled),("),h,")","{#modernizr{top:9px;position:absolute}}"].join(""),function(a){c=a.offsetTop===9}),c},s.geolocation=function(){return"geolocation"in navigator},s.postmessage=function(){return!!a.postMessage},s.webs
qldatabase=function(){return!!a.openDatabase},s.indexedDB=function(){return!!J("indexedDB",a)},s.hashchange=function(){return A("hashchange",a)&&(b.documentMode===c||b.documentMode>7)},s.history=function(){return!!a.history&&!!history.pushState},s.draganddrop=function(){var a=b.createElement("div");return"draggable"in a||"ondragstart"in a&&"ondrop"in a},s.websockets=function(){return"WebSocket"in a||"MozWebSocket"in a},s.rgba=function(){return D("background-color:rgba(150,255,150,.5)"),G(j.backgroundColor,"rgba")},s.hsla=function(){return D("background-color:hsla(120,40%,100%,.5)"),G(j.backgroundColor,"rgba")||G(j.backgroundColor,"hsla")},s.multiplebgs=function(){return D("background:url(https://),url(https://),red url(https://)"),/(url\s*\(.*?){3}/.test(j.background)},s.backgroundsize=function(){return J("backgroundSize")},s.borderimage=function(){return J("borderImage")},s.borderradius=function(){return J("borderRadius")},s.boxshadow=function(){return J("boxShadow")},s.textshadow=
function(){return b.createElement("div").style.textShadow===""},s.opacity=function(){return E("opacity:.55"),/^0.55$/.test(j.opacity)},s.cssanimations=function(){return J("animationName")},s.csscolumns=function(){return J("columnCount")},s.cssgradients=function(){var a="background-image:",b="gradient(linear,left top,right bottom,from(#9f9),to(white));",c="linear-gradient(left top,#9f9, white);";return D((a+"-webkit- ".split(" ").join(b+a)+n.join(c+a)).slice(0,-a.length)),G(j.backgroundImage,"gradient")},s.cssreflections=function(){return J("boxReflect")},s.csstransforms=function(){return!!J("transform")},s.csstransforms3d=function(){var a=!!J("perspective");return a&&"webkitPerspective"in g.style&&y("@media (transform-3d),(-webkit-transform-3d){#modernizr{left:9px;position:absolute;height:3px;}}",function(b,c){a=b.offsetLeft===9&&b.offsetHeight===3}),a},s.csstransitions=function(){return J("transition")},s.fontface=function(){var a;return y('@font-face {font-family:"font";src:url("h
ttps://")}',function(c,d){var e=b.getElementById("smodernizr"),f=e.sheet||e.styleSheet,g=f?f.cssRules&&f.cssRules[0]?f.cssRules[0].cssText:f.cssText||"":"";a=/src/i.test(g)&&g.indexOf(d.split(" ")[0])===0}),a},s.generatedcontent=function(){var a;return y(['#modernizr:after{content:"',l,'";visibility:hidden}'].join(""),function(b){a=b.offsetHeight>=1}),a},s.video=function(){var a=b.createElement("video"),c=!1;try{if(c=!!a.canPlayType)c=new Boolean(c),c.ogg=a.canPlayType('video/ogg; codecs="theora"').replace(/^no$/,""),c.h264=a.canPlayType('video/mp4; codecs="avc1.42E01E"').replace(/^no$/,""),c.webm=a.canPlayType('video/webm; codecs="vp8, vorbis"').replace(/^no$/,"")}catch(d){}return c},s.audio=function(){var a=b.createElement("audio"),c=!1;try{if(c=!!a.canPlayType)c=new Boolean(c),c.ogg=a.canPlayType('audio/ogg; codecs="vorbis"').replace(/^no$/,""),c.mp3=a.canPlayType("audio/mpeg;").replace(/^no$/,""),c.wav=a.canPlayType('audio/wav; codecs="1"').replace(/^no$/,""),c.m4a=(a.canPlayTyp
e("audio/x-m4a;")||a.canPlayType("audio/aac;")).replace(/^no$/,"")}catch(d){}return c},s.localstorage=function(){try{return localStorage.setItem(h,h),localStorage.removeItem(h),!0}catch(a){return!1}},s.sessionstorage=function(){try{return sessionStorage.setItem(h,h),sessionStorage.removeItem(h),!0}catch(a){return!1}},s.webworkers=function(){return!!a.Worker},s.applicationcache=function(){return!!a.applicationCache},s.svg=function(){return!!b.createElementNS&&!!b.createElementNS(r.svg,"svg").createSVGRect},s.inlinesvg=function(){var a=b.createElement("div");return a.innerHTML="<svg/>",(a.firstChild&&a.firstChild.namespaceURI)==r.svg},s.smil=function(){return!!b.createElementNS&&/SVGAnimate/.test(m.call(b.createElementNS(r.svg,"animate")))},s.svgclippaths=function(){return!!b.createElementNS&&/SVGClipPath/.test(m.call(b.createElementNS(r.svg,"clipPath")))};for(var L in s)C(s,L)&&(x=L.toLowerCase(),e[x]=s[L](),v.push((e[x]?"":"no-")+x));return e.input||K(),e.addTest=function(a,b){if(ty
peof a=="object")for(var d in a)C(a,d)&&e.addTest(d,a[d]);else{a=a.toLowerCase();if(e[a]!==c)return e;b=typeof b=="function"?b():b,f&&(g.className+=" "+(b?"":"no-")+a),e[a]=b}return e},D(""),i=k=null,function(a,b){function k(a,b){var c=a.createElement("p"),d=a.getElementsByTagName("head")[0]||a.documentElement;return c.innerHTML="x<style>"+b+"</style>",d.insertBefore(c.lastChild,d.firstChild)}function l(){var a=r.elements;return typeof a=="string"?a.split(" "):a}function m(a){var b=i[a[g]];return b||(b={},h++,a[g]=h,i[h]=b),b}function n(a,c,f){c||(c=b);if(j)return c.createElement(a);f||(f=m(c));var g;return f.cache[a]?g=f.cache[a].cloneNode():e.test(a)?g=(f.cache[a]=f.createElem(a)).cloneNode():g=f.createElem(a),g.canHaveChildren&&!d.test(a)?f.frag.appendChild(g):g}function o(a,c){a||(a=b);if(j)return a.createDocumentFragment();c=c||m(a);var d=c.frag.cloneNode(),e=0,f=l(),g=f.length;for(;e<g;e++)d.createElement(f[e]);return d}function p(a,b){b.cache||(b.cache={},b.createElem=a.creat
eElement,b.createFrag=a.createDocumentFragment,b.frag=b.createFrag()),a.createElement=function(c){return r.shivMethods?n(c,a,b):b.createElem(c)},a.createDocumentFragment=Function("h,f","return function(){var n=f.cloneNode(),c=n.createElement;h.shivMethods&&("+l().join().replace(/\w+/g,function(a){return b.createElem(a),b.frag.createElement(a),'c("'+a+'")'})+");return n}")(r,b.frag)}function q(a){a||(a=b);var c=m(a);return r.shivCSS&&!f&&!c.hasCSS&&(c.hasCSS=!!k(a,"article,aside,figcaption,figure,footer,header,hgroup,nav,section{display:block}mark{background:#FF0;color:#000}")),j||p(a,c),a}var c=a.html5||{},d=/^<|^(?:button|map|select|textarea|object|iframe|option|optgroup)$/i,e=/^<|^(?:a|b|button|code|div|fieldset|form|h1|h2|h3|h4|h5|h6|i|iframe|img|input|label|li|link|ol|option|p|param|q|script|select|span|strong|style|table|tbody|td|textarea|tfoot|th|thead|tr|ul)$/i,f,g="_html5shiv",h=0,i={},j;(function(){try{var a=b.createElement("a");a.innerHTML="<xyz></xyz>",f="hidden"in a,j=a.
childNodes.length==1||function(){b.createElement("a");var a=b.createDocumentFragment();return typeof a.cloneNode=="undefined"||typeof a.createDocumentFragment=="undefined"||typeof a.createElement=="undefined"}()}catch(c){f=!0,j=!0}})();var r={elements:c.elements||"abbr article aside audio bdi canvas data datalist details figcaption figure footer header hgroup mark meter nav output progress section summary time video",shivCSS:c.shivCSS!==!1,supportsUnknownElements:j,shivMethods:c.shivMethods!==!1,type:"default",shivDocument:q,createElement:n,createDocumentFragment:o};a.html5=r,q(b)}(this,b),e._version=d,e._prefixes=n,e._domPrefixes=q,e._cssomPrefixes=p,e.mq=z,e.hasEvent=A,e.testProp=function(a){return H([a])},e.testAllProps=J,e.testStyles=y,e.prefixed=function(a,b,c){return b?J(a,b,c):J(a,"pfx")},g.className=g.className.replace(/(^|\s)no-js(\s|$)/,"$1$2")+(f?" js "+v.join(" "):""),e}(this,this.document),function(a,b,c){function d(a){return o.call(a)=="[object Function]"}function e(a)
{return typeof a=="string"}function f(){}function g(a){return!a||a=="loaded"||a=="complete"||a=="uninitialized"}function h(){var a=p.shift();q=1,a?a.t?m(function(){(a.t=="c"?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){a!="img"&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l={},o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};y[c]===1&&(r=1,y[c]=[],l=b.createElement(a)),a=="object"?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),a!="img"&&(r||y[c]===2?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i(b=="c"?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),p.length==1&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTi
meout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&o.call(a.opera)=="[object Opera]",l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return o.call(a)=="[object Array]"},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,i){var j=b(a),l=j.autoCallback;j.url.split(".").pop().split("?").shift(),j.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]||h),j.instead?j.instead(a,e,f,g,i):(y[j.url]?j.noexec=!0:y[j.url]=1,f.load(j.url,j.forceCSS||!j.forceJS&&"css"==j.url.split(".").pop().split("?").shift()?"c":c,j.noexec,j.attrs,j.timeout),(d(e)||d(l))&&f.load(functio
n(){k(),e&&e(j.origUrl,i,g),l&&l(j.origUrl,i,g),y[j.url]=2})))}function i(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var j,l,m=this.yepnope.loader;if(e(a))g(a,0,m,0);else if(w(a))for(j=0;j<a.length;j++)l=a[j],e(l)?g(l,0,m,0):w(l)?B(l):Object(l)===l&&i(l,m);else Object(a)===a&&i(a,m)},B.addPrefix=function(a,b){z[a]=b},B.addFilter=function(a){x.push(a)},B.errorTimeout=1e4,b.readyState==null&&b.addEventListener&&(b.readyState="loading",b.addEventListener("DOMContentLoaded",A=function(
){b.removeEventListener("DOMContentLoaded",A,0),b.readyState="complete"},0)),a.yepnope=k(),a.yepnope.executeStack=h,a.yepnope.injectJs=function(a,c,d,e,i,j){var k=b.createElement("script"),l,o,e=e||B.errorTimeout;k.src=a;for(o in d)k.setAttribute(o,d[o]);c=j?h:c||f,k.onreadystatechange=k.onload=function(){!l&&g(k.readyState)&&(l=1,c(),k.onload=k.onreadystatechange=null)},m(function(){l||(l=1,c(1))},e),i?k.onload():n.parentNode.insertBefore(k,n)},a.yepnope.injectCss=function(a,c,d,e,g,i){var e=b.createElement("link"),j,c=i?h:c||f;e.href=a,e.rel="stylesheet",e.type="text/css";for(j in d)e.setAttribute(j,d[j]);g||(n.parentNode.insertBefore(e,n),m(c,0))}}(this,document),Modernizr.load=function(){yepnope.apply(window,[].slice.call(arguments,0))};
+
+/*! matchMedia() polyfill - Test a CSS media type/query in JS. Authors & copyright (c) 2012: Scott Jehl, Paul Irish, Nicholas Zakas. Dual MIT/BSD license */
+/*! NOTE: If you're already including a window.matchMedia polyfill via Modernizr or otherwise, you don't need this part */
+window.matchMedia=window.matchMedia||(function(e,f){var c,a=e.documentElement,b=a.firstElementChild||a.firstChild,d=e.createElement("body"),g=e.createElement("div");g.id="mq-test-1";g.style.cssText="position:absolute;top:-100em";d.style.background="none";d.appendChild(g);return function(h){g.innerHTML='­<style media="'+h+'"> #mq-test-1 { width: 42px; }</style>';a.insertBefore(d,b);c=g.offsetWidth==42;a.removeChild(d);return{matches:c,media:h}}})(document);
+
+/*! Respond.js v1.1.0: min/max-width media query polyfill. (c) Scott Jehl. MIT/GPLv2 Lic. j.mp/respondjs */
+(function(e){e.respond={};respond.update=function(){};respond.mediaQueriesSupported=e.matchMedia&&e.matchMedia("only all").matches;if(respond.mediaQueriesSupported){return}var w=e.document,s=w.documentElement,i=[],k=[],q=[],o={},h=30,f=w.getElementsByTagName("head")[0]||s,g=w.getElementsByTagName("base")[0],b=f.getElementsByTagName("link"),d=[],a=function(){var D=b,y=D.length,B=0,A,z,C,x;for(;B<y;B++){A=D[B],z=A.href,C=A.media,x=A.rel&&A.rel.toLowerCase()==="stylesheet";if(!!z&&x&&!o[z]){if(A.styleSheet&&A.styleSheet.rawCssText){m(A.styleSheet.rawCssText,z,C);o[z]=true}else{if((!/^([a-zA-Z:]*\/\/)/.test(z)&&!g)||z.replace(RegExp.$1,"").split("/")[0]===e.location.host){d.push({href:z,media:C})}}}}u()},u=function(){if(d.length){var x=d.shift();n(x.href,function(y){m(y,x.href,x.media);o[x.href]=true;u()})}},m=function(I,x,z){var G=I.match(/@media[^\{]+\{([^\{\}]*\{[^\}\{]*\})+/gi),J=G&&G.length||0,x=x.substring(0,x.lastIndexOf("/")),y=function(K){return K.replace(/(url\()['"]?([^\/\)'"
][^:\)'"]+)['"]?(\))/g,"$1"+x+"$2$3")},A=!J&&z,D=0,C,E,F,B,H;if(x.length){x+="/"}if(A){J=1}for(;D<J;D++){C=0;if(A){E=z;k.push(y(I))}else{E=G[D].match(/@media *([^\{]+)\{([\S\s]+?)$/)&&RegExp.$1;k.push(RegExp.$2&&y(RegExp.$2))}B=E.split(",");H=B.length;for(;C<H;C++){F=B[C];i.push({media:F.split("(")[0].match(/(only\s+)?([a-zA-Z]+)\s?/)&&RegExp.$2||"all",rules:k.length-1,hasquery:F.indexOf("(")>-1,minw:F.match(/\(min\-width:[\s]*([\s]*[0-9\.]+)(px|em)[\s]*\)/)&&parseFloat(RegExp.$1)+(RegExp.$2||""),maxw:F.match(/\(max\-width:[\s]*([\s]*[0-9\.]+)(px|em)[\s]*\)/)&&parseFloat(RegExp.$1)+(RegExp.$2||"")})}}j()},l,r,v=function(){var z,A=w.createElement("div"),x=w.body,y=false;A.style.cssText="position:absolute;font-size:1em;width:1em";if(!x){x=y=w.createElement("body");x.style.background="none"}x.appendChild(A);s.insertBefore(x,s.firstChild);z=A.offsetWidth;if(y){s.removeChild(x)}else{x.removeChild(A)}z=p=parseFloat(z);return z},p,j=function(I){var x="clientWidth",B=s[x],H=w.compatMode==="
CSS1Compat"&&B||w.body[x]||B,D={},G=b[b.length-1],z=(new Date()).getTime();if(I&&l&&z-l<h){clearTimeout(r);r=setTimeout(j,h);return}else{l=z}for(var E in i){var K=i[E],C=K.minw,J=K.maxw,A=C===null,L=J===null,y="em";if(!!C){C=parseFloat(C)*(C.indexOf(y)>-1?(p||v()):1)}if(!!J){J=parseFloat(J)*(J.indexOf(y)>-1?(p||v()):1)}if(!K.hasquery||(!A||!L)&&(A||H>=C)&&(L||H<=J)){if(!D[K.media]){D[K.media]=[]}D[K.media].push(k[K.rules])}}for(var E in q){if(q[E]&&q[E].parentNode===f){f.removeChild(q[E])}}for(var E in D){var M=w.createElement("style"),F=D[E].join("\n");M.type="text/css";M.media=E;f.insertBefore(M,G.nextSibling);if(M.styleSheet){M.styleSheet.cssText=F}else{M.appendChild(w.createTextNode(F))}q.push(M)}},n=function(x,z){var y=c();if(!y){return}y.open("GET",x,true);y.onreadystatechange=function(){if(y.readyState!=4||y.status!=200&&y.status!=304){return}z(y.responseText)};if(y.readyState==4){return}y.send(null)},c=(function(){var x=false;try{x=new XMLHttpRequest()}catch(y){x=new ActiveX
Object("Microsoft.XMLHTTP")}return function(){return x}})();a();respond.update=a;function t(){j(true)}if(e.addEventListener){e.addEventListener("resize",t,false)}else{if(e.attachEvent){e.attachEvent("onresize",t)}}})(this);
\ No newline at end of file
Propchange: dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/js/vendor/modernizr-2.6.1-respond-1.1.0.min.js
------------------------------------------------------------------------------
svn:executable = *
Added: dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/mllib-guide.html
==============================================================================
--- dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/mllib-guide.html (added)
+++ dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/mllib-guide.html Wed Sep 25 00:14:43 2013
@@ -0,0 +1,390 @@
+<!DOCTYPE html>
+<!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
+<!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]-->
+<!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]-->
+ <head>
+ <meta charset="utf-8">
+ <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
+ <title>Machine Learning Library (MLlib) - Spark 0.8.0 Documentation</title>
+ <meta name="description" content="">
+
+ <link rel="stylesheet" href="css/bootstrap.min.css">
+ <style>
+ body {
+ padding-top: 60px;
+ padding-bottom: 40px;
+ }
+ </style>
+ <meta name="viewport" content="width=device-width">
+ <link rel="stylesheet" href="css/bootstrap-responsive.min.css">
+ <link rel="stylesheet" href="css/main.css">
+
+ <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script>
+
+ <link rel="stylesheet" href="css/pygments-default.css">
+
+ <!-- Google analytics script -->
+ <script type="text/javascript">
+ /*
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _gaq.push(['_trackPageview']);
+
+ (function() {
+ var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+ ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+ var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+ })();
+ */
+ </script>
+
+ </head>
+ <body>
+ <!--[if lt IE 7]>
+ <p class="chromeframe">You are using an outdated browser. <a href="http://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p>
+ <![endif]-->
+
+ <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html -->
+
+ <div class="navbar navbar-fixed-top" id="topbar">
+ <div class="navbar-inner">
+ <div class="container">
+ <div class="brand"><a href="index.html">
+ <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">0.8.0</span>
+ </div>
+ <ul class="nav">
+ <!--TODO(andyk): Add class="active" attribute to li some how.-->
+ <li><a href="index.html">Overview</a></li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="quick-start.html">Quick Start</a></li>
+ <li><a href="scala-programming-guide.html">Spark in Scala</a></li>
+ <li><a href="java-programming-guide.html">Spark in Java</a></li>
+ <li><a href="python-programming-guide.html">Spark in Python</a></li>
+ <li class="divider"></li>
+ <li><a href="streaming-programming-guide.html">Spark Streaming</a></li>
+ <li><a href="mllib-guide.html">MLlib (Machine Learning)</a></li>
+ <li><a href="bagel-programming-guide.html">Bagel (Pregel on Spark)</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">API Docs<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="api/core/index.html">Spark Core for Java/Scala</a></li>
+ <li><a href="api/pyspark/index.html">Spark Core for Python</a></li>
+ <li class="divider"></li>
+ <li><a href="api/streaming/index.html">Spark Streaming</a></li>
+ <li><a href="api/mllib/index.html">MLlib (Machine Learning)</a></li>
+ <li><a href="api/bagel/index.html">Bagel (Pregel on Spark)</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="cluster-overview.html">Overview</a></li>
+ <li><a href="ec2-scripts.html">Amazon EC2</a></li>
+ <li><a href="spark-standalone.html">Standalone Mode</a></li>
+ <li><a href="running-on-mesos.html">Mesos</a></li>
+ <li><a href="running-on-yarn.html">YARN</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="configuration.html">Configuration</a></li>
+ <li><a href="monitoring.html">Monitoring</a></li>
+ <li><a href="tuning.html">Tuning Guide</a></li>
+ <li><a href="hadoop-third-party-distributions.html">Running with CDH/HDP</a></li>
+ <li><a href="hardware-provisioning.html">Hardware Provisioning</a></li>
+ <li><a href="job-scheduling.html">Job Scheduling</a></li>
+ <li class="divider"></li>
+ <li><a href="building-with-maven.html">Building Spark with Maven</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li>
+ </ul>
+ </li>
+ </ul>
+ <!--<p class="navbar-text pull-right"><span class="version-text">v0.8.0</span></p>-->
+ </div>
+ </div>
+ </div>
+
+ <div class="container" id="content">
+ <h1 class="title">Machine Learning Library (MLlib)</h1>
+
+ <p>MLlib is a Spark implementation of some common machine learning (ML)
+functionality, as well associated tests and data generators. MLlib
+currently supports four common types of machine learning problem settings,
+namely, binary classification, regression, clustering and collaborative
+filtering, as well as an underlying gradient descent optimization primitive.
+This guide will outline the functionality supported in MLlib and also provides
+an example of invoking MLlib.</p>
+
+<h1 id="dependencies">Dependencies</h1>
+<p>MLlib uses the <a href="https://github.com/mikiobraun/jblas">jblas</a> linear algebra library, which itself
+depends on native Fortran routines. You may need to install the
+<a href="https://github.com/mikiobraun/jblas/wiki/Missing-Libraries">gfortran runtime library</a>
+if it is not already present on your nodes. MLlib will throw a linking error if it cannot
+detect these libraries automatically.</p>
+
+<h1 id="binary-classification">Binary Classification</h1>
+
+<p>Binary classification is a supervised learning problem in which we want to
+classify entities into one of two distinct categories or labels, e.g.,
+predicting whether or not emails are spam. This problem involves executing a
+learning <em>Algorithm</em> on a set of <em>labeled</em> examples, i.e., a set of entities
+represented via (numerical) features along with underlying category labels.
+The algorithm returns a trained <em>Model</em> that can predict the label for new
+entities for which the underlying label is unknown. </p>
+
+<p>MLlib currently supports two standard model families for binary classification,
+namely <a href="http://en.wikipedia.org/wiki/Support_vector_machine">Linear Support Vector Machines
+(SVMs)</a> and <a href="http://en.wikipedia.org/wiki/Logistic_regression">Logistic
+Regression</a>, along with <a href="http://en.wikipedia.org/wiki/Regularization_(mathematics)">L1
+and L2 regularized</a>
+variants of each model family. The training algorithms all leverage an
+underlying gradient descent primitive (described
+<a href="#gradient-descent-primitive">below</a>), and take as input a regularization
+parameter (<em>regParam</em>) along with various parameters associated with gradient
+descent (<em>stepSize</em>, <em>numIterations</em>, <em>miniBatchFraction</em>). </p>
+
+<p>The following code snippet illustrates how to load a sample dataset, execute a
+training algorithm on this training data using a static method in the algorithm
+object, and make predictions with the resulting model to compute the training
+error.</p>
+
+<div class="highlight"><pre><code class="scala"><span class="k">import</span> <span class="nn">org.apache.spark.SparkContext</span>
+<span class="k">import</span> <span class="nn">org.apache.spark.mllib.classification.SVMWithSGD</span>
+<span class="k">import</span> <span class="nn">org.apache.spark.mllib.regression.LabeledPoint</span>
+
+<span class="c1">// Load and parse the data file</span>
+<span class="k">val</span> <span class="n">data</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">"mllib/data/sample_svm_data.txt"</span><span class="o">)</span>
+<span class="k">val</span> <span class="n">parsedData</span> <span class="k">=</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="n">line</span> <span class="k">=></span>
+ <span class="k">val</span> <span class="n">parts</span> <span class="k">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="o">(</span><span class="sc">' '</span><span class="o">)</span>
+ <span class="nc">LabeledPoint</span><span class="o">(</span><span class="n">parts</span><span class="o">(</span><span class="mi">0</span><span class="o">).</span><span class="n">toDouble</span><span class="o">,</span> <span class="n">parts</span><span class="o">.</span><span class="n">tail</span><span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">x</span> <span class="k">=></span> <span class="n">x</span><span class="o">.</span><span class="n">toDouble</span><span class="o">).</span><span class="n">toArray</span><span class="o">)</span>
+<span class="o">}</span>
+
+<span class="c1">// Run training algorithm</span>
+<span class="k">val</span> <span class="n">numIterations</span> <span class="k">=</span> <span class="mi">20</span>
+<span class="k">val</span> <span class="n">model</span> <span class="k">=</span> <span class="nc">SVMWithSGD</span><span class="o">.</span><span class="n">train</span><span class="o">(</span><span class="n">parsedData</span><span class="o">,</span> <span class="n">numIterations</span><span class="o">)</span>
+
+<span class="c1">// Evaluate model on training examples and compute training error</span>
+<span class="k">val</span> <span class="n">labelAndPreds</span> <span class="k">=</span> <span class="n">parsedData</span><span class="o">.</span><span class="n">map</span> <span class="o">{</span> <span class="n">point</span> <span class="k">=></span>
+ <span class="k">val</span> <span class="n">prediction</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="o">(</span><span class="n">point</span><span class="o">.</span><span class="n">features</span><span class="o">)</span>
+ <span class="o">(</span><span class="n">point</span><span class="o">.</span><span class="n">label</span><span class="o">,</span> <span class="n">prediction</span><span class="o">)</span>
+<span class="o">}</span>
+<span class="k">val</span> <span class="n">trainErr</span> <span class="k">=</span> <span class="n">labelAndPreds</span><span class="o">.</span><span class="n">filter</span><span class="o">(</span><span class="n">r</span> <span class="k">=></span> <span class="n">r</span><span class="o">.</span><span class="n">_1</span> <span class="o">!=</span> <span class="n">r</span><span class="o">.</span><span class="n">_2</span><span class="o">).</span><span class="n">count</span><span class="o">.</span><span class="n">toDouble</span> <span class="o">/</span> <span class="n">parsedData</span><span class="o">.</span><span class="n">count</span>
+<span class="n">println</span><span class="o">(</span><span class="s">"trainError = "</span> <span class="o">+</span> <span class="n">trainErr</span><span class="o">)</span>
+</code></pre></div>
+
+<p>The <code>SVMWithSGD.train()</code> method by default performs L2 regularization with the
+regularization parameter set to 1.0. If we want to configure this algorithm, we
+can customize <code>SVMWithSGD</code> further by creating a new object directly and
+calling setter methods. All other MLlib algorithms support customization in
+this way as well. For example, the following code produces an L1 regularized
+variant of SVMs with regularization parameter set to 0.1, and runs the training
+algorithm for 200 iterations. </p>
+
+<div class="highlight"><pre><code class="scala"><span class="k">import</span> <span class="nn">org.apache.spark.mllib.optimization.L1Updater</span>
+
+<span class="k">val</span> <span class="n">svmAlg</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">SVMWithSGD</span><span class="o">()</span>
+<span class="n">svmAlg</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">setNumIterations</span><span class="o">(</span><span class="mi">200</span><span class="o">)</span>
+ <span class="o">.</span><span class="n">setRegParam</span><span class="o">(</span><span class="mf">0.1</span><span class="o">)</span>
+ <span class="o">.</span><span class="n">setUpdater</span><span class="o">(</span><span class="k">new</span> <span class="n">L1Updater</span><span class="o">)</span>
+<span class="k">val</span> <span class="n">modelL1</span> <span class="k">=</span> <span class="n">svmAlg</span><span class="o">.</span><span class="n">run</span><span class="o">(</span><span class="n">parsedData</span><span class="o">)</span>
+</code></pre></div>
+
+<p>Both of the code snippets above can be executed in <code>spark-shell</code> to generate a
+classifier for the provided dataset.</p>
+
+<p>Available algorithms for binary classification:</p>
+
+<ul>
+ <li><a href="api/mllib/index.html#org.apache.spark.mllib.classification.SVMWithSGD">SVMWithSGD</a></li>
+ <li><a href="api/mllib/index.html#org.apache.spark.mllib.classification.LogisticRegressionWithSGD">LogisticRegressionWithSGD</a></li>
+</ul>
+
+<h1 id="linear-regression">Linear Regression</h1>
+
+<p>Linear regression is another classical supervised learning setting. In this
+problem, each entity is associated with a real-valued label (as opposed to a
+binary label as in binary classification), and we want to predict labels as
+closely as possible given numerical features representing entities. MLlib
+supports linear regression as well as L1
+(<a href="http://en.wikipedia.org/wiki/Lasso_(statistics)#Lasso_method">lasso</a>) and L2
+(<a href="http://en.wikipedia.org/wiki/Ridge_regression">ridge</a>) regularized variants.
+The regression algorithms in MLlib also leverage the underlying gradient
+descent primitive (described <a href="#gradient-descent-primitive">below</a>), and have
+the same parameters as the binary classification algorithms described above. </p>
+
+<p>Available algorithms for linear regression: </p>
+
+<ul>
+ <li><a href="api/mllib/index.html#org.apache.spark.mllib.regression.LinearRegressionWithSGD">LinearRegressionWithSGD</a></li>
+ <li><a href="api/mllib/index.html#org.apache.spark.mllib.regression.RidgeRegressionWithSGD">RidgeRegressionWithSGD</a></li>
+ <li><a href="api/mllib/index.html#org.apache.spark.mllib.regression.LassoWithSGD">LassoWithSGD</a></li>
+</ul>
+
+<h1 id="clustering">Clustering</h1>
+
+<p>Clustering is an unsupervised learning problem whereby we aim to group subsets
+of entities with one another based on some notion of similarity. Clustering is
+often used for exploratory analysis and/or as a component of a hierarchical
+supervised learning pipeline (in which distinct classifiers or regression
+models are trained for each cluster). MLlib supports
+<a href="http://en.wikipedia.org/wiki/K-means_clustering">k-means</a> clustering, arguably
+the most commonly used clustering approach that clusters the data points into
+<em>k</em> clusters. The MLlib implementation includes a parallelized
+variant of the <a href="http://en.wikipedia.org/wiki/K-means%2B%2B">k-means++</a> method
+called <a href="http://theory.stanford.edu/~sergei/papers/vldb12-kmpar.pdf">kmeans||</a>.
+The implementation in MLlib has the following parameters: </p>
+
+<ul>
+ <li><em>k</em> is the number of clusters.</li>
+ <li><em>maxIterations</em> is the maximum number of iterations to run.</li>
+ <li><em>initializationMode</em> specifies either random initialization or
+initialization via k-means||.</li>
+ <li><em>runs</em> is the number of times to run the k-means algorithm (k-means is not
+guaranteed to find a globally optimal solution, and when run multiple times on
+a given dataset, the algorithm returns the best clustering result).</li>
+ <li><em>initializiationSteps</em> determines the number of steps in the k-means|| algorithm.</li>
+ <li><em>epsilon</em> determines the distance threshold within which we consider k-means to have converged. </li>
+</ul>
+
+<p>Available algorithms for clustering: </p>
+
+<ul>
+ <li><a href="api/mllib/index.html#org.apache.spark.mllib.clustering.KMeans">KMeans</a></li>
+</ul>
+
+<h1 id="collaborative-filtering">Collaborative Filtering</h1>
+
+<p><a href="http://en.wikipedia.org/wiki/Recommender_system#Collaborative_filtering">Collaborative
+filtering</a>
+is commonly used for recommender systems. These techniques aim to fill in the
+missing entries of a user-product association matrix. MLlib currently supports
+model-based collaborative filtering, in which users and products are described
+by a small set of latent factors that can be used to predict missing entries.
+In particular, we implement the <a href="http://www2.research.att.com/~volinsky/papers/ieeecomputer.pdf">alternating least squares
+(ALS)</a>
+algorithm to learn these latent factors. The implementation in MLlib has the
+following parameters:</p>
+
+<ul>
+ <li><em>numBlocks</em> is the number of blacks used to parallelize computation (set to -1 to auto-configure). </li>
+ <li><em>rank</em> is the number of latent factors in our model.</li>
+ <li><em>iterations</em> is the number of iterations to run.</li>
+ <li><em>lambda</em> specifies the regularization parameter in ALS. </li>
+</ul>
+
+<p>Available algorithms for collaborative filtering: </p>
+
+<ul>
+ <li><a href="api/mllib/index.html#org.apache.spark.mllib.recommendation.ALS">ALS</a></li>
+</ul>
+
+<h1 id="gradient-descent-primitive">Gradient Descent Primitive</h1>
+
+<p><a href="http://en.wikipedia.org/wiki/Gradient_descent">Gradient descent</a> (along with
+stochastic variants thereof) are first-order optimization methods that are
+well-suited for large-scale and distributed computation. Gradient descent
+methods aim to find a local minimum of a function by iteratively taking steps
+in the direction of the negative gradient of the function at the current point,
+i.e., the current parameter value. Gradient descent is included as a low-level
+primitive in MLlib, upon which various ML algorithms are developed, and has the
+following parameters:</p>
+
+<ul>
+ <li><em>gradient</em> is a class that computes the stochastic gradient of the function
+being optimized, i.e., with respect to a single training example, at the
+current parameter value. MLlib includes gradient classes for common loss
+functions, e.g., hinge, logistic, least-squares. The gradient class takes as
+input a training example, its label, and the current parameter value. </li>
+ <li><em>updater</em> is a class that updates weights in each iteration of gradient
+descent. MLlib includes updaters for cases without regularization, as well as
+L1 and L2 regularizers.</li>
+ <li><em>stepSize</em> is a scalar value denoting the initial step size for gradient
+descent. All updaters in MLlib use a step size at the t-th step equal to
+stepSize / sqrt(t). </li>
+ <li><em>numIterations</em> is the number of iterations to run.</li>
+ <li><em>regParam</em> is the regularization parameter when using L1 or L2 regularization.</li>
+ <li><em>miniBatchFraction</em> is the fraction of the data used to compute the gradient
+at each iteration.</li>
+</ul>
+
+<p>Available algorithms for gradient descent:</p>
+
+<ul>
+ <li><a href="api/mllib/index.html#org.apache.spark.mllib.optimization.GradientDescent">GradientDescent</a></li>
+</ul>
+
+ <!-- Main hero unit for a primary marketing message or call to action -->
+ <!--<div class="hero-unit">
+ <h1>Hello, world!</h1>
+ <p>This is a template for a simple marketing or informational website. It includes a large callout called the hero unit and three supporting pieces of content. Use it as a starting point to create something more unique.</p>
+ <p><a class="btn btn-primary btn-large">Learn more »</a></p>
+ </div>-->
+
+ <!-- Example row of columns -->
+ <!--<div class="row">
+ <div class="span4">
+ <h2>Heading</h2>
+ <p>Donec id elit non mi porta gravida at eget metus. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet risus. Etiam porta sem malesuada magna mollis euismod. Donec sed odio dui. </p>
+ <p><a class="btn" href="#">View details »</a></p>
+ </div>
+ <div class="span4">
+ <h2>Heading</h2>
+ <p>Donec id elit non mi porta gravida at eget metus. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet risus. Etiam porta sem malesuada magna mollis euismod. Donec sed odio dui. </p>
+ <p><a class="btn" href="#">View details »</a></p>
+ </div>
+ <div class="span4">
+ <h2>Heading</h2>
+ <p>Donec sed odio dui. Cras justo odio, dapibus ac facilisis in, egestas eget quam. Vestibulum id ligula porta felis euismod semper. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet risus.</p>
+ <p><a class="btn" href="#">View details »</a></p>
+ </div>
+ </div>
+
+ <hr>-->
+
+ <footer>
+ <hr>
+ <p style="text-align: center; veritcal-align: middle; color: #999;">
+ Apache Spark is an effort undergoing incubation at the Apache Software Foundation.
+ <a href="http://incubator.apache.org">
+ <img style="margin-left: 20px;" src="img/incubator-logo.png" />
+ </a>
+ </p>
+ </footer>
+
+ </div> <!-- /container -->
+
+ <script src="js/vendor/jquery-1.8.0.min.js"></script>
+ <script src="js/vendor/bootstrap.min.js"></script>
+ <script src="js/main.js"></script>
+
+ <!-- A script to fix internal hash links because we have an overlapping top bar.
+ Based on https://github.com/twitter/bootstrap/issues/193#issuecomment-2281510 -->
+ <script>
+ $(function() {
+ function maybeScrollToHash() {
+ if (window.location.hash && $(window.location.hash).length) {
+ var newTop = $(window.location.hash).offset().top - $('#topbar').height() - 5;
+ $(window).scrollTop(newTop);
+ }
+ }
+ $(window).bind('hashchange', function() {
+ maybeScrollToHash();
+ });
+ // Scroll now too in case we had opened the page on a hash, but wait 1 ms because some browsers
+ // will try to do *their* initial scroll after running the onReady handler.
+ setTimeout(function() { maybeScrollToHash(); }, 1)
+ })
+ </script>
+
+ </body>
+</html>
Added: dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/monitoring.html
==============================================================================
--- dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/monitoring.html (added)
+++ dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/monitoring.html Wed Sep 25 00:14:43 2013
@@ -0,0 +1,258 @@
+<!DOCTYPE html>
+<!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
+<!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]-->
+<!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]-->
+ <head>
+ <meta charset="utf-8">
+ <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
+ <title>Monitoring and Instrumentation - Spark 0.8.0 Documentation</title>
+ <meta name="description" content="">
+
+ <link rel="stylesheet" href="css/bootstrap.min.css">
+ <style>
+ body {
+ padding-top: 60px;
+ padding-bottom: 40px;
+ }
+ </style>
+ <meta name="viewport" content="width=device-width">
+ <link rel="stylesheet" href="css/bootstrap-responsive.min.css">
+ <link rel="stylesheet" href="css/main.css">
+
+ <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script>
+
+ <link rel="stylesheet" href="css/pygments-default.css">
+
+ <!-- Google analytics script -->
+ <script type="text/javascript">
+ /*
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _gaq.push(['_trackPageview']);
+
+ (function() {
+ var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+ ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+ var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+ })();
+ */
+ </script>
+
+ </head>
+ <body>
+ <!--[if lt IE 7]>
+ <p class="chromeframe">You are using an outdated browser. <a href="http://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p>
+ <![endif]-->
+
+ <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html -->
+
+ <div class="navbar navbar-fixed-top" id="topbar">
+ <div class="navbar-inner">
+ <div class="container">
+ <div class="brand"><a href="index.html">
+ <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">0.8.0</span>
+ </div>
+ <ul class="nav">
+ <!--TODO(andyk): Add class="active" attribute to li some how.-->
+ <li><a href="index.html">Overview</a></li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="quick-start.html">Quick Start</a></li>
+ <li><a href="scala-programming-guide.html">Spark in Scala</a></li>
+ <li><a href="java-programming-guide.html">Spark in Java</a></li>
+ <li><a href="python-programming-guide.html">Spark in Python</a></li>
+ <li class="divider"></li>
+ <li><a href="streaming-programming-guide.html">Spark Streaming</a></li>
+ <li><a href="mllib-guide.html">MLlib (Machine Learning)</a></li>
+ <li><a href="bagel-programming-guide.html">Bagel (Pregel on Spark)</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">API Docs<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="api/core/index.html">Spark Core for Java/Scala</a></li>
+ <li><a href="api/pyspark/index.html">Spark Core for Python</a></li>
+ <li class="divider"></li>
+ <li><a href="api/streaming/index.html">Spark Streaming</a></li>
+ <li><a href="api/mllib/index.html">MLlib (Machine Learning)</a></li>
+ <li><a href="api/bagel/index.html">Bagel (Pregel on Spark)</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="cluster-overview.html">Overview</a></li>
+ <li><a href="ec2-scripts.html">Amazon EC2</a></li>
+ <li><a href="spark-standalone.html">Standalone Mode</a></li>
+ <li><a href="running-on-mesos.html">Mesos</a></li>
+ <li><a href="running-on-yarn.html">YARN</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="configuration.html">Configuration</a></li>
+ <li><a href="monitoring.html">Monitoring</a></li>
+ <li><a href="tuning.html">Tuning Guide</a></li>
+ <li><a href="hadoop-third-party-distributions.html">Running with CDH/HDP</a></li>
+ <li><a href="hardware-provisioning.html">Hardware Provisioning</a></li>
+ <li><a href="job-scheduling.html">Job Scheduling</a></li>
+ <li class="divider"></li>
+ <li><a href="building-with-maven.html">Building Spark with Maven</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li>
+ </ul>
+ </li>
+ </ul>
+ <!--<p class="navbar-text pull-right"><span class="version-text">v0.8.0</span></p>-->
+ </div>
+ </div>
+ </div>
+
+ <div class="container" id="content">
+ <h1 class="title">Monitoring and Instrumentation</h1>
+
+ <p>There are several ways to monitor Spark applications.</p>
+
+<h1 id="web-interfaces">Web Interfaces</h1>
+
+<p>Every SparkContext launches a web UI, by default on port 4040, that
+displays useful information about the application. This includes:</p>
+
+<ul>
+ <li>A list of scheduler stages and tasks</li>
+ <li>A summary of RDD sizes and memory usage</li>
+ <li>Information about the running executors</li>
+ <li>Environmental information.</li>
+</ul>
+
+<p>You can access this interface by simply opening <code>http://<driver-node>:4040</code> in a web browser.
+If multiple SparkContexts are running on the same host, they will bind to succesive ports
+beginning with 4040 (4041, 4042, etc).</p>
+
+<p>Spark’s Standlone Mode cluster manager also has its own
+<a href="spark-standalone.html#monitoring-and-logging">web UI</a>. </p>
+
+<p>Note that in both of these UIs, the tables are sortable by clicking their headers,
+making it easy to identify slow tasks, data skew, etc.</p>
+
+<h1 id="metrics">Metrics</h1>
+
+<p>Spark has a configurable metrics system based on the
+<a href="http://metrics.codahale.com/">Coda Hale Metrics Library</a>.
+This allows users to report Spark metrics to a variety of sinks including HTTP, JMX, and CSV
+files. The metrics system is configured via a configuration file that Spark expects to be present
+at <code>$SPARK_HOME/conf/metrics.conf</code>. A custom file location can be specified via the
+<code>spark.metrics.conf</code> Java system property. Spark’s metrics are decoupled into different
+<em>instances</em> corresponding to Spark components. Within each instance, you can configure a
+set of sinks to which metrics are reported. The following instances are currently supported:</p>
+
+<ul>
+ <li><code>master</code>: The Spark standalone master process.</li>
+ <li><code>applications</code>: A component within the master which reports on various applications.</li>
+ <li><code>worker</code>: A Spark standalone worker process.</li>
+ <li><code>executor</code>: A Spark executor.</li>
+ <li><code>driver</code>: The Spark driver process (the process in which your SparkContext is created).</li>
+</ul>
+
+<p>Each instance can report to zero or more <em>sinks</em>. Sinks are contained in the
+<code>org.apache.spark.metrics.sink</code> package:</p>
+
+<ul>
+ <li><code>ConsoleSink</code>: Logs metrics information to the console.</li>
+ <li><code>CSVSink</code>: Exports metrics data to CSV files at regular intervals.</li>
+ <li><code>GangliaSink</code>: Sends metrics to a Ganglia node or multicast group.</li>
+ <li><code>JmxSink</code>: Registers metrics for viewing in a JXM console.</li>
+ <li><code>MetricsServlet</code>: Adds a servlet within the existing Spark UI to serve metrics data as JSON data.</li>
+</ul>
+
+<p>The syntax of the metrics configuration file is defined in an example configuration file,
+<code>$SPARK_HOME/conf/metrics.conf.template</code>.</p>
+
+<h1 id="advanced-instrumentation">Advanced Instrumentation</h1>
+
+<p>Several external tools can be used to help profile the performance of Spark jobs:</p>
+
+<ul>
+ <li>Cluster-wide monitoring tools, such as <a href="http://ganglia.sourceforge.net/">Ganglia</a>, can provide
+insight into overall cluster utilization and resource bottlenecks. For instance, a Ganglia
+dashboard can quickly reveal whether a particular workload is disk bound, network bound, or
+CPU bound.</li>
+ <li>OS profiling tools such as <a href="http://dag.wieers.com/home-made/dstat/">dstat</a>,
+<a href="http://linux.die.net/man/1/iostat">iostat</a>, and <a href="http://linux.die.net/man/1/iotop">iotop</a>
+can provide fine-grained profiling on individual nodes.</li>
+ <li>JVM utilities such as <code>jstack</code> for providing stack traces, <code>jmap</code> for creating heap-dumps,
+<code>jstat</code> for reporting time-series statistics and <code>jconsole</code> for visually exploring various JVM
+properties are useful for those comfortable with JVM internals.</li>
+</ul>
+
+ <!-- Main hero unit for a primary marketing message or call to action -->
+ <!--<div class="hero-unit">
+ <h1>Hello, world!</h1>
+ <p>This is a template for a simple marketing or informational website. It includes a large callout called the hero unit and three supporting pieces of content. Use it as a starting point to create something more unique.</p>
+ <p><a class="btn btn-primary btn-large">Learn more »</a></p>
+ </div>-->
+
+ <!-- Example row of columns -->
+ <!--<div class="row">
+ <div class="span4">
+ <h2>Heading</h2>
+ <p>Donec id elit non mi porta gravida at eget metus. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet risus. Etiam porta sem malesuada magna mollis euismod. Donec sed odio dui. </p>
+ <p><a class="btn" href="#">View details »</a></p>
+ </div>
+ <div class="span4">
+ <h2>Heading</h2>
+ <p>Donec id elit non mi porta gravida at eget metus. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet risus. Etiam porta sem malesuada magna mollis euismod. Donec sed odio dui. </p>
+ <p><a class="btn" href="#">View details »</a></p>
+ </div>
+ <div class="span4">
+ <h2>Heading</h2>
+ <p>Donec sed odio dui. Cras justo odio, dapibus ac facilisis in, egestas eget quam. Vestibulum id ligula porta felis euismod semper. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet risus.</p>
+ <p><a class="btn" href="#">View details »</a></p>
+ </div>
+ </div>
+
+ <hr>-->
+
+ <footer>
+ <hr>
+ <p style="text-align: center; veritcal-align: middle; color: #999;">
+ Apache Spark is an effort undergoing incubation at the Apache Software Foundation.
+ <a href="http://incubator.apache.org">
+ <img style="margin-left: 20px;" src="img/incubator-logo.png" />
+ </a>
+ </p>
+ </footer>
+
+ </div> <!-- /container -->
+
+ <script src="js/vendor/jquery-1.8.0.min.js"></script>
+ <script src="js/vendor/bootstrap.min.js"></script>
+ <script src="js/main.js"></script>
+
+ <!-- A script to fix internal hash links because we have an overlapping top bar.
+ Based on https://github.com/twitter/bootstrap/issues/193#issuecomment-2281510 -->
+ <script>
+ $(function() {
+ function maybeScrollToHash() {
+ if (window.location.hash && $(window.location.hash).length) {
+ var newTop = $(window.location.hash).offset().top - $('#topbar').height() - 5;
+ $(window).scrollTop(newTop);
+ }
+ }
+ $(window).bind('hashchange', function() {
+ maybeScrollToHash();
+ });
+ // Scroll now too in case we had opened the page on a hash, but wait 1 ms because some browsers
+ // will try to do *their* initial scroll after running the onReady handler.
+ setTimeout(function() { maybeScrollToHash(); }, 1)
+ })
+ </script>
+
+ </body>
+</html>
Added: dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/python-programming-guide.html
==============================================================================
--- dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/python-programming-guide.html (added)
+++ dev/incubator/spark/spark-0.8.0-incubating-rc6-docs/python-programming-guide.html Wed Sep 25 00:14:43 2013
@@ -0,0 +1,313 @@
+<!DOCTYPE html>
+<!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
+<!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]-->
+<!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]-->
+ <head>
+ <meta charset="utf-8">
+ <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
+ <title>Python Programming Guide - Spark 0.8.0 Documentation</title>
+ <meta name="description" content="">
+
+ <link rel="stylesheet" href="css/bootstrap.min.css">
+ <style>
+ body {
+ padding-top: 60px;
+ padding-bottom: 40px;
+ }
+ </style>
+ <meta name="viewport" content="width=device-width">
+ <link rel="stylesheet" href="css/bootstrap-responsive.min.css">
+ <link rel="stylesheet" href="css/main.css">
+
+ <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script>
+
+ <link rel="stylesheet" href="css/pygments-default.css">
+
+ <!-- Google analytics script -->
+ <script type="text/javascript">
+ /*
+ var _gaq = _gaq || [];
+ _gaq.push(['_setAccount', 'UA-32518208-1']);
+ _gaq.push(['_trackPageview']);
+
+ (function() {
+ var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+ ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+ var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+ })();
+ */
+ </script>
+
+ </head>
+ <body>
+ <!--[if lt IE 7]>
+ <p class="chromeframe">You are using an outdated browser. <a href="http://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p>
+ <![endif]-->
+
+ <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html -->
+
+ <div class="navbar navbar-fixed-top" id="topbar">
+ <div class="navbar-inner">
+ <div class="container">
+ <div class="brand"><a href="index.html">
+ <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">0.8.0</span>
+ </div>
+ <ul class="nav">
+ <!--TODO(andyk): Add class="active" attribute to li some how.-->
+ <li><a href="index.html">Overview</a></li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="quick-start.html">Quick Start</a></li>
+ <li><a href="scala-programming-guide.html">Spark in Scala</a></li>
+ <li><a href="java-programming-guide.html">Spark in Java</a></li>
+ <li><a href="python-programming-guide.html">Spark in Python</a></li>
+ <li class="divider"></li>
+ <li><a href="streaming-programming-guide.html">Spark Streaming</a></li>
+ <li><a href="mllib-guide.html">MLlib (Machine Learning)</a></li>
+ <li><a href="bagel-programming-guide.html">Bagel (Pregel on Spark)</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">API Docs<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="api/core/index.html">Spark Core for Java/Scala</a></li>
+ <li><a href="api/pyspark/index.html">Spark Core for Python</a></li>
+ <li class="divider"></li>
+ <li><a href="api/streaming/index.html">Spark Streaming</a></li>
+ <li><a href="api/mllib/index.html">MLlib (Machine Learning)</a></li>
+ <li><a href="api/bagel/index.html">Bagel (Pregel on Spark)</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="cluster-overview.html">Overview</a></li>
+ <li><a href="ec2-scripts.html">Amazon EC2</a></li>
+ <li><a href="spark-standalone.html">Standalone Mode</a></li>
+ <li><a href="running-on-mesos.html">Mesos</a></li>
+ <li><a href="running-on-yarn.html">YARN</a></li>
+ </ul>
+ </li>
+
+ <li class="dropdown">
+ <a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a>
+ <ul class="dropdown-menu">
+ <li><a href="configuration.html">Configuration</a></li>
+ <li><a href="monitoring.html">Monitoring</a></li>
+ <li><a href="tuning.html">Tuning Guide</a></li>
+ <li><a href="hadoop-third-party-distributions.html">Running with CDH/HDP</a></li>
+ <li><a href="hardware-provisioning.html">Hardware Provisioning</a></li>
+ <li><a href="job-scheduling.html">Job Scheduling</a></li>
+ <li class="divider"></li>
+ <li><a href="building-with-maven.html">Building Spark with Maven</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li>
+ </ul>
+ </li>
+ </ul>
+ <!--<p class="navbar-text pull-right"><span class="version-text">v0.8.0</span></p>-->
+ </div>
+ </div>
+ </div>
+
+ <div class="container" id="content">
+ <h1 class="title">Python Programming Guide</h1>
+
+ <p>The Spark Python API (PySpark) exposes the Spark programming model to Python.
+To learn the basics of Spark, we recommend reading through the
+<a href="scala-programming-guide.html">Scala programming guide</a> first; it should be
+easy to follow even if you don’t know Scala.
+This guide will show how to use the Spark features described there in Python.</p>
+
+<h1 id="key-differences-in-the-python-api">Key Differences in the Python API</h1>
+
+<p>There are a few key differences between the Python and Scala APIs:</p>
+
+<ul>
+ <li>Python is dynamically typed, so RDDs can hold objects of multiple types.</li>
+ <li>PySpark does not yet support a few API calls, such as <code>lookup</code>, <code>sort</code>, and non-text input files, though these will be added in future releases.</li>
+</ul>
+
+<p>In PySpark, RDDs support the same methods as their Scala counterparts but take Python functions and return Python collection types.
+Short functions can be passed to RDD methods using Python’s <a href="http://www.diveintopython.net/power_of_introspection/lambda_functions.html"><code>lambda</code></a> syntax:</p>
+
+<div class="highlight"><pre><code class="python"><span class="n">logData</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="n">logFile</span><span class="p">)</span><span class="o">.</span><span class="n">cache</span><span class="p">()</span>
+<span class="n">errors</span> <span class="o">=</span> <span class="n">logData</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="k">lambda</span> <span class="n">line</span><span class="p">:</span> <span class="s">"ERROR"</span> <span class="ow">in</span> <span class="n">line</span><span class="p">)</span>
+</code></pre></div>
+
+<p>You can also pass functions that are defined with the <code>def</code> keyword; this is useful for longer functions that can’t be expressed using <code>lambda</code>:</p>
+
+<div class="highlight"><pre><code class="python"><span class="k">def</span> <span class="nf">is_error</span><span class="p">(</span><span class="n">line</span><span class="p">):</span>
+ <span class="k">return</span> <span class="s">"ERROR"</span> <span class="ow">in</span> <span class="n">line</span>
+<span class="n">errors</span> <span class="o">=</span> <span class="n">logData</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">is_error</span><span class="p">)</span>
+</code></pre></div>
+
+<p>Functions can access objects in enclosing scopes, although modifications to those objects within RDD methods will not be propagated back:</p>
+
+<div class="highlight"><pre><code class="python"><span class="n">error_keywords</span> <span class="o">=</span> <span class="p">[</span><span class="s">"Exception"</span><span class="p">,</span> <span class="s">"Error"</span><span class="p">]</span>
+<span class="k">def</span> <span class="nf">is_error</span><span class="p">(</span><span class="n">line</span><span class="p">):</span>
+ <span class="k">return</span> <span class="nb">any</span><span class="p">(</span><span class="n">keyword</span> <span class="ow">in</span> <span class="n">line</span> <span class="k">for</span> <span class="n">keyword</span> <span class="ow">in</span> <span class="n">error_keywords</span><span class="p">)</span>
+<span class="n">errors</span> <span class="o">=</span> <span class="n">logData</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">is_error</span><span class="p">)</span>
+</code></pre></div>
+
+<p>PySpark will automatically ship these functions to workers, along with any objects that they reference.
+Instances of classes will be serialized and shipped to workers by PySpark, but classes themselves cannot be automatically distributed to workers.
+The <a href="#standalone-use">Standalone Use</a> section describes how to ship code dependencies to workers.</p>
+
+<p>In addition, PySpark fully supports interactive use—simply run <code>./pyspark</code> to launch an interactive shell.</p>
+
+<h1 id="installing-and-configuring-pyspark">Installing and Configuring PySpark</h1>
+
+<p>PySpark requires Python 2.6 or higher.
+PySpark applications are executed using a standard CPython interpreter in order to support Python modules that use C extensions.
+We have not tested PySpark with Python 3 or with alternative Python interpreters, such as <a href="http://pypy.org/">PyPy</a> or <a href="http://www.jython.org/">Jython</a>.</p>
+
+<p>By default, PySpark requires <code>python</code> to be available on the system <code>PATH</code> and use it to run programs; an alternate Python executable may be specified by setting the <code>PYSPARK_PYTHON</code> environment variable in <code>conf/spark-env.sh</code> (or <code>.cmd</code> on Windows).</p>
+
+<p>All of PySpark’s library dependencies, including <a href="http://py4j.sourceforge.net/">Py4J</a>, are bundled with PySpark and automatically imported.</p>
+
+<p>Standalone PySpark applications should be run using the <code>pyspark</code> script, which automatically configures the Java and Python environment using the settings in <code>conf/spark-env.sh</code> or <code>.cmd</code>.
+The script automatically adds the <code>pyspark</code> package to the <code>PYTHONPATH</code>.</p>
+
+<h1 id="interactive-use">Interactive Use</h1>
+
+<p>The <code>pyspark</code> script launches a Python interpreter that is configured to run PySpark applications. To use <code>pyspark</code> interactively, first build Spark, then launch it directly from the command line without any options:</p>
+
+<div class="highlight"><pre><code class="bash"><span class="nv">$ </span>sbt/sbt assembly
+<span class="nv">$ </span>./pyspark
+</code></pre></div>
+
+<p>The Python shell can be used explore data interactively and is a simple way to learn the API:</p>
+
+<div class="highlight"><pre><code class="python"><span class="o">>>></span> <span class="n">words</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="s">"/usr/share/dict/words"</span><span class="p">)</span>
+<span class="o">>>></span> <span class="n">words</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="k">lambda</span> <span class="n">w</span><span class="p">:</span> <span class="n">w</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s">"spar"</span><span class="p">))</span><span class="o">.</span><span class="n">take</span><span class="p">(</span><span class="mi">5</span><span class="p">)</span>
+<span class="p">[</span><span class="s">u'spar'</span><span class="p">,</span> <span class="s">u'sparable'</span><span class="p">,</span> <span class="s">u'sparada'</span><span class="p">,</span> <span class="s">u'sparadrap'</span><span class="p">,</span> <span class="s">u'sparagrass'</span><span class="p">]</span>
+<span class="o">>>></span> <span class="n">help</span><span class="p">(</span><span class="n">pyspark</span><span class="p">)</span> <span class="c"># Show all pyspark functions</span>
+</code></pre></div>
+
+<p>By default, the <code>pyspark</code> shell creates SparkContext that runs applications locally on a single core.
+To connect to a non-local cluster, or use multiple cores, set the <code>MASTER</code> environment variable.
+For example, to use the <code>pyspark</code> shell with a <a href="spark-standalone.html">standalone Spark cluster</a>:</p>
+
+<div class="highlight"><pre><code class="bash"><span class="nv">$ MASTER</span><span class="o">=</span>spark://IP:PORT ./pyspark
+</code></pre></div>
+
+<p>Or, to use four cores on the local machine:</p>
+
+<div class="highlight"><pre><code class="bash"><span class="nv">$ MASTER</span><span class="o">=</span><span class="nb">local</span><span class="o">[</span>4<span class="o">]</span> ./pyspark
+</code></pre></div>
+
+<h2 id="ipython">IPython</h2>
+
+<p>It is also possible to launch PySpark in <a href="http://ipython.org">IPython</a>, the enhanced Python interpreter.
+To do this, set the <code>IPYTHON</code> variable to <code>1</code> when running <code>pyspark</code>:</p>
+
+<div class="highlight"><pre><code class="bash"><span class="nv">$ IPYTHON</span><span class="o">=</span>1 ./pyspark
+</code></pre></div>
+
+<p>Alternatively, you can customize the <code>ipython</code> command by setting <code>IPYTHON_OPTS</code>. For example, to launch
+the <a href="http://ipython.org/notebook.html">IPython Notebook</a> with PyLab graphing support:</p>
+
+<div class="highlight"><pre><code class="bash"><span class="nv">$ IPYTHON_OPTS</span><span class="o">=</span><span class="s2">"notebook --pylab inline"</span> ./pyspark
+</code></pre></div>
+
+<p>IPython also works on a cluster or on multiple cores if you set the <code>MASTER</code> environment variable.</p>
+
+<h1 id="standalone-programs">Standalone Programs</h1>
+
+<p>PySpark can also be used from standalone Python scripts by creating a SparkContext in your script and running the script using <code>pyspark</code>.
+The Quick Start guide includes a <a href="quick-start.html#a-standalone-app-in-python">complete example</a> of a standalone Python application.</p>
+
+<p>Code dependencies can be deployed by listing them in the <code>pyFiles</code> option in the SparkContext constructor:</p>
+
+<div class="highlight"><pre><code class="python"><span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</span>
+<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s">"local"</span><span class="p">,</span> <span class="s">"App Name"</span><span class="p">,</span> <span class="n">pyFiles</span><span class="o">=</span><span class="p">[</span><span class="s">'MyFile.py'</span><span class="p">,</span> <span class="s">'lib.zip'</span><span class="p">,</span> <span class="s">'app.egg'</span><span class="p">])</span>
+</code></pre></div>
+
+<p>Files listed here will be added to the <code>PYTHONPATH</code> and shipped to remote worker machines.
+Code dependencies can be added to an existing SparkContext using its <code>addPyFile()</code> method.</p>
+
+<h1 id="api-docs">API Docs</h1>
+
+<p><a href="api/pyspark/index.html">API documentation</a> for PySpark is available as Epydoc.
+Many of the methods also contain <a href="http://docs.python.org/2/library/doctest.html">doctests</a> that provide additional usage examples.</p>
+
+<h1 id="where-to-go-from-here">Where to Go from Here</h1>
+
+<p>PySpark also includes several sample programs in the <a href="https://github.com/apache/incubator-spark/tree/master/python/examples"><code>python/examples</code> folder</a>.
+You can run them by passing the files to <code>pyspark</code>; e.g.:</p>
+
+<pre><code>./pyspark python/examples/wordcount.py
+</code></pre>
+
+<p>Each program prints usage help when run without arguments.</p>
+
+ <!-- Main hero unit for a primary marketing message or call to action -->
+ <!--<div class="hero-unit">
+ <h1>Hello, world!</h1>
+ <p>This is a template for a simple marketing or informational website. It includes a large callout called the hero unit and three supporting pieces of content. Use it as a starting point to create something more unique.</p>
+ <p><a class="btn btn-primary btn-large">Learn more »</a></p>
+ </div>-->
+
+ <!-- Example row of columns -->
+ <!--<div class="row">
+ <div class="span4">
+ <h2>Heading</h2>
+ <p>Donec id elit non mi porta gravida at eget metus. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet risus. Etiam porta sem malesuada magna mollis euismod. Donec sed odio dui. </p>
+ <p><a class="btn" href="#">View details »</a></p>
+ </div>
+ <div class="span4">
+ <h2>Heading</h2>
+ <p>Donec id elit non mi porta gravida at eget metus. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet risus. Etiam porta sem malesuada magna mollis euismod. Donec sed odio dui. </p>
+ <p><a class="btn" href="#">View details »</a></p>
+ </div>
+ <div class="span4">
+ <h2>Heading</h2>
+ <p>Donec sed odio dui. Cras justo odio, dapibus ac facilisis in, egestas eget quam. Vestibulum id ligula porta felis euismod semper. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet risus.</p>
+ <p><a class="btn" href="#">View details »</a></p>
+ </div>
+ </div>
+
+ <hr>-->
+
+ <footer>
+ <hr>
+ <p style="text-align: center; veritcal-align: middle; color: #999;">
+ Apache Spark is an effort undergoing incubation at the Apache Software Foundation.
+ <a href="http://incubator.apache.org">
+ <img style="margin-left: 20px;" src="img/incubator-logo.png" />
+ </a>
+ </p>
+ </footer>
+
+ </div> <!-- /container -->
+
+ <script src="js/vendor/jquery-1.8.0.min.js"></script>
+ <script src="js/vendor/bootstrap.min.js"></script>
+ <script src="js/main.js"></script>
+
+ <!-- A script to fix internal hash links because we have an overlapping top bar.
+ Based on https://github.com/twitter/bootstrap/issues/193#issuecomment-2281510 -->
+ <script>
+ $(function() {
+ function maybeScrollToHash() {
+ if (window.location.hash && $(window.location.hash).length) {
+ var newTop = $(window.location.hash).offset().top - $('#topbar').height() - 5;
+ $(window).scrollTop(newTop);
+ }
+ }
+ $(window).bind('hashchange', function() {
+ maybeScrollToHash();
+ });
+ // Scroll now too in case we had opened the page on a hash, but wait 1 ms because some browsers
+ // will try to do *their* initial scroll after running the onReady handler.
+ setTimeout(function() { maybeScrollToHash(); }, 1)
+ })
+ </script>
+
+ </body>
+</html>