http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/b8a847fa/userguide/misc/generic_funcs.html ---------------------------------------------------------------------- diff --git a/userguide/misc/generic_funcs.html b/userguide/misc/generic_funcs.html index 64d8623..d5218ed 100644 --- a/userguide/misc/generic_funcs.html +++ b/userguide/misc/generic_funcs.html @@ -4,7 +4,7 @@ <head> <meta charset="UTF-8"> <meta content="text/html; charset=utf-8" http-equiv="Content-Type"> - <title>List of generic Hivemall functions · Hivemall User Manual</title> + <title>List of Generic Hivemall Functions · Hivemall User Manual</title> <meta http-equiv="X-UA-Compatible" content="IE=edge" /> <meta name="description" content=""> <meta name="generator" content="GitBook 3.2.3"> @@ -221,13 +221,28 @@ </li> - <li class="chapter " data-level="1.3" data-path="../tips/"> + <li class="chapter " data-level="1.3" data-path="funcs.html"> - <a href="../tips/"> + <a href="funcs.html"> <b>1.3.</b> + List of Functions + + </a> + + + + </li> + + <li class="chapter " data-level="1.4" data-path="../tips/"> + + <a href="../tips/"> + + + <b>1.4.</b> + Tips for Effective Hivemall </a> @@ -237,12 +252,12 @@ <ul class="articles"> - <li class="chapter " data-level="1.3.1" data-path="../tips/addbias.html"> + <li class="chapter " data-level="1.4.1" data-path="../tips/addbias.html"> <a href="../tips/addbias.html"> - <b>1.3.1.</b> + <b>1.4.1.</b> Explicit add_bias() for better prediction @@ -252,12 +267,12 @@ </li> - <li class="chapter " data-level="1.3.2" data-path="../tips/rand_amplify.html"> + <li class="chapter " data-level="1.4.2" data-path="../tips/rand_amplify.html"> <a href="../tips/rand_amplify.html"> - <b>1.3.2.</b> + <b>1.4.2.</b> Use rand_amplify() to better prediction results @@ -267,14 +282,14 @@ </li> - <li class="chapter " data-level="1.3.3" data-path="../tips/rt_prediction.html"> + <li class="chapter " data-level="1.4.3" data-path="../tips/rt_prediction.html"> <a href="../tips/rt_prediction.html"> - <b>1.3.3.</b> + <b>1.4.3.</b> - Real-time Prediction on RDBMS + Real-time prediction on RDBMS </a> @@ -282,12 +297,12 @@ </li> - <li class="chapter " data-level="1.3.4" data-path="../tips/ensemble_learning.html"> + <li class="chapter " data-level="1.4.4" data-path="../tips/ensemble_learning.html"> <a href="../tips/ensemble_learning.html"> - <b>1.3.4.</b> + <b>1.4.4.</b> Ensemble learning for stable prediction @@ -297,12 +312,12 @@ </li> - <li class="chapter " data-level="1.3.5" data-path="../tips/mixserver.html"> + <li class="chapter " data-level="1.4.5" data-path="../tips/mixserver.html"> <a href="../tips/mixserver.html"> - <b>1.3.5.</b> + <b>1.4.5.</b> Mixing models for a better prediction convergence (MIX server) @@ -312,12 +327,12 @@ </li> - <li class="chapter " data-level="1.3.6" data-path="../tips/emr.html"> + <li class="chapter " data-level="1.4.6" data-path="../tips/emr.html"> <a href="../tips/emr.html"> - <b>1.3.6.</b> + <b>1.4.6.</b> Run Hivemall on Amazon Elastic MapReduce @@ -332,14 +347,14 @@ </li> - <li class="chapter " data-level="1.4" data-path="../tips/general_tips.html"> + <li class="chapter " data-level="1.5" data-path="../tips/general_tips.html"> <a href="../tips/general_tips.html"> - <b>1.4.</b> + <b>1.5.</b> - General Hive/Hadoop tips + General Hive/Hadoop Tips </a> @@ -348,12 +363,12 @@ <ul class="articles"> - <li class="chapter " data-level="1.4.1" data-path="../tips/rowid.html"> + <li class="chapter " data-level="1.5.1" data-path="../tips/rowid.html"> <a href="../tips/rowid.html"> - <b>1.4.1.</b> + <b>1.5.1.</b> Adding rowid for each row @@ -363,12 +378,12 @@ </li> - <li class="chapter " data-level="1.4.2" data-path="../tips/hadoop_tuning.html"> + <li class="chapter " data-level="1.5.2" data-path="../tips/hadoop_tuning.html"> <a href="../tips/hadoop_tuning.html"> - <b>1.4.2.</b> + <b>1.5.2.</b> Hadoop tuning for Hivemall @@ -383,12 +398,12 @@ </li> - <li class="chapter " data-level="1.5" data-path="../troubleshooting/"> + <li class="chapter " data-level="1.6" data-path="../troubleshooting/"> <a href="../troubleshooting/"> - <b>1.5.</b> + <b>1.6.</b> Troubleshooting @@ -399,12 +414,12 @@ <ul class="articles"> - <li class="chapter " data-level="1.5.1" data-path="../troubleshooting/oom.html"> + <li class="chapter " data-level="1.6.1" data-path="../troubleshooting/oom.html"> <a href="../troubleshooting/oom.html"> - <b>1.5.1.</b> + <b>1.6.1.</b> OutOfMemoryError in training @@ -414,14 +429,14 @@ </li> - <li class="chapter " data-level="1.5.2" data-path="../troubleshooting/mapjoin_task_error.html"> + <li class="chapter " data-level="1.6.2" data-path="../troubleshooting/mapjoin_task_error.html"> <a href="../troubleshooting/mapjoin_task_error.html"> - <b>1.5.2.</b> + <b>1.6.2.</b> - SemanticException Generate Map Join Task Error: Cannot serialize object + SemanticException generate map join task error: Cannot serialize object </a> @@ -429,12 +444,12 @@ </li> - <li class="chapter " data-level="1.5.3" data-path="../troubleshooting/asterisk.html"> + <li class="chapter " data-level="1.6.3" data-path="../troubleshooting/asterisk.html"> <a href="../troubleshooting/asterisk.html"> - <b>1.5.3.</b> + <b>1.6.3.</b> Asterisk argument for UDTF does not work @@ -444,12 +459,12 @@ </li> - <li class="chapter " data-level="1.5.4" data-path="../troubleshooting/num_mappers.html"> + <li class="chapter " data-level="1.6.4" data-path="../troubleshooting/num_mappers.html"> <a href="../troubleshooting/num_mappers.html"> - <b>1.5.4.</b> + <b>1.6.4.</b> The number of mappers is less than input splits in Hadoop 2.x @@ -459,14 +474,14 @@ </li> - <li class="chapter " data-level="1.5.5" data-path="../troubleshooting/mapjoin_classcastex.html"> + <li class="chapter " data-level="1.6.5" data-path="../troubleshooting/mapjoin_classcastex.html"> <a href="../troubleshooting/mapjoin_classcastex.html"> - <b>1.5.5.</b> + <b>1.6.5.</b> - Map-side Join causes ClassCastException on Tez + Map-side join causes ClassCastException on Tez </a> @@ -493,7 +508,7 @@ <b>2.1.</b> - List of generic Hivemall functions + List of Generic Hivemall Functions </a> @@ -508,7 +523,7 @@ <b>2.2.</b> - Efficient Top-K query processing + Efficient Top-K Query Processing </a> @@ -620,7 +635,7 @@ <b>3.5.</b> - FEATURE PAIRING + Feature Paring </a> @@ -636,7 +651,7 @@ <b>3.5.1.</b> - Polynomial Features + Polynomial features </a> @@ -656,7 +671,7 @@ <b>3.6.</b> - FEATURE TRANSFORMATION + Feature Transformation </a> @@ -672,7 +687,7 @@ <b>3.6.1.</b> - Feature Vectorization + Feature vectorization </a> @@ -745,7 +760,7 @@ <b>4.1.1.</b> - Area Under the ROC Curve + Area under the ROC curve </a> @@ -780,7 +795,7 @@ <b>4.3.</b> - Regression metrics + Regression Metrics </a> @@ -864,7 +879,7 @@ - <li class="header">Part VI - Binary classification</li> + <li class="header">Part VI - Binary Classification</li> @@ -890,7 +905,7 @@ <b>6.2.</b> - a9a tutorial + a9a Tutorial </a> @@ -936,7 +951,7 @@ <b>6.2.3.</b> - Mini-batch Gradient Descent + Mini-batch gradient descent </a> @@ -956,7 +971,7 @@ <b>6.3.</b> - News20 tutorial + News20 Tutorial </a> @@ -1052,7 +1067,7 @@ <b>6.4.</b> - KDD2010a tutorial + KDD2010a Tutorial </a> @@ -1103,7 +1118,7 @@ <b>6.5.</b> - KDD2010b tutorial + KDD2010b Tutorial </a> @@ -1154,7 +1169,7 @@ <b>6.6.</b> - Webspam tutorial + Webspam Tutorial </a> @@ -1205,7 +1220,7 @@ <b>6.7.</b> - Kaggle Titanic tutorial + Kaggle Titanic Tutorial </a> @@ -1216,7 +1231,7 @@ - <li class="header">Part VII - Multiclass classification</li> + <li class="header">Part VII - Multiclass Classification</li> @@ -1227,7 +1242,7 @@ <b>7.1.</b> - News20 Multiclass tutorial + News20 Multiclass Tutorial </a> @@ -1338,7 +1353,7 @@ <b>7.2.</b> - Iris tutorial + Iris Tutorial </a> @@ -1426,7 +1441,7 @@ <b>8.2.</b> - E2006-tfidf regression tutorial + E2006-tfidf Regression Tutorial </a> @@ -1477,7 +1492,7 @@ <b>8.3.</b> - KDDCup 2012 track 2 CTR prediction tutorial + KDDCup 2012 Track 2 CTR Prediction Tutorial </a> @@ -1523,7 +1538,7 @@ <b>8.3.3.</b> - Logistic Regression with Amplifier + Logistic Regression with amplifier </a> @@ -1581,7 +1596,7 @@ <b>9.1.1.</b> - Item-based Collaborative Filtering + Item-based collaborative filtering </a> @@ -1601,7 +1616,7 @@ <b>9.2.</b> - News20 related article recommendation Tutorial + News20 Related Article Recommendation Tutorial </a> @@ -1632,7 +1647,7 @@ <b>9.2.2.</b> - LSH/Minhash and Jaccard Similarity + LSH/MinHash and Jaccard similarity </a> @@ -1647,7 +1662,7 @@ <b>9.2.3.</b> - LSH/Minhash and Brute-Force Search + LSH/MinHash and brute-force search </a> @@ -1662,7 +1677,7 @@ <b>9.2.4.</b> - kNN search using b-Bits Minhash + kNN search using b-Bits MinHash </a> @@ -1682,7 +1697,7 @@ <b>9.3.</b> - MovieLens movie recommendation Tutorial + MovieLens Movie Recommendation Tutorial </a> @@ -1713,7 +1728,7 @@ <b>9.3.2.</b> - Item-based Collaborative Filtering + Item-based collaborative filtering </a> @@ -1758,7 +1773,7 @@ <b>9.3.5.</b> - SLIM for Fast Top-K Recommendation + SLIM for fast top-k recommendation </a> @@ -1773,7 +1788,7 @@ <b>9.3.6.</b> - 10-fold Cross Validation (Matrix Factorization) + 10-fold cross validation (Matrix Factorization) </a> @@ -1878,7 +1893,7 @@ - <li class="header">Part XII - GeoSpatial functions</li> + <li class="header">Part XII - GeoSpatial Functions</li> @@ -1963,7 +1978,7 @@ <b>13.2.1.</b> - a9a Tutorial for DataFrame + a9a tutorial for DataFrame </a> @@ -1978,7 +1993,7 @@ <b>13.2.2.</b> - a9a Tutorial for SQL + a9a tutorial for SQL </a> @@ -2014,7 +2029,7 @@ <b>13.3.1.</b> - E2006-tfidf regression Tutorial for DataFrame + E2006-tfidf regression tutorial for DataFrame </a> @@ -2029,7 +2044,7 @@ <b>13.3.2.</b> - E2006-tfidf regression Tutorial for SQL + E2006-tfidf regression tutorial for SQL </a> @@ -2065,7 +2080,7 @@ <b>13.4.1.</b> - Top-k Join processing + Top-k join processing </a> @@ -2124,25 +2139,10 @@ <li class="chapter " data-level="15.1" > - <a target="_blank" href="https://github.com/maropu/hivemall-spark";> - - - <b>15.1.</b> - - Hivemall on Apache Spark - - </a> - - - - </li> - - <li class="chapter " data-level="15.2" > - <a target="_blank" href="https://github.com/daijyc/hivemall/wiki/PigHome";> - <b>15.2.</b> + <b>15.1.</b> Hivemall on Apache Pig @@ -2182,7 +2182,7 @@ <!-- Title --> <h1> <i class="fa fa-circle-o-notch fa-spin"></i> - <a href=".." >List of generic Hivemall functions</a> + <a href=".." >List of Generic Hivemall Functions</a> </h1> </div> @@ -2215,7 +2215,7 @@ specific language governing permissions and limitations under the License. --> -<p>This page describes a list of useful Hivemall generic functions.</p> +<p>This page describes a list of useful Hivemall generic functions. See also a <a href="funcs.html">list of machine-learning-related functions</a>.</p> <!-- toc --><div id="toc" class="toc"> <ul> @@ -2238,6 +2238,7 @@ </li> <li><a href="#mapreduce-functions">MapReduce functions</a></li> <li><a href="#math-functions">Math functions</a></li> +<li><a href="#matrix-functions">Matrix functions</a></li> <li><a href="#text-processing-functions">Text processing functions</a></li> <li><a href="#other-functions">Other functions</a></li> </ul> @@ -2284,6 +2285,12 @@ > [3,4] </code></pre> </li> +<li><p><code>float_array(nDims)</code> - Returns an array<float> of nDims elements</p> +</li> +<li><p><code>select_k_best(array<number> array, const array<number> importance, const int k)</code> - Returns selected top-k elements as array<double></p> +</li> +<li><p><code>to_string_array(array<ANY>)</code> - Returns an array of strings</p> +</li> </ul> <h2 id="array-udafs">Array UDAFs</h2> <ul> @@ -2315,10 +2322,10 @@ to_ordered_list(<span class="hljs-keyword">value</span>, <span class="hljs-keyword">key</span>, <span class="hljs-string">'-k -2'</span>), <span class="hljs-comment">-- [donut, (banana | egg)] (tail-k)</span> to_ordered_list(<span class="hljs-keyword">value</span>, <span class="hljs-keyword">key</span>, <span class="hljs-string">'-k -100'</span>), <span class="hljs-comment">-- [donut, (banana, egg | egg, banana), candy, apple]</span> to_ordered_list(<span class="hljs-keyword">value</span>, <span class="hljs-keyword">key</span>, <span class="hljs-string">'-k -2 -reverse'</span>), <span class="hljs-comment">-- [apple, candy] (reverse tail-k = top-k)</span> - to_ordered_list(<span class="hljs-keyword">value</span>, <span class="hljs-string">'-k 2'</span>), <span class="hljs-comment">-- [egg, donut] (alphabetically) </span> + to_ordered_list(<span class="hljs-keyword">value</span>, <span class="hljs-string">'-k 2'</span>), <span class="hljs-comment">-- [egg, donut] (alphabetically)</span> to_ordered_list(<span class="hljs-keyword">key</span>, <span class="hljs-string">'-k -2 -reverse'</span>), <span class="hljs-comment">-- [5, 4] (top-2 keys)</span> to_ordered_list(<span class="hljs-keyword">key</span>) <span class="hljs-comment">-- [2, 3, 3, 4, 5] (natural ordered keys)</span> - <span class="hljs-keyword">from</span> + <span class="hljs-keyword">from</span> t ; </code></pre> @@ -2399,14 +2406,29 @@ The compression level must be in range [-1,9]</p> </ul> <h1 id="mapreduce-functions">MapReduce functions</h1> <ul> +<li><p><code>distcache_gets(filepath, key, default_value [, parseKey])</code> - Returns map<key_type, value_type>|value_type</p> +</li> +<li><p><code>jobconf_gets()</code> - Returns the value from JobConf</p> +</li> +<li><p><code>jobid()</code> - Returns the value of mapred.job.id</p> +</li> <li><p><code>rowid()</code> - Returns a generated row id of a form {TASK_ID}-{SEQUENCE_NUMBER}</p> </li> +<li><p><code>rownum()</code> - Returns a generated row number in long</p> +</li> <li><p><code>taskid()</code> - Returns the value of mapred.task.partition</p> </li> </ul> <h1 id="math-functions">Math functions</h1> <ul> -<li><code>sigmoid(x)</code> - Returns <code>1.0 / (1.0 + exp(-x))</code></li> +<li><p><code>l2_norm(double xi)</code> - Return L2 norm of a vector which has the given values in each dimension</p> +</li> +<li><p><code>sigmoid(x)</code> - Returns <code>1.0 / (1.0 + exp(-x))</code></p> +</li> +</ul> +<h1 id="matrix-functions">Matrix functions</h1> +<ul> +<li><code>transpose_and_dot(array<number> matrix0_row, array<number> matrix1_row)</code> - Returns dot(matrix0.T, matrix1) as array<array<double>>, shape = (matrix0.#cols, matrix1.#cols)</li> </ul> <h1 id="text-processing-functions">Text processing functions</h1> <ul> @@ -2440,12 +2462,14 @@ The compression level must be in range [-1,9]</p> </li> <li><p><code>tokenize(string englishText [, boolean toLowerCase])</code> - Returns words in array<string></string></p> </li> -<li><p><code>tokenize_ja(String line [, const string mode = "normal", const list<string> stopWords, const list<string> stopTags])</code> - returns tokenized strings in array<string>. Refer <a href="tokenizer.html">this article</a> for detail.</string></p> +<li><p><code>tokenize_ja(String line [, const string mode = "normal", const list<string> stopWords, const list<string> stopTags])</code> - returns tokenized Japanese string in array<string>. Refer <a href="tokenizer.html">this article</a> for detail.</string></p> <pre><code class="lang-sql"> select tokenize_ja("kuromojiを使った分かち書きのテストです。第二引数にはnormal/search/extendedを指定できます。デフォルトではnormalモードです。"); > ["kuromoji","使う","分かち書き","テスト","第","二","引数","normal","search","extended","指定","デフォルト","normal"," モード"] </code></pre> </li> +<li><p><code>tokenize_cn(String line [, const list<string> stopWords])</code> - returns tokenized Chinese string in array<string>. Refer <a href="tokenizer.html">this article</a> for detail.</p> +</li> <li><p><code>word_ngrams(array<string> words, int minSize, int maxSize)</code> - Returns list of n-grams where <code>minSize <= n <= maxSize</code></p> <pre><code class="lang-sql"> select word_ngrams(tokenize('Machine learning is fun!', true), 1, 2); @@ -2533,7 +2557,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda <script> var gitbook = gitbook || []; gitbook.push(function() { - gitbook.page.hasChanged({"page":{"title":"List of generic Hivemall functions","level":"2.1","depth":1,"next":{"title":"Efficient Top-K query processing","level":"2.2","depth":1,"path":"misc/topk.md","ref":"misc/topk.md","articles":[]},"previous":{"title":"Map-side Join causes ClassCastException on Tez","level":"1.5.5","depth":2,"path":"troubleshooting/mapjoin_classcastex.md","ref":"troubleshooting/mapjoin_classcastex.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{" url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/eb ook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/generic_funcs.md","mtime":"2017-11-02T05:41:05.000Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-03-13T16:05:28.906Z"},"basePath":"..","book":{"language":""}}); + gitbook.page.hasChanged({"page":{"title":"List of Generic Hivemall Functions","level":"2.1","depth":1,"next":{"title":"Efficient Top-K Query Processing","level":"2.2","depth":1,"path":"misc/topk.md","ref":"misc/topk.md","articles":[]},"previous":{"title":"Map-side join causes ClassCastException on Tez","level":"1.6.5","depth":2,"path":"troubleshooting/mapjoin_classcastex.md","ref":"troubleshooting/mapjoin_classcastex.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{" url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/eb ook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/generic_funcs.md","mtime":"2018-04-16T14:13:57.886Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-04-16T14:16:24.937Z"},"basePath":"..","book":{"language":""}}); }); </script> </div>
http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/b8a847fa/userguide/misc/prediction.html ---------------------------------------------------------------------- diff --git a/userguide/misc/prediction.html b/userguide/misc/prediction.html index b7b9c15..610149a 100644 --- a/userguide/misc/prediction.html +++ b/userguide/misc/prediction.html @@ -221,13 +221,28 @@ </li> - <li class="chapter " data-level="1.3" data-path="../tips/"> + <li class="chapter " data-level="1.3" data-path="funcs.html"> - <a href="../tips/"> + <a href="funcs.html"> <b>1.3.</b> + List of Functions + + </a> + + + + </li> + + <li class="chapter " data-level="1.4" data-path="../tips/"> + + <a href="../tips/"> + + + <b>1.4.</b> + Tips for Effective Hivemall </a> @@ -237,12 +252,12 @@ <ul class="articles"> - <li class="chapter " data-level="1.3.1" data-path="../tips/addbias.html"> + <li class="chapter " data-level="1.4.1" data-path="../tips/addbias.html"> <a href="../tips/addbias.html"> - <b>1.3.1.</b> + <b>1.4.1.</b> Explicit add_bias() for better prediction @@ -252,12 +267,12 @@ </li> - <li class="chapter " data-level="1.3.2" data-path="../tips/rand_amplify.html"> + <li class="chapter " data-level="1.4.2" data-path="../tips/rand_amplify.html"> <a href="../tips/rand_amplify.html"> - <b>1.3.2.</b> + <b>1.4.2.</b> Use rand_amplify() to better prediction results @@ -267,14 +282,14 @@ </li> - <li class="chapter " data-level="1.3.3" data-path="../tips/rt_prediction.html"> + <li class="chapter " data-level="1.4.3" data-path="../tips/rt_prediction.html"> <a href="../tips/rt_prediction.html"> - <b>1.3.3.</b> + <b>1.4.3.</b> - Real-time Prediction on RDBMS + Real-time prediction on RDBMS </a> @@ -282,12 +297,12 @@ </li> - <li class="chapter " data-level="1.3.4" data-path="../tips/ensemble_learning.html"> + <li class="chapter " data-level="1.4.4" data-path="../tips/ensemble_learning.html"> <a href="../tips/ensemble_learning.html"> - <b>1.3.4.</b> + <b>1.4.4.</b> Ensemble learning for stable prediction @@ -297,12 +312,12 @@ </li> - <li class="chapter " data-level="1.3.5" data-path="../tips/mixserver.html"> + <li class="chapter " data-level="1.4.5" data-path="../tips/mixserver.html"> <a href="../tips/mixserver.html"> - <b>1.3.5.</b> + <b>1.4.5.</b> Mixing models for a better prediction convergence (MIX server) @@ -312,12 +327,12 @@ </li> - <li class="chapter " data-level="1.3.6" data-path="../tips/emr.html"> + <li class="chapter " data-level="1.4.6" data-path="../tips/emr.html"> <a href="../tips/emr.html"> - <b>1.3.6.</b> + <b>1.4.6.</b> Run Hivemall on Amazon Elastic MapReduce @@ -332,14 +347,14 @@ </li> - <li class="chapter " data-level="1.4" data-path="../tips/general_tips.html"> + <li class="chapter " data-level="1.5" data-path="../tips/general_tips.html"> <a href="../tips/general_tips.html"> - <b>1.4.</b> + <b>1.5.</b> - General Hive/Hadoop tips + General Hive/Hadoop Tips </a> @@ -348,12 +363,12 @@ <ul class="articles"> - <li class="chapter " data-level="1.4.1" data-path="../tips/rowid.html"> + <li class="chapter " data-level="1.5.1" data-path="../tips/rowid.html"> <a href="../tips/rowid.html"> - <b>1.4.1.</b> + <b>1.5.1.</b> Adding rowid for each row @@ -363,12 +378,12 @@ </li> - <li class="chapter " data-level="1.4.2" data-path="../tips/hadoop_tuning.html"> + <li class="chapter " data-level="1.5.2" data-path="../tips/hadoop_tuning.html"> <a href="../tips/hadoop_tuning.html"> - <b>1.4.2.</b> + <b>1.5.2.</b> Hadoop tuning for Hivemall @@ -383,12 +398,12 @@ </li> - <li class="chapter " data-level="1.5" data-path="../troubleshooting/"> + <li class="chapter " data-level="1.6" data-path="../troubleshooting/"> <a href="../troubleshooting/"> - <b>1.5.</b> + <b>1.6.</b> Troubleshooting @@ -399,12 +414,12 @@ <ul class="articles"> - <li class="chapter " data-level="1.5.1" data-path="../troubleshooting/oom.html"> + <li class="chapter " data-level="1.6.1" data-path="../troubleshooting/oom.html"> <a href="../troubleshooting/oom.html"> - <b>1.5.1.</b> + <b>1.6.1.</b> OutOfMemoryError in training @@ -414,14 +429,14 @@ </li> - <li class="chapter " data-level="1.5.2" data-path="../troubleshooting/mapjoin_task_error.html"> + <li class="chapter " data-level="1.6.2" data-path="../troubleshooting/mapjoin_task_error.html"> <a href="../troubleshooting/mapjoin_task_error.html"> - <b>1.5.2.</b> + <b>1.6.2.</b> - SemanticException Generate Map Join Task Error: Cannot serialize object + SemanticException generate map join task error: Cannot serialize object </a> @@ -429,12 +444,12 @@ </li> - <li class="chapter " data-level="1.5.3" data-path="../troubleshooting/asterisk.html"> + <li class="chapter " data-level="1.6.3" data-path="../troubleshooting/asterisk.html"> <a href="../troubleshooting/asterisk.html"> - <b>1.5.3.</b> + <b>1.6.3.</b> Asterisk argument for UDTF does not work @@ -444,12 +459,12 @@ </li> - <li class="chapter " data-level="1.5.4" data-path="../troubleshooting/num_mappers.html"> + <li class="chapter " data-level="1.6.4" data-path="../troubleshooting/num_mappers.html"> <a href="../troubleshooting/num_mappers.html"> - <b>1.5.4.</b> + <b>1.6.4.</b> The number of mappers is less than input splits in Hadoop 2.x @@ -459,14 +474,14 @@ </li> - <li class="chapter " data-level="1.5.5" data-path="../troubleshooting/mapjoin_classcastex.html"> + <li class="chapter " data-level="1.6.5" data-path="../troubleshooting/mapjoin_classcastex.html"> <a href="../troubleshooting/mapjoin_classcastex.html"> - <b>1.5.5.</b> + <b>1.6.5.</b> - Map-side Join causes ClassCastException on Tez + Map-side join causes ClassCastException on Tez </a> @@ -493,7 +508,7 @@ <b>2.1.</b> - List of generic Hivemall functions + List of Generic Hivemall Functions </a> @@ -508,7 +523,7 @@ <b>2.2.</b> - Efficient Top-K query processing + Efficient Top-K Query Processing </a> @@ -620,7 +635,7 @@ <b>3.5.</b> - FEATURE PAIRING + Feature Paring </a> @@ -636,7 +651,7 @@ <b>3.5.1.</b> - Polynomial Features + Polynomial features </a> @@ -656,7 +671,7 @@ <b>3.6.</b> - FEATURE TRANSFORMATION + Feature Transformation </a> @@ -672,7 +687,7 @@ <b>3.6.1.</b> - Feature Vectorization + Feature vectorization </a> @@ -745,7 +760,7 @@ <b>4.1.1.</b> - Area Under the ROC Curve + Area under the ROC curve </a> @@ -780,7 +795,7 @@ <b>4.3.</b> - Regression metrics + Regression Metrics </a> @@ -864,7 +879,7 @@ - <li class="header">Part VI - Binary classification</li> + <li class="header">Part VI - Binary Classification</li> @@ -890,7 +905,7 @@ <b>6.2.</b> - a9a tutorial + a9a Tutorial </a> @@ -936,7 +951,7 @@ <b>6.2.3.</b> - Mini-batch Gradient Descent + Mini-batch gradient descent </a> @@ -956,7 +971,7 @@ <b>6.3.</b> - News20 tutorial + News20 Tutorial </a> @@ -1052,7 +1067,7 @@ <b>6.4.</b> - KDD2010a tutorial + KDD2010a Tutorial </a> @@ -1103,7 +1118,7 @@ <b>6.5.</b> - KDD2010b tutorial + KDD2010b Tutorial </a> @@ -1154,7 +1169,7 @@ <b>6.6.</b> - Webspam tutorial + Webspam Tutorial </a> @@ -1205,7 +1220,7 @@ <b>6.7.</b> - Kaggle Titanic tutorial + Kaggle Titanic Tutorial </a> @@ -1216,7 +1231,7 @@ - <li class="header">Part VII - Multiclass classification</li> + <li class="header">Part VII - Multiclass Classification</li> @@ -1227,7 +1242,7 @@ <b>7.1.</b> - News20 Multiclass tutorial + News20 Multiclass Tutorial </a> @@ -1338,7 +1353,7 @@ <b>7.2.</b> - Iris tutorial + Iris Tutorial </a> @@ -1426,7 +1441,7 @@ <b>8.2.</b> - E2006-tfidf regression tutorial + E2006-tfidf Regression Tutorial </a> @@ -1477,7 +1492,7 @@ <b>8.3.</b> - KDDCup 2012 track 2 CTR prediction tutorial + KDDCup 2012 Track 2 CTR Prediction Tutorial </a> @@ -1523,7 +1538,7 @@ <b>8.3.3.</b> - Logistic Regression with Amplifier + Logistic Regression with amplifier </a> @@ -1581,7 +1596,7 @@ <b>9.1.1.</b> - Item-based Collaborative Filtering + Item-based collaborative filtering </a> @@ -1601,7 +1616,7 @@ <b>9.2.</b> - News20 related article recommendation Tutorial + News20 Related Article Recommendation Tutorial </a> @@ -1632,7 +1647,7 @@ <b>9.2.2.</b> - LSH/Minhash and Jaccard Similarity + LSH/MinHash and Jaccard similarity </a> @@ -1647,7 +1662,7 @@ <b>9.2.3.</b> - LSH/Minhash and Brute-Force Search + LSH/MinHash and brute-force search </a> @@ -1662,7 +1677,7 @@ <b>9.2.4.</b> - kNN search using b-Bits Minhash + kNN search using b-Bits MinHash </a> @@ -1682,7 +1697,7 @@ <b>9.3.</b> - MovieLens movie recommendation Tutorial + MovieLens Movie Recommendation Tutorial </a> @@ -1713,7 +1728,7 @@ <b>9.3.2.</b> - Item-based Collaborative Filtering + Item-based collaborative filtering </a> @@ -1758,7 +1773,7 @@ <b>9.3.5.</b> - SLIM for Fast Top-K Recommendation + SLIM for fast top-k recommendation </a> @@ -1773,7 +1788,7 @@ <b>9.3.6.</b> - 10-fold Cross Validation (Matrix Factorization) + 10-fold cross validation (Matrix Factorization) </a> @@ -1878,7 +1893,7 @@ - <li class="header">Part XII - GeoSpatial functions</li> + <li class="header">Part XII - GeoSpatial Functions</li> @@ -1963,7 +1978,7 @@ <b>13.2.1.</b> - a9a Tutorial for DataFrame + a9a tutorial for DataFrame </a> @@ -1978,7 +1993,7 @@ <b>13.2.2.</b> - a9a Tutorial for SQL + a9a tutorial for SQL </a> @@ -2014,7 +2029,7 @@ <b>13.3.1.</b> - E2006-tfidf regression Tutorial for DataFrame + E2006-tfidf regression tutorial for DataFrame </a> @@ -2029,7 +2044,7 @@ <b>13.3.2.</b> - E2006-tfidf regression Tutorial for SQL + E2006-tfidf regression tutorial for SQL </a> @@ -2065,7 +2080,7 @@ <b>13.4.1.</b> - Top-k Join processing + Top-k join processing </a> @@ -2124,25 +2139,10 @@ <li class="chapter " data-level="15.1" > - <a target="_blank" href="https://github.com/maropu/hivemall-spark";> - - - <b>15.1.</b> - - Hivemall on Apache Spark - - </a> - - - - </li> - - <li class="chapter " data-level="15.2" > - <a target="_blank" href="https://github.com/daijyc/hivemall/wiki/PigHome";> - <b>15.2.</b> + <b>15.1.</b> Hivemall on Apache Pig @@ -2463,7 +2463,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda <script> var gitbook = gitbook || []; gitbook.push(function() { - gitbook.page.hasChanged({"page":{"title":"How Prediction Works","level":"5.1","depth":1,"next":{"title":"Binary Classification","level":"6.1","depth":1,"path":"binaryclass/general.md","ref":"binaryclass/general.md","articles":[]},"previous":{"title":"Logistic Regression data generation","level":"4.5.1","depth":2,"path":"eval/lr_datagen.md","ref":"eval/lr_datagen.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"s plitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"; anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/prediction.md","mtime":"2017-11-02T05:41:05.000Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-03-13T16:05:28.906Z"},"basePath":"..","book":{"language":""}}); + gitbook.page.hasChanged({"page":{"title":"How Prediction Works","level":"5.1","depth":1,"next":{"title":"Binary Classification","level":"6.1","depth":1,"path":"binaryclass/general.md","ref":"binaryclass/general.md","articles":[]},"previous":{"title":"Logistic Regression data generation","level":"4.5.1","depth":2,"path":"eval/lr_datagen.md","ref":"eval/lr_datagen.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"s plitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"; anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/prediction.md","mtime":"2017-11-02T05:41:05.000Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-04-16T14:16:24.937Z"},"basePath":"..","book":{"language":""}}); }); </script> </div> http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/b8a847fa/userguide/misc/tokenizer.html ---------------------------------------------------------------------- diff --git a/userguide/misc/tokenizer.html b/userguide/misc/tokenizer.html index 509a82e..436e5d3 100644 --- a/userguide/misc/tokenizer.html +++ b/userguide/misc/tokenizer.html @@ -221,13 +221,28 @@ </li> - <li class="chapter " data-level="1.3" data-path="../tips/"> + <li class="chapter " data-level="1.3" data-path="funcs.html"> - <a href="../tips/"> + <a href="funcs.html"> <b>1.3.</b> + List of Functions + + </a> + + + + </li> + + <li class="chapter " data-level="1.4" data-path="../tips/"> + + <a href="../tips/"> + + + <b>1.4.</b> + Tips for Effective Hivemall </a> @@ -237,12 +252,12 @@ <ul class="articles"> - <li class="chapter " data-level="1.3.1" data-path="../tips/addbias.html"> + <li class="chapter " data-level="1.4.1" data-path="../tips/addbias.html"> <a href="../tips/addbias.html"> - <b>1.3.1.</b> + <b>1.4.1.</b> Explicit add_bias() for better prediction @@ -252,12 +267,12 @@ </li> - <li class="chapter " data-level="1.3.2" data-path="../tips/rand_amplify.html"> + <li class="chapter " data-level="1.4.2" data-path="../tips/rand_amplify.html"> <a href="../tips/rand_amplify.html"> - <b>1.3.2.</b> + <b>1.4.2.</b> Use rand_amplify() to better prediction results @@ -267,14 +282,14 @@ </li> - <li class="chapter " data-level="1.3.3" data-path="../tips/rt_prediction.html"> + <li class="chapter " data-level="1.4.3" data-path="../tips/rt_prediction.html"> <a href="../tips/rt_prediction.html"> - <b>1.3.3.</b> + <b>1.4.3.</b> - Real-time Prediction on RDBMS + Real-time prediction on RDBMS </a> @@ -282,12 +297,12 @@ </li> - <li class="chapter " data-level="1.3.4" data-path="../tips/ensemble_learning.html"> + <li class="chapter " data-level="1.4.4" data-path="../tips/ensemble_learning.html"> <a href="../tips/ensemble_learning.html"> - <b>1.3.4.</b> + <b>1.4.4.</b> Ensemble learning for stable prediction @@ -297,12 +312,12 @@ </li> - <li class="chapter " data-level="1.3.5" data-path="../tips/mixserver.html"> + <li class="chapter " data-level="1.4.5" data-path="../tips/mixserver.html"> <a href="../tips/mixserver.html"> - <b>1.3.5.</b> + <b>1.4.5.</b> Mixing models for a better prediction convergence (MIX server) @@ -312,12 +327,12 @@ </li> - <li class="chapter " data-level="1.3.6" data-path="../tips/emr.html"> + <li class="chapter " data-level="1.4.6" data-path="../tips/emr.html"> <a href="../tips/emr.html"> - <b>1.3.6.</b> + <b>1.4.6.</b> Run Hivemall on Amazon Elastic MapReduce @@ -332,14 +347,14 @@ </li> - <li class="chapter " data-level="1.4" data-path="../tips/general_tips.html"> + <li class="chapter " data-level="1.5" data-path="../tips/general_tips.html"> <a href="../tips/general_tips.html"> - <b>1.4.</b> + <b>1.5.</b> - General Hive/Hadoop tips + General Hive/Hadoop Tips </a> @@ -348,12 +363,12 @@ <ul class="articles"> - <li class="chapter " data-level="1.4.1" data-path="../tips/rowid.html"> + <li class="chapter " data-level="1.5.1" data-path="../tips/rowid.html"> <a href="../tips/rowid.html"> - <b>1.4.1.</b> + <b>1.5.1.</b> Adding rowid for each row @@ -363,12 +378,12 @@ </li> - <li class="chapter " data-level="1.4.2" data-path="../tips/hadoop_tuning.html"> + <li class="chapter " data-level="1.5.2" data-path="../tips/hadoop_tuning.html"> <a href="../tips/hadoop_tuning.html"> - <b>1.4.2.</b> + <b>1.5.2.</b> Hadoop tuning for Hivemall @@ -383,12 +398,12 @@ </li> - <li class="chapter " data-level="1.5" data-path="../troubleshooting/"> + <li class="chapter " data-level="1.6" data-path="../troubleshooting/"> <a href="../troubleshooting/"> - <b>1.5.</b> + <b>1.6.</b> Troubleshooting @@ -399,12 +414,12 @@ <ul class="articles"> - <li class="chapter " data-level="1.5.1" data-path="../troubleshooting/oom.html"> + <li class="chapter " data-level="1.6.1" data-path="../troubleshooting/oom.html"> <a href="../troubleshooting/oom.html"> - <b>1.5.1.</b> + <b>1.6.1.</b> OutOfMemoryError in training @@ -414,14 +429,14 @@ </li> - <li class="chapter " data-level="1.5.2" data-path="../troubleshooting/mapjoin_task_error.html"> + <li class="chapter " data-level="1.6.2" data-path="../troubleshooting/mapjoin_task_error.html"> <a href="../troubleshooting/mapjoin_task_error.html"> - <b>1.5.2.</b> + <b>1.6.2.</b> - SemanticException Generate Map Join Task Error: Cannot serialize object + SemanticException generate map join task error: Cannot serialize object </a> @@ -429,12 +444,12 @@ </li> - <li class="chapter " data-level="1.5.3" data-path="../troubleshooting/asterisk.html"> + <li class="chapter " data-level="1.6.3" data-path="../troubleshooting/asterisk.html"> <a href="../troubleshooting/asterisk.html"> - <b>1.5.3.</b> + <b>1.6.3.</b> Asterisk argument for UDTF does not work @@ -444,12 +459,12 @@ </li> - <li class="chapter " data-level="1.5.4" data-path="../troubleshooting/num_mappers.html"> + <li class="chapter " data-level="1.6.4" data-path="../troubleshooting/num_mappers.html"> <a href="../troubleshooting/num_mappers.html"> - <b>1.5.4.</b> + <b>1.6.4.</b> The number of mappers is less than input splits in Hadoop 2.x @@ -459,14 +474,14 @@ </li> - <li class="chapter " data-level="1.5.5" data-path="../troubleshooting/mapjoin_classcastex.html"> + <li class="chapter " data-level="1.6.5" data-path="../troubleshooting/mapjoin_classcastex.html"> <a href="../troubleshooting/mapjoin_classcastex.html"> - <b>1.5.5.</b> + <b>1.6.5.</b> - Map-side Join causes ClassCastException on Tez + Map-side join causes ClassCastException on Tez </a> @@ -493,7 +508,7 @@ <b>2.1.</b> - List of generic Hivemall functions + List of Generic Hivemall Functions </a> @@ -508,7 +523,7 @@ <b>2.2.</b> - Efficient Top-K query processing + Efficient Top-K Query Processing </a> @@ -620,7 +635,7 @@ <b>3.5.</b> - FEATURE PAIRING + Feature Paring </a> @@ -636,7 +651,7 @@ <b>3.5.1.</b> - Polynomial Features + Polynomial features </a> @@ -656,7 +671,7 @@ <b>3.6.</b> - FEATURE TRANSFORMATION + Feature Transformation </a> @@ -672,7 +687,7 @@ <b>3.6.1.</b> - Feature Vectorization + Feature vectorization </a> @@ -745,7 +760,7 @@ <b>4.1.1.</b> - Area Under the ROC Curve + Area under the ROC curve </a> @@ -780,7 +795,7 @@ <b>4.3.</b> - Regression metrics + Regression Metrics </a> @@ -864,7 +879,7 @@ - <li class="header">Part VI - Binary classification</li> + <li class="header">Part VI - Binary Classification</li> @@ -890,7 +905,7 @@ <b>6.2.</b> - a9a tutorial + a9a Tutorial </a> @@ -936,7 +951,7 @@ <b>6.2.3.</b> - Mini-batch Gradient Descent + Mini-batch gradient descent </a> @@ -956,7 +971,7 @@ <b>6.3.</b> - News20 tutorial + News20 Tutorial </a> @@ -1052,7 +1067,7 @@ <b>6.4.</b> - KDD2010a tutorial + KDD2010a Tutorial </a> @@ -1103,7 +1118,7 @@ <b>6.5.</b> - KDD2010b tutorial + KDD2010b Tutorial </a> @@ -1154,7 +1169,7 @@ <b>6.6.</b> - Webspam tutorial + Webspam Tutorial </a> @@ -1205,7 +1220,7 @@ <b>6.7.</b> - Kaggle Titanic tutorial + Kaggle Titanic Tutorial </a> @@ -1216,7 +1231,7 @@ - <li class="header">Part VII - Multiclass classification</li> + <li class="header">Part VII - Multiclass Classification</li> @@ -1227,7 +1242,7 @@ <b>7.1.</b> - News20 Multiclass tutorial + News20 Multiclass Tutorial </a> @@ -1338,7 +1353,7 @@ <b>7.2.</b> - Iris tutorial + Iris Tutorial </a> @@ -1426,7 +1441,7 @@ <b>8.2.</b> - E2006-tfidf regression tutorial + E2006-tfidf Regression Tutorial </a> @@ -1477,7 +1492,7 @@ <b>8.3.</b> - KDDCup 2012 track 2 CTR prediction tutorial + KDDCup 2012 Track 2 CTR Prediction Tutorial </a> @@ -1523,7 +1538,7 @@ <b>8.3.3.</b> - Logistic Regression with Amplifier + Logistic Regression with amplifier </a> @@ -1581,7 +1596,7 @@ <b>9.1.1.</b> - Item-based Collaborative Filtering + Item-based collaborative filtering </a> @@ -1601,7 +1616,7 @@ <b>9.2.</b> - News20 related article recommendation Tutorial + News20 Related Article Recommendation Tutorial </a> @@ -1632,7 +1647,7 @@ <b>9.2.2.</b> - LSH/Minhash and Jaccard Similarity + LSH/MinHash and Jaccard similarity </a> @@ -1647,7 +1662,7 @@ <b>9.2.3.</b> - LSH/Minhash and Brute-Force Search + LSH/MinHash and brute-force search </a> @@ -1662,7 +1677,7 @@ <b>9.2.4.</b> - kNN search using b-Bits Minhash + kNN search using b-Bits MinHash </a> @@ -1682,7 +1697,7 @@ <b>9.3.</b> - MovieLens movie recommendation Tutorial + MovieLens Movie Recommendation Tutorial </a> @@ -1713,7 +1728,7 @@ <b>9.3.2.</b> - Item-based Collaborative Filtering + Item-based collaborative filtering </a> @@ -1758,7 +1773,7 @@ <b>9.3.5.</b> - SLIM for Fast Top-K Recommendation + SLIM for fast top-k recommendation </a> @@ -1773,7 +1788,7 @@ <b>9.3.6.</b> - 10-fold Cross Validation (Matrix Factorization) + 10-fold cross validation (Matrix Factorization) </a> @@ -1878,7 +1893,7 @@ - <li class="header">Part XII - GeoSpatial functions</li> + <li class="header">Part XII - GeoSpatial Functions</li> @@ -1963,7 +1978,7 @@ <b>13.2.1.</b> - a9a Tutorial for DataFrame + a9a tutorial for DataFrame </a> @@ -1978,7 +1993,7 @@ <b>13.2.2.</b> - a9a Tutorial for SQL + a9a tutorial for SQL </a> @@ -2014,7 +2029,7 @@ <b>13.3.1.</b> - E2006-tfidf regression Tutorial for DataFrame + E2006-tfidf regression tutorial for DataFrame </a> @@ -2029,7 +2044,7 @@ <b>13.3.2.</b> - E2006-tfidf regression Tutorial for SQL + E2006-tfidf regression tutorial for SQL </a> @@ -2065,7 +2080,7 @@ <b>13.4.1.</b> - Top-k Join processing + Top-k join processing </a> @@ -2124,25 +2139,10 @@ <li class="chapter " data-level="15.1" > - <a target="_blank" href="https://github.com/maropu/hivemall-spark";> - - - <b>15.1.</b> - - Hivemall on Apache Spark - - </a> - - - - </li> - - <li class="chapter " data-level="15.2" > - <a target="_blank" href="https://github.com/daijyc/hivemall/wiki/PigHome";> - <b>15.2.</b> + <b>15.1.</b> Hivemall on Apache Pig @@ -2342,7 +2342,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda <script> var gitbook = gitbook || []; gitbook.push(function() { - gitbook.page.hasChanged({"page":{"title":"Text Tokenizer","level":"2.3","depth":1,"next":{"title":"Approximate Aggregate Functions","level":"2.4","depth":1,"path":"misc/approx.md","ref":"misc/approx.md","articles":[]},"previous":{"title":"Efficient Top-K query processing","level":"2.2","depth":1,"path":"misc/topk.md","ref":"misc/topk.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"down loadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"selector":"h1,h2, h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/tokenizer.md","mtime":"2017-12-28T14:29:13.886Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-03-13T16:05:28.906Z"},"basePath":"..","book":{"language":""}}); + gitbook.page.hasChanged({"page":{"title":"Text Tokenizer","level":"2.3","depth":1,"next":{"title":"Approximate Aggregate Functions","level":"2.4","depth":1,"path":"misc/approx.md","ref":"misc/approx.md","articles":[]},"previous":{"title":"Efficient Top-K Query Processing","level":"2.2","depth":1,"path":"misc/topk.md","ref":"misc/topk.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"down loadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"selector":"h1,h2, h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/tokenizer.md","mtime":"2017-12-28T14:29:13.886Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-04-16T14:16:24.937Z"},"basePath":"..","book":{"language":""}}); }); </script> </div>
