http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/30afb6e4/userguide/misc/topk.html
----------------------------------------------------------------------
diff --git a/userguide/misc/topk.html b/userguide/misc/topk.html
new file mode 100644
index 0000000..a1ddad7
--- /dev/null
+++ b/userguide/misc/topk.html
@@ -0,0 +1,2003 @@
+
+<!DOCTYPE HTML>
+<html lang="" >
+ <head>
+ <meta charset="UTF-8">
+ <meta content="text/html; charset=utf-8" http-equiv="Content-Type">
+ <title>Efficient Top-K query processing · Hivemall User Manual</title>
+ <meta http-equiv="X-UA-Compatible" content="IE=edge" />
+ <meta name="description" content="">
+ <meta name="generator" content="GitBook 3.2.2">
+
+
+
+
+ <link rel="stylesheet" href="../gitbook/style.css">
+
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-splitter/splitter.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-etoc/plugin.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-callouts/plugin.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-toggle-chapters/toggle.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-codeblock-filename/block.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-expandable-chapters/expandable-chapters.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-multipart/multipart.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-katex/katex.min.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-emphasize/plugin.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-highlight/website.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-search/search.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-fontsettings/website.css">
+
+
+
+ <link rel="stylesheet"
href="../gitbook/gitbook-plugin-theme-api/theme-api.css">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <meta name="HandheldFriendly" content="true"/>
+ <meta name="viewport" content="width=device-width, initial-scale=1,
user-scalable=no">
+ <meta name="apple-mobile-web-app-capable" content="yes">
+ <meta name="apple-mobile-web-app-status-bar-style" content="black">
+ <link rel="apple-touch-icon-precomposed" sizes="152x152"
href="../gitbook/images/apple-touch-icon-precomposed-152.png">
+ <link rel="shortcut icon" href="../gitbook/images/favicon.ico"
type="image/x-icon">
+
+
+ <link rel="next" href="tokenizer.html" />
+
+
+ <link rel="prev" href="generic_funcs.html" />
+
+
+ </head>
+ <body>
+
+<div class="book">
+ <div class="book-summary">
+
+
+<div id="book-search-input" role="search">
+ <input type="text" placeholder="Type to search" />
+</div>
+
+
+ <nav role="navigation">
+
+
+
+<ul class="summary">
+
+
+
+
+ <li>
+ <a href="http://hivemall.incubator.apache.org/"; target="_blank"
class="custom-link"><i class="fa fa-home"></i> Home</a>
+ </li>
+
+
+
+
+ <li class="divider"></li>
+
+
+
+
+ <li class="header">TABLE OF CONTENTS</li>
+
+
+
+ <li class="chapter " data-level="1.1" data-path="../">
+
+ <a href="../">
+
+
+ <b>1.1.</b>
+
+ Introduction
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.2" data-path="../getting_started/">
+
+ <a href="../getting_started/">
+
+
+ <b>1.2.</b>
+
+ Getting Started
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="1.2.1"
data-path="../getting_started/installation.html">
+
+ <a href="../getting_started/installation.html">
+
+
+ <b>1.2.1.</b>
+
+ Installation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.2.2"
data-path="../getting_started/permanent-functions.html">
+
+ <a href="../getting_started/permanent-functions.html">
+
+
+ <b>1.2.2.</b>
+
+ Install as permanent functions
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.2.3"
data-path="../getting_started/input-format.html">
+
+ <a href="../getting_started/input-format.html">
+
+
+ <b>1.2.3.</b>
+
+ Input Format
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="1.3" data-path="../tips/">
+
+ <a href="../tips/">
+
+
+ <b>1.3.</b>
+
+ Tips for Effective Hivemall
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="1.3.1"
data-path="../tips/addbias.html">
+
+ <a href="../tips/addbias.html">
+
+
+ <b>1.3.1.</b>
+
+ Explicit addBias() for better prediction
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.3.2"
data-path="../tips/rand_amplify.html">
+
+ <a href="../tips/rand_amplify.html">
+
+
+ <b>1.3.2.</b>
+
+ Use rand_amplify() to better prediction results
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.3.3"
data-path="../tips/rt_prediction.html">
+
+ <a href="../tips/rt_prediction.html">
+
+
+ <b>1.3.3.</b>
+
+ Real-time Prediction on RDBMS
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.3.4"
data-path="../tips/ensemble_learning.html">
+
+ <a href="../tips/ensemble_learning.html">
+
+
+ <b>1.3.4.</b>
+
+ Ensemble learning for stable prediction
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.3.5"
data-path="../tips/mixserver.html">
+
+ <a href="../tips/mixserver.html">
+
+
+ <b>1.3.5.</b>
+
+ Mixing models for a better prediction convergence (MIX
server)
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.3.6" data-path="../tips/emr.html">
+
+ <a href="../tips/emr.html">
+
+
+ <b>1.3.6.</b>
+
+ Run Hivemall on Amazon Elastic MapReduce
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="1.4"
data-path="../tips/general_tips.html">
+
+ <a href="../tips/general_tips.html">
+
+
+ <b>1.4.</b>
+
+ General Hive/Hadoop tips
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="1.4.1" data-path="../tips/rowid.html">
+
+ <a href="../tips/rowid.html">
+
+
+ <b>1.4.1.</b>
+
+ Adding rowid for each row
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.4.2"
data-path="../tips/hadoop_tuning.html">
+
+ <a href="../tips/hadoop_tuning.html">
+
+
+ <b>1.4.2.</b>
+
+ Hadoop tuning for Hivemall
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="1.5" data-path="../troubleshooting/">
+
+ <a href="../troubleshooting/">
+
+
+ <b>1.5.</b>
+
+ Troubleshooting
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="1.5.1"
data-path="../troubleshooting/oom.html">
+
+ <a href="../troubleshooting/oom.html">
+
+
+ <b>1.5.1.</b>
+
+ OutOfMemoryError in training
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.5.2"
data-path="../troubleshooting/mapjoin_task_error.html">
+
+ <a href="../troubleshooting/mapjoin_task_error.html">
+
+
+ <b>1.5.2.</b>
+
+ SemanticException Generate Map Join Task Error: Cannot
serialize object
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.5.3"
data-path="../troubleshooting/asterisk.html">
+
+ <a href="../troubleshooting/asterisk.html">
+
+
+ <b>1.5.3.</b>
+
+ Asterisk argument for UDTF does not work
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.5.4"
data-path="../troubleshooting/num_mappers.html">
+
+ <a href="../troubleshooting/num_mappers.html">
+
+
+ <b>1.5.4.</b>
+
+ The number of mappers is less than input splits in Hadoop
2.x
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="1.5.5"
data-path="../troubleshooting/mapjoin_classcastex.html">
+
+ <a href="../troubleshooting/mapjoin_classcastex.html">
+
+
+ <b>1.5.5.</b>
+
+ Map-side Join causes ClassCastException on Tez
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+
+
+
+ <li class="header">Part II - Generic Features</li>
+
+
+
+ <li class="chapter " data-level="2.1" data-path="generic_funcs.html">
+
+ <a href="generic_funcs.html">
+
+
+ <b>2.1.</b>
+
+ List of generic Hivemall functions
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter active" data-level="2.2" data-path="topk.html">
+
+ <a href="topk.html">
+
+
+ <b>2.2.</b>
+
+ Efficient Top-K query processing
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="2.3" data-path="tokenizer.html">
+
+ <a href="tokenizer.html">
+
+
+ <b>2.3.</b>
+
+ English/Japanese Text Tokenizer
+
+ </a>
+
+
+
+ </li>
+
+
+
+
+ <li class="header">Part III - Feature Engineering</li>
+
+
+
+ <li class="chapter " data-level="3.1"
data-path="../ft_engineering/scaling.html">
+
+ <a href="../ft_engineering/scaling.html">
+
+
+ <b>3.1.</b>
+
+ Feature Scaling
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="3.2"
data-path="../ft_engineering/hashing.html">
+
+ <a href="../ft_engineering/hashing.html">
+
+
+ <b>3.2.</b>
+
+ Feature Hashing
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="3.3"
data-path="../ft_engineering/tfidf.html">
+
+ <a href="../ft_engineering/tfidf.html">
+
+
+ <b>3.3.</b>
+
+ TF-IDF calculation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="3.4"
data-path="../ft_engineering/ft_trans.html">
+
+ <a href="../ft_engineering/ft_trans.html">
+
+
+ <b>3.4.</b>
+
+ FEATURE TRANSFORMATION
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="3.4.1"
data-path="../ft_engineering/vectorizer.html">
+
+ <a href="../ft_engineering/vectorizer.html">
+
+
+ <b>3.4.1.</b>
+
+ Vectorize Features
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="3.4.2"
data-path="../ft_engineering/quantify.html">
+
+ <a href="../ft_engineering/quantify.html">
+
+
+ <b>3.4.2.</b>
+
+ Quantify non-number features
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+
+
+
+ <li class="header">Part IV - Evaluation</li>
+
+
+
+ <li class="chapter " data-level="4.1"
data-path="../eval/stat_eval.html">
+
+ <a href="../eval/stat_eval.html">
+
+
+ <b>4.1.</b>
+
+ Statistical evaluation of a prediction model
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="4.2" data-path="../eval/datagen.html">
+
+ <a href="../eval/datagen.html">
+
+
+ <b>4.2.</b>
+
+ Data Generation
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="4.2.1"
data-path="../eval/lr_datagen.html">
+
+ <a href="../eval/lr_datagen.html">
+
+
+ <b>4.2.1.</b>
+
+ Logistic Regression data generation
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+
+
+
+ <li class="header">Part V - Binary classification</li>
+
+
+
+ <li class="chapter " data-level="5.1"
data-path="../binaryclass/a9a.html">
+
+ <a href="../binaryclass/a9a.html">
+
+
+ <b>5.1.</b>
+
+ a9a Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="5.1.1"
data-path="../binaryclass/a9a_dataset.html">
+
+ <a href="../binaryclass/a9a_dataset.html">
+
+
+ <b>5.1.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="5.1.2"
data-path="../binaryclass/a9a_lr.html">
+
+ <a href="../binaryclass/a9a_lr.html">
+
+
+ <b>5.1.2.</b>
+
+ Logistic Regression
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="5.1.3"
data-path="../binaryclass/a9a_minibatch.html">
+
+ <a href="../binaryclass/a9a_minibatch.html">
+
+
+ <b>5.1.3.</b>
+
+ Mini-batch Gradient Descent
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="5.2"
data-path="../binaryclass/news20.html">
+
+ <a href="../binaryclass/news20.html">
+
+
+ <b>5.2.</b>
+
+ News20 Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="5.2.1"
data-path="../binaryclass/news20_dataset.html">
+
+ <a href="../binaryclass/news20_dataset.html">
+
+
+ <b>5.2.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="5.2.2"
data-path="../binaryclass/news20_pa.html">
+
+ <a href="../binaryclass/news20_pa.html">
+
+
+ <b>5.2.2.</b>
+
+ Perceptron, Passive Aggressive
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="5.2.3"
data-path="../binaryclass/news20_scw.html">
+
+ <a href="../binaryclass/news20_scw.html">
+
+
+ <b>5.2.3.</b>
+
+ CW, AROW, SCW
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="5.2.4"
data-path="../binaryclass/news20_adagrad.html">
+
+ <a href="../binaryclass/news20_adagrad.html">
+
+
+ <b>5.2.4.</b>
+
+ AdaGradRDA, AdaGrad, AdaDelta
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="5.3"
data-path="../binaryclass/kdd2010a.html">
+
+ <a href="../binaryclass/kdd2010a.html">
+
+
+ <b>5.3.</b>
+
+ KDD2010a Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="5.3.1"
data-path="../binaryclass/kdd2010a_dataset.html">
+
+ <a href="../binaryclass/kdd2010a_dataset.html">
+
+
+ <b>5.3.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="5.3.2"
data-path="../binaryclass/kdd2010a_scw.html">
+
+ <a href="../binaryclass/kdd2010a_scw.html">
+
+
+ <b>5.3.2.</b>
+
+ PA, CW, AROW, SCW
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="5.4"
data-path="../binaryclass/kdd2010b.html">
+
+ <a href="../binaryclass/kdd2010b.html">
+
+
+ <b>5.4.</b>
+
+ KDD2010b Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="5.4.1"
data-path="../binaryclass/kdd2010b_dataset.html">
+
+ <a href="../binaryclass/kdd2010b_dataset.html">
+
+
+ <b>5.4.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="5.4.2"
data-path="../binaryclass/kdd2010b_arow.html">
+
+ <a href="../binaryclass/kdd2010b_arow.html">
+
+
+ <b>5.4.2.</b>
+
+ AROW
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="5.5"
data-path="../binaryclass/webspam.html">
+
+ <a href="../binaryclass/webspam.html">
+
+
+ <b>5.5.</b>
+
+ Webspam Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="5.5.1"
data-path="../binaryclass/webspam_dataset.html">
+
+ <a href="../binaryclass/webspam_dataset.html">
+
+
+ <b>5.5.1.</b>
+
+ Data pareparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="5.5.2"
data-path="../binaryclass/webspam_scw.html">
+
+ <a href="../binaryclass/webspam_scw.html">
+
+
+ <b>5.5.2.</b>
+
+ PA1, AROW, SCW
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+
+
+
+ <li class="header">Part VI - Multiclass classification</li>
+
+
+
+ <li class="chapter " data-level="6.1"
data-path="../multiclass/news20.html">
+
+ <a href="../multiclass/news20.html">
+
+
+ <b>6.1.</b>
+
+ News20 Multiclass Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="6.1.1"
data-path="../multiclass/news20_dataset.html">
+
+ <a href="../multiclass/news20_dataset.html">
+
+
+ <b>6.1.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.1.2"
data-path="../multiclass/news20_one-vs-the-rest_dataset.html">
+
+ <a href="../multiclass/news20_one-vs-the-rest_dataset.html">
+
+
+ <b>6.1.2.</b>
+
+ Data preparation for one-vs-the-rest classifiers
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.1.3"
data-path="../multiclass/news20_pa.html">
+
+ <a href="../multiclass/news20_pa.html">
+
+
+ <b>6.1.3.</b>
+
+ PA
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.1.4"
data-path="../multiclass/news20_scw.html">
+
+ <a href="../multiclass/news20_scw.html">
+
+
+ <b>6.1.4.</b>
+
+ CW, AROW, SCW
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.1.5"
data-path="../multiclass/news20_ensemble.html">
+
+ <a href="../multiclass/news20_ensemble.html">
+
+
+ <b>6.1.5.</b>
+
+ Ensemble learning
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.1.6"
data-path="../multiclass/news20_one-vs-the-rest.html">
+
+ <a href="../multiclass/news20_one-vs-the-rest.html">
+
+
+ <b>6.1.6.</b>
+
+ one-vs-the-rest classifier
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="6.2"
data-path="../multiclass/iris.html">
+
+ <a href="../multiclass/iris.html">
+
+
+ <b>6.2.</b>
+
+ Iris Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="6.2.1"
data-path="../multiclass/iris_dataset.html">
+
+ <a href="../multiclass/iris_dataset.html">
+
+
+ <b>6.2.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.2.2"
data-path="../multiclass/iris_scw.html">
+
+ <a href="../multiclass/iris_scw.html">
+
+
+ <b>6.2.2.</b>
+
+ SCW
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.2.3"
data-path="../multiclass/iris_randomforest.html">
+
+ <a href="../multiclass/iris_randomforest.html">
+
+
+ <b>6.2.3.</b>
+
+ RandomForest
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+
+
+
+ <li class="header">Part VII - Regression</li>
+
+
+
+ <li class="chapter " data-level="7.1"
data-path="../regression/e2006.html">
+
+ <a href="../regression/e2006.html">
+
+
+ <b>7.1.</b>
+
+ E2006-tfidf regression Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="7.1.1"
data-path="../regression/e2006_dataset.html">
+
+ <a href="../regression/e2006_dataset.html">
+
+
+ <b>7.1.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="7.1.2"
data-path="../regression/e2006_arow.html">
+
+ <a href="../regression/e2006_arow.html">
+
+
+ <b>7.1.2.</b>
+
+ Passive Aggressive, AROW
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="7.2"
data-path="../regression/kddcup12tr2.html">
+
+ <a href="../regression/kddcup12tr2.html">
+
+
+ <b>7.2.</b>
+
+ KDDCup 2012 track 2 CTR prediction Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="7.2.1"
data-path="../regression/kddcup12tr2_dataset.html">
+
+ <a href="../regression/kddcup12tr2_dataset.html">
+
+
+ <b>7.2.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="7.2.2"
data-path="../regression/kddcup12tr2_lr.html">
+
+ <a href="../regression/kddcup12tr2_lr.html">
+
+
+ <b>7.2.2.</b>
+
+ Logistic Regression, Passive Aggressive
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="7.2.3"
data-path="../regression/kddcup12tr2_lr_amplify.html">
+
+ <a href="../regression/kddcup12tr2_lr_amplify.html">
+
+
+ <b>7.2.3.</b>
+
+ Logistic Regression with Amplifier
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="7.2.4"
data-path="../regression/kddcup12tr2_adagrad.html">
+
+ <a href="../regression/kddcup12tr2_adagrad.html">
+
+
+ <b>7.2.4.</b>
+
+ AdaGrad, AdaDelta
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+
+
+
+ <li class="header">Part VIII - Recommendation</li>
+
+
+
+ <li class="chapter " data-level="8.1" data-path="../recommend/cf.html">
+
+ <a href="../recommend/cf.html">
+
+
+ <b>8.1.</b>
+
+ Collaborative Filtering
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="8.1.1"
data-path="../recommend/item_based_cf.html">
+
+ <a href="../recommend/item_based_cf.html">
+
+
+ <b>8.1.1.</b>
+
+ Item-based Collaborative Filtering
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="8.2"
data-path="../recommend/news20.html">
+
+ <a href="../recommend/news20.html">
+
+
+ <b>8.2.</b>
+
+ News20 related article recommendation Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="8.2.1"
data-path="../multiclass/news20_dataset.html">
+
+ <a href="../multiclass/news20_dataset.html">
+
+
+ <b>8.2.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="8.2.2"
data-path="../recommend/news20_jaccard.html">
+
+ <a href="../recommend/news20_jaccard.html">
+
+
+ <b>8.2.2.</b>
+
+ LSH/Minhash and Jaccard Similarity
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="8.2.3"
data-path="../recommend/news20_knn.html">
+
+ <a href="../recommend/news20_knn.html">
+
+
+ <b>8.2.3.</b>
+
+ LSH/Minhash and Brute-Force Search
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="8.2.4"
data-path="../recommend/news20_bbit_minhash.html">
+
+ <a href="../recommend/news20_bbit_minhash.html">
+
+
+ <b>8.2.4.</b>
+
+ kNN search using b-Bits Minhash
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+ <li class="chapter " data-level="8.3"
data-path="../recommend/movielens.html">
+
+ <a href="../recommend/movielens.html">
+
+
+ <b>8.3.</b>
+
+ MovieLens movie recommendation Tutorial
+
+ </a>
+
+
+
+ <ul class="articles">
+
+
+ <li class="chapter " data-level="8.3.1"
data-path="../recommend/movielens_dataset.html">
+
+ <a href="../recommend/movielens_dataset.html">
+
+
+ <b>8.3.1.</b>
+
+ Data preparation
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="8.3.2"
data-path="../recommend/movielens_mf.html">
+
+ <a href="../recommend/movielens_mf.html">
+
+
+ <b>8.3.2.</b>
+
+ Matrix Factorization
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="8.3.3"
data-path="../recommend/movielens_fm.html">
+
+ <a href="../recommend/movielens_fm.html">
+
+
+ <b>8.3.3.</b>
+
+ Factorization Machine
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="8.3.4"
data-path="../recommend/movielens_cv.html">
+
+ <a href="../recommend/movielens_cv.html">
+
+
+ <b>8.3.4.</b>
+
+ 10-fold Cross Validation (Matrix Factorization)
+
+ </a>
+
+
+
+ </li>
+
+
+ </ul>
+
+ </li>
+
+
+
+
+ <li class="header">Part IX - Anomaly Detection</li>
+
+
+
+ <li class="chapter " data-level="9.1" data-path="../anomaly/lof.html">
+
+ <a href="../anomaly/lof.html">
+
+
+ <b>9.1.</b>
+
+ Outlier Detection using Local Outlier Factor (LOF)
+
+ </a>
+
+
+
+ </li>
+
+
+
+
+ <li class="header">Part X - External References</li>
+
+
+
+ <li class="chapter " data-level="10.1" >
+
+ <a target="_blank"
href="https://github.com/maropu/hivemall-spark";>
+
+
+ <b>10.1.</b>
+
+ Hivemall on Apache Spark
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="10.2" >
+
+ <a target="_blank"
href="https://github.com/daijyc/hivemall/wiki/PigHome";>
+
+
+ <b>10.2.</b>
+
+ Hivemall on Apache Pig
+
+ </a>
+
+
+
+ </li>
+
+
+
+
+ <li class="divider"></li>
+
+ <li>
+ <a href="https://www.gitbook.com"; target="blank" class="gitbook-link">
+ Published with GitBook
+ </a>
+ </li>
+</ul>
+
+
+ </nav>
+
+
+ </div>
+
+ <div class="book-body">
+
+ <div class="body-inner">
+
+
+
+<div class="book-header" role="navigation">
+
+
+ <!-- Title -->
+ <h1>
+ <i class="fa fa-circle-o-notch fa-spin"></i>
+ <a href=".." >Efficient Top-K query processing</a>
+ </h1>
+</div>
+
+
+
+
+ <div class="page-wrapper" tabindex="-1" role="main">
+ <div class="page-inner">
+
+<div id="book-search-results">
+ <div class="search-noresults">
+
+ <section class="normal markdown-section">
+
+ <p><code>each_top_k(int k, ANY group, double
value, arg1, arg2, ..., argN)</code> returns a top-k records for each
<code>group</code>. It returns a relation consists of <code>(int rank, double
value, arg1, arg2, .., argN)</code>.</p>
+<p>This function is particularly useful for applying a similarity/distance
function where the computation complexity is <strong>O(nm)</strong>.</p>
+<p><code>each_top_k</code> is very fast when compared to other methods running
top-k queries (e.g., <a
href="https://ragrawal.wordpress.com/2011/11/18/extract-top-n-records-in-each-group-in-hadoophive/";
target="_blank"><code>rank/distributed by</code></a>) in Hive.</p>
+<h2 id="caution">Caution</h2>
+<ul>
+<li><code>each_top_k</code> is supported from Hivemall v0.3.2-3 or later.</li>
+<li>This UDTF assumes that input records are sorted by <code>group</code>. Use
<code>DISTRIBUTED BY group SORTED BY group</code> to ensure that. Or, you can
use <code>LEFT OUTER JOIN</code> for certain cases.</li>
+<li>It takes variable lengths arguments in <code>argN</code>. </li>
+<li>The third argument <code>value</code> is used for the comparison.</li>
+<li><code>Any number types</code> or <code>timestamp</code> are accepted for
the type of <code>value</code>.</li>
+<li>If k is less than 0, reverse order is used and <code>tail-K</code> records
are returned for each <code>group</code>.</li>
+<li>Note that this function returns <a
href="http://www.michaelpollmeier.com/selecting-top-k-items-from-a-list-efficiently-in-java-groovy/";
target="_blank">a pseudo ranking</a> for top-k. It always returns
<code>at-most K</code> records for each group. The ranking scheme is similar to
<code>dense_rank</code> but slightly different in certain cases.</li>
+</ul>
+<h1 id="usage">Usage</h1>
+<h2 id="top-k-clicks">top-k clicks</h2>
+<p><a
href="http://stackoverflow.com/questions/9390698/hive-getting-top-n-records-in-group-by-query/32559050#32559050";
target="_blank">http://stackoverflow.com/questions/9390698/hive-getting-top-n-records-in-group-by-query/32559050#32559050</a></p>
+<pre><code class="lang-sql"><span class="hljs-keyword">set</span>
hivevar:k=<span class="hljs-number">5</span>;
+
+<span class="hljs-keyword">select</span>
+ page-<span class="hljs-keyword">id</span>,
+ <span class="hljs-keyword">user</span>-<span class="hljs-keyword">id</span>,
+ clicks
+<span class="hljs-keyword">from</span> (
+ <span class="hljs-keyword">select</span>
+ each_top_k(${k}, page-<span class="hljs-keyword">id</span>, clicks,
page-<span class="hljs-keyword">id</span>, <span
class="hljs-keyword">user</span>-<span class="hljs-keyword">id</span>)
+ <span class="hljs-keyword">as</span> (<span
class="hljs-keyword">rank</span>, clicks, page-<span
class="hljs-keyword">id</span>, <span class="hljs-keyword">user</span>-<span
class="hljs-keyword">id</span>)
+ <span class="hljs-keyword">from</span> (
+ <span class="hljs-keyword">select</span>
+ page-<span class="hljs-keyword">id</span>, <span
class="hljs-keyword">user</span>-<span class="hljs-keyword">id</span>, clicks
+ <span class="hljs-keyword">from</span>
+ mytable
+ <span class="hljs-keyword">DISTRIBUTE</span> <span
class="hljs-keyword">BY</span> page-<span class="hljs-keyword">id</span> <span
class="hljs-keyword">SORT</span> <span class="hljs-keyword">BY</span>
page-<span class="hljs-keyword">id</span>
+ ) t1
+) t2
+<span class="hljs-keyword">order</span> <span class="hljs-keyword">by</span>
page-<span class="hljs-keyword">id</span> <span
class="hljs-keyword">ASC</span>, clicks <span class="hljs-keyword">DESC</span>;
+</code></pre>
+<h2 id="top-k-similarity-computation">Top-k similarity computation</h2>
+<pre><code class="lang-sql"><span class="hljs-keyword">set</span>
hivevar:k=<span class="hljs-number">10</span>;
+
+<span class="hljs-keyword">SELECT</span>
+ each_top_k(
+ ${k}, t2.<span class="hljs-keyword">id</span>,
angular_similarity(t2.features, t1.features),
+ t2.<span class="hljs-keyword">id</span>,
+ t1.<span class="hljs-keyword">id</span>,
+ t1.y
+ ) <span class="hljs-keyword">as</span> (<span
class="hljs-keyword">rank</span>, similarity, base_id, neighbor_id, y)
+<span class="hljs-keyword">FROM</span>
+ test_hivemall t2
+ <span class="hljs-keyword">LEFT</span> <span
class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span>
train_hivemall t1;
+</code></pre>
+<pre><code>1 0.8594650626182556 12 10514 0
+2 0.8585299849510193 12 11719 0
+3 0.856602132320404 12 21009 0
+4 0.8562054634094238 12 17582 0
+5 0.8516314029693604 12 22006 0
+6 0.8499397039413452 12 25364 0
+7 0.8467264771461487 12 900 0
+8 0.8463355302810669 12 8018 0
+9 0.8439178466796875 12 7041 0
+10 0.8438876867294312 12 21595 0
+1 0.8390793800354004 25 21125 0
+2 0.8344510793685913 25 14073 0
+3 0.8340602517127991 25 9008 0
+4 0.8328862190246582 25 6598 0
+5 0.8301891088485718 25 943 0
+6 0.8271955251693726 25 20400 0
+7 0.8255619406700134 25 10922 0
+8 0.8241575956344604 25 8477 0
+9 0.822281539440155 25 25977 0
+10 0.8205751180648804 25 21115 0
+1 0.9761330485343933 34 2513 0
+2 0.9536819458007812 34 8697 0
+3 0.9531533122062683 34 7326 0
+4 0.9493276476860046 34 15173 0
+5 0.9480557441711426 34 19468 0
+...
+</code></pre><h3
id="explicit-grouping-using-distribute-by-and-sort-by">Explicit grouping using
<code>distribute by</code> and <code>sort by</code></h3>
+<pre><code class="lang-sql"><span class="hljs-keyword">SELECT</span>
+ each_top_k(
+ <span class="hljs-number">10</span>, id1, angular_similarity(features1,
features2),
+ id1,
+ id2,
+ y
+ ) <span class="hljs-keyword">as</span> (<span
class="hljs-keyword">rank</span>, similarity, <span
class="hljs-keyword">id</span>, other_id, y)
+<span class="hljs-keyword">FROM</span> (
+<span class="hljs-keyword">select</span>
+ t1.<span class="hljs-keyword">id</span> <span class="hljs-keyword">as</span>
id1,
+ t2.<span class="hljs-keyword">id</span> <span class="hljs-keyword">as</span>
id2,
+ t1.features <span class="hljs-keyword">as</span> features1,
+ t2.features <span class="hljs-keyword">as</span> features2,
+ t1.y
+<span class="hljs-keyword">from</span>
+ train_hivemall t1
+ <span class="hljs-keyword">CROSS</span> <span
class="hljs-keyword">JOIN</span> test_hivemall t2
+<span class="hljs-keyword">DISTRIBUTE</span> <span
class="hljs-keyword">BY</span> id1 <span class="hljs-keyword">SORT</span> <span
class="hljs-keyword">BY</span> id1
+) t;
+</code></pre>
+<h3
id="parallelization-of-similarity-computation-using-with-clause">Parallelization
of similarity computation using WITH clause</h3>
+<pre><code class="lang-sql"><span class="hljs-keyword">create</span> <span
class="hljs-keyword">table</span> similarities
+<span class="hljs-keyword">as</span>
+<span class="hljs-keyword">WITH</span> test_rnd <span
class="hljs-keyword">as</span> (
+<span class="hljs-keyword">select</span>
+ <span class="hljs-keyword">rand</span>(<span class="hljs-number">31</span>)
<span class="hljs-keyword">as</span> rnd,
+ <span class="hljs-keyword">id</span>,
+ features
+<span class="hljs-keyword">from</span>
+ test_hivemall
+),
+t01 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">select</span>
+ <span class="hljs-keyword">id</span>,
+ features
+<span class="hljs-keyword">from</span>
+ test_rnd
+<span class="hljs-keyword">where</span>
+ rnd < <span class="hljs-number">0.2</span>
+),
+t02 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">select</span>
+ <span class="hljs-keyword">id</span>,
+ features
+<span class="hljs-keyword">from</span>
+ test_rnd
+<span class="hljs-keyword">where</span>
+ rnd >= <span class="hljs-number">0.2</span> <span
class="hljs-keyword">and</span> rnd < <span class="hljs-number">0.4</span>
+),
+t03 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">select</span>
+ <span class="hljs-keyword">id</span>,
+ features
+<span class="hljs-keyword">from</span>
+ test_rnd
+<span class="hljs-keyword">where</span>
+ rnd >= <span class="hljs-number">0.4</span> <span
class="hljs-keyword">and</span> rnd < <span class="hljs-number">0.6</span>
+),
+t04 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">select</span>
+ <span class="hljs-keyword">id</span>,
+ features
+<span class="hljs-keyword">from</span>
+ test_rnd
+<span class="hljs-keyword">where</span>
+ rnd >= <span class="hljs-number">0.6</span> <span
class="hljs-keyword">and</span> rnd < <span class="hljs-number">0.8</span>
+),
+t05 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">select</span>
+ <span class="hljs-keyword">id</span>,
+ features
+<span class="hljs-keyword">from</span>
+ test_rnd
+<span class="hljs-keyword">where</span>
+ rnd >= <span class="hljs-number">0.8</span>
+),
+s01 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">SELECT</span>
+ each_top_k(
+ <span class="hljs-number">10</span>, t2.<span
class="hljs-keyword">id</span>, angular_similarity(t2.features, t1.features),
+ t2.<span class="hljs-keyword">id</span>,
+ t1.<span class="hljs-keyword">id</span>,
+ t1.y
+ ) <span class="hljs-keyword">as</span> (<span
class="hljs-keyword">rank</span>, similarity, base_id, neighbor_id, y)
+<span class="hljs-keyword">FROM</span>
+ t01 t2
+ <span class="hljs-keyword">LEFT</span> <span
class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span>
train_hivemall t1
+),
+s02 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">SELECT</span>
+ each_top_k(
+ <span class="hljs-number">10</span>, t2.<span
class="hljs-keyword">id</span>, angular_similarity(t2.features, t1.features),
+ t2.<span class="hljs-keyword">id</span>,
+ t1.<span class="hljs-keyword">id</span>,
+ t1.y
+ ) <span class="hljs-keyword">as</span> (<span
class="hljs-keyword">rank</span>, similarity, base_id, neighbor_id, y)
+<span class="hljs-keyword">FROM</span>
+ t02 t2
+ <span class="hljs-keyword">LEFT</span> <span
class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span>
train_hivemall t1
+),
+s03 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">SELECT</span>
+ each_top_k(
+ <span class="hljs-number">10</span>, t2.<span
class="hljs-keyword">id</span>, angular_similarity(t2.features, t1.features),
+ t2.<span class="hljs-keyword">id</span>,
+ t1.<span class="hljs-keyword">id</span>,
+ t1.y
+ ) <span class="hljs-keyword">as</span> (<span
class="hljs-keyword">rank</span>, similarity, base_id, neighbor_id, y)
+<span class="hljs-keyword">FROM</span>
+ t03 t2
+ <span class="hljs-keyword">LEFT</span> <span
class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span>
train_hivemall t1
+),
+s04 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">SELECT</span>
+ each_top_k(
+ <span class="hljs-number">10</span>, t2.<span
class="hljs-keyword">id</span>, angular_similarity(t2.features, t1.features),
+ t2.<span class="hljs-keyword">id</span>,
+ t1.<span class="hljs-keyword">id</span>,
+ t1.y
+ ) <span class="hljs-keyword">as</span> (<span
class="hljs-keyword">rank</span>, similarity, base_id, neighbor_id, y)
+<span class="hljs-keyword">FROM</span>
+ t04 t2
+ <span class="hljs-keyword">LEFT</span> <span
class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span>
train_hivemall t1
+),
+s05 <span class="hljs-keyword">as</span> (
+<span class="hljs-keyword">SELECT</span>
+ each_top_k(
+ <span class="hljs-number">10</span>, t2.<span
class="hljs-keyword">id</span>, angular_similarity(t2.features, t1.features),
+ t2.<span class="hljs-keyword">id</span>,
+ t1.<span class="hljs-keyword">id</span>,
+ t1.y
+ ) <span class="hljs-keyword">as</span> (<span
class="hljs-keyword">rank</span>, similarity, base_id, neighbor_id, y)
+<span class="hljs-keyword">FROM</span>
+ t05 t2
+ <span class="hljs-keyword">LEFT</span> <span
class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span>
train_hivemall t1
+)
+<span class="hljs-keyword">select</span> * <span
class="hljs-keyword">from</span> s01
+<span class="hljs-keyword">union</span> all
+<span class="hljs-keyword">select</span> * <span
class="hljs-keyword">from</span> s02
+<span class="hljs-keyword">union</span> all
+<span class="hljs-keyword">select</span> * <span
class="hljs-keyword">from</span> s03
+<span class="hljs-keyword">union</span> all
+<span class="hljs-keyword">select</span> * <span
class="hljs-keyword">from</span> s04
+<span class="hljs-keyword">union</span> all
+<span class="hljs-keyword">select</span> * <span
class="hljs-keyword">from</span> s05;
+</code></pre>
+<h2 id="tail-k">tail-K</h2>
+<pre><code class="lang-sql"><span class="hljs-keyword">set</span>
hivevar:k=<span class="hljs-number">-10</span>;
+
+<span class="hljs-keyword">SELECT</span>
+ each_top_k(
+ ${k}, t2.<span class="hljs-keyword">id</span>,
angular_similarity(t2.features, t1.features),
+ t2.<span class="hljs-keyword">id</span>,
+ t1.<span class="hljs-keyword">id</span>,
+ t1.y
+ ) <span class="hljs-keyword">as</span> (<span
class="hljs-keyword">rank</span>, similarity, base_id, neighbor_id, y)
+<span class="hljs-keyword">FROM</span>
+ test_hivemall t2
+ <span class="hljs-keyword">LEFT</span> <span
class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span>
train_hivemall t1
+<span class="hljs-comment">-- limit 25</span>
+</code></pre>
+<pre><code>1 0.4383084177970886 1 7503 0
+2 0.44166821241378784 1 10143 0
+3 0.4424300789833069 1 11073 0
+4 0.44254064559936523 1 17782 0
+5 0.4442034363746643 1 18556 0
+6 0.45163780450820923 1 3786 0
+7 0.45244503021240234 1 10242 0
+8 0.4525672197341919 1 21657 0
+9 0.4527127146720886 1 17218 0
+10 0.45314133167266846 1 25141 0
+1 0.44030147790908813 2 3786 0
+2 0.4408798813819885 2 23386 0
+3 0.44112563133239746 2 11073 0
+4 0.4415401816368103 2 22853 0
+5 0.4422193765640259 2 21657 0
+6 0.4429032802581787 2 10143 0
+7 0.4435907006263733 2 24413 0
+8 0.44569307565689087 2 7503 0
+9 0.4460843801498413 2 25141 0
+10 0.4464914798736572 2 24289 0
+1 0.43862903118133545 3 23150 1
+2 0.4398220181465149 3 9881 1
+3 0.44283604621887207 3 27121 0
+4 0.4432108402252197 3 26220 1
+5 0.44323229789733887 3 18541 0
+...
+</code></pre>
+
+ </section>
+
+ </div>
+ <div class="search-results">
+ <div class="has-results">
+
+ <h1 class="search-results-title"><span
class='search-results-count'></span> results matching "<span
class='search-query'></span>"</h1>
+ <ul class="search-results-list"></ul>
+
+ </div>
+ <div class="no-results">
+
+ <h1 class="search-results-title">No results matching "<span
class='search-query'></span>"</h1>
+
+ </div>
+ </div>
+</div>
+
+ </div>
+ </div>
+
+ </div>
+
+
+
+
+ </div>
+
+ <script>
+ var gitbook = gitbook || [];
+ gitbook.push(function() {
+ gitbook.page.hasChanged({"page":{"title":"Efficient Top-K query
processing","level":"2.2","depth":1,"next":{"title":"English/Japanese Text
Tokenizer","level":"2.3","depth":1,"path":"misc/tokenizer.md","ref":"misc/tokenizer.md","articles":[]},"previous":{"title":"List
of generic Hivemall
functions","level":"2.1","depth":1,"path":"misc/generic_funcs.md","ref":"misc/generic_funcs.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"],"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":{"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":{},"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/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-chap
ters":{}},"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/topk.md","mtime":"2016-10-22T16:18:30.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2016-10-22T19:10:36.585Z"},"basePath":"..","book":{"language":""}});
+ });
+ </script>
+</div>
+
+
+ <script src="../gitbook/gitbook.js"></script>
+ <script src="../gitbook/theme.js"></script>
+
+
+ <script src="../gitbook/gitbook-plugin-edit-link/plugin.js"></script>
+
+
+
+ <script src="../gitbook/gitbook-plugin-github/plugin.js"></script>
+
+
+
+ <script src="../gitbook/gitbook-plugin-splitter/splitter.js"></script>
+
+
+
+ <script src="../gitbook/gitbook-plugin-etoc/plugin.js"></script>
+
+
+
+ <script
src="../gitbook/gitbook-plugin-toggle-chapters/toggle.js"></script>
+
+
+
+ <script
src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/3.1.1/anchor.min.js";></script>
+
+
+
+ <script
src="../gitbook/gitbook-plugin-anchorjs/anchor-style.js"></script>
+
+
+
+ <script
src="../gitbook/gitbook-plugin-expandable-chapters/expandable-chapters.js"></script>
+
+
+
+ <script
src="../gitbook/gitbook-plugin-search/search-engine.js"></script>
+
+
+
+ <script src="../gitbook/gitbook-plugin-search/search.js"></script>
+
+
+
+ <script src="../gitbook/gitbook-plugin-lunr/lunr.min.js"></script>
+
+
+
+ <script src="../gitbook/gitbook-plugin-lunr/search-lunr.js"></script>
+
+
+
+ <script src="../gitbook/gitbook-plugin-sharing/buttons.js"></script>
+
+
+
+ <script
src="../gitbook/gitbook-plugin-fontsettings/fontsettings.js"></script>
+
+
+
+ <script
src="../gitbook/gitbook-plugin-theme-api/theme-api.js"></script>
+
+
+
+ </body>
+</html>
+
