http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/68241a08/userguide/binaryclass/titanic_rf.html ---------------------------------------------------------------------- diff --git a/userguide/binaryclass/titanic_rf.html b/userguide/binaryclass/titanic_rf.html new file mode 100644 index 0000000..2a75faf --- /dev/null +++ b/userguide/binaryclass/titanic_rf.html @@ -0,0 +1,2081 @@ + +<!DOCTYPE HTML> +<html lang="" > + <head> + <meta charset="UTF-8"> + <meta content="text/html; charset=utf-8" http-equiv="Content-Type"> + <title>Kaggle Titanic Tutorial · 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="../multiclass/news20.html" /> + + + <link rel="prev" href="webspam_scw.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="../misc/generic_funcs.html"> + + <a href="../misc/generic_funcs.html"> + + + <b>2.1.</b> + + List of generic Hivemall functions + + </a> + + + + </li> + + <li class="chapter " data-level="2.2" data-path="../misc/topk.html"> + + <a href="../misc/topk.html"> + + + <b>2.2.</b> + + Efficient Top-K query processing + + </a> + + + + </li> + + <li class="chapter " data-level="2.3" data-path="../misc/tokenizer.html"> + + <a href="../misc/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="a9a.html"> + + <a href="a9a.html"> + + + <b>5.1.</b> + + a9a Tutorial + + </a> + + + + <ul class="articles"> + + + <li class="chapter " data-level="5.1.1" data-path="a9a_dataset.html"> + + <a href="a9a_dataset.html"> + + + <b>5.1.1.</b> + + Data preparation + + </a> + + + + </li> + + <li class="chapter " data-level="5.1.2" data-path="a9a_lr.html"> + + <a href="a9a_lr.html"> + + + <b>5.1.2.</b> + + Logistic Regression + + </a> + + + + </li> + + <li class="chapter " data-level="5.1.3" data-path="a9a_minibatch.html"> + + <a href="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="news20.html"> + + <a href="news20.html"> + + + <b>5.2.</b> + + News20 Tutorial + + </a> + + + + <ul class="articles"> + + + <li class="chapter " data-level="5.2.1" data-path="news20_dataset.html"> + + <a href="news20_dataset.html"> + + + <b>5.2.1.</b> + + Data preparation + + </a> + + + + </li> + + <li class="chapter " data-level="5.2.2" data-path="news20_pa.html"> + + <a href="news20_pa.html"> + + + <b>5.2.2.</b> + + Perceptron, Passive Aggressive + + </a> + + + + </li> + + <li class="chapter " data-level="5.2.3" data-path="news20_scw.html"> + + <a href="news20_scw.html"> + + + <b>5.2.3.</b> + + CW, AROW, SCW + + </a> + + + + </li> + + <li class="chapter " data-level="5.2.4" data-path="news20_adagrad.html"> + + <a href="news20_adagrad.html"> + + + <b>5.2.4.</b> + + AdaGradRDA, AdaGrad, AdaDelta + + </a> + + + + </li> + + + </ul> + + </li> + + <li class="chapter " data-level="5.3" data-path="kdd2010a.html"> + + <a href="kdd2010a.html"> + + + <b>5.3.</b> + + KDD2010a Tutorial + + </a> + + + + <ul class="articles"> + + + <li class="chapter " data-level="5.3.1" data-path="kdd2010a_dataset.html"> + + <a href="kdd2010a_dataset.html"> + + + <b>5.3.1.</b> + + Data preparation + + </a> + + + + </li> + + <li class="chapter " data-level="5.3.2" data-path="kdd2010a_scw.html"> + + <a href="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="kdd2010b.html"> + + <a href="kdd2010b.html"> + + + <b>5.4.</b> + + KDD2010b Tutorial + + </a> + + + + <ul class="articles"> + + + <li class="chapter " data-level="5.4.1" data-path="kdd2010b_dataset.html"> + + <a href="kdd2010b_dataset.html"> + + + <b>5.4.1.</b> + + Data preparation + + </a> + + + + </li> + + <li class="chapter " data-level="5.4.2" data-path="kdd2010b_arow.html"> + + <a href="kdd2010b_arow.html"> + + + <b>5.4.2.</b> + + AROW + + </a> + + + + </li> + + + </ul> + + </li> + + <li class="chapter " data-level="5.5" data-path="webspam.html"> + + <a href="webspam.html"> + + + <b>5.5.</b> + + Webspam Tutorial + + </a> + + + + <ul class="articles"> + + + <li class="chapter " data-level="5.5.1" data-path="webspam_dataset.html"> + + <a href="webspam_dataset.html"> + + + <b>5.5.1.</b> + + Data pareparation + + </a> + + + + </li> + + <li class="chapter " data-level="5.5.2" data-path="webspam_scw.html"> + + <a href="webspam_scw.html"> + + + <b>5.5.2.</b> + + PA1, AROW, SCW + + </a> + + + + </li> + + + </ul> + + </li> + + <li class="chapter active" data-level="5.6" data-path="titanic_rf.html"> + + <a href="titanic_rf.html"> + + + <b>5.6.</b> + + Kaggle Titanic Tutorial + + </a> + + + + </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=".." >Kaggle Titanic Tutorial</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"> + + <!-- + Licensed to the Apache Software Foundation (ASF) under one + or more contributor license agreements. See the NOTICE file + distributed with this work for additional information + regarding copyright ownership. The ASF licenses this file + to you under the Apache License, Version 2.0 (the + "License"); you may not use this file except in compliance + with the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, + software distributed under the License is distributed on an + "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + KIND, either express or implied. See the License for the + specific language governing permissions and limitations + under the License. +--> +<p>This examples gives a basic usage of RandomForest on Hivemall using <a href="https://www.kaggle.com/c/titanic"; target="_blank">Kaggle Titanic</a> dataset. +The example gives a baseline score without any feature engineering.</p> +<!-- toc --><div id="toc" class="toc"> + +<ul> +<li><a href="#data-preparation">Data preparation</a><ul> +<li><a href="#data-preparation-for-randomforest">Data preparation for RandomForest</a></li> +</ul> +</li> +<li><a href="#training">Training</a></li> +<li><a href="#prediction">Prediction</a></li> +<li><a href="#kaggle-submission">Kaggle submission</a></li> +<li><a href="#test-by-dividing-training-dataset">Test by dividing training dataset</a></li> +</ul> + +</div><!-- tocstop --> +<h1 id="data-preparation">Data preparation</h1> +<pre><code class="lang-sql">create database titanic; +use titanic; + +drop table train; +create external table train ( + passengerid int, -- unique id + survived int, -- target label + pclass int, + name string, + sex string, + age int, + sibsp int, -- Number of Siblings/Spouses Aboard + parch int, -- Number of Parents/Children Aboard + ticket string, + fare double, + cabin string, + embarked string +) +ROW FORMAT DELIMITED + FIELDS TERMINATED BY '|' + LINES TERMINATED BY '\n' +STORED AS TEXTFILE LOCATION '/dataset/titanic/train'; + +hadoop fs -rm /dataset/titanic/train/train.csv +awk '{ FPAT="([^,]*)|(\"[^\"]+\")";OFS="|"; } NR >1 {$1=$1;$4=substr($4,2,length($4)-2);print $0}' train.csv | hadoop fs -put - /dataset/titanic/train/train.csv + +drop table test_raw; +create external table test_raw ( + passengerid int, + pclass int, + name string, + sex string, + age int, + sibsp int, -- Number of Siblings/Spouses Aboard + parch int, -- Number of Parents/Children Aboard + ticket string, + fare double, + cabin string, + embarked string +) +ROW FORMAT DELIMITED + FIELDS TERMINATED BY '|' + LINES TERMINATED BY '\n' +STORED AS TEXTFILE LOCATION '/dataset/titanic/test_raw'; + +hadoop fs -rm /dataset/titanic/test_raw/test.csv +awk '{ FPAT="([^,]*)|(\"[^\"]+\")";OFS="|"; } NR >1 {$1=$1;$3=substr($3,2,length($3)-2);print $0}' test.csv | hadoop fs -put - /dataset/titanic/test_raw/test.csv +</code></pre> +<h2 id="data-preparation-for-randomforest">Data preparation for RandomForest</h2> +<pre><code class="lang-sql"><span class="hljs-keyword">set</span> hivevar:output_row=<span class="hljs-literal">true</span>; + +<span class="hljs-keyword">drop</span> <span class="hljs-keyword">table</span> train_rf; +<span class="hljs-keyword">create</span> <span class="hljs-keyword">table</span> train_rf +<span class="hljs-keyword">as</span> +<span class="hljs-keyword">WITH</span> train_quantified <span class="hljs-keyword">as</span> ( + <span class="hljs-keyword">select</span> + quantify( + ${output_row}, passengerid, survived, pclass, <span class="hljs-keyword">name</span>, sex, age, sibsp, parch, ticket, fare, cabin, embarked + ) <span class="hljs-keyword">as</span> (passengerid, survived, pclass, <span class="hljs-keyword">name</span>, sex, age, sibsp, parch, ticket, fare, cabin, embarked) + <span class="hljs-keyword">from</span> ( + <span class="hljs-keyword">select</span> * <span class="hljs-keyword">from</span> train + <span class="hljs-keyword">order</span> <span class="hljs-keyword">by</span> passengerid <span class="hljs-keyword">asc</span> + ) t +) +<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, + passengerid, + <span class="hljs-built_in">array</span>(pclass, <span class="hljs-keyword">name</span>, sex, age, sibsp, parch, ticket, fare, cabin, embarked) <span class="hljs-keyword">as</span> features, + survived +<span class="hljs-keyword">from</span> + train_quantified +; + +<span class="hljs-keyword">drop</span> <span class="hljs-keyword">table</span> test_rf; +<span class="hljs-keyword">create</span> <span class="hljs-keyword">table</span> test_rf +<span class="hljs-keyword">as</span> +<span class="hljs-keyword">WITH</span> test_quantified <span class="hljs-keyword">as</span> ( + <span class="hljs-keyword">select</span> + quantify( + output_row, passengerid, pclass, <span class="hljs-keyword">name</span>, sex, age, sibsp, parch, ticket, fare, cabin, embarked + ) <span class="hljs-keyword">as</span> (passengerid, pclass, <span class="hljs-keyword">name</span>, sex, age, sibsp, parch, ticket, fare, cabin, embarked) + <span class="hljs-keyword">from</span> ( + <span class="hljs-comment">-- need training data to assign consistent ids to categorical variables</span> + <span class="hljs-keyword">select</span> * <span class="hljs-keyword">from</span> ( + <span class="hljs-keyword">select</span> + <span class="hljs-number">1</span> <span class="hljs-keyword">as</span> train_first, <span class="hljs-literal">false</span> <span class="hljs-keyword">as</span> output_row, passengerid, pclass, <span class="hljs-keyword">name</span>, sex, age, sibsp, parch, ticket, fare, cabin, embarked + <span class="hljs-keyword">from</span> + train + <span class="hljs-keyword">union</span> all + <span class="hljs-keyword">select</span> + <span class="hljs-number">2</span> <span class="hljs-keyword">as</span> train_first, <span class="hljs-literal">true</span> <span class="hljs-keyword">as</span> output_row, passengerid, pclass, <span class="hljs-keyword">name</span>, sex, age, sibsp, parch, ticket, fare, cabin, embarked + <span class="hljs-keyword">from</span> + test_raw + ) t0 + <span class="hljs-keyword">order</span> <span class="hljs-keyword">by</span> train_first <span class="hljs-keyword">asc</span>, passengerid <span class="hljs-keyword">asc</span> + ) t1 +) +<span class="hljs-keyword">select</span> + passengerid, + <span class="hljs-built_in">array</span>(pclass, <span class="hljs-keyword">name</span>, sex, age, sibsp, parch, ticket, fare, cabin, embarked) <span class="hljs-keyword">as</span> features +<span class="hljs-keyword">from</span> + test_quantified +; +</code></pre> +<hr> +<h1 id="training">Training</h1> +<p><code>select guess_attribute_types(pclass, name, sex, age, sibsp, parch, ticket, fare, cabin, embarked) from train limit 1;</code></p> +<blockquote> +<p>Q,C,C,Q,Q,Q,C,Q,C,C</p> +</blockquote> +<p><code>Q</code> and <code>C</code> represent quantitative variable and categorical variables, respectively.</p> +<p><em>Caution:</em> Note that the output of <code>guess_attribute_types</code> is not perfect. Revise it by your self. +For example, <code>pclass</code> is a categorical variable.</p> +<pre><code class="lang-sql">set hivevar:attrs=C,C,C,Q,Q,Q,C,Q,C,C; + +drop table model_rf; +create table model_rf +AS +select + train_randomforest_classifier(features, survived, "-trees 500 -attrs ${attrs}") + -- as (model_id, model_type, pred_model, var_importance, oob_errors, oob_tests) +from + train_rf +; + +select + array_sum(var_importance) as var_importance, + sum(oob_errors) / sum(oob_tests) as oob_err_rate +from + model_rf; + +> [137.00242639169272,1194.2140119834373,328.78017188176966,628.2568660509628,200.31275032394072,160.12876797647078,1083.5987543408116,664.1234312561456,422.89449844090393,130.72019667694784] 0.18742985409652077 +</code></pre> +<h1 id="prediction">Prediction</h1> +<pre><code class="lang-sql"><span class="hljs-keyword">SET</span> hivevar:classification=<span class="hljs-literal">true</span>; +<span class="hljs-keyword">set</span> hive.<span class="hljs-keyword">auto</span>.<span class="hljs-keyword">convert</span>.<span class="hljs-keyword">join</span>=<span class="hljs-literal">true</span>; +<span class="hljs-keyword">SET</span> hive.mapjoin.optimized.hashtable=<span class="hljs-literal">false</span>; +<span class="hljs-keyword">SET</span> mapred.reduce.tasks=<span class="hljs-number">16</span>; + +<span class="hljs-keyword">drop</span> <span class="hljs-keyword">table</span> predicted_rf; +<span class="hljs-keyword">create</span> <span class="hljs-keyword">table</span> predicted_rf +<span class="hljs-keyword">as</span> +<span class="hljs-keyword">SELECT</span> + passengerid, + predicted.label, + predicted.probability, + predicted.probabilities +<span class="hljs-keyword">FROM</span> ( + <span class="hljs-keyword">SELECT</span> + passengerid, + rf_ensemble(predicted) <span class="hljs-keyword">as</span> predicted + <span class="hljs-keyword">FROM</span> ( + <span class="hljs-keyword">SELECT</span> + t.passengerid, + <span class="hljs-comment">-- hivemall v0.4.1-alpha.2 or before</span> + <span class="hljs-comment">-- tree_predict(p.model, t.features, ${classification}) as predicted</span> +　　 <span class="hljs-comment">-- hivemall v0.4.1-alpha.3 or later</span> + tree_predict(p.model_id, p.model_type, p.pred_model, t.features, ${classification}) <span class="hljs-keyword">as</span> predicted + <span class="hljs-keyword">FROM</span> ( + <span class="hljs-keyword">SELECT</span> model_id, model_type, pred_model <span class="hljs-keyword">FROM</span> model_rf + <span class="hljs-keyword">DISTRIBUTE</span> <span class="hljs-keyword">BY</span> <span class="hljs-keyword">rand</span>(<span class="hljs-number">1</span>) + ) p + <span class="hljs-keyword">LEFT</span> <span class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span> test_rf t + ) t1 + <span class="hljs-keyword">group</span> <span class="hljs-keyword">by</span> + passengerid +) t2 +; +</code></pre> +<h1 id="kaggle-submission">Kaggle submission</h1> +<pre><code class="lang-sql"><span class="hljs-keyword">drop</span> <span class="hljs-keyword">table</span> predicted_rf_submit; +<span class="hljs-keyword">create</span> <span class="hljs-keyword">table</span> predicted_rf_submit + <span class="hljs-keyword">ROW</span> <span class="hljs-keyword">FORMAT</span> <span class="hljs-keyword">DELIMITED</span> + <span class="hljs-keyword">FIELDS</span> <span class="hljs-keyword">TERMINATED</span> <span class="hljs-keyword">BY</span> <span class="hljs-string">","</span> + <span class="hljs-keyword">LINES</span> <span class="hljs-keyword">TERMINATED</span> <span class="hljs-keyword">BY</span> <span class="hljs-string">"\n"</span> + <span class="hljs-keyword">STORED</span> <span class="hljs-keyword">AS</span> TEXTFILE +<span class="hljs-keyword">as</span> +<span class="hljs-keyword">SELECT</span> passengerid, label <span class="hljs-keyword">as</span> survived +<span class="hljs-keyword">FROM</span> predicted_rf +<span class="hljs-keyword">ORDER</span> <span class="hljs-keyword">BY</span> passengerid <span class="hljs-keyword">ASC</span>; +</code></pre> +<pre><code class="lang-sh">hadoop fs -getmerge /user/hive/warehouse/titanic.db/predicted_rf_submit predicted_rf_submit.csv + +sed -i <span class="hljs-_">-e</span> <span class="hljs-string">"1i PassengerId,Survived"</span> predicted_rf_submit.csv +</code></pre> +<p>Accuracy would gives <code>0.76555</code> for a Kaggle submission.</p> +<hr> +<h1 id="test-by-dividing-training-dataset">Test by dividing training dataset</h1> +<pre><code class="lang-sql">drop table train_rf_07; +create table train_rf_07 +as +select * from train_rf +where rnd < 0.7; + +drop table test_rf_03; +create table test_rf_03 +as +select * from train_rf +where rnd >= 0.7; + +drop table model_rf_07; +create table model_rf_07 +AS +select + train_randomforest_classifier(features, survived, "-trees 500 -attrs ${attrs}") +from + train_rf_07; + +select + array_sum(var_importance) as var_importance, + sum(oob_errors) / sum(oob_tests) as oob_err_rate +from + model_rf_07; +> [116.12055542977338,960.8569891444097,291.08765260103837,469.74671636586226,163.721292772701,120.784769882858,847.9769298113661,554.4617571355476,346.3500941757221,97.42593940113392] 0.1838351822503962 + +SET hivevar:classification=true; +SET hive.mapjoin.optimized.hashtable=false; +SET mapred.reduce.tasks=16; + +drop table predicted_rf_03; +create table predicted_rf_03 +as +SELECT + passengerid, + predicted.label, + predicted.probability, + predicted.probabilities +FROM ( + SELECT + passengerid, + rf_ensemble(predicted) as predicted + FROM ( + SELECT + t.passengerid, + -- hivemall v0.4.1-alpha.2 or before + -- tree_predict(p.model, t.features, ${classification}) as predicted + -- hivemall v0.4.1-alpha.3 or later + tree_predict(p.model_id, p.model_type, p.pred_model, t.features, ${classification}) as predicted + FROM ( + SELECT model_id, model_type, pred_model FROM model_rf_07 + DISTRIBUTE BY rand(1) + ) p + LEFT OUTER JOIN test_rf_03 t + ) t1 + group by + passengerid +) t2 +; + +create or replace view rf_submit_03 as +select + t.survived as actual, + p.label as predicted, + p.probabilities +from + test_rf_03 t + JOIN predicted_rf_03 p on (t.passengerid = p.passengerid) +; + +select count(1) from test_rf_03; +> 260 + +set hivevar:testcnt=260; + +select count(1)/${testcnt} as accuracy +from rf_submit_03 +where actual = predicted; + +> 0.8 +</code></pre> +<p><div id="page-footer"><hr><!-- + Licensed to the Apache Software Foundation (ASF) under one + or more contributor license agreements. See the NOTICE file + distributed with this work for additional information + regarding copyright ownership. The ASF licenses this file + to you under the Apache License, Version 2.0 (the + "License"); you may not use this file except in compliance + with the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, + software distributed under the License is distributed on an + "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + KIND, either express or implied. See the License for the + specific language governing permissions and limitations + under the License. +--> +<p><sub><font color="gray"> +Apache Hivemall is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. +</font></sub></p> +</div></p> + + + </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":"Kaggle Titanic Tutorial","level":"5.6","depth":1,"next":{"title":"News20 Multiclass Tutorial","level":"6.1","depth":1,"path":"multiclass/news20.md","ref":"multiclass/news20.md","articles":[{"title":"Data preparation","level":"6.1.1","depth":2,"path":"multiclass/news20_dataset.md","ref":"multiclass/news20_dataset.md","articles":[]},{"title":"Data preparation for one-vs-the-rest classifiers","level":"6.1.2","depth":2,"path":"multiclass/news20_one-vs-the-rest_dataset.md","ref":"multiclass/news20_one-vs-the-rest_dataset.md","articles":[]},{"title":"PA","level":"6.1.3","depth":2,"path":"multiclass/news20_pa.md","ref":"multiclass/news20_pa.md","articles":[]},{"title":"CW, AROW, SCW","level":"6.1.4","depth":2,"path":"multiclass/news20_scw.md","ref":"multiclass/news20_scw.md","articles":[]},{"title":"Ensemble learning","level":"6.1.5","depth":2,"path":"multiclass/news20_ensemble.md","ref":"multiclass/news20_ensemble.md","articles":[]},{" title":"one-vs-the-rest classifier","level":"6.1.6","depth":2,"path":"multiclass/news20_one-vs-the-rest.md","ref":"multiclass/news20_one-vs-the-rest.md","articles":[]}]},"previous":{"title":"PA1, AROW, SCW","level":"5.5.2","depth":2,"path":"binaryclass/webspam_scw.md","ref":"binaryclass/webspam_scw.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":{"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"},"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-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":"binaryclass/titanic_rf.md","mtime":"2016-11-17T11:57:11.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2016-11-17T12:16:14.647Z"},"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> +
http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/68241a08/userguide/binaryclass/webspam.html ---------------------------------------------------------------------- diff --git a/userguide/binaryclass/webspam.html b/userguide/binaryclass/webspam.html index 5c332d0..c632456 100644 --- a/userguide/binaryclass/webspam.html +++ b/userguide/binaryclass/webspam.html @@ -999,6 +999,21 @@ </li> + <li class="chapter " data-level="5.6" data-path="titanic_rf.html"> + + <a href="titanic_rf.html"> + + + <b>5.6.</b> + + Kaggle Titanic Tutorial + + </a> + + + + </li> + @@ -1649,7 +1664,25 @@ specific language governing permissions and limitations under the License. --> -<p><div id="page-footer"><hr><p><sub><font color="gray"> +<p><div id="page-footer"><hr><!-- + Licensed to the Apache Software Foundation (ASF) under one + or more contributor license agreements. See the NOTICE file + distributed with this work for additional information + regarding copyright ownership. The ASF licenses this file + to you under the Apache License, Version 2.0 (the + "License"); you may not use this file except in compliance + with the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, + software distributed under the License is distributed on an + "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + KIND, either express or implied. See the License for the + specific language governing permissions and limitations + under the License. +--> +<p><sub><font color="gray"> Apache Hivemall is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. </font></sub></p> </div></p> @@ -1686,7 +1719,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda <script> var gitbook = gitbook || []; gitbook.push(function() { - gitbook.page.hasChanged({"page":{"title":"Webspam Tutorial","level":"5.5","depth":1,"next":{"title":"Data pareparation","level":"5.5.1","depth":2,"path":"binaryclass/webspam_dataset.md","ref":"binaryclass/webspam_dataset.md","articles":[]},"previous":{"title":"AROW","level":"5.4.2","depth":2,"path":"binaryclass/kdd2010b_arow.md","ref":"binaryclass/kdd2010b_arow.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":{"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"},"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-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":"binaryclass/webspam.md","mtime":"2016-11-12T07:18:00.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2016-11-14T10:40:22.987Z"},"basePath":"..","book":{"language":""}}); + gitbook.page.hasChanged({"page":{"title":"Webspam Tutorial","level":"5.5","depth":1,"next":{"title":"Data pareparation","level":"5.5.1","depth":2,"path":"binaryclass/webspam_dataset.md","ref":"binaryclass/webspam_dataset.md","articles":[]},"previous":{"title":"AROW","level":"5.4.2","depth":2,"path":"binaryclass/kdd2010b_arow.md","ref":"binaryclass/kdd2010b_arow.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":{"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"},"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-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":"binaryclass/webspam.md","mtime":"2016-11-16T08:39:12.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2016-11-17T12:16:14.647Z"},"basePath":"..","book":{"language":""}}); }); </script> </div> http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/68241a08/userguide/binaryclass/webspam_dataset.html ---------------------------------------------------------------------- diff --git a/userguide/binaryclass/webspam_dataset.html b/userguide/binaryclass/webspam_dataset.html index 1a49dd7..d990544 100644 --- a/userguide/binaryclass/webspam_dataset.html +++ b/userguide/binaryclass/webspam_dataset.html @@ -999,6 +999,21 @@ </li> + <li class="chapter " data-level="5.6" data-path="titanic_rf.html"> + + <a href="titanic_rf.html"> + + + <b>5.6.</b> + + Kaggle Titanic Tutorial + + </a> + + + + </li> + @@ -1719,7 +1734,25 @@ CLUSTER <span class="hljs-keyword">BY</span> <span class="hljs-keyword">rand</sp webspam_test LATERAL <span class="hljs-keyword">VIEW</span> explode(addBias(features)) t <span class="hljs-keyword">AS</span> feature; </code></pre> <p><em>Caution:</em> For this dataset, use small <em>shufflebuffersize</em> because each training example has lots of features though (xtimes <em> shufflebuffersize </em> N) training examples are cached in memory. -<div id="page-footer"><hr><p><sub><font color="gray"> +<div id="page-footer"><hr><!-- + Licensed to the Apache Software Foundation (ASF) under one + or more contributor license agreements. See the NOTICE file + distributed with this work for additional information + regarding copyright ownership. The ASF licenses this file + to you under the Apache License, Version 2.0 (the + "License"); you may not use this file except in compliance + with the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, + software distributed under the License is distributed on an + "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + KIND, either express or implied. See the License for the + specific language governing permissions and limitations + under the License. +--> +<p><sub><font color="gray"> Apache Hivemall is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. </font></sub></p> </div></p> @@ -1756,7 +1789,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda <script> var gitbook = gitbook || []; gitbook.push(function() { - gitbook.page.hasChanged({"page":{"title":"Data pareparation","level":"5.5.1","depth":2,"next":{"title":"PA1, AROW, SCW","level":"5.5.2","depth":2,"path":"binaryclass/webspam_scw.md","ref":"binaryclass/webspam_scw.md","articles":[]},"previous":{"title":"Webspam Tutorial","level":"5.5","depth":1,"path":"binaryclass/webspam.md","ref":"binaryclass/webspam.md","articles":[{"title":"Data pareparation","level":"5.5.1","depth":2,"path":"binaryclass/webspam_dataset.md","ref":"binaryclass/webspam_dataset.md","articles":[]},{"title":"PA1, AROW, SCW","level":"5.5.2","depth":2,"path":"binaryclass/webspam_scw.md","ref":"binaryclass/webspam_scw.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":"sty les/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":{},"localized-footer":{"filename":"FOOTER.md"},"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-h ivemall/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":"binaryclass/webspam_dataset.md","mtime":"2016-11-12T07:18:00.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2016-11-14T10 :40:22.987Z"},"basePath":"..","book":{"language":""}}); + gitbook.page.hasChanged({"page":{"title":"Data pareparation","level":"5.5.1","depth":2,"next":{"title":"PA1, AROW, SCW","level":"5.5.2","depth":2,"path":"binaryclass/webspam_scw.md","ref":"binaryclass/webspam_scw.md","articles":[]},"previous":{"title":"Webspam Tutorial","level":"5.5","depth":1,"path":"binaryclass/webspam.md","ref":"binaryclass/webspam.md","articles":[{"title":"Data pareparation","level":"5.5.1","depth":2,"path":"binaryclass/webspam_dataset.md","ref":"binaryclass/webspam_dataset.md","articles":[]},{"title":"PA1, AROW, SCW","level":"5.5.2","depth":2,"path":"binaryclass/webspam_scw.md","ref":"binaryclass/webspam_scw.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":"sty les/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":{},"localized-footer":{"filename":"FOOTER.md"},"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-h ivemall/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":"binaryclass/webspam_dataset.md","mtime":"2016-11-16T08:39:12.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2016-11-17T12 :16:14.647Z"},"basePath":"..","book":{"language":""}}); }); </script> </div> http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/68241a08/userguide/binaryclass/webspam_scw.html ---------------------------------------------------------------------- diff --git a/userguide/binaryclass/webspam_scw.html b/userguide/binaryclass/webspam_scw.html index dfc24ae..6d18b1a 100644 --- a/userguide/binaryclass/webspam_scw.html +++ b/userguide/binaryclass/webspam_scw.html @@ -97,7 +97,7 @@ <link rel="shortcut icon" href="../gitbook/images/favicon.ico" type="image/x-icon"> - <link rel="next" href="../multiclass/news20.html" /> + <link rel="next" href="titanic_rf.html" /> <link rel="prev" href="webspam_dataset.html" /> @@ -999,6 +999,21 @@ </li> + <li class="chapter " data-level="5.6" data-path="titanic_rf.html"> + + <a href="titanic_rf.html"> + + + <b>5.6.</b> + + Kaggle Titanic Tutorial + + </a> + + + + </li> + @@ -1777,12 +1792,30 @@ source ./tmp/define-all.hive; <span class="hljs-keyword">where</span> actual = predicted; </code></pre> <blockquote> -<p>Prediction accuracy: 0.9778714285714286 -<div id="page-footer"><hr><p><sub><font color="gray"> +<p>Prediction accuracy: 0.9778714285714286</p> +</blockquote> +<p><div id="page-footer"><hr><!-- + Licensed to the Apache Software Foundation (ASF) under one + or more contributor license agreements. See the NOTICE file + distributed with this work for additional information + regarding copyright ownership. The ASF licenses this file + to you under the Apache License, Version 2.0 (the + "License"); you may not use this file except in compliance + with the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, + software distributed under the License is distributed on an + "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + KIND, either express or implied. See the License for the + specific language governing permissions and limitations + under the License. +--> +<p><sub><font color="gray"> Apache Hivemall is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. </font></sub></p> </div></p> -</blockquote> </section> @@ -1816,7 +1849,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda <script> var gitbook = gitbook || []; gitbook.push(function() { - gitbook.page.hasChanged({"page":{"title":"PA1, AROW, SCW","level":"5.5.2","depth":2,"next":{"title":"News20 Multiclass Tutorial","level":"6.1","depth":1,"path":"multiclass/news20.md","ref":"multiclass/news20.md","articles":[{"title":"Data preparation","level":"6.1.1","depth":2,"path":"multiclass/news20_dataset.md","ref":"multiclass/news20_dataset.md","articles":[]},{"title":"Data preparation for one-vs-the-rest classifiers","level":"6.1.2","depth":2,"path":"multiclass/news20_one-vs-the-rest_dataset.md","ref":"multiclass/news20_one-vs-the-rest_dataset.md","articles":[]},{"title":"PA","level":"6.1.3","depth":2,"path":"multiclass/news20_pa.md","ref":"multiclass/news20_pa.md","articles":[]},{"title":"CW, AROW, SCW","level":"6.1.4","depth":2,"path":"multiclass/news20_scw.md","ref":"multiclass/news20_scw.md","articles":[]},{"title":"Ensemble learning","level":"6.1.5","depth":2,"path":"multiclass/news20_ensemble.md","ref":"multiclass/news20_ensemble.md","articles":[]},{"title": "one-vs-the-rest classifier","level":"6.1.6","depth":2,"path":"multiclass/news20_one-vs-the-rest.md","ref":"multiclass/news20_one-vs-the-rest.md","articles":[]}]},"previous":{"title":"Data pareparation","level":"5.5.1","depth":2,"path":"binaryclass/webspam_dataset.md","ref":"binaryclass/webspam_dataset.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":{"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/d ocs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md"},"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-chapters":{}},"theme":"defaul t","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":"binaryclass/webspam_scw.md","mtime":"2016-11-12T07:18:00.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2016-11-14T10:40:22.987Z"},"basePath":"..","book":{"language":""}}); + gitbook.page.hasChanged({"page":{"title":"PA1, AROW, SCW","level":"5.5.2","depth":2,"next":{"title":"Kaggle Titanic Tutorial","level":"5.6","depth":1,"path":"binaryclass/titanic_rf.md","ref":"binaryclass/titanic_rf.md","articles":[]},"previous":{"title":"Data pareparation","level":"5.5.1","depth":2,"path":"binaryclass/webspam_dataset.md","ref":"binaryclass/webspam_dataset.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":{"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"},"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-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":"binaryclass/webspam_scw.md","mtime":"2016-11-17T08:51:39.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2016-11-17T12:16:14.647Z"},"basePath":"..","book":{"language":""}}); }); </script> </div>
