| |
| <!DOCTYPE HTML> |
| <html lang="" > |
| <head> |
| <meta charset="UTF-8"> |
| <meta content="text/html; charset=utf-8" http-equiv="Content-Type"> |
| <title>Text Tokenizer ยท Hivemall User Manual</title> |
| <meta http-equiv="X-UA-Compatible" content="IE=edge" /> |
| <meta name="description" content=""> |
| <meta name="generator" content="GitBook 3.2.3"> |
| |
| |
| |
| |
| <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="approx.html" /> |
| |
| |
| <link rel="prev" href="topk.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="https://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="funcs.html"> |
| |
| <a href="funcs.html"> |
| |
| |
| <b>1.3.</b> |
| |
| List of Functions |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.4" data-path="../tips/"> |
| |
| <a href="../tips/"> |
| |
| |
| <b>1.4.</b> |
| |
| Tips for Effective Hivemall |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="1.4.1" data-path="../tips/addbias.html"> |
| |
| <a href="../tips/addbias.html"> |
| |
| |
| <b>1.4.1.</b> |
| |
| Explicit add_bias() for better prediction |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.4.2" data-path="../tips/rand_amplify.html"> |
| |
| <a href="../tips/rand_amplify.html"> |
| |
| |
| <b>1.4.2.</b> |
| |
| Use rand_amplify() to better prediction results |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.4.3" data-path="../tips/rt_prediction.html"> |
| |
| <a href="../tips/rt_prediction.html"> |
| |
| |
| <b>1.4.3.</b> |
| |
| Real-time prediction on RDBMS |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.4.4" data-path="../tips/ensemble_learning.html"> |
| |
| <a href="../tips/ensemble_learning.html"> |
| |
| |
| <b>1.4.4.</b> |
| |
| Ensemble learning for stable prediction |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.4.5" data-path="../tips/mixserver.html"> |
| |
| <a href="../tips/mixserver.html"> |
| |
| |
| <b>1.4.5.</b> |
| |
| Mixing models for a better prediction convergence (MIX server) |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.4.6" data-path="../tips/emr.html"> |
| |
| <a href="../tips/emr.html"> |
| |
| |
| <b>1.4.6.</b> |
| |
| Run Hivemall on Amazon Elastic MapReduce |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="1.5" data-path="../tips/general_tips.html"> |
| |
| <a href="../tips/general_tips.html"> |
| |
| |
| <b>1.5.</b> |
| |
| General Hive/Hadoop Tips |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="1.5.1" data-path="../tips/rowid.html"> |
| |
| <a href="../tips/rowid.html"> |
| |
| |
| <b>1.5.1.</b> |
| |
| Adding rowid for each row |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.5.2" data-path="../tips/hadoop_tuning.html"> |
| |
| <a href="../tips/hadoop_tuning.html"> |
| |
| |
| <b>1.5.2.</b> |
| |
| Hadoop tuning for Hivemall |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="1.6" data-path="../troubleshooting/"> |
| |
| <a href="../troubleshooting/"> |
| |
| |
| <b>1.6.</b> |
| |
| Troubleshooting |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="1.6.1" data-path="../troubleshooting/oom.html"> |
| |
| <a href="../troubleshooting/oom.html"> |
| |
| |
| <b>1.6.1.</b> |
| |
| OutOfMemoryError in training |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.6.2" data-path="../troubleshooting/mapjoin_task_error.html"> |
| |
| <a href="../troubleshooting/mapjoin_task_error.html"> |
| |
| |
| <b>1.6.2.</b> |
| |
| SemanticException generate map join task error: Cannot serialize object |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.6.3" data-path="../troubleshooting/asterisk.html"> |
| |
| <a href="../troubleshooting/asterisk.html"> |
| |
| |
| <b>1.6.3.</b> |
| |
| Asterisk argument for UDTF does not work |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.6.4" data-path="../troubleshooting/num_mappers.html"> |
| |
| <a href="../troubleshooting/num_mappers.html"> |
| |
| |
| <b>1.6.4.</b> |
| |
| The number of mappers is less than input splits in Hadoop 2.x |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="1.6.5" data-path="../troubleshooting/mapjoin_classcastex.html"> |
| |
| <a href="../troubleshooting/mapjoin_classcastex.html"> |
| |
| |
| <b>1.6.5.</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 " 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 active" data-level="2.3" data-path="tokenizer.html"> |
| |
| <a href="tokenizer.html"> |
| |
| |
| <b>2.3.</b> |
| |
| Text Tokenizer |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="2.4" data-path="approx.html"> |
| |
| <a href="approx.html"> |
| |
| |
| <b>2.4.</b> |
| |
| Approximate Aggregate Functions |
| |
| </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/selection.html"> |
| |
| <a href="../ft_engineering/selection.html"> |
| |
| |
| <b>3.3.</b> |
| |
| Feature Selection |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="3.4" data-path="../ft_engineering/binning.html"> |
| |
| <a href="../ft_engineering/binning.html"> |
| |
| |
| <b>3.4.</b> |
| |
| Feature Binning |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="3.5" data-path="../ft_engineering/pairing.html"> |
| |
| <a href="../ft_engineering/pairing.html"> |
| |
| |
| <b>3.5.</b> |
| |
| Feature Paring |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="3.5.1" data-path="../ft_engineering/polynomial.html"> |
| |
| <a href="../ft_engineering/polynomial.html"> |
| |
| |
| <b>3.5.1.</b> |
| |
| Polynomial features |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="3.6" data-path="../ft_engineering/ft_trans.html"> |
| |
| <a href="../ft_engineering/ft_trans.html"> |
| |
| |
| <b>3.6.</b> |
| |
| Feature Transformation |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="3.6.1" data-path="../ft_engineering/vectorization.html"> |
| |
| <a href="../ft_engineering/vectorization.html"> |
| |
| |
| <b>3.6.1.</b> |
| |
| Feature vectorization |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="3.6.2" data-path="../ft_engineering/quantify.html"> |
| |
| <a href="../ft_engineering/quantify.html"> |
| |
| |
| <b>3.6.2.</b> |
| |
| Quantify non-number features |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="3.6.3" data-path="../ft_engineering/binarize.html"> |
| |
| <a href="../ft_engineering/binarize.html"> |
| |
| |
| <b>3.6.3.</b> |
| |
| Binarize label |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="3.6.4" data-path="../ft_engineering/onehot.html"> |
| |
| <a href="../ft_engineering/onehot.html"> |
| |
| |
| <b>3.6.4.</b> |
| |
| One-hot encoding |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="3.7" data-path="../ft_engineering/term_vector.html"> |
| |
| <a href="../ft_engineering/term_vector.html"> |
| |
| |
| <b>3.7.</b> |
| |
| Term Vector Model |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="3.7.1" data-path="../ft_engineering/tfidf.html"> |
| |
| <a href="../ft_engineering/tfidf.html"> |
| |
| |
| <b>3.7.1.</b> |
| |
| TF-IDF Term Weighting |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="3.7.2" data-path="../ft_engineering/bm25.html"> |
| |
| <a href="../ft_engineering/bm25.html"> |
| |
| |
| <b>3.7.2.</b> |
| |
| Okapi BM25 Term Weighting |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part IV - Evaluation</li> |
| |
| |
| |
| <li class="chapter " data-level="4.1" data-path="../eval/binary_classification_measures.html"> |
| |
| <a href="../eval/binary_classification_measures.html"> |
| |
| |
| <b>4.1.</b> |
| |
| Binary Classification Metrics |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="4.1.1" data-path="../eval/auc.html"> |
| |
| <a href="../eval/auc.html"> |
| |
| |
| <b>4.1.1.</b> |
| |
| Area under the ROC curve |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="4.2" data-path="../eval/multilabel_classification_measures.html"> |
| |
| <a href="../eval/multilabel_classification_measures.html"> |
| |
| |
| <b>4.2.</b> |
| |
| Multi-label Classification Metrics |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="4.3" data-path="../eval/regression.html"> |
| |
| <a href="../eval/regression.html"> |
| |
| |
| <b>4.3.</b> |
| |
| Regression Metrics |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="4.4" data-path="../eval/rank.html"> |
| |
| <a href="../eval/rank.html"> |
| |
| |
| <b>4.4.</b> |
| |
| Ranking Measures |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="4.5" data-path="../eval/datagen.html"> |
| |
| <a href="../eval/datagen.html"> |
| |
| |
| <b>4.5.</b> |
| |
| Data Generation |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="4.5.1" data-path="../eval/lr_datagen.html"> |
| |
| <a href="../eval/lr_datagen.html"> |
| |
| |
| <b>4.5.1.</b> |
| |
| Logistic Regression data generation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part V - Supervised Learning</li> |
| |
| |
| |
| <li class="chapter " data-level="5.1" data-path="../supervised_learning/prediction.html"> |
| |
| <a href="../supervised_learning/prediction.html"> |
| |
| |
| <b>5.1.</b> |
| |
| How Prediction Works |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="5.2" data-path="../supervised_learning/tutorial.html"> |
| |
| <a href="../supervised_learning/tutorial.html"> |
| |
| |
| <b>5.2.</b> |
| |
| Step-by-Step Tutorial on Supervised Learning |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part VI - Binary Classification</li> |
| |
| |
| |
| <li class="chapter " data-level="6.1" data-path="../binaryclass/general.html"> |
| |
| <a href="../binaryclass/general.html"> |
| |
| |
| <b>6.1.</b> |
| |
| Binary Classification |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.2" data-path="../binaryclass/a9a.html"> |
| |
| <a href="../binaryclass/a9a.html"> |
| |
| |
| <b>6.2.</b> |
| |
| a9a Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="6.2.1" data-path="../binaryclass/a9a_dataset.html"> |
| |
| <a href="../binaryclass/a9a_dataset.html"> |
| |
| |
| <b>6.2.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.2.2" data-path="../binaryclass/a9a_generic.html"> |
| |
| <a href="../binaryclass/a9a_generic.html"> |
| |
| |
| <b>6.2.2.</b> |
| |
| General Binary Classifier |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.2.3" data-path="../binaryclass/a9a_lr.html"> |
| |
| <a href="../binaryclass/a9a_lr.html"> |
| |
| |
| <b>6.2.3.</b> |
| |
| Logistic Regression |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.2.4" data-path="../binaryclass/a9a_minibatch.html"> |
| |
| <a href="../binaryclass/a9a_minibatch.html"> |
| |
| |
| <b>6.2.4.</b> |
| |
| Mini-batch Gradient Descent |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="6.3" data-path="../binaryclass/news20.html"> |
| |
| <a href="../binaryclass/news20.html"> |
| |
| |
| <b>6.3.</b> |
| |
| News20 Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="6.3.1" data-path="../binaryclass/news20_dataset.html"> |
| |
| <a href="../binaryclass/news20_dataset.html"> |
| |
| |
| <b>6.3.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.3.2" data-path="../binaryclass/news20_pa.html"> |
| |
| <a href="../binaryclass/news20_pa.html"> |
| |
| |
| <b>6.3.2.</b> |
| |
| Perceptron, Passive Aggressive |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.3.3" data-path="../binaryclass/news20_scw.html"> |
| |
| <a href="../binaryclass/news20_scw.html"> |
| |
| |
| <b>6.3.3.</b> |
| |
| CW, AROW, SCW |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.3.4" data-path="../binaryclass/news20_generic.html"> |
| |
| <a href="../binaryclass/news20_generic.html"> |
| |
| |
| <b>6.3.4.</b> |
| |
| General Binary Classifier |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.3.5" data-path="../binaryclass/news20_generic_bagging.html"> |
| |
| <a href="../binaryclass/news20_generic_bagging.html"> |
| |
| |
| <b>6.3.5.</b> |
| |
| Baggnig classiers |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.3.6" data-path="../binaryclass/news20_adagrad.html"> |
| |
| <a href="../binaryclass/news20_adagrad.html"> |
| |
| |
| <b>6.3.6.</b> |
| |
| AdaGradRDA, AdaGrad, AdaDelta |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.3.7" data-path="../binaryclass/news20_rf.html"> |
| |
| <a href="../binaryclass/news20_rf.html"> |
| |
| |
| <b>6.3.7.</b> |
| |
| Random Forest |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.3.8" data-path="../binaryclass/news20b_xgboost.html"> |
| |
| <a href="../binaryclass/news20b_xgboost.html"> |
| |
| |
| <b>6.3.8.</b> |
| |
| XGBoost |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="6.4" data-path="../binaryclass/kdd2010a.html"> |
| |
| <a href="../binaryclass/kdd2010a.html"> |
| |
| |
| <b>6.4.</b> |
| |
| KDD2010a Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="6.4.1" data-path="../binaryclass/kdd2010a_dataset.html"> |
| |
| <a href="../binaryclass/kdd2010a_dataset.html"> |
| |
| |
| <b>6.4.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.4.2" data-path="../binaryclass/kdd2010a_scw.html"> |
| |
| <a href="../binaryclass/kdd2010a_scw.html"> |
| |
| |
| <b>6.4.2.</b> |
| |
| PA, CW, AROW, SCW |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="6.5" data-path="../binaryclass/kdd2010b.html"> |
| |
| <a href="../binaryclass/kdd2010b.html"> |
| |
| |
| <b>6.5.</b> |
| |
| KDD2010b Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="6.5.1" data-path="../binaryclass/kdd2010b_dataset.html"> |
| |
| <a href="../binaryclass/kdd2010b_dataset.html"> |
| |
| |
| <b>6.5.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.5.2" data-path="../binaryclass/kdd2010b_arow.html"> |
| |
| <a href="../binaryclass/kdd2010b_arow.html"> |
| |
| |
| <b>6.5.2.</b> |
| |
| AROW |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="6.6" data-path="../binaryclass/webspam.html"> |
| |
| <a href="../binaryclass/webspam.html"> |
| |
| |
| <b>6.6.</b> |
| |
| Webspam Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="6.6.1" data-path="../binaryclass/webspam_dataset.html"> |
| |
| <a href="../binaryclass/webspam_dataset.html"> |
| |
| |
| <b>6.6.1.</b> |
| |
| Data Pareparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.6.2" data-path="../binaryclass/webspam_scw.html"> |
| |
| <a href="../binaryclass/webspam_scw.html"> |
| |
| |
| <b>6.6.2.</b> |
| |
| PA1, AROW, SCW |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="6.7" data-path="../binaryclass/titanic_rf.html"> |
| |
| <a href="../binaryclass/titanic_rf.html"> |
| |
| |
| <b>6.7.</b> |
| |
| Kaggle Titanic Tutorial |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.8" data-path="../binaryclass/criteo.html"> |
| |
| <a href="../binaryclass/criteo.html"> |
| |
| |
| <b>6.8.</b> |
| |
| Criteo Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="6.8.1" data-path="../binaryclass/criteo_dataset.html"> |
| |
| <a href="../binaryclass/criteo_dataset.html"> |
| |
| |
| <b>6.8.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="6.8.2" data-path="../binaryclass/criteo_ffm.html"> |
| |
| <a href="../binaryclass/criteo_ffm.html"> |
| |
| |
| <b>6.8.2.</b> |
| |
| Field-Aware Factorization Machines |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part VII - Multiclass Classification</li> |
| |
| |
| |
| <li class="chapter " data-level="7.1" data-path="../multiclass/news20.html"> |
| |
| <a href="../multiclass/news20.html"> |
| |
| |
| <b>7.1.</b> |
| |
| News20 Multiclass Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="7.1.1" data-path="../multiclass/news20_dataset.html"> |
| |
| <a href="../multiclass/news20_dataset.html"> |
| |
| |
| <b>7.1.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="7.1.2" data-path="../multiclass/news20_one-vs-the-rest_dataset.html"> |
| |
| <a href="../multiclass/news20_one-vs-the-rest_dataset.html"> |
| |
| |
| <b>7.1.2.</b> |
| |
| Data Preparation for one-vs-the-rest classifiers |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="7.1.3" data-path="../multiclass/news20_pa.html"> |
| |
| <a href="../multiclass/news20_pa.html"> |
| |
| |
| <b>7.1.3.</b> |
| |
| PA |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="7.1.4" data-path="../multiclass/news20_scw.html"> |
| |
| <a href="../multiclass/news20_scw.html"> |
| |
| |
| <b>7.1.4.</b> |
| |
| CW, AROW, SCW |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="7.1.5" data-path="../multiclass/news20_xgboost.html"> |
| |
| <a href="../multiclass/news20_xgboost.html"> |
| |
| |
| <b>7.1.5.</b> |
| |
| XGBoost |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="7.1.6" data-path="../multiclass/news20_ensemble.html"> |
| |
| <a href="../multiclass/news20_ensemble.html"> |
| |
| |
| <b>7.1.6.</b> |
| |
| Ensemble learning |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="7.1.7" data-path="../multiclass/news20_one-vs-the-rest.html"> |
| |
| <a href="../multiclass/news20_one-vs-the-rest.html"> |
| |
| |
| <b>7.1.7.</b> |
| |
| one-vs-the-rest Classifier |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="7.2" data-path="../multiclass/iris.html"> |
| |
| <a href="../multiclass/iris.html"> |
| |
| |
| <b>7.2.</b> |
| |
| Iris Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="7.2.1" data-path="../multiclass/iris_dataset.html"> |
| |
| <a href="../multiclass/iris_dataset.html"> |
| |
| |
| <b>7.2.1.</b> |
| |
| Data preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="7.2.2" data-path="../multiclass/iris_scw.html"> |
| |
| <a href="../multiclass/iris_scw.html"> |
| |
| |
| <b>7.2.2.</b> |
| |
| SCW |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="7.2.3" data-path="../multiclass/iris_randomforest.html"> |
| |
| <a href="../multiclass/iris_randomforest.html"> |
| |
| |
| <b>7.2.3.</b> |
| |
| Random Forest |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="7.2.4" data-path="../multiclass/iris_xgboost.html"> |
| |
| <a href="../multiclass/iris_xgboost.html"> |
| |
| |
| <b>7.2.4.</b> |
| |
| XGBoost |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part VIII - Regression</li> |
| |
| |
| |
| <li class="chapter " data-level="8.1" data-path="../regression/general.html"> |
| |
| <a href="../regression/general.html"> |
| |
| |
| <b>8.1.</b> |
| |
| Regression |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="8.2" data-path="../regression/e2006.html"> |
| |
| <a href="../regression/e2006.html"> |
| |
| |
| <b>8.2.</b> |
| |
| E2006-tfidf Regression Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="8.2.1" data-path="../regression/e2006_dataset.html"> |
| |
| <a href="../regression/e2006_dataset.html"> |
| |
| |
| <b>8.2.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_generic.html"> |
| |
| <a href="../regression/e2006_generic.html"> |
| |
| |
| <b>8.2.2.</b> |
| |
| General Regessor |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="8.2.3" data-path="../regression/e2006_arow.html"> |
| |
| <a href="../regression/e2006_arow.html"> |
| |
| |
| <b>8.2.3.</b> |
| |
| Passive Aggressive, AROW |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="8.2.4" data-path="../regression/e2006_xgboost.html"> |
| |
| <a href="../regression/e2006_xgboost.html"> |
| |
| |
| <b>8.2.4.</b> |
| |
| XGBoost |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="8.3" data-path="../regression/kddcup12tr2.html"> |
| |
| <a href="../regression/kddcup12tr2.html"> |
| |
| |
| <b>8.3.</b> |
| |
| KDDCup 2012 Track 2 CTR Prediction Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="8.3.1" data-path="../regression/kddcup12tr2_dataset.html"> |
| |
| <a href="../regression/kddcup12tr2_dataset.html"> |
| |
| |
| <b>8.3.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="8.3.2" data-path="../regression/kddcup12tr2_lr.html"> |
| |
| <a href="../regression/kddcup12tr2_lr.html"> |
| |
| |
| <b>8.3.2.</b> |
| |
| Logistic Regression, Passive Aggressive |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="8.3.3" data-path="../regression/kddcup12tr2_lr_amplify.html"> |
| |
| <a href="../regression/kddcup12tr2_lr_amplify.html"> |
| |
| |
| <b>8.3.3.</b> |
| |
| Logistic Regression with amplifier |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="8.3.4" data-path="../regression/kddcup12tr2_adagrad.html"> |
| |
| <a href="../regression/kddcup12tr2_adagrad.html"> |
| |
| |
| <b>8.3.4.</b> |
| |
| AdaGrad, AdaDelta |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part IX - Recommendation</li> |
| |
| |
| |
| <li class="chapter " data-level="9.1" data-path="../recommend/cf.html"> |
| |
| <a href="../recommend/cf.html"> |
| |
| |
| <b>9.1.</b> |
| |
| Collaborative Filtering |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="9.1.1" data-path="../recommend/item_based_cf.html"> |
| |
| <a href="../recommend/item_based_cf.html"> |
| |
| |
| <b>9.1.1.</b> |
| |
| Item-based Collaborative Filtering |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="9.2" data-path="../recommend/news20.html"> |
| |
| <a href="../recommend/news20.html"> |
| |
| |
| <b>9.2.</b> |
| |
| News20 Related Article Recommendation Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="9.2.1" data-path="../multiclass/news20_dataset.html"> |
| |
| <a href="../multiclass/news20_dataset.html"> |
| |
| |
| <b>9.2.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="9.2.2" data-path="../recommend/news20_jaccard.html"> |
| |
| <a href="../recommend/news20_jaccard.html"> |
| |
| |
| <b>9.2.2.</b> |
| |
| LSH/MinHash and Jaccard Similarity |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="9.2.3" data-path="../recommend/news20_knn.html"> |
| |
| <a href="../recommend/news20_knn.html"> |
| |
| |
| <b>9.2.3.</b> |
| |
| LSH/MinHash and Brute-force Search |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="9.2.4" data-path="../recommend/news20_bbit_minhash.html"> |
| |
| <a href="../recommend/news20_bbit_minhash.html"> |
| |
| |
| <b>9.2.4.</b> |
| |
| kNN search using b-Bits MinHash |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="9.3" data-path="../recommend/movielens.html"> |
| |
| <a href="../recommend/movielens.html"> |
| |
| |
| <b>9.3.</b> |
| |
| MovieLens Movie Recommendation Tutorial |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="9.3.1" data-path="../recommend/movielens_dataset.html"> |
| |
| <a href="../recommend/movielens_dataset.html"> |
| |
| |
| <b>9.3.1.</b> |
| |
| Data Preparation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="9.3.2" data-path="../recommend/movielens_cf.html"> |
| |
| <a href="../recommend/movielens_cf.html"> |
| |
| |
| <b>9.3.2.</b> |
| |
| Item-based Collaborative Filtering |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="9.3.3" data-path="../recommend/movielens_mf.html"> |
| |
| <a href="../recommend/movielens_mf.html"> |
| |
| |
| <b>9.3.3.</b> |
| |
| Matrix Factorization |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="9.3.4" data-path="../recommend/movielens_fm.html"> |
| |
| <a href="../recommend/movielens_fm.html"> |
| |
| |
| <b>9.3.4.</b> |
| |
| Factorization Machine |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="9.3.5" data-path="../recommend/movielens_slim.html"> |
| |
| <a href="../recommend/movielens_slim.html"> |
| |
| |
| <b>9.3.5.</b> |
| |
| SLIM for fast top-k Recommendation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="9.3.6" data-path="../recommend/movielens_cv.html"> |
| |
| <a href="../recommend/movielens_cv.html"> |
| |
| |
| <b>9.3.6.</b> |
| |
| 10-fold Cross Validation (Matrix Factorization) |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part X - Anomaly Detection</li> |
| |
| |
| |
| <li class="chapter " data-level="10.1" data-path="../anomaly/lof.html"> |
| |
| <a href="../anomaly/lof.html"> |
| |
| |
| <b>10.1.</b> |
| |
| Outlier Detection using Local Outlier Factor (LOF) |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="10.2" data-path="../anomaly/sst.html"> |
| |
| <a href="../anomaly/sst.html"> |
| |
| |
| <b>10.2.</b> |
| |
| Change-Point Detection using Singular Spectrum Transformation (SST) |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="10.3" data-path="../anomaly/changefinder.html"> |
| |
| <a href="../anomaly/changefinder.html"> |
| |
| |
| <b>10.3.</b> |
| |
| ChangeFinder: Detecting Outlier and Change-Point Simultaneously |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part XI - Clustering</li> |
| |
| |
| |
| <li class="chapter " data-level="11.1" data-path="../clustering/lda.html"> |
| |
| <a href="../clustering/lda.html"> |
| |
| |
| <b>11.1.</b> |
| |
| Latent Dirichlet Allocation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| <li class="chapter " data-level="11.2" data-path="../clustering/plsa.html"> |
| |
| <a href="../clustering/plsa.html"> |
| |
| |
| <b>11.2.</b> |
| |
| Probabilistic Latent Semantic Analysis |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part XII - GeoSpatial Functions</li> |
| |
| |
| |
| <li class="chapter " data-level="12.1" data-path="../geospatial/latlon.html"> |
| |
| <a href="../geospatial/latlon.html"> |
| |
| |
| <b>12.1.</b> |
| |
| Lat/Lon functions |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part XIII - Hivemall on SparkSQL</li> |
| |
| |
| |
| <li class="chapter " data-level="13.1" data-path="../spark/getting_started/README.md"> |
| |
| <span> |
| |
| |
| <b>13.1.</b> |
| |
| Getting Started |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="13.1.1" data-path="../spark/getting_started/installation.html"> |
| |
| <a href="../spark/getting_started/installation.html"> |
| |
| |
| <b>13.1.1.</b> |
| |
| Installation |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="13.2" data-path="../spark/binaryclass/"> |
| |
| <a href="../spark/binaryclass/"> |
| |
| |
| <b>13.2.</b> |
| |
| Binary Classification |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="13.2.1" data-path="../spark/binaryclass/a9a_sql.html"> |
| |
| <a href="../spark/binaryclass/a9a_sql.html"> |
| |
| |
| <b>13.2.1.</b> |
| |
| a9a Tutorial for SQL |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| <li class="chapter " data-level="13.3" data-path="../spark/binaryclass/"> |
| |
| <a href="../spark/binaryclass/"> |
| |
| |
| <b>13.3.</b> |
| |
| Regression |
| |
| </a> |
| |
| |
| |
| <ul class="articles"> |
| |
| |
| <li class="chapter " data-level="13.3.1" data-path="../spark/regression/e2006_sql.html"> |
| |
| <a href="../spark/regression/e2006_sql.html"> |
| |
| |
| <b>13.3.1.</b> |
| |
| E2006-tfidf Regression Tutorial for SQL |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| </ul> |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part XIV - Hivemall on Docker</li> |
| |
| |
| |
| <li class="chapter " data-level="14.1" data-path="../docker/getting_started.html"> |
| |
| <a href="../docker/getting_started.html"> |
| |
| |
| <b>14.1.</b> |
| |
| Getting Started |
| |
| </a> |
| |
| |
| |
| </li> |
| |
| |
| |
| |
| <li class="header">Part XIV - External References</li> |
| |
| |
| |
| <li class="chapter " data-level="15.1" > |
| |
| <a target="_blank" href="https://github.com/daijyc/hivemall/wiki/PigHome"> |
| |
| |
| <b>15.1.</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=".." >Text Tokenizer</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. |
| --> |
| <!-- toc --><div id="toc" class="toc"> |
| |
| <ul> |
| <li><a href="#tokenizer-for-english-texts">Tokenizer for English Texts</a></li> |
| <li><a href="#tokenizer-for-non-english-texts">Tokenizer for Non-English Texts</a><ul> |
| <li><a href="#japanese-tokenizer">Japanese Tokenizer</a><ul> |
| <li><a href="#custom-dictionary">Custom dictionary</a></li> |
| <li><a href="#part-of-speech">Part-of-speech</a></li> |
| </ul> |
| </li> |
| <li><a href="#chinese-tokenizer">Chinese Tokenizer</a></li> |
| <li><a href="#korean-tokenizer">Korean Tokenizer</a><ul> |
| <li><a href="#custom-dictionary-1">Custom dictionary</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| |
| </div><!-- tocstop --> |
| <h1 id="tokenizer-for-english-texts">Tokenizer for English Texts</h1> |
| <p>Hivemall provides simple English text tokenizer UDF that has following syntax:</p> |
| <pre><code class="lang-sql">tokenize(text input, optional boolean toLowerCase = false) |
| </code></pre> |
| <h1 id="tokenizer-for-non-english-texts">Tokenizer for Non-English Texts</h1> |
| <h2 id="japanese-tokenizer">Japanese Tokenizer</h2> |
| <p>Japanese text tokenizer UDF uses <a href="https://github.com/atilika/kuromoji" target="_blank">Kuromoji</a>. </p> |
| <p>The signature of the UDF is as follows:</p> |
| <pre><code class="lang-sql">-- uses Kuromoji default dictionary by the default |
| tokenize_ja(text input, optional const text mode = "normal", optional const array<string> stopWords, const array<string> stopTags, const array<string> userDict) |
| |
| -- tokenize_ja_neologd uses mecab-ipa-neologd for it's dictionary. |
| tokenize_ja_neologd(text input, optional const text mode = "normal", optional const array<string> stopWords, const array<string> stopTags, const array<string> userDict) |
| </code></pre> |
| <div class="panel panel-primary"><div class="panel-heading"><h3 class="panel-title" id="note"><i class="fa fa-edit"></i> Note</h3></div><div class="panel-body"><p><code>tokenize_ja_neologd</code> returns tokenized strings in an array by using the NEologd dictionary. <a href="https://github.com/neologd/mecab-ipadic-neologd" target="_blank">mecab-ipadic-NEologd</a> is a customized system dictionary for MeCab inclucing new vocablaries extracted from many resources on the Web. </p></div></div> |
| <p>See differences between with and without Neologd as follows:</p> |
| <pre><code class="lang-sql">select tokenize_ja("彼女はペンパイナッポーアッポーペンと恋ダンスを踊った。"); |
| >["彼女","ペンパイナッポーアッポーペン","恋","ダンス","踊る"] |
| |
| select tokenize_ja_neologd("彼女はペンパイナッポーアッポーペンと恋ダンスを踊った。"); |
| > ["彼女","ペンパイナッポーアッポーペン","恋ダンス","踊る"] |
| </code></pre> |
| <p>You can print versions for Kuromoji UDFs as follows:</p> |
| <pre><code class="lang-sql">select tokenize_ja(); |
| > ["8.8.2"] |
| |
| select tokenize_ja_neologd(); |
| > ["8.8.2-20200910.2"] |
| </code></pre> |
| <p>Its basic usage is as follows:</p> |
| <pre><code class="lang-sql"><span class="hljs-keyword">select</span> tokenize_ja(<span class="hljs-string">"kuromojiを使った分かち書きのテストです。第二引数にはnormal/search/extendedを指定できます。デフォルトではnormalモードです。"</span>); |
| </code></pre> |
| <blockquote> |
| <p>["kuromoji","使う","分かち書き","テスト","第","二","引数","normal","search","extended","指定","デフォルト","normal","モード"]</p> |
| </blockquote> |
| <p>In addition, the third and fourth argument respectively allow you to use your own list of stop words and stop tags. For example, the following query simply ignores "kuromoji" (as a stop word) and noun word "分かち書き" (as a stop tag):</p> |
| <pre><code class="lang-sql"><span class="hljs-keyword">select</span> tokenize_ja(<span class="hljs-string">"kuromojiを使った分かち書きのテストです。"</span>, <span class="hljs-string">"normal"</span>, <span class="hljs-built_in">array</span>(<span class="hljs-string">"kuromoji"</span>), <span class="hljs-built_in">array</span>(<span class="hljs-string">"名詞-一般"</span>)); |
| </code></pre> |
| <blockquote> |
| <p>["を","使う","た","の","テスト","です"]</p> |
| </blockquote> |
| <pre><code class="lang-sql"><span class="hljs-keyword">select</span> tokenize_ja(<span class="hljs-string">"kuromojiを使った分かち書きのテストです。"</span>, <span class="hljs-string">"normal"</span>, <span class="hljs-built_in">array</span>(<span class="hljs-string">"kuromoji"</span>), stoptags_exclude(<span class="hljs-built_in">array</span>(<span class="hljs-string">"名詞"</span>))); |
| </code></pre> |
| <blockquote> |
| <p>["分かち書き","テスト"]</p> |
| </blockquote> |
| <p><code>stoptags_exclude(array<string> tags, [, const string lang='ja'])</code> is a useful UDF for getting <a href="https://github.com/apache/lucene-solr/blob/master/lucene/analysis/kuromoji/src/resources/org/apache/lucene/analysis/ja/stoptags.txt" target="_blank">stoptags</a> excluding given part-of-speech tags as seen below:</p> |
| <pre><code class="lang-sql"><span class="hljs-keyword">select</span> stoptags_exclude(<span class="hljs-built_in">array</span>(<span class="hljs-string">"名詞-固有名詞"</span>)); |
| </code></pre> |
| <blockquote> |
| <p>["その他","その他-間投","フィラー","副詞","副詞-一般","副詞-助詞類接続","助動詞","助詞","助詞-並立助詞" |
| ,"助詞-係助詞","助詞-副助詞","助詞-副助詞／並立助詞／終助詞","助詞-副詞化","助詞-接続助詞","助詞-格助詞 |
| ","助詞-格助詞-一般","助詞-格助詞-引用","助詞-格助詞-連語","助詞-特殊","助詞-終助詞","助詞-連体化","助 |
| 詞-間投助詞","動詞","動詞-接尾","動詞-自立","動詞-非自立","名詞","名詞-サ変接続","名詞-ナイ形容詞語幹", |
| "名詞-一般","名詞-代名詞","名詞-代名詞-一般","名詞-代名詞-縮約","名詞-副詞可能","名詞-動詞非自立的","名 |
| 詞-引用文字列","名詞-形容動詞語幹","名詞-接尾","名詞-接尾-サ変接続","名詞-接尾-一般","名詞-接尾-人名"," |
| 名詞-接尾-副詞可能","名詞-接尾-助動詞語幹","名詞-接尾-助数詞","名詞-接尾-地域","名詞-接尾-形容動詞語幹" |
| ,"名詞-接尾-特殊","名詞-接続詞的","名詞-数","名詞-特殊","名詞-特殊-助動詞語幹","名詞-非自立","名詞-非自 |
| 立-一般","名詞-非自立-副詞可能","名詞-非自立-助動詞語幹","名詞-非自立-形容動詞語幹","形容詞","形容詞-接 |
| 尾","形容詞-自立","形容詞-非自立","感動詞","接続詞","接頭詞","接頭詞-動詞接続","接頭詞-名詞接続","接頭 |
| 詞-形容詞接続","接頭詞-数接","未知語","記号","記号-アルファベット","記号-一般","記号-句点","記号-括弧閉 |
| ","記号-括弧開","記号-空白","記号-読点","語断片","連体詞","非言語音"]</p> |
| </blockquote> |
| <h3 id="custom-dictionary">Custom dictionary</h3> |
| <p>Moreover, the fifth argument <code>userDict</code> enables you to register a user-defined custom dictionary in <a href="https://github.com/atilika/kuromoji/blob/909fd6b32bf4e9dc86b7599de5c9b50ca8f004a1/kuromoji-core/src/test/resources/userdict.txt" target="_blank">Kuromoji official format</a>:</p> |
| <pre><code class="lang-sql"><span class="hljs-keyword">select</span> tokenize_ja(<span class="hljs-string">"日本経済新聞＆関西国際空港"</span>, <span class="hljs-string">"normal"</span>, <span class="hljs-literal">null</span>, <span class="hljs-literal">null</span>, |
| <span class="hljs-built_in">array</span>( |
| <span class="hljs-string">"日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞"</span>, |
| <span class="hljs-string">"関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,テスト名詞"</span> |
| )); |
| </code></pre> |
| <blockquote> |
| <p>["日本","経済","新聞","関西","国際","空港"]</p> |
| </blockquote> |
| <p>Note that you can pass <code>null</code> to each of the third and fourth argument to explicitly use Kuromoji's <a href="https://github.com/apache/lucene-solr/blob/master/lucene/analysis/kuromoji/src/resources/org/apache/lucene/analysis/ja/stopwords.txt" target="_blank">default stop words</a> and <a href="https://github.com/apache/lucene-solr/blob/master/lucene/analysis/kuromoji/src/resources/org/apache/lucene/analysis/ja/stoptags.txt" target="_blank">stop tags</a>.</p> |
| <p>If you have a large custom dictionary as an external file, <code>userDict</code> can also be <code>const string userDictURL</code> which indicates URL of the external file on somewhere like Amazon S3:</p> |
| <pre><code class="lang-sql">select tokenize_ja("日本経済新聞＆関西国際空港", "normal", null, null, |
| "https://raw.githubusercontent.com/atilika/kuromoji/909fd6b32bf4e9dc86b7599de5c9b50ca8f004a1/kuromoji-core/src/test/resources/userdict.txt"); |
| |
| > ["日本","経済","新聞","関西","国際","空港"] |
| </code></pre> |
| <div class="panel panel-primary"><div class="panel-heading"><h3 class="panel-title" id="note"><i class="fa fa-edit"></i> Note</h3></div><div class="panel-body"><p>Dictionary SHOULD be accessible through http/https protocol. And, it SHOULD be compressed using gzip with <code>.gz</code> suffix because the maximum dictionary size is limited to 32MB and read timeout is set to 60 sec. Also, connection must be established in 10 sec.</p><p>If you want to use HTTP Basic Authentication, please use the following form: <code>https://user:password@www.sitreurl.com/my_dict.txt.gz</code> (see Sec 3.1 of <a href="https://www.ietf.org/rfc/rfc1738.txt" target="_blank">rfc1738</a>)</p></div></div> |
| <p>For detailed APIs, please refer Javadoc of <a href="https://lucene.apache.org/core/5_3_1/analyzers-kuromoji/org/apache/lucene/analysis/ja/JapaneseAnalyzer.html" target="_blank">JapaneseAnalyzer</a> as well.</p> |
| <h3 id="part-of-speech">Part-of-speech</h3> |
| <p>From Hivemall v0.6.0, the second argument can also accept the following option format:</p> |
| <pre><code> -mode <arg> The tokenization mode. One of ['normal', 'search', |
| 'extended', 'default' (normal)] |
| -pos Return part-of-speech information |
| </code></pre><p>Then, you can get part-of-speech information as follows:</p> |
| <pre><code class="lang-sql">WITH tmp as ( |
| <span class="hljs-keyword">select</span> |
| tokenize_ja(<span class="hljs-string">'kuromojiを使った分かち書きのテストです。'</span>,<span class="hljs-string">'-mode search -pos'</span>) <span class="hljs-keyword">as</span> r |
| ) |
| <span class="hljs-keyword">select</span> |
| r.tokens, |
| r.pos, |
| r.tokens[<span class="hljs-number">0</span>] <span class="hljs-keyword">as</span> token0, |
| r.pos[<span class="hljs-number">0</span>] <span class="hljs-keyword">as</span> pos0 |
| <span class="hljs-keyword">from</span> |
| tmp; |
| </code></pre> |
| <table> |
| <thead> |
| <tr> |
| <th style="text-align:center">tokens</th> |
| <th style="text-align:center">pos</th> |
| <th style="text-align:center">token0</th> |
| <th style="text-align:center">pos0</th> |
| </tr> |
| </thead> |
| <tbody> |
| <tr> |
| <td style="text-align:center">["kuromoji","使う","分かち書き","テスト"]</td> |
| <td style="text-align:center">["名詞-一般","動詞-自立","名詞-一般","名詞-サ変接続"]</td> |
| <td style="text-align:center">kuromoji</td> |
| <td style="text-align:center">名詞-一般</td> |
| </tr> |
| </tbody> |
| </table> |
| <p>Note that when <code>-pos</code> option is specified, <code>tokenize_ja</code> returns a struct record containing <code>array<string> tokens</code> and <code>array<string> pos</code> as the elements.</p> |
| <h2 id="chinese-tokenizer">Chinese Tokenizer</h2> |
| <p>Chinese text tokenizer UDF uses <a href="https://lucene.apache.org/core/5_3_1/analyzers-smartcn/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.html" target="_blank">SmartChineseAnalyzer</a>. </p> |
| <p>The signature of the UDF is as follows:</p> |
| <pre><code class="lang-sql">tokenize_cn(string line, optional const array<string> stopWords) |
| </code></pre> |
| <p>Its basic usage is as follows:</p> |
| <pre><code class="lang-sql">select tokenize_cn("Smartcn为Apache2.0协议的开源中文分词系统，Java语言编写，修改的中科院计算所ICTCLAS分词系统。"); |
| |
| > [smartcn, 为, apach, 2, 0, 协议, 的, 开源, 中文, 分词, 系统, java, 语言, 编写, 修改, 的, 中科院, 计算, 所, ictcla, 分词, 系统] |
| </code></pre> |
| <p>For detailed APIs, please refer Javadoc of <a href="https://lucene.apache.org/core/5_3_1/analyzers-smartcn/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.html" target="_blank">SmartChineseAnalyzer</a> as well.</p> |
| <h2 id="korean-tokenizer">Korean Tokenizer</h2> |
| <p>Korean toknizer internally uses <a href="https://www.slideshare.net/elasticsearch/nori-the-official-elasticsearch-plugin-for-korean-language-analysis" target="_blank">lucene-analyzers-nori</a> for tokenization.</p> |
| <p>The signature of the UDF is as follows:</p> |
| <pre><code class="lang-sql">tokenize_ko( |
| String line [, const string mode = "discard" (or const string opts), |
| const array<string> stopWords, |
| const array<string> |
| stopTags, |
| const array<string> userDict (or const string userDictURL)] |
| ) - returns tokenized strings in array<string> |
| </code></pre> |
| <div class="panel panel-primary"><div class="panel-heading"><h3 class="panel-title" id="note"><i class="fa fa-edit"></i> Note</h3></div><div class="panel-body"><p>Instead of mode, the 2nd argument can take options starting with <code>-</code>.</p></div></div> |
| <p>You can get usage as follows:</p> |
| <pre><code class="lang-sql">select tokenize_ko("", "-help"); |
| |
| usage: tokenize_ko(String line [, const string mode = "discard" (or const |
| string opts), const array<string> stopWords, const array<string> |
| stopTags, const array<string> userDict (or const string |
| userDictURL)]) - returns tokenized strings in array<string> [-help] |
| [-mode <arg>] [-outputUnknownUnigrams] |
| -help Show function help |
| -mode <arg> The tokenization mode. One of ['node', 'discard' |
| (default), 'mixed'] |
| -outputUnknownUnigrams outputs unigrams for unknown words. |
| </code></pre> |
| <div class="panel panel-primary"><div class="panel-heading"><h3 class="panel-title" id="note"><i class="fa fa-edit"></i> Note</h3></div><div class="panel-body"><p>For details options, please refer <a href="https://lucene.apache.org/core/8_8_2/analyzers-nori/org/apache/lucene/analysis/ko/KoreanAnalyzer.html" target="_blank">Lucene API document</a>. <code>none</code>, <code>discord</code> (default), or <code>mixed</code> are supported for the mode argument.</p></div></div> |
| <p>See the following examples for the usage.</p> |
| <pre><code class="lang-sql">-- show version of lucene-analyzers-nori |
| select tokenize_ko(); |
| > 8.8.2 |
| |
| select tokenize_ko('중요한 새 기능을 개발해줘서 정말 고마워요!'); |
| > ["중요","기능","개발","주","고맙"] |
| |
| -- explicitly using default options |
| select tokenize_ko('중요한 새 기능을 개발해줘서 정말 고마워요!', '-mode discard', |
| -- stopwords (null to use default) |
| -- see https://github.com/apache/incubator-hivemall/blob/master/nlp/src/main/resources/hivemall/nlp/tokenizer/ext/stopwords-ko.txt |
| null, |
| -- stoptags |
| -- see https://lucene.apache.org/core/8_8_2/analyzers-nori/org/apache/lucene/analysis/ko/POS.Tag.html |
| array( |
| 'E', -- Verbal endings |
| 'IC', -- Interjection |
| 'J', -- Ending Particle |
| 'MAG', -- General Adverb |
| 'MAJ', -- Conjunctive adverb |
| 'MM', -- Determiner |
| 'SP', -- Space |
| 'SSC', -- Closing brackets |
| 'SSO', -- Opening brackets |
| 'SC', -- Separator |
| 'SE', -- Ellipsis |
| 'XPN', -- Prefix |
| 'XSA', -- Adjective Suffix |
| 'XSN', -- Noun Suffix |
| 'XSV', -- Verb Suffix |
| 'UNA', -- Unknown |
| 'NA', -- Unknown |
| 'VSV' -- Unknown |
| ) |
| ); |
| > ["중요","기능","개발","주","고맙"] |
| |
| -- None mode, without General Adverb (MAG) |
| select tokenize_ko('중요한 새 기능을 개발해줘서 정말 고마워요!', |
| -- No decomposition for compound. |
| '-mode none', |
| -- stopwords (null to use default) |
| null, |
| array( |
| 'E', -- Verbal endings |
| 'IC', -- Interjection |
| 'J', -- Ending Particle |
| -- 'MAG', -- General Adverb |
| 'MAJ', -- Conjunctive adverb |
| 'MM', -- Determiner |
| 'SP', -- Space |
| 'SSC', -- Closing brackets |
| 'SSO', -- Opening brackets |
| 'SC', -- Separator |
| 'SE', -- Ellipsis |
| 'XPN', -- Prefix |
| 'XSA', -- Adjective Suffix |
| 'XSN', -- Noun Suffix |
| 'XSV', -- Verb Suffix |
| 'UNA', -- Unknown |
| 'NA', -- Unknown |
| 'VSV' -- Unknown |
| ) |
| ); |
| > ["중요","기능","개발","줘서","정말","고마워요"] |
| |
| -- discard mode: Decompose compounds and discards the original form (default). |
| -- https://lucene.apache.org/core/8_8_2/analyzers-nori/org/apache/lucene/analysis/ko/KoreanTokenizer.DecompoundMode.html |
| select tokenize_ko('중요한 새 기능을 개발해줘서 정말 고마워요!', '-mode discard'); |
| > ["중요","기능","개발","주","고맙"] |
| |
| -- default stopward (null), with stoptags |
| select tokenize_ko('중요한 새 기능을 개발해줘서 정말 고마워요!', '-mode discard', null, array('E', 'VV')); |
| > ["중요","하","새","기능","을","개발","하","주","정말","고맙"] |
| |
| -- mixed mode: Decompose compounds and keeps the original form. |
| select tokenize_ko('중요한 새 기능을 개발해줘서 정말 고마워요!', 'mixed'); |
| > ["중요","기능","개발","줘서","주","고마워요","고맙"] |
| |
| select tokenize_ko('중요한 새 기능을 개발해줘서 정말 고마워요!', '-mode mixed'); |
| > ["중요","기능","개발","줘서","주","고마워요","고맙"] |
| |
| -- node mode: No decomposition for compound. |
| select tokenize_ko('중요한 새 기능을 개발해줘서 정말 고마워요!', '-mode none'); |
| > ["중요","기능","개발","줘서","고마워요"] |
| |
| select tokenize_ko('Hello, world.', '-mode none'); |
| > ["hello","world"] |
| |
| select tokenize_ko('Hello, world.', '-mode none -outputUnknownUnigrams'); |
| > ["h","e","l","l","o","w","o","r","l","d"] |
| |
| select tokenize_ko('나는 C++ 언어를 프로그래밍 언어로 사랑한다.', '-mode discard'); |
| > ["나","c","언어","프로그래밍","언어","사랑"] |
| |
| select tokenize_ko('나는 C++ 언어를 프로그래밍 언어로 사랑한다.', '-mode discard', array(), null); |
| > ["나","는","c","언어","를","프로그래밍","언어","로","사랑","하","ᆫ다"] |
| |
| -- default stopward (null), default stoptags (null) |
| select tokenize_ko('나는 C++ 언어를 프로그래밍 언어로 사랑한다.', '-mode discard'); |
| select tokenize_ko('나는 C++ 언어를 프로그래밍 언어로 사랑한다.', '-mode discard', null, null); |
| > ["나","c","언어","프로그래밍","언어","사랑"] |
| |
| -- no stopward (empty array), default stoptags (null) |
| select tokenize_ko('나는 C++ 언어를 프로그래밍 언어로 사랑한다.', '-mode discard', array()); |
| select tokenize_ko('나는 C++ 언어를 프로그래밍 언어로 사랑한다.', '-mode discard', array(), null); |
| > ["나","c","언어","프로그래밍","언어","사랑"] |
| |
| -- no stopward (empty array), no stoptags (emptry array), custom dict |
| select tokenize_ko('나는 C++ 언어를 프로그래밍 언어로 사랑한다.', '-mode discard', array(), array(), array('C++')); |
| > ["나","는","c++","언어","를","프로그래밍","언어","로","사랑","하","ᆫ다"] |
| |
| > -- default stopward (null), default stoptags (null), custom dict |
| select tokenize_ko('나는 C++ 언어를 프로그래밍 언어로 사랑한다.', '-mode discard', null, null, array('C++')); |
| > ["나","c++","언어","프로그래밍","언어","사랑"] |
| </code></pre> |
| <h3 id="custom-dictionary">Custom dictionary</h3> |
| <p>Moreover, the fifth argument <code>userDictURL</code> enables you to register a user-defined custom dictionary placed in http/https accessible external site. Find the dictionary format <a href="https://raw.githubusercontent.com/apache/lucene/main/lucene/analysis/nori/src/test/org/apache/lucene/analysis/ko/userdict.txt" target="_blank">here from Lucene's one</a>.</p> |
| <pre><code class="lang-sql">select tokenize_ko('나는 c++ 프로그래밍을 즐긴다.', '-mode discard', null, null, 'https://raw.githubusercontent.com/apache/lucene/main/lucene/analysis/nori/src/test/org/apache/lucene/analysis/ko/userdict.txt'); |
| |
| > ["나","c++","프로그래밍","즐기"] |
| </code></pre> |
| <div class="panel panel-primary"><div class="panel-heading"><h3 class="panel-title" id="note"><i class="fa fa-edit"></i> Note</h3></div><div class="panel-body"><p>Dictionary SHOULD be accessible through http/https protocol. And, it SHOULD be compressed using gzip with <code>.gz</code> suffix because the maximum dictionary size is limited to 32MB and read timeout is set to 60 sec. Also, connection must be established in 10 sec.</p></div></div> |
| <p><div id="page-footer" class="localized-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":"Text Tokenizer","level":"2.3","depth":1,"next":{"title":"Approximate Aggregate Functions","level":"2.4","depth":1,"path":"misc/approx.md","ref":"misc/approx.md","articles":[]},"previous":{"title":"Efficient Top-K Query Processing","level":"2.2","depth":1,"path":"misc/topk.md","ref":"misc/topk.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"https://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/tokenizer.md","mtime":"2021-05-14T03:34:47.827Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2021-05-14T03:36:16.688Z"},"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="../gitbook/gitbook-plugin-anchorjs/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> |
| |
