You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hivemall.apache.org by my...@apache.org on 2018/12/26 10:23:17 UTC
[29/33] incubator-hivemall-site git commit: Update tutorial for
general classifier/regressor
http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/d9012d92/userguide/binaryclass/criteo_ffm.html
----------------------------------------------------------------------
diff --git a/userguide/binaryclass/criteo_ffm.html b/userguide/binaryclass/criteo_ffm.html
index 465f74d..b83faf0 100644
--- a/userguide/binaryclass/criteo_ffm.html
+++ b/userguide/binaryclass/criteo_ffm.html
@@ -972,7 +972,7 @@
<b>6.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -980,13 +980,28 @@
</li>
- <li class="chapter " data-level="6.2.2" data-path="a9a_lr.html">
+ <li class="chapter " data-level="6.2.2" data-path="a9a_generic.html">
- <a href="a9a_lr.html">
+ <a href="a9a_generic.html">
<b>6.2.2.</b>
+ General Binary Classifier
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.2.3" data-path="a9a_lr.html">
+
+ <a href="a9a_lr.html">
+
+
+ <b>6.2.3.</b>
+
Logistic Regression
</a>
@@ -995,14 +1010,14 @@
</li>
- <li class="chapter " data-level="6.2.3" data-path="a9a_minibatch.html">
+ <li class="chapter " data-level="6.2.4" data-path="a9a_minibatch.html">
<a href="a9a_minibatch.html">
- <b>6.2.3.</b>
+ <b>6.2.4.</b>
- Mini-batch gradient descent
+ Mini-batch Gradient Descent
</a>
@@ -1038,7 +1053,7 @@
<b>6.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1076,13 +1091,28 @@
</li>
- <li class="chapter " data-level="6.3.4" data-path="news20_adagrad.html">
+ <li class="chapter " data-level="6.3.4" data-path="news20_generic.html">
- <a href="news20_adagrad.html">
+ <a href="news20_generic.html">
<b>6.3.4.</b>
+ General Binary Classifier
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.3.5" data-path="news20_adagrad.html">
+
+ <a href="news20_adagrad.html">
+
+
+ <b>6.3.5.</b>
+
AdaGradRDA, AdaGrad, AdaDelta
</a>
@@ -1091,12 +1121,12 @@
</li>
- <li class="chapter " data-level="6.3.5" data-path="news20_rf.html">
+ <li class="chapter " data-level="6.3.6" data-path="news20_rf.html">
<a href="news20_rf.html">
- <b>6.3.5.</b>
+ <b>6.3.6.</b>
Random Forest
@@ -1134,7 +1164,7 @@
<b>6.4.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1185,7 +1215,7 @@
<b>6.5.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1236,7 +1266,7 @@
<b>6.6.1.</b>
- Data pareparation
+ Data Pareparation
</a>
@@ -1302,7 +1332,7 @@
<b>6.8.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1360,7 +1390,7 @@
<b>7.1.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1375,7 +1405,7 @@
<b>7.1.2.</b>
- Data preparation for one-vs-the-rest classifiers
+ Data Preparation for one-vs-the-rest classifiers
</a>
@@ -1435,7 +1465,7 @@
<b>7.1.6.</b>
- one-vs-the-rest classifier
+ one-vs-the-rest Classifier
</a>
@@ -1559,7 +1589,7 @@
<b>8.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1567,13 +1597,28 @@
</li>
- <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_arow.html">
+ <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_generic.html">
- <a href="../regression/e2006_arow.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>
@@ -1610,7 +1655,7 @@
<b>8.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1698,7 +1743,7 @@
<b>9.1.1.</b>
- Item-based collaborative filtering
+ Item-based Collaborative Filtering
</a>
@@ -1734,7 +1779,7 @@
<b>9.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1749,7 +1794,7 @@
<b>9.2.2.</b>
- LSH/MinHash and Jaccard similarity
+ LSH/MinHash and Jaccard Similarity
</a>
@@ -1764,7 +1809,7 @@
<b>9.2.3.</b>
- LSH/MinHash and brute-force search
+ LSH/MinHash and Brute-force Search
</a>
@@ -1815,7 +1860,7 @@
<b>9.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1830,7 +1875,7 @@
<b>9.3.2.</b>
- Item-based collaborative filtering
+ Item-based Collaborative Filtering
</a>
@@ -1875,7 +1920,7 @@
<b>9.3.5.</b>
- SLIM for fast top-k recommendation
+ SLIM for fast top-k Recommendation
</a>
@@ -1890,7 +1935,7 @@
<b>9.3.6.</b>
- 10-fold cross validation (Matrix Factorization)
+ 10-fold Cross Validation (Matrix Factorization)
</a>
@@ -2080,7 +2125,7 @@
<b>13.2.1.</b>
- a9a tutorial for DataFrame
+ a9a Tutorial for DataFrame
</a>
@@ -2095,7 +2140,7 @@
<b>13.2.2.</b>
- a9a tutorial for SQL
+ a9a Tutorial for SQL
</a>
@@ -2131,7 +2176,7 @@
<b>13.3.1.</b>
- E2006-tfidf regression tutorial for DataFrame
+ E2006-tfidf Regression Tutorial for DataFrame
</a>
@@ -2146,7 +2191,7 @@
<b>13.3.2.</b>
- E2006-tfidf regression tutorial for SQL
+ E2006-tfidf Regression Tutorial for SQL
</a>
@@ -2166,7 +2211,7 @@
<b>13.4.</b>
- Generic features
+ Generic Features
</a>
@@ -2182,7 +2227,7 @@
<b>13.4.1.</b>
- Top-k join processing
+ Top-k Join Processing
</a>
@@ -2197,7 +2242,7 @@
<b>13.4.2.</b>
- Other utility functions
+ Other Utility Functions
</a>
@@ -2669,7 +2714,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda
<script>
var gitbook = gitbook || [];
gitbook.push(function() {
- gitbook.page.hasChanged({"page":{"title":"Field-Aware Factorization Machines","level":"6.8.2","depth":2,"next":{"title":"News20 Multiclass Tutorial","level":"7.1","depth":1,"path":"multiclass/news20.md","ref":"multiclass/news20.md","articles":[{"title":"Data preparation","level":"7.1.1","depth":2,"path":"multiclass/news20_dataset.md","ref":"multiclass/news20_dataset.md","articles":[]},{"title":"Data preparation for one-vs-the-rest classifiers","level":"7.1.2","depth":2,"path":"multiclass/news20_one-vs-the-rest_dataset.md","ref":"multiclass/news20_one-vs-the-rest_dataset.md","articles":[]},{"title":"PA","level":"7.1.3","depth":2,"path":"multiclass/news20_pa.md","ref":"multiclass/news20_pa.md","articles":[]},{"title":"CW, AROW, SCW","level":"7.1.4","depth":2,"path":"multiclass/news20_scw.md","ref":"multiclass/news20_scw.md","articles":[]},{"title":"Ensemble learning","level":"7.1.5","depth":2,"path":"multiclass/news20_ensemble.md","ref":"multiclass/news20_ensemble.md","art
icles":[]},{"title":"one-vs-the-rest classifier","level":"7.1.6","depth":2,"path":"multiclass/news20_one-vs-the-rest.md","ref":"multiclass/news20_one-vs-the-rest.md","articles":[]}]},"previous":{"title":"Data preparation","level":"6.8.1","depth":2,"path":"binaryclass/criteo_dataset.md","ref":"binaryclass/criteo_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":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://g
ithub.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"https://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5
"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"https://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"binaryclass/criteo_ffm.md","mtime":"2018-10-18T10:26:56.667Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-11-13T09:32:29.643Z"},"basePath":"..","book":{"language":""}});
+ gitbook.page.hasChanged({"page":{"title":"Field-Aware Factorization Machines","level":"6.8.2","depth":2,"next":{"title":"News20 Multiclass Tutorial","level":"7.1","depth":1,"path":"multiclass/news20.md","ref":"multiclass/news20.md","articles":[{"title":"Data Preparation","level":"7.1.1","depth":2,"path":"multiclass/news20_dataset.md","ref":"multiclass/news20_dataset.md","articles":[]},{"title":"Data Preparation for one-vs-the-rest classifiers","level":"7.1.2","depth":2,"path":"multiclass/news20_one-vs-the-rest_dataset.md","ref":"multiclass/news20_one-vs-the-rest_dataset.md","articles":[]},{"title":"PA","level":"7.1.3","depth":2,"path":"multiclass/news20_pa.md","ref":"multiclass/news20_pa.md","articles":[]},{"title":"CW, AROW, SCW","level":"7.1.4","depth":2,"path":"multiclass/news20_scw.md","ref":"multiclass/news20_scw.md","articles":[]},{"title":"Ensemble learning","level":"7.1.5","depth":2,"path":"multiclass/news20_ensemble.md","ref":"multiclass/news20_ensemble.md","art
icles":[]},{"title":"one-vs-the-rest Classifier","level":"7.1.6","depth":2,"path":"multiclass/news20_one-vs-the-rest.md","ref":"multiclass/news20_one-vs-the-rest.md","articles":[]}]},"previous":{"title":"Data Preparation","level":"6.8.1","depth":2,"path":"binaryclass/criteo_dataset.md","ref":"binaryclass/criteo_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":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://g
ithub.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"https://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5
"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"https://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"binaryclass/criteo_ffm.md","mtime":"2018-10-18T10:26:56.667Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-12-26T10:20:07.153Z"},"basePath":"..","book":{"language":""}});
});
</script>
</div>
@@ -2699,7 +2744,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda
- <script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/4.1.1/anchor.min.js"></script>
+ <script src="../gitbook/gitbook-plugin-anchorjs/anchor.min.js"></script>
http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/d9012d92/userguide/binaryclass/general.html
----------------------------------------------------------------------
diff --git a/userguide/binaryclass/general.html b/userguide/binaryclass/general.html
index c940a38..45c5aa8 100644
--- a/userguide/binaryclass/general.html
+++ b/userguide/binaryclass/general.html
@@ -972,7 +972,7 @@
<b>6.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -980,13 +980,28 @@
</li>
- <li class="chapter " data-level="6.2.2" data-path="a9a_lr.html">
+ <li class="chapter " data-level="6.2.2" data-path="a9a_generic.html">
- <a href="a9a_lr.html">
+ <a href="a9a_generic.html">
<b>6.2.2.</b>
+ General Binary Classifier
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.2.3" data-path="a9a_lr.html">
+
+ <a href="a9a_lr.html">
+
+
+ <b>6.2.3.</b>
+
Logistic Regression
</a>
@@ -995,14 +1010,14 @@
</li>
- <li class="chapter " data-level="6.2.3" data-path="a9a_minibatch.html">
+ <li class="chapter " data-level="6.2.4" data-path="a9a_minibatch.html">
<a href="a9a_minibatch.html">
- <b>6.2.3.</b>
+ <b>6.2.4.</b>
- Mini-batch gradient descent
+ Mini-batch Gradient Descent
</a>
@@ -1038,7 +1053,7 @@
<b>6.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1076,13 +1091,28 @@
</li>
- <li class="chapter " data-level="6.3.4" data-path="news20_adagrad.html">
+ <li class="chapter " data-level="6.3.4" data-path="news20_generic.html">
- <a href="news20_adagrad.html">
+ <a href="news20_generic.html">
<b>6.3.4.</b>
+ General Binary Classifier
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.3.5" data-path="news20_adagrad.html">
+
+ <a href="news20_adagrad.html">
+
+
+ <b>6.3.5.</b>
+
AdaGradRDA, AdaGrad, AdaDelta
</a>
@@ -1091,12 +1121,12 @@
</li>
- <li class="chapter " data-level="6.3.5" data-path="news20_rf.html">
+ <li class="chapter " data-level="6.3.6" data-path="news20_rf.html">
<a href="news20_rf.html">
- <b>6.3.5.</b>
+ <b>6.3.6.</b>
Random Forest
@@ -1134,7 +1164,7 @@
<b>6.4.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1185,7 +1215,7 @@
<b>6.5.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1236,7 +1266,7 @@
<b>6.6.1.</b>
- Data pareparation
+ Data Pareparation
</a>
@@ -1302,7 +1332,7 @@
<b>6.8.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1360,7 +1390,7 @@
<b>7.1.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1375,7 +1405,7 @@
<b>7.1.2.</b>
- Data preparation for one-vs-the-rest classifiers
+ Data Preparation for one-vs-the-rest classifiers
</a>
@@ -1435,7 +1465,7 @@
<b>7.1.6.</b>
- one-vs-the-rest classifier
+ one-vs-the-rest Classifier
</a>
@@ -1559,7 +1589,7 @@
<b>8.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1567,13 +1597,28 @@
</li>
- <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_arow.html">
+ <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_generic.html">
- <a href="../regression/e2006_arow.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>
@@ -1610,7 +1655,7 @@
<b>8.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1698,7 +1743,7 @@
<b>9.1.1.</b>
- Item-based collaborative filtering
+ Item-based Collaborative Filtering
</a>
@@ -1734,7 +1779,7 @@
<b>9.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1749,7 +1794,7 @@
<b>9.2.2.</b>
- LSH/MinHash and Jaccard similarity
+ LSH/MinHash and Jaccard Similarity
</a>
@@ -1764,7 +1809,7 @@
<b>9.2.3.</b>
- LSH/MinHash and brute-force search
+ LSH/MinHash and Brute-force Search
</a>
@@ -1815,7 +1860,7 @@
<b>9.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1830,7 +1875,7 @@
<b>9.3.2.</b>
- Item-based collaborative filtering
+ Item-based Collaborative Filtering
</a>
@@ -1875,7 +1920,7 @@
<b>9.3.5.</b>
- SLIM for fast top-k recommendation
+ SLIM for fast top-k Recommendation
</a>
@@ -1890,7 +1935,7 @@
<b>9.3.6.</b>
- 10-fold cross validation (Matrix Factorization)
+ 10-fold Cross Validation (Matrix Factorization)
</a>
@@ -2080,7 +2125,7 @@
<b>13.2.1.</b>
- a9a tutorial for DataFrame
+ a9a Tutorial for DataFrame
</a>
@@ -2095,7 +2140,7 @@
<b>13.2.2.</b>
- a9a tutorial for SQL
+ a9a Tutorial for SQL
</a>
@@ -2131,7 +2176,7 @@
<b>13.3.1.</b>
- E2006-tfidf regression tutorial for DataFrame
+ E2006-tfidf Regression Tutorial for DataFrame
</a>
@@ -2146,7 +2191,7 @@
<b>13.3.2.</b>
- E2006-tfidf regression tutorial for SQL
+ E2006-tfidf Regression Tutorial for SQL
</a>
@@ -2166,7 +2211,7 @@
<b>13.4.</b>
- Generic features
+ Generic Features
</a>
@@ -2182,7 +2227,7 @@
<b>13.4.1.</b>
- Top-k join processing
+ Top-k Join Processing
</a>
@@ -2197,7 +2242,7 @@
<b>13.4.2.</b>
- Other utility functions
+ Other Utility Functions
</a>
@@ -2317,12 +2362,11 @@
specific language governing permissions and limitations
under the License.
-->
-<p>Hivemall has a generic function for classification: <code>train_classifier</code>. Compared to the other functions we will see in the later chapters, <code>train_classifier</code> provides simpler and configureable generic interface which can be utilized to build binary classification models in a variety of settings.</p>
+<p>Hivemall has a generic function for classification: <code>train_classifier</code>. Compared to the other functions we will see in the later chapters, <code>train_classifier</code> provides simpler and configurable generic interface which can be utilized to build binary classification models in a variety of settings.</p>
<p>Here, we briefly introduce usage of the function. Before trying sample queries, you first need to prepare <a href="https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html#a9a" target="_blank">a9a data</a>. See <a href="a9a_dataset.html">our a9a tutorial page</a> for further instructions.</p>
<!-- toc --><div id="toc" class="toc">
<ul>
-<li><a href="#preparation">Preparation</a></li>
<li><a href="#training">Training</a></li>
<li><a href="#prediction--evaluation">Prediction & evaluation</a></li>
<li><a href="#comparison-with-the-other-binary-classifiers">Comparison with the other binary classifiers</a></li>
@@ -2330,15 +2374,6 @@
</div><!-- tocstop -->
<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>This feature is supported from Hivemall v0.5-rc.1 or later.</p></div></div>
-<h1 id="preparation">Preparation</h1>
-<ul>
-<li>Set <code>total_steps</code> ideally be <code>count(1) / {# of map tasks}</code>:<pre><code> hive> select count(1) from a9a_train;
- hive> set hivevar:total_steps=32561;
-</code></pre></li>
-<li>Set <code>n_samples</code> to compute accuracy of prediction:<pre><code> hive> select count(1) from a9a_test;
- hive> set hivevar:n_samples=16281;
-</code></pre></li>
-</ul>
<h1 id="training">Training</h1>
<pre><code class="lang-sql"><span class="hljs-keyword">create</span> <span class="hljs-keyword">table</span> classification_model <span class="hljs-keyword">as</span>
<span class="hljs-keyword">select</span>
@@ -2347,13 +2382,12 @@
<span class="hljs-keyword">from</span>
(
<span class="hljs-keyword">select</span>
- train_classifier(add_bias(features), label, <span class="hljs-string">'-loss logloss -opt SGD -reg no -eta simple -total_steps ${total_steps}'</span>) <span class="hljs-keyword">as</span> (feature, weight)
+ train_classifier(add_bias(features), label, <span class="hljs-string">'-loss logloss -opt SGD -reg no'</span>) <span class="hljs-keyword">as</span> (feature, weight)
<span class="hljs-keyword">from</span>
a9a_train
) t
<span class="hljs-keyword">group</span> <span class="hljs-keyword">by</span> feature;
</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>-total_steps</code> option is an optional parameter and training works without it.</p></div></div>
<h1 id="prediction--evaluation">Prediction & evaluation</h1>
<pre><code class="lang-sql">WITH test_exploded as (
<span class="hljs-keyword">select</span>
@@ -2370,23 +2404,39 @@ predict <span class="hljs-keyword">as</span> (
sigmoid(<span class="hljs-keyword">sum</span>(m.weight * t.<span class="hljs-keyword">value</span>)) <span class="hljs-keyword">as</span> prob,
(<span class="hljs-keyword">case</span> <span class="hljs-keyword">when</span> sigmoid(<span class="hljs-keyword">sum</span>(m.weight * t.<span class="hljs-keyword">value</span>)) >= <span class="hljs-number">0.5</span> <span class="hljs-keyword">then</span> <span class="hljs-number">1.0</span> <span class="hljs-keyword">else</span> <span class="hljs-number">0.0</span> <span class="hljs-keyword">end</span>)<span class="hljs-keyword">as</span> label
<span class="hljs-keyword">from</span>
- test_exploded t <span class="hljs-keyword">LEFT</span> <span class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span>
- classification_model m <span class="hljs-keyword">ON</span> (t.feature = m.feature)
+ test_exploded t
+ <span class="hljs-keyword">LEFT</span> <span class="hljs-keyword">OUTER</span> <span class="hljs-keyword">JOIN</span> classification_model m
+ <span class="hljs-keyword">ON</span> (t.feature = m.feature)
<span class="hljs-keyword">group</span> <span class="hljs-keyword">by</span>
t.<span class="hljs-keyword">rowid</span>
),
submit <span class="hljs-keyword">as</span> (
<span class="hljs-keyword">select</span>
t.label <span class="hljs-keyword">as</span> actual,
- pd.label <span class="hljs-keyword">as</span> predicted,
- pd.prob <span class="hljs-keyword">as</span> probability
+ p.label <span class="hljs-keyword">as</span> predicted,
+ p.prob <span class="hljs-keyword">as</span> probability
<span class="hljs-keyword">from</span>
- a9a_test t <span class="hljs-keyword">JOIN</span> predict pd
- <span class="hljs-keyword">on</span> (t.<span class="hljs-keyword">rowid</span> = pd.<span class="hljs-keyword">rowid</span>)
+ a9a_test t
+ <span class="hljs-keyword">JOIN</span> predict p
+ <span class="hljs-keyword">on</span> (t.<span class="hljs-keyword">rowid</span> = p.<span class="hljs-keyword">rowid</span>)
)
-<span class="hljs-keyword">select</span> <span class="hljs-keyword">count</span>(<span class="hljs-number">1</span>) / ${n_samples} <span class="hljs-keyword">from</span> submit
-<span class="hljs-keyword">where</span> actual = predicted;
+<span class="hljs-keyword">select</span>
+ <span class="hljs-keyword">sum</span>(<span class="hljs-keyword">if</span>(actual = predicted, <span class="hljs-number">1</span>, <span class="hljs-number">0</span>)) / <span class="hljs-keyword">count</span>(<span class="hljs-number">1</span>) <span class="hljs-keyword">as</span> accuracy
+<span class="hljs-keyword">from</span>
+ submit;
</code></pre>
+<table>
+<thead>
+<tr>
+<th style="text-align:center">accuracy</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td style="text-align:center">0.8461396720103188</td>
+</tr>
+</tbody>
+</table>
<h1 id="comparison-with-the-other-binary-classifiers">Comparison with the other binary classifiers</h1>
<p>In the next part of this user guide, our binary classification tutorials introduce many different functions:</p>
<ul>
@@ -2405,15 +2455,15 @@ submit <span class="hljs-keyword">as</span> (
</ul>
<p>All of them actually have the same interface, but mathematical formulation and its implementation differ from each other.</p>
<p>In particular, the above sample queries are almost same as <a href="a9a_lr.html">a9a tutorial using Logistic Regression</a>. The difference is only in a choice of training function: <code>logress()</code> vs. <code>train_classifier()</code>.</p>
-<p>However, at the same time, the options <code>-loss logloss -opt SGD -reg no -eta simple -total_steps ${total_steps}</code> for <code>train_classifier</code> indicates that Hivemall uses the generic classifier as Logistic Regressor (<code>logress</code>). Hence, the accuracy of prediction based on either <code>logress</code> and <code>train_classifier</code> should be same under the configuration.</p>
+<p>However, at the same time, the options <code>-loss logloss -opt SGD -reg no</code> for <code>train_classifier</code> indicates that Hivemall uses the generic classifier as <code>logress</code>. Hence, the accuracy of prediction based on either <code>logress</code> and <code>train_classifier</code> would be (almost) same under the configuration.</p>
<p>In addition, <code>train_classifier</code> supports the <code>-mini_batch</code> option in a similar manner to <a href="a9a_minibatch.html">what <code>logress</code> does</a>. Thus, following two training queries show the same results:</p>
<pre><code class="lang-sql"><span class="hljs-keyword">select</span>
- logress(add_bias(features), label, <span class="hljs-string">'-total_steps ${total_steps} -mini_batch 10'</span>) <span class="hljs-keyword">as</span> (feature, weight)
+ logress(add_bias(features), label, <span class="hljs-string">'-mini_batch 10'</span>) <span class="hljs-keyword">as</span> (feature, weight)
<span class="hljs-keyword">from</span>
a9a_train
</code></pre>
<pre><code class="lang-sql"><span class="hljs-keyword">select</span>
- train_classifier(add_bias(features), label, <span class="hljs-string">'-loss logloss -opt SGD -reg no -eta simple -total_steps ${total_steps} -mini_batch 10'</span>) <span class="hljs-keyword">as</span> (feature, weight)
+ train_classifier(add_bias(features), label, <span class="hljs-string">'-loss logloss -opt SGD -reg no -mini_batch 10'</span>) <span class="hljs-keyword">as</span> (feature, weight)
<span class="hljs-keyword">from</span>
a9a_train
</code></pre>
@@ -2473,7 +2523,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda
<script>
var gitbook = gitbook || [];
gitbook.push(function() {
- gitbook.page.hasChanged({"page":{"title":"Binary Classification","level":"6.1","depth":1,"next":{"title":"a9a Tutorial","level":"6.2","depth":1,"path":"binaryclass/a9a.md","ref":"binaryclass/a9a.md","articles":[{"title":"Data preparation","level":"6.2.1","depth":2,"path":"binaryclass/a9a_dataset.md","ref":"binaryclass/a9a_dataset.md","articles":[]},{"title":"Logistic Regression","level":"6.2.2","depth":2,"path":"binaryclass/a9a_lr.md","ref":"binaryclass/a9a_lr.md","articles":[]},{"title":"Mini-batch gradient descent","level":"6.2.3","depth":2,"path":"binaryclass/a9a_minibatch.md","ref":"binaryclass/a9a_minibatch.md","articles":[]}]},"previous":{"title":"Step-by-Step Tutorial on Supervised Learning","level":"5.2","depth":1,"path":"supervised_learning/tutorial.md","ref":"supervised_learning/tutorial.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","
expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"https://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"t
witter":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":"binaryclass/general.md","mtime":"2018-11-02T10:33:52.938Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-11-13T09:32:29.643Z"},"basePath":"..","book":{"language":""}});
+ gitbook.page.hasChanged({"page":{"title":"Binary Classification","level":"6.1","depth":1,"next":{"title":"a9a Tutorial","level":"6.2","depth":1,"path":"binaryclass/a9a.md","ref":"binaryclass/a9a.md","articles":[{"title":"Data Preparation","level":"6.2.1","depth":2,"path":"binaryclass/a9a_dataset.md","ref":"binaryclass/a9a_dataset.md","articles":[]},{"title":"General Binary Classifier","level":"6.2.2","depth":2,"path":"binaryclass/a9a_generic.md","ref":"binaryclass/a9a_generic.md","articles":[]},{"title":"Logistic Regression","level":"6.2.3","depth":2,"path":"binaryclass/a9a_lr.md","ref":"binaryclass/a9a_lr.md","articles":[]},{"title":"Mini-batch Gradient Descent","level":"6.2.4","depth":2,"path":"binaryclass/a9a_minibatch.md","ref":"binaryclass/a9a_minibatch.md","articles":[]}]},"previous":{"title":"Step-by-Step Tutorial on Supervised Learning","level":"5.2","depth":1,"path":"supervised_learning/tutorial.md","ref":"supervised_learning/tutorial.md","articles":[]},"dir":"l
tr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"s
itemap":{"hostname":"https://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md
"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"https://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"binaryclass/general.md","mtime":"2018-12-26T10:16:03.078Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-12-26T10:20:07.153Z"},"basePath":"..","book":{"language":""}});
});
</script>
</div>
@@ -2503,7 +2553,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda
- <script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/4.1.1/anchor.min.js"></script>
+ <script src="../gitbook/gitbook-plugin-anchorjs/anchor.min.js"></script>
http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/d9012d92/userguide/binaryclass/kdd2010a.html
----------------------------------------------------------------------
diff --git a/userguide/binaryclass/kdd2010a.html b/userguide/binaryclass/kdd2010a.html
index e8edf8e..c807a7c 100644
--- a/userguide/binaryclass/kdd2010a.html
+++ b/userguide/binaryclass/kdd2010a.html
@@ -972,7 +972,7 @@
<b>6.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -980,13 +980,28 @@
</li>
- <li class="chapter " data-level="6.2.2" data-path="a9a_lr.html">
+ <li class="chapter " data-level="6.2.2" data-path="a9a_generic.html">
- <a href="a9a_lr.html">
+ <a href="a9a_generic.html">
<b>6.2.2.</b>
+ General Binary Classifier
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.2.3" data-path="a9a_lr.html">
+
+ <a href="a9a_lr.html">
+
+
+ <b>6.2.3.</b>
+
Logistic Regression
</a>
@@ -995,14 +1010,14 @@
</li>
- <li class="chapter " data-level="6.2.3" data-path="a9a_minibatch.html">
+ <li class="chapter " data-level="6.2.4" data-path="a9a_minibatch.html">
<a href="a9a_minibatch.html">
- <b>6.2.3.</b>
+ <b>6.2.4.</b>
- Mini-batch gradient descent
+ Mini-batch Gradient Descent
</a>
@@ -1038,7 +1053,7 @@
<b>6.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1076,13 +1091,28 @@
</li>
- <li class="chapter " data-level="6.3.4" data-path="news20_adagrad.html">
+ <li class="chapter " data-level="6.3.4" data-path="news20_generic.html">
- <a href="news20_adagrad.html">
+ <a href="news20_generic.html">
<b>6.3.4.</b>
+ General Binary Classifier
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.3.5" data-path="news20_adagrad.html">
+
+ <a href="news20_adagrad.html">
+
+
+ <b>6.3.5.</b>
+
AdaGradRDA, AdaGrad, AdaDelta
</a>
@@ -1091,12 +1121,12 @@
</li>
- <li class="chapter " data-level="6.3.5" data-path="news20_rf.html">
+ <li class="chapter " data-level="6.3.6" data-path="news20_rf.html">
<a href="news20_rf.html">
- <b>6.3.5.</b>
+ <b>6.3.6.</b>
Random Forest
@@ -1134,7 +1164,7 @@
<b>6.4.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1185,7 +1215,7 @@
<b>6.5.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1236,7 +1266,7 @@
<b>6.6.1.</b>
- Data pareparation
+ Data Pareparation
</a>
@@ -1302,7 +1332,7 @@
<b>6.8.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1360,7 +1390,7 @@
<b>7.1.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1375,7 +1405,7 @@
<b>7.1.2.</b>
- Data preparation for one-vs-the-rest classifiers
+ Data Preparation for one-vs-the-rest classifiers
</a>
@@ -1435,7 +1465,7 @@
<b>7.1.6.</b>
- one-vs-the-rest classifier
+ one-vs-the-rest Classifier
</a>
@@ -1559,7 +1589,7 @@
<b>8.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1567,13 +1597,28 @@
</li>
- <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_arow.html">
+ <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_generic.html">
- <a href="../regression/e2006_arow.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>
@@ -1610,7 +1655,7 @@
<b>8.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1698,7 +1743,7 @@
<b>9.1.1.</b>
- Item-based collaborative filtering
+ Item-based Collaborative Filtering
</a>
@@ -1734,7 +1779,7 @@
<b>9.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1749,7 +1794,7 @@
<b>9.2.2.</b>
- LSH/MinHash and Jaccard similarity
+ LSH/MinHash and Jaccard Similarity
</a>
@@ -1764,7 +1809,7 @@
<b>9.2.3.</b>
- LSH/MinHash and brute-force search
+ LSH/MinHash and Brute-force Search
</a>
@@ -1815,7 +1860,7 @@
<b>9.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1830,7 +1875,7 @@
<b>9.3.2.</b>
- Item-based collaborative filtering
+ Item-based Collaborative Filtering
</a>
@@ -1875,7 +1920,7 @@
<b>9.3.5.</b>
- SLIM for fast top-k recommendation
+ SLIM for fast top-k Recommendation
</a>
@@ -1890,7 +1935,7 @@
<b>9.3.6.</b>
- 10-fold cross validation (Matrix Factorization)
+ 10-fold Cross Validation (Matrix Factorization)
</a>
@@ -2080,7 +2125,7 @@
<b>13.2.1.</b>
- a9a tutorial for DataFrame
+ a9a Tutorial for DataFrame
</a>
@@ -2095,7 +2140,7 @@
<b>13.2.2.</b>
- a9a tutorial for SQL
+ a9a Tutorial for SQL
</a>
@@ -2131,7 +2176,7 @@
<b>13.3.1.</b>
- E2006-tfidf regression tutorial for DataFrame
+ E2006-tfidf Regression Tutorial for DataFrame
</a>
@@ -2146,7 +2191,7 @@
<b>13.3.2.</b>
- E2006-tfidf regression tutorial for SQL
+ E2006-tfidf Regression Tutorial for SQL
</a>
@@ -2166,7 +2211,7 @@
<b>13.4.</b>
- Generic features
+ Generic Features
</a>
@@ -2182,7 +2227,7 @@
<b>13.4.1.</b>
- Top-k join processing
+ Top-k Join Processing
</a>
@@ -2197,7 +2242,7 @@
<b>13.4.2.</b>
- Other utility functions
+ Other Utility Functions
</a>
@@ -2372,7 +2417,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda
<script>
var gitbook = gitbook || [];
gitbook.push(function() {
- gitbook.page.hasChanged({"page":{"title":"KDD2010a Tutorial","level":"6.4","depth":1,"next":{"title":"Data preparation","level":"6.4.1","depth":2,"path":"binaryclass/kdd2010a_dataset.md","ref":"binaryclass/kdd2010a_dataset.md","articles":[]},"previous":{"title":"Random Forest","level":"6.3.5","depth":2,"path":"binaryclass/news20_rf.md","ref":"binaryclass/news20_rf.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},
"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"https://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true
},"anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"https://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"binaryclass/kdd2010a.md","mtime":"2018-10-18T10:26:56.669Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-11-13T09:32:29.643Z"},"basePath":"..","book":{"language":""}});
+ gitbook.page.hasChanged({"page":{"title":"KDD2010a Tutorial","level":"6.4","depth":1,"next":{"title":"Data Preparation","level":"6.4.1","depth":2,"path":"binaryclass/kdd2010a_dataset.md","ref":"binaryclass/kdd2010a_dataset.md","articles":[]},"previous":{"title":"Random Forest","level":"6.3.6","depth":2,"path":"binaryclass/news20_rf.md","ref":"binaryclass/news20_rf.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},
"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"https://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/tree/master/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true
},"anchorjs":{"selector":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"https://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"binaryclass/kdd2010a.md","mtime":"2018-10-18T10:26:56.669Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2018-12-26T10:20:07.153Z"},"basePath":"..","book":{"language":""}});
});
</script>
</div>
@@ -2402,7 +2447,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda
- <script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/4.1.1/anchor.min.js"></script>
+ <script src="../gitbook/gitbook-plugin-anchorjs/anchor.min.js"></script>
http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/d9012d92/userguide/binaryclass/kdd2010a_dataset.html
----------------------------------------------------------------------
diff --git a/userguide/binaryclass/kdd2010a_dataset.html b/userguide/binaryclass/kdd2010a_dataset.html
index 5d0aece..5ce07ce 100644
--- a/userguide/binaryclass/kdd2010a_dataset.html
+++ b/userguide/binaryclass/kdd2010a_dataset.html
@@ -4,7 +4,7 @@
<head>
<meta charset="UTF-8">
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
- <title>Data preparation · Hivemall User Manual</title>
+ <title>Data Preparation · 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">
@@ -972,7 +972,7 @@
<b>6.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -980,13 +980,28 @@
</li>
- <li class="chapter " data-level="6.2.2" data-path="a9a_lr.html">
+ <li class="chapter " data-level="6.2.2" data-path="a9a_generic.html">
- <a href="a9a_lr.html">
+ <a href="a9a_generic.html">
<b>6.2.2.</b>
+ General Binary Classifier
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.2.3" data-path="a9a_lr.html">
+
+ <a href="a9a_lr.html">
+
+
+ <b>6.2.3.</b>
+
Logistic Regression
</a>
@@ -995,14 +1010,14 @@
</li>
- <li class="chapter " data-level="6.2.3" data-path="a9a_minibatch.html">
+ <li class="chapter " data-level="6.2.4" data-path="a9a_minibatch.html">
<a href="a9a_minibatch.html">
- <b>6.2.3.</b>
+ <b>6.2.4.</b>
- Mini-batch gradient descent
+ Mini-batch Gradient Descent
</a>
@@ -1038,7 +1053,7 @@
<b>6.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1076,13 +1091,28 @@
</li>
- <li class="chapter " data-level="6.3.4" data-path="news20_adagrad.html">
+ <li class="chapter " data-level="6.3.4" data-path="news20_generic.html">
- <a href="news20_adagrad.html">
+ <a href="news20_generic.html">
<b>6.3.4.</b>
+ General Binary Classifier
+
+ </a>
+
+
+
+ </li>
+
+ <li class="chapter " data-level="6.3.5" data-path="news20_adagrad.html">
+
+ <a href="news20_adagrad.html">
+
+
+ <b>6.3.5.</b>
+
AdaGradRDA, AdaGrad, AdaDelta
</a>
@@ -1091,12 +1121,12 @@
</li>
- <li class="chapter " data-level="6.3.5" data-path="news20_rf.html">
+ <li class="chapter " data-level="6.3.6" data-path="news20_rf.html">
<a href="news20_rf.html">
- <b>6.3.5.</b>
+ <b>6.3.6.</b>
Random Forest
@@ -1134,7 +1164,7 @@
<b>6.4.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1185,7 +1215,7 @@
<b>6.5.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1236,7 +1266,7 @@
<b>6.6.1.</b>
- Data pareparation
+ Data Pareparation
</a>
@@ -1302,7 +1332,7 @@
<b>6.8.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1360,7 +1390,7 @@
<b>7.1.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1375,7 +1405,7 @@
<b>7.1.2.</b>
- Data preparation for one-vs-the-rest classifiers
+ Data Preparation for one-vs-the-rest classifiers
</a>
@@ -1435,7 +1465,7 @@
<b>7.1.6.</b>
- one-vs-the-rest classifier
+ one-vs-the-rest Classifier
</a>
@@ -1559,7 +1589,7 @@
<b>8.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1567,13 +1597,28 @@
</li>
- <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_arow.html">
+ <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_generic.html">
- <a href="../regression/e2006_arow.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>
@@ -1610,7 +1655,7 @@
<b>8.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1698,7 +1743,7 @@
<b>9.1.1.</b>
- Item-based collaborative filtering
+ Item-based Collaborative Filtering
</a>
@@ -1734,7 +1779,7 @@
<b>9.2.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1749,7 +1794,7 @@
<b>9.2.2.</b>
- LSH/MinHash and Jaccard similarity
+ LSH/MinHash and Jaccard Similarity
</a>
@@ -1764,7 +1809,7 @@
<b>9.2.3.</b>
- LSH/MinHash and brute-force search
+ LSH/MinHash and Brute-force Search
</a>
@@ -1815,7 +1860,7 @@
<b>9.3.1.</b>
- Data preparation
+ Data Preparation
</a>
@@ -1830,7 +1875,7 @@
<b>9.3.2.</b>
- Item-based collaborative filtering
+ Item-based Collaborative Filtering
</a>
@@ -1875,7 +1920,7 @@
<b>9.3.5.</b>
- SLIM for fast top-k recommendation
+ SLIM for fast top-k Recommendation
</a>
@@ -1890,7 +1935,7 @@
<b>9.3.6.</b>
- 10-fold cross validation (Matrix Factorization)
+ 10-fold Cross Validation (Matrix Factorization)
</a>
@@ -2080,7 +2125,7 @@
<b>13.2.1.</b>
- a9a tutorial for DataFrame
+ a9a Tutorial for DataFrame
</a>
@@ -2095,7 +2140,7 @@
<b>13.2.2.</b>
- a9a tutorial for SQL
+ a9a Tutorial for SQL
</a>
@@ -2131,7 +2176,7 @@
<b>13.3.1.</b>
- E2006-tfidf regression tutorial for DataFrame
+ E2006-tfidf Regression Tutorial for DataFrame
</a>
@@ -2146,7 +2191,7 @@
<b>13.3.2.</b>
- E2006-tfidf regression tutorial for SQL
+ E2006-tfidf Regression Tutorial for SQL
</a>
@@ -2166,7 +2211,7 @@
<b>13.4.</b>
- Generic features
+ Generic Features
</a>
@@ -2182,7 +2227,7 @@
<b>13.4.1.</b>
- Top-k join processing
+ Top-k Join Processing
</a>
@@ -2197,7 +2242,7 @@
<b>13.4.2.</b>
- Other utility functions
+ Other Utility Functions
</a>
@@ -2284,7 +2329,7 @@
<!-- Title -->
<h1>
<i class="fa fa-circle-o-notch fa-spin"></i>
- <a href=".." >Data preparation</a>
+ <a href=".." >Data Preparation</a>
</h1>
</div>
@@ -2439,7 +2484,7 @@ 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 preparation","level":"6.4.1","depth":2,"next":{"title":"PA, CW, AROW, SCW","level":"6.4.2","depth":2,"path":"binaryclass/kdd2010a_scw.md","ref":"binaryclass/kdd2010a_scw.md","articles":[]},"previous":{"title":"KDD2010a Tutorial","level":"6.4","depth":1,"path":"binaryclass/kdd2010a.md","ref":"binaryclass/kdd2010a.md","articles":[{"title":"Data preparation","level":"6.4.1","depth":2,"path":"binaryclass/kdd2010a_dataset.md","ref":"binaryclass/kdd2010a_dataset.md","articles":[]},{"title":"PA, CW, AROW, SCW","level":"6.4.2","depth":2,"path":"binaryclass/kdd2010a_scw.md","ref":"binaryclass/kdd2010a_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":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"https://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":"Ed
it","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":"binaryclass/kdd2010a_dataset.md","mtime":"2018-11-02T10:33:52.939Z","type"
:"markdown"},"gitbook":{"version":"3.2.3","time":"2018-11-13T09:32:29.643Z"},"basePath":"..","book":{"language":""}});
+ gitbook.page.hasChanged({"page":{"title":"Data Preparation","level":"6.4.1","depth":2,"next":{"title":"PA, CW, AROW, SCW","level":"6.4.2","depth":2,"path":"binaryclass/kdd2010a_scw.md","ref":"binaryclass/kdd2010a_scw.md","articles":[]},"previous":{"title":"KDD2010a Tutorial","level":"6.4","depth":1,"path":"binaryclass/kdd2010a.md","ref":"binaryclass/kdd2010a.md","articles":[{"title":"Data Preparation","level":"6.4.1","depth":2,"path":"binaryclass/kdd2010a_dataset.md","ref":"binaryclass/kdd2010a_dataset.md","articles":[]},{"title":"PA, CW, AROW, SCW","level":"6.4.2","depth":2,"path":"binaryclass/kdd2010a_scw.md","ref":"binaryclass/kdd2010a_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":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"https://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":"Ed
it","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":"binaryclass/kdd2010a_dataset.md","mtime":"2018-12-25T07:50:37.531Z","type"
:"markdown"},"gitbook":{"version":"3.2.3","time":"2018-12-26T10:20:07.153Z"},"basePath":"..","book":{"language":""}});
});
</script>
</div>
@@ -2469,7 +2514,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda
- <script src="https://cdnjs.cloudflare.com/ajax/libs/anchor-js/4.1.1/anchor.min.js"></script>
+ <script src="../gitbook/gitbook-plugin-anchorjs/anchor.min.js"></script>