http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/ba518dab/userguide/misc/prediction.html ---------------------------------------------------------------------- diff --git a/userguide/misc/prediction.html b/userguide/misc/prediction.html index 60204e5..44462aa 100644 --- a/userguide/misc/prediction.html +++ b/userguide/misc/prediction.html @@ -97,7 +97,7 @@ <link rel="shortcut icon" href="../gitbook/images/favicon.ico" type="image/x-icon"> - <link rel="next" href="../regression/general.html" /> + <link rel="next" href="../binaryclass/general.html" /> <link rel="prev" href="../eval/lr_datagen.html" /> @@ -598,14 +598,30 @@ </li> - <li class="chapter " data-level="3.5" data-path="../ft_engineering/tfidf.html"> + <li class="chapter " data-level="3.5" data-path="../ft_engineering/pairing.html"> - <a href="../ft_engineering/tfidf.html"> + <a href="../ft_engineering/pairing.html"> <b>3.5.</b> - TF-IDF Calculation + FEATURE PAIRING + + </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> @@ -613,6 +629,11 @@ </li> + + </ul> + + </li> + <li class="chapter " data-level="3.6" data-path="../ft_engineering/ft_trans.html"> <a href="../ft_engineering/ft_trans.html"> @@ -664,6 +685,21 @@ </li> + <li class="chapter " data-level="3.7" data-path="../ft_engineering/tfidf.html"> + + <a href="../ft_engineering/tfidf.html"> + + + <b>3.7.</b> + + TF-IDF Calculation + + </a> + + + + </li> + @@ -761,7 +797,7 @@ - <li class="header">Part V - Prediction</li> + <li class="header">Part V - Supervised Learning</li> @@ -780,27 +816,19 @@ </li> - <li class="chapter " data-level="5.2" data-path="../regression/general.html"> - - <a href="../regression/general.html"> - - - <b>5.2.</b> - - Regression - - </a> - - - </li> - <li class="chapter " data-level="5.3" data-path="../binaryclass/general.html"> + + <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>5.3.</b> + <b>6.1.</b> Binary Classification @@ -810,21 +838,14 @@ </li> - - - - <li class="header">Part VI - Binary classification tutorials</li> - - - - <li class="chapter " data-level="6.1" data-path="../binaryclass/a9a.html"> + <li class="chapter " data-level="6.2" data-path="../binaryclass/a9a.html"> <a href="../binaryclass/a9a.html"> - <b>6.1.</b> + <b>6.2.</b> - a9a + a9a tutorial </a> @@ -833,12 +854,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.1.1" data-path="../binaryclass/a9a_dataset.html"> + <li class="chapter " data-level="6.2.1" data-path="../binaryclass/a9a_dataset.html"> <a href="../binaryclass/a9a_dataset.html"> - <b>6.1.1.</b> + <b>6.2.1.</b> Data preparation @@ -848,12 +869,12 @@ </li> - <li class="chapter " data-level="6.1.2" data-path="../binaryclass/a9a_lr.html"> + <li class="chapter " data-level="6.2.2" data-path="../binaryclass/a9a_lr.html"> <a href="../binaryclass/a9a_lr.html"> - <b>6.1.2.</b> + <b>6.2.2.</b> Logistic Regression @@ -863,12 +884,12 @@ </li> - <li class="chapter " data-level="6.1.3" data-path="../binaryclass/a9a_minibatch.html"> + <li class="chapter " data-level="6.2.3" data-path="../binaryclass/a9a_minibatch.html"> <a href="../binaryclass/a9a_minibatch.html"> - <b>6.1.3.</b> + <b>6.2.3.</b> Mini-batch Gradient Descent @@ -883,14 +904,14 @@ </li> - <li class="chapter " data-level="6.2" data-path="../binaryclass/news20.html"> + <li class="chapter " data-level="6.3" data-path="../binaryclass/news20.html"> <a href="../binaryclass/news20.html"> - <b>6.2.</b> + <b>6.3.</b> - News20 + News20 tutorial </a> @@ -899,12 +920,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.2.1" data-path="../binaryclass/news20_dataset.html"> + <li class="chapter " data-level="6.3.1" data-path="../binaryclass/news20_dataset.html"> <a href="../binaryclass/news20_dataset.html"> - <b>6.2.1.</b> + <b>6.3.1.</b> Data preparation @@ -914,12 +935,12 @@ </li> - <li class="chapter " data-level="6.2.2" data-path="../binaryclass/news20_pa.html"> + <li class="chapter " data-level="6.3.2" data-path="../binaryclass/news20_pa.html"> <a href="../binaryclass/news20_pa.html"> - <b>6.2.2.</b> + <b>6.3.2.</b> Perceptron, Passive Aggressive @@ -929,12 +950,12 @@ </li> - <li class="chapter " data-level="6.2.3" data-path="../binaryclass/news20_scw.html"> + <li class="chapter " data-level="6.3.3" data-path="../binaryclass/news20_scw.html"> <a href="../binaryclass/news20_scw.html"> - <b>6.2.3.</b> + <b>6.3.3.</b> CW, AROW, SCW @@ -944,12 +965,12 @@ </li> - <li class="chapter " data-level="6.2.4" data-path="../binaryclass/news20_adagrad.html"> + <li class="chapter " data-level="6.3.4" data-path="../binaryclass/news20_adagrad.html"> <a href="../binaryclass/news20_adagrad.html"> - <b>6.2.4.</b> + <b>6.3.4.</b> AdaGradRDA, AdaGrad, AdaDelta @@ -964,14 +985,14 @@ </li> - <li class="chapter " data-level="6.3" data-path="../binaryclass/kdd2010a.html"> + <li class="chapter " data-level="6.4" data-path="../binaryclass/kdd2010a.html"> <a href="../binaryclass/kdd2010a.html"> - <b>6.3.</b> + <b>6.4.</b> - KDD2010a + KDD2010a tutorial </a> @@ -980,12 +1001,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.3.1" data-path="../binaryclass/kdd2010a_dataset.html"> + <li class="chapter " data-level="6.4.1" data-path="../binaryclass/kdd2010a_dataset.html"> <a href="../binaryclass/kdd2010a_dataset.html"> - <b>6.3.1.</b> + <b>6.4.1.</b> Data preparation @@ -995,12 +1016,12 @@ </li> - <li class="chapter " data-level="6.3.2" data-path="../binaryclass/kdd2010a_scw.html"> + <li class="chapter " data-level="6.4.2" data-path="../binaryclass/kdd2010a_scw.html"> <a href="../binaryclass/kdd2010a_scw.html"> - <b>6.3.2.</b> + <b>6.4.2.</b> PA, CW, AROW, SCW @@ -1015,14 +1036,14 @@ </li> - <li class="chapter " data-level="6.4" data-path="../binaryclass/kdd2010b.html"> + <li class="chapter " data-level="6.5" data-path="../binaryclass/kdd2010b.html"> <a href="../binaryclass/kdd2010b.html"> - <b>6.4.</b> + <b>6.5.</b> - KDD2010b + KDD2010b tutorial </a> @@ -1031,12 +1052,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.4.1" data-path="../binaryclass/kdd2010b_dataset.html"> + <li class="chapter " data-level="6.5.1" data-path="../binaryclass/kdd2010b_dataset.html"> <a href="../binaryclass/kdd2010b_dataset.html"> - <b>6.4.1.</b> + <b>6.5.1.</b> Data preparation @@ -1046,12 +1067,12 @@ </li> - <li class="chapter " data-level="6.4.2" data-path="../binaryclass/kdd2010b_arow.html"> + <li class="chapter " data-level="6.5.2" data-path="../binaryclass/kdd2010b_arow.html"> <a href="../binaryclass/kdd2010b_arow.html"> - <b>6.4.2.</b> + <b>6.5.2.</b> AROW @@ -1066,14 +1087,14 @@ </li> - <li class="chapter " data-level="6.5" data-path="../binaryclass/webspam.html"> + <li class="chapter " data-level="6.6" data-path="../binaryclass/webspam.html"> <a href="../binaryclass/webspam.html"> - <b>6.5.</b> + <b>6.6.</b> - Webspam + Webspam tutorial </a> @@ -1082,12 +1103,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.5.1" data-path="../binaryclass/webspam_dataset.html"> + <li class="chapter " data-level="6.6.1" data-path="../binaryclass/webspam_dataset.html"> <a href="../binaryclass/webspam_dataset.html"> - <b>6.5.1.</b> + <b>6.6.1.</b> Data pareparation @@ -1097,12 +1118,12 @@ </li> - <li class="chapter " data-level="6.5.2" data-path="../binaryclass/webspam_scw.html"> + <li class="chapter " data-level="6.6.2" data-path="../binaryclass/webspam_scw.html"> <a href="../binaryclass/webspam_scw.html"> - <b>6.5.2.</b> + <b>6.6.2.</b> PA1, AROW, SCW @@ -1117,14 +1138,14 @@ </li> - <li class="chapter " data-level="6.6" data-path="../binaryclass/titanic_rf.html"> + <li class="chapter " data-level="6.7" data-path="../binaryclass/titanic_rf.html"> <a href="../binaryclass/titanic_rf.html"> - <b>6.6.</b> + <b>6.7.</b> - Kaggle Titanic + Kaggle Titanic tutorial </a> @@ -1135,7 +1156,7 @@ - <li class="header">Part VII - Multiclass classification tutorials</li> + <li class="header">Part VII - Multiclass classification</li> @@ -1146,7 +1167,7 @@ <b>7.1.</b> - News20 Multiclass + News20 Multiclass tutorial </a> @@ -1257,7 +1278,7 @@ <b>7.2.</b> - Iris + Iris tutorial </a> @@ -1319,18 +1340,33 @@ - <li class="header">Part VIII - Regression tutorials</li> + <li class="header">Part VIII - Regression</li> - <li class="chapter " data-level="8.1" data-path="../regression/e2006.html"> + <li class="chapter " data-level="8.1" data-path="../regression/general.html"> - <a href="../regression/e2006.html"> + <a href="../regression/general.html"> <b>8.1.</b> - E2006-tfidf regression + 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> @@ -1339,12 +1375,12 @@ <ul class="articles"> - <li class="chapter " data-level="8.1.1" data-path="../regression/e2006_dataset.html"> + <li class="chapter " data-level="8.2.1" data-path="../regression/e2006_dataset.html"> <a href="../regression/e2006_dataset.html"> - <b>8.1.1.</b> + <b>8.2.1.</b> Data preparation @@ -1354,12 +1390,12 @@ </li> - <li class="chapter " data-level="8.1.2" data-path="../regression/e2006_arow.html"> + <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_arow.html"> <a href="../regression/e2006_arow.html"> - <b>8.1.2.</b> + <b>8.2.2.</b> Passive Aggressive, AROW @@ -1374,14 +1410,14 @@ </li> - <li class="chapter " data-level="8.2" data-path="../regression/kddcup12tr2.html"> + <li class="chapter " data-level="8.3" data-path="../regression/kddcup12tr2.html"> <a href="../regression/kddcup12tr2.html"> - <b>8.2.</b> + <b>8.3.</b> - KDDCup 2012 track 2 CTR prediction + KDDCup 2012 track 2 CTR prediction tutorial </a> @@ -1390,12 +1426,12 @@ <ul class="articles"> - <li class="chapter " data-level="8.2.1" data-path="../regression/kddcup12tr2_dataset.html"> + <li class="chapter " data-level="8.3.1" data-path="../regression/kddcup12tr2_dataset.html"> <a href="../regression/kddcup12tr2_dataset.html"> - <b>8.2.1.</b> + <b>8.3.1.</b> Data preparation @@ -1405,12 +1441,12 @@ </li> - <li class="chapter " data-level="8.2.2" data-path="../regression/kddcup12tr2_lr.html"> + <li class="chapter " data-level="8.3.2" data-path="../regression/kddcup12tr2_lr.html"> <a href="../regression/kddcup12tr2_lr.html"> - <b>8.2.2.</b> + <b>8.3.2.</b> Logistic Regression, Passive Aggressive @@ -1420,12 +1456,12 @@ </li> - <li class="chapter " data-level="8.2.3" data-path="../regression/kddcup12tr2_lr_amplify.html"> + <li class="chapter " data-level="8.3.3" data-path="../regression/kddcup12tr2_lr_amplify.html"> <a href="../regression/kddcup12tr2_lr_amplify.html"> - <b>8.2.3.</b> + <b>8.3.3.</b> Logistic Regression with Amplifier @@ -1435,12 +1471,12 @@ </li> - <li class="chapter " data-level="8.2.4" data-path="../regression/kddcup12tr2_adagrad.html"> + <li class="chapter " data-level="8.3.4" data-path="../regression/kddcup12tr2_adagrad.html"> <a href="../regression/kddcup12tr2_adagrad.html"> - <b>8.2.4.</b> + <b>8.3.4.</b> AdaGrad, AdaDelta @@ -2176,14 +2212,14 @@ <li><strong>Input:</strong> a vector <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mrow><mi mathvariant="bold">x</mi></mrow></mrow><annotation encoding="application/x-tex">\mathbf{x}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.44444em;"></span><span class="strut bottom" style="height:0.44444em;vertical-align:0em;"></span><span class="base textstyle uncramped"><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span></span></span></span></li> <li><strong>Output:</strong> a value <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.43056em;"></span><span class="strut bottom" style="height:0.625em;vertical-align:-0.19444em;"></span><span class="base textstyle uncramped"><span class="mord mathit" style="margin-right:0.03588em;">y</span></span></span></span></li> </ul> -<p>For a set of samples <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mo>(</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>y</mi><mn>1</mn></msub><mo>)</mo><mo separator="true">,</mo><mo>(</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mn>2</mn></msub><mo separator="true">,</mo><msub><mi>y</mi><mn>2</mn></msub><mo>)</mo><mo separator="true">,</mo><mo>⋯</mo><mo separator="true">,</mo><mo>(</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mi>n</mi></msub><mo separator="true">,</mo><msub><mi>y</mi><mi>n</mi></msub><mo>)</mo></mrow><annotation encoding="application/x-tex">(\mathbf{x}_1, y_1), (\mathbf{x}_2, y_2), \cdots, (\mathbf{x}_n, y_n)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.75em;"></span><span class="strut bottom" style="height:1em;vertical-align:-0.25em;"></span><span class="base textstyle uncramped"><spa n class="mopen">(</span><span class="mord"><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathrm mtight">1</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathrm mtig ht">1</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mclose">)</span><span class="mpunct">,</span><span class="mopen">(</span><span class="mord"><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathrm mtight">2</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist"><spa n style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathrm mtight">2</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mclose">)</span><span class="mpunct">,</span><span class="minner">⋯</span><span class="mpunct">,</span><span class="mopen">(</span><span class="mord"><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathit mtight">n</span></span></span><span c lass="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathit mtight">n</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mclose">)</span></span></span></span>, the goal of prediction algorithms is to find a weight vector (i.e., parameters) <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mrow><mi mathvariant="bold">w</mi></mr ow></mrow><annotation encoding="application/x-tex">\mathbf{w}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.44444em;"></span><span class="strut bottom" style="height:0.44444em;vertical-align:0em;"></span><span class="base textstyle uncramped"><span class="mord textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span></span></span></span> by minimizing the following error:</p> +<p>For a set of samples <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mo>(</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>y</mi><mn>1</mn></msub><mo>)</mo><mo separator="true">,</mo><mo>(</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mn>2</mn></msub><mo separator="true">,</mo><msub><mi>y</mi><mn>2</mn></msub><mo>)</mo><mo separator="true">,</mo><mo>⋯</mo><mo separator="true">,</mo><mo>(</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mi>n</mi></msub><mo separator="true">,</mo><msub><mi>y</mi><mi>n</mi></msub><mo>)</mo></mrow><annotation encoding="application/x-tex">(\mathbf{x}_1, y_1), (\mathbf{x}_2, y_2), \cdots, (\mathbf{x}_n, y_n)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.75em;"></span><span class="strut bottom" style="height:1em;vertical-align:-0.25em;"></span><span class="base textstyle uncramped"><spa n class="mopen">(</span><span class=""><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathrm">1</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathrm">1</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mclose">)</span><span class="mpunct">,</span><span class="mopen">(</span><span class=""><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathrm">2</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span>< /span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathrm">2</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mclose">)</span><span class="mpunct">,</span><span class="minner">⋯</span><span class="mpunct">,</span><span class="mopen">(</span><span class=""><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathit">n</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathi t" style="margin-right:0.03588em;">y</span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathit">n</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mclose">)</span></span></span></span>, the goal of prediction algorithms is to find a weight vector (i.e., parameters) <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mrow><mi mathvariant="bold">w</mi></mrow></mrow><annotation encoding="application/x-tex">\mathbf{w}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.44444em;"></span><span class="strut bottom" style="height:0.44444em;vertical-align:0em;">< /span><span class="base textstyle uncramped"><span class="mord textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span></span></span></span> by minimizing the following error:</p> <p><span class="katex-display"><span class="katex"><span class="katex-mathml"><math><semantics><mrow><mi>E</mi><mo>(</mo><mrow><mi mathvariant="bold">w</mi></mrow><mo>)</mo><mo>:</mo><mo>=</mo><mfrac><mrow><mn>1</mn></mrow><mrow><mi>n</mi></mrow></mfrac><msubsup><mo>∑</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mrow><mi>n</mi></mrow></msubsup><mi>L</mi><mo>(</mo><mrow><mi mathvariant="bold">w</mi></mrow><mo separator="true">;</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mi>i</mi></msub><mo separator="true">,</mo><msub><mi>y</mi><mi>i</mi></msub><mo>)</mo><mo>+</mo><mi>λ</mi><mi>R</mi><mo>(</mo><mrow><mi mathvariant="bold">w</mi></mrow><mo>)</mo></mrow><annotation encoding="application/x-tex"> E(\mathbf{w}) := \frac{1}{n} \sum_{i=1}^{n} L(\mathbf{w}; \mathbf{x}_i, y_i) + \lambda R(\mathbf{w}) -</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:1.6513970000000002em;"></span><span class="strut bottom" style="height:2.929066em;vertical-align:-1.277669em;"></span><span class="base displaystyle textstyle uncramped"><span class="mord mathit" style="margin-right:0.05764em;">E</span><span class="mopen">(</span><span class="mord displaystyle textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span><span class="mclose">)</span><span class="mrel">:</span><span class="mrel">=</span><span class="mord reset-textstyle displaystyle textstyle uncramped"><span class="mopen sizing reset-size5 size5 reset-textstyle textstyle uncramped nulldelimiter"></span><span class="mfrac"><span class="vlist"><span style="top:0.686em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle textstyle cramped"><span class="mord texts tyle cramped"><span class="mord mathit">n</span></span></span></span><span style="top:-0.22999999999999998em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle textstyle uncramped frac-line"></span></span><span style="top:-0.677em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle textstyle uncramped"><span class="mord textstyle uncramped"><span class="mord mathrm">1</span></span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mclose sizing reset-size5 size5 reset-textstyle textstyle uncramped nulldelimiter"></span></span><span class="mop op-limits"><span class="vlist"><span style="top:1.1776689999999999em;margin-left:0em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-siz e:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord scriptstyle cramped mtight"><span class="mord mathit mtight">i</span><span class="mrel mtight">=</span><span class="mord mathrm mtight">1</span></span></span></span><span style="top:-0.000005000000000143778em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span><span class="mop op-symbol large-op">∑</span></span></span><span style="top:-1.2500050000000003em;margin-left:0em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle uncramped mtight"><span class="mord scriptstyle uncramped mtight"><span class="mord mathit mtight">n</span></span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mord mathit">L </span><span class="mopen">(</span><span class="mord displaystyle textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span><span class="mpunct">;</span><span class="mord"><span class="mord displaystyle textstyle uncramped"><span class="mord mathbf">x</span></span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathit mtight">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span cl ass="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathit mtight">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mclose">)</span><span class="mbin">+</span><span class="mord mathit">λ</span><span class="mord mathit" style="margin-right:0.00773em;">R</span><span class="mopen">(</span><span class="mord displaystyle textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span><span class="mclose">)</span></span></span></span></span></p> +</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:1.6513970000000002em;"></span><span class="strut bottom" style="height:2.929066em;vertical-align:-1.277669em;"></span><span class="base displaystyle textstyle uncramped"><span class="mord mathit" style="margin-right:0.05764em;">E</span><span class="mopen">(</span><span class="mord displaystyle textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span><span class="mclose">)</span><span class="mrel">:</span><span class="mrel">=</span><span class="mord reset-textstyle displaystyle textstyle uncramped"><span class="sizing reset-size5 size5 reset-textstyle textstyle uncramped nulldelimiter"></span><span class="mfrac"><span class="vlist"><span style="top:0.686em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle textstyle cramped"><span class="mord textstyle c ramped"><span class="mord mathit">n</span></span></span></span><span style="top:-0.22999999999999998em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle textstyle uncramped frac-line"></span></span><span style="top:-0.677em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle textstyle uncramped"><span class="mord textstyle uncramped"><span class="mord mathrm">1</span></span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="sizing reset-size5 size5 reset-textstyle textstyle uncramped nulldelimiter"></span></span><span class="mop op-limits"><span class="vlist"><span style="top:1.1776689999999999em;margin-left:0em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">  0B;</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord scriptstyle cramped"><span class="mord mathit">i</span><span class="mrel">=</span><span class="mord mathrm">1</span></span></span></span><span style="top:-0.000005000000000143778em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span><span class="op-symbol large-op mop">∑</span></span></span><span style="top:-1.2500050000000003em;margin-left:0em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle uncramped"><span class="mord scriptstyle uncramped"><span class="mord mathit">n</span></span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mord mathit">L</span><span class="mopen">(</span><span class="mord displaystyle tex tstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span><span class="mpunct">;</span><span class=""><span class="mord displaystyle textstyle uncramped"><span class="mord mathbf">x</span></span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathit">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramp ed"><span class="mord mathit">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mclose">)</span><span class="mbin">+</span><span class="mord mathit">λ</span><span class="mord mathit" style="margin-right:0.00773em;">R</span><span class="mopen">(</span><span class="mord displaystyle textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span><span class="mclose">)</span></span></span></span></span></p> <p>In the above formulation, there are two auxiliary functions we have to know: </p> <ul> -<li><span class="katex"><span class="katex-mathml"><math><semantics><mrow><mi>L</mi><mo>(</mo><mrow><mi mathvariant="bold">w</mi></mrow><mo separator="true">;</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mi>i</mi></msub><mo separator="true">,</mo><msub><mi>y</mi><mi>i</mi></msub><mo>)</mo></mrow><annotation encoding="application/x-tex">L(\mathbf{w}; \mathbf{x}_i, y_i)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.75em;"></span><span class="strut bottom" style="height:1em;vertical-align:-0.25em;"></span><span class="base textstyle uncramped"><span class="mord mathit">L</span><span class="mopen">(</span><span class="mord textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span><span class="mpunct">;</span><span class="mord"><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="msupsub"><span class="vlist"><span style="top:0.15em;ma rgin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathit mtight">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathit mtight">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><s pan class="mclose">)</span></span></span></span><ul> -<li><strong>Loss function</strong> for a single sample <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mo>(</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mi>i</mi></msub><mo separator="true">,</mo><msub><mi>y</mi><mi>i</mi></msub><mo>)</mo></mrow><annotation encoding="application/x-tex">(\mathbf{x}_i, y_i)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.75em;"></span><span class="strut bottom" style="height:1em;vertical-align:-0.25em;"></span><span class="base textstyle uncramped"><span class="mopen">(</span><span class="mord"><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathit mtight">i</spa n></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped mtight"><span class="mord mathit mtight">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span></span><span class="mclose">)</span></span></span></span> and given <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mrow><mi mathvariant="bold">w</mi></mrow></mrow><annotation encoding="application/x-te x">\mathbf{w}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.44444em;"></span><span class="strut bottom" style="height:0.44444em;vertical-align:0em;"></span><span class="base textstyle uncramped"><span class="mord textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span></span></span></span>.</li> +<li><span class="katex"><span class="katex-mathml"><math><semantics><mrow><mi>L</mi><mo>(</mo><mrow><mi mathvariant="bold">w</mi></mrow><mo separator="true">;</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mi>i</mi></msub><mo separator="true">,</mo><msub><mi>y</mi><mi>i</mi></msub><mo>)</mo></mrow><annotation encoding="application/x-tex">L(\mathbf{w}; \mathbf{x}_i, y_i)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.75em;"></span><span class="strut bottom" style="height:1em;vertical-align:-0.25em;"></span><span class="base textstyle uncramped"><span class="mord mathit">L</span><span class="mopen">(</span><span class="mord textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span><span class="mpunct">;</span><span class=""><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathit">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathit">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mclose">)</span></span></span></span><ul> +<li><strong>Loss function</strong> for a single sample <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mo>(</mo><msub><mrow><mi mathvariant="bold">x</mi></mrow><mi>i</mi></msub><mo separator="true">,</mo><msub><mi>y</mi><mi>i</mi></msub><mo>)</mo></mrow><annotation encoding="application/x-tex">(\mathbf{x}_i, y_i)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.75em;"></span><span class="strut bottom" style="height:1em;vertical-align:-0.25em;"></span><span class="base textstyle uncramped"><span class="mopen">(</span><span class=""><span class="mord textstyle uncramped"><span class="mord mathbf">x</span></span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathit">i</span></span></span><span class="baseline-fi x"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mpunct">,</span><span class="mord"><span class="mord mathit" style="margin-right:0.03588em;">y</span><span class="vlist"><span style="top:0.15em;margin-right:0.05em;margin-left:-0.03588em;"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span><span class="reset-textstyle scriptstyle cramped"><span class="mord mathit">i</span></span></span><span class="baseline-fix"><span class="fontsize-ensurer reset-size5 size5"><span style="font-size:0em;">​</span></span>​</span></span></span><span class="mclose">)</span></span></span></span> and given <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mrow><mi mathvariant="bold">w</mi></mrow></mrow><annotation encoding="application/x-tex">\mathbf{w}</annotation></semantics></math></span><span class="katex-html" aria-hidden=" true"><span class="strut" style="height:0.44444em;"></span><span class="strut bottom" style="height:0.44444em;vertical-align:0em;"></span><span class="base textstyle uncramped"><span class="mord textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span></span></span></span>.</li> <li>If this function produces small values, it means the parameter <span class="katex"><span class="katex-mathml"><math><semantics><mrow><mrow><mi mathvariant="bold">w</mi></mrow></mrow><annotation encoding="application/x-tex">\mathbf{w}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="strut" style="height:0.44444em;"></span><span class="strut bottom" style="height:0.44444em;vertical-align:0em;"></span><span class="base textstyle uncramped"><span class="mord textstyle uncramped"><span class="mord mathbf" style="margin-right:0.01597em;">w</span></span></span></span></span> is successfully learnt. </li> </ul> </li> @@ -2198,30 +2234,35 @@ E(\mathbf{w}) := \frac{1}{n} \sum_{i=1}^{n} L(\mathbf{w}; \mathbf{x}_i, y_i) + \ <p>Interestingly, depending on a choice of loss and regularization function, prediction model you obtained will behave differently; even if one combination could work as a classifier, another choice might be appropriate for regression.</p> <p>Below we list possible options for <code>train_regression</code> and <code>train_classifier</code>, and this is the reason why these two functions are the most flexible in Hivemall:</p> <ul> -<li>Loss function: <code>-loss</code>, <code>-loss_function</code><ul> +<li><p>Loss function: <code>-loss</code>, <code>-loss_function</code></p> +<ul> <li>For <code>train_regression</code><ul> -<li>SquaredLoss</li> -<li>QuantileLoss</li> -<li>EpsilonInsensitiveLoss</li> -<li>SquaredEpsilonInsensitiveLoss</li> -<li>HuberLoss</li> +<li>SquaredLoss (synonym: squared)</li> +<li>QuantileLoss (synonym: quantile)</li> +<li>EpsilonInsensitiveLoss (synonym: epsilon_intensitive)</li> +<li>SquaredEpsilonInsensitiveLoss (synonym: squared_epsilon_intensitive)</li> +<li>HuberLoss (synonym: huber)</li> </ul> </li> <li>For <code>train_classifier</code><ul> -<li>HingeLoss</li> -<li>LogLoss</li> -<li>SquaredHingeLoss</li> -<li>ModifiedHuberLoss</li> -<li>SquaredLoss</li> -<li>QuantileLoss</li> -<li>EpsilonInsensitiveLoss</li> -<li>SquaredEpsilonInsensitiveLoss</li> -<li>HuberLoss</li> +<li>HingeLoss (synonym: hinge)</li> +<li>LogLoss (synonym: log, logistic)</li> +<li>SquaredHingeLoss (synonym: squared_hinge)</li> +<li>ModifiedHuberLoss (synonym: modified_huber)</li> +<li>The following losses are mainly designed for regression but can sometimes be useful in classification as well:<ul> +<li>SquaredLoss (synonym: squared)</li> +<li>QuantileLoss (synonym: quantile)</li> +<li>EpsilonInsensitiveLoss (synonym: epsilon_intensitive)</li> +<li>SquaredEpsilonInsensitiveLoss (synonym: squared_epsilon_intensitive)</li> +<li>HuberLoss (synonym: huber)</li> </ul> </li> </ul> </li> -<li>Regularization function: <code>-reg</code>, <code>-regularization</code><ul> +</ul> +</li> +<li><p>Regularization function: <code>-reg</code>, <code>-regularization</code></p> +<ul> <li>L1</li> <li>L2</li> <li>ElasticNet</li> @@ -2239,6 +2280,7 @@ E(\mathbf{w}) := \frac{1}{n} \sum_{i=1}^{n} L(\mathbf{w}; \mathbf{x}_i, y_i) + \ </ul> </li> </ul> +<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>Option values are case insensitive and you can use <code>sgd</code> or <code>rda</code>, or <code>huberloss</code>.</p></div></div> <p>In practice, you can try different combinations of the options in order to achieve higher prediction accuracy. <div id="page-footer" class="localized-footer"><hr><!-- Licensed to the Apache Software Foundation (ASF) under one @@ -2295,7 +2337,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda <script> var gitbook = gitbook || []; gitbook.push(function() { - gitbook.page.hasChanged({"page":{"title":"How Prediction Works","level":"5.1","depth":1,"next":{"title":"Regression","level":"5.2","depth":1,"path":"regression/general.md","ref":"regression/general.md","articles":[]},"previous":{"title":"Logistic Regression data generation","level":"4.3.1","depth":2,"path":"eval/lr_datagen.md","ref":"eval/lr_datagen.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitter":{},"; search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"selector":"h1 ,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/prediction.md","mtime":"2017-06-15T10:18:54.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2017-06-15T10:33:21.138Z"},"basePath":"..","book":{"language":""}}); + gitbook.page.hasChanged({"page":{"title":"How Prediction Works","level":"5.1","depth":1,"next":{"title":"Binary Classification","level":"6.1","depth":1,"path":"binaryclass/general.md","ref":"binaryclass/general.md","articles":[]},"previous":{"title":"Logistic Regression data generation","level":"4.3.1","depth":2,"path":"eval/lr_datagen.md","ref":"eval/lr_datagen.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"s plitter":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/docs/gitbook"},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":true},"anchorjs":{"; selector":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/prediction.md","mtime":"2017-06-23T09:56:22.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2017-06-23T09:59:20.878Z"},"basePath":"..","book":{"language":""}}); }); </script> </div>
http://git-wip-us.apache.org/repos/asf/incubator-hivemall-site/blob/ba518dab/userguide/misc/tokenizer.html ---------------------------------------------------------------------- diff --git a/userguide/misc/tokenizer.html b/userguide/misc/tokenizer.html index 33bf07b..81bbefa 100644 --- a/userguide/misc/tokenizer.html +++ b/userguide/misc/tokenizer.html @@ -598,14 +598,30 @@ </li> - <li class="chapter " data-level="3.5" data-path="../ft_engineering/tfidf.html"> + <li class="chapter " data-level="3.5" data-path="../ft_engineering/pairing.html"> - <a href="../ft_engineering/tfidf.html"> + <a href="../ft_engineering/pairing.html"> <b>3.5.</b> - TF-IDF Calculation + FEATURE PAIRING + + </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> @@ -613,6 +629,11 @@ </li> + + </ul> + + </li> + <li class="chapter " data-level="3.6" data-path="../ft_engineering/ft_trans.html"> <a href="../ft_engineering/ft_trans.html"> @@ -664,6 +685,21 @@ </li> + <li class="chapter " data-level="3.7" data-path="../ft_engineering/tfidf.html"> + + <a href="../ft_engineering/tfidf.html"> + + + <b>3.7.</b> + + TF-IDF Calculation + + </a> + + + + </li> + @@ -761,7 +797,7 @@ - <li class="header">Part V - Prediction</li> + <li class="header">Part V - Supervised Learning</li> @@ -780,27 +816,19 @@ </li> - <li class="chapter " data-level="5.2" data-path="../regression/general.html"> - - <a href="../regression/general.html"> - - - <b>5.2.</b> - - Regression - - </a> - - - </li> - <li class="chapter " data-level="5.3" data-path="../binaryclass/general.html"> + + <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>5.3.</b> + <b>6.1.</b> Binary Classification @@ -810,21 +838,14 @@ </li> - - - - <li class="header">Part VI - Binary classification tutorials</li> - - - - <li class="chapter " data-level="6.1" data-path="../binaryclass/a9a.html"> + <li class="chapter " data-level="6.2" data-path="../binaryclass/a9a.html"> <a href="../binaryclass/a9a.html"> - <b>6.1.</b> + <b>6.2.</b> - a9a + a9a tutorial </a> @@ -833,12 +854,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.1.1" data-path="../binaryclass/a9a_dataset.html"> + <li class="chapter " data-level="6.2.1" data-path="../binaryclass/a9a_dataset.html"> <a href="../binaryclass/a9a_dataset.html"> - <b>6.1.1.</b> + <b>6.2.1.</b> Data preparation @@ -848,12 +869,12 @@ </li> - <li class="chapter " data-level="6.1.2" data-path="../binaryclass/a9a_lr.html"> + <li class="chapter " data-level="6.2.2" data-path="../binaryclass/a9a_lr.html"> <a href="../binaryclass/a9a_lr.html"> - <b>6.1.2.</b> + <b>6.2.2.</b> Logistic Regression @@ -863,12 +884,12 @@ </li> - <li class="chapter " data-level="6.1.3" data-path="../binaryclass/a9a_minibatch.html"> + <li class="chapter " data-level="6.2.3" data-path="../binaryclass/a9a_minibatch.html"> <a href="../binaryclass/a9a_minibatch.html"> - <b>6.1.3.</b> + <b>6.2.3.</b> Mini-batch Gradient Descent @@ -883,14 +904,14 @@ </li> - <li class="chapter " data-level="6.2" data-path="../binaryclass/news20.html"> + <li class="chapter " data-level="6.3" data-path="../binaryclass/news20.html"> <a href="../binaryclass/news20.html"> - <b>6.2.</b> + <b>6.3.</b> - News20 + News20 tutorial </a> @@ -899,12 +920,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.2.1" data-path="../binaryclass/news20_dataset.html"> + <li class="chapter " data-level="6.3.1" data-path="../binaryclass/news20_dataset.html"> <a href="../binaryclass/news20_dataset.html"> - <b>6.2.1.</b> + <b>6.3.1.</b> Data preparation @@ -914,12 +935,12 @@ </li> - <li class="chapter " data-level="6.2.2" data-path="../binaryclass/news20_pa.html"> + <li class="chapter " data-level="6.3.2" data-path="../binaryclass/news20_pa.html"> <a href="../binaryclass/news20_pa.html"> - <b>6.2.2.</b> + <b>6.3.2.</b> Perceptron, Passive Aggressive @@ -929,12 +950,12 @@ </li> - <li class="chapter " data-level="6.2.3" data-path="../binaryclass/news20_scw.html"> + <li class="chapter " data-level="6.3.3" data-path="../binaryclass/news20_scw.html"> <a href="../binaryclass/news20_scw.html"> - <b>6.2.3.</b> + <b>6.3.3.</b> CW, AROW, SCW @@ -944,12 +965,12 @@ </li> - <li class="chapter " data-level="6.2.4" data-path="../binaryclass/news20_adagrad.html"> + <li class="chapter " data-level="6.3.4" data-path="../binaryclass/news20_adagrad.html"> <a href="../binaryclass/news20_adagrad.html"> - <b>6.2.4.</b> + <b>6.3.4.</b> AdaGradRDA, AdaGrad, AdaDelta @@ -964,14 +985,14 @@ </li> - <li class="chapter " data-level="6.3" data-path="../binaryclass/kdd2010a.html"> + <li class="chapter " data-level="6.4" data-path="../binaryclass/kdd2010a.html"> <a href="../binaryclass/kdd2010a.html"> - <b>6.3.</b> + <b>6.4.</b> - KDD2010a + KDD2010a tutorial </a> @@ -980,12 +1001,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.3.1" data-path="../binaryclass/kdd2010a_dataset.html"> + <li class="chapter " data-level="6.4.1" data-path="../binaryclass/kdd2010a_dataset.html"> <a href="../binaryclass/kdd2010a_dataset.html"> - <b>6.3.1.</b> + <b>6.4.1.</b> Data preparation @@ -995,12 +1016,12 @@ </li> - <li class="chapter " data-level="6.3.2" data-path="../binaryclass/kdd2010a_scw.html"> + <li class="chapter " data-level="6.4.2" data-path="../binaryclass/kdd2010a_scw.html"> <a href="../binaryclass/kdd2010a_scw.html"> - <b>6.3.2.</b> + <b>6.4.2.</b> PA, CW, AROW, SCW @@ -1015,14 +1036,14 @@ </li> - <li class="chapter " data-level="6.4" data-path="../binaryclass/kdd2010b.html"> + <li class="chapter " data-level="6.5" data-path="../binaryclass/kdd2010b.html"> <a href="../binaryclass/kdd2010b.html"> - <b>6.4.</b> + <b>6.5.</b> - KDD2010b + KDD2010b tutorial </a> @@ -1031,12 +1052,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.4.1" data-path="../binaryclass/kdd2010b_dataset.html"> + <li class="chapter " data-level="6.5.1" data-path="../binaryclass/kdd2010b_dataset.html"> <a href="../binaryclass/kdd2010b_dataset.html"> - <b>6.4.1.</b> + <b>6.5.1.</b> Data preparation @@ -1046,12 +1067,12 @@ </li> - <li class="chapter " data-level="6.4.2" data-path="../binaryclass/kdd2010b_arow.html"> + <li class="chapter " data-level="6.5.2" data-path="../binaryclass/kdd2010b_arow.html"> <a href="../binaryclass/kdd2010b_arow.html"> - <b>6.4.2.</b> + <b>6.5.2.</b> AROW @@ -1066,14 +1087,14 @@ </li> - <li class="chapter " data-level="6.5" data-path="../binaryclass/webspam.html"> + <li class="chapter " data-level="6.6" data-path="../binaryclass/webspam.html"> <a href="../binaryclass/webspam.html"> - <b>6.5.</b> + <b>6.6.</b> - Webspam + Webspam tutorial </a> @@ -1082,12 +1103,12 @@ <ul class="articles"> - <li class="chapter " data-level="6.5.1" data-path="../binaryclass/webspam_dataset.html"> + <li class="chapter " data-level="6.6.1" data-path="../binaryclass/webspam_dataset.html"> <a href="../binaryclass/webspam_dataset.html"> - <b>6.5.1.</b> + <b>6.6.1.</b> Data pareparation @@ -1097,12 +1118,12 @@ </li> - <li class="chapter " data-level="6.5.2" data-path="../binaryclass/webspam_scw.html"> + <li class="chapter " data-level="6.6.2" data-path="../binaryclass/webspam_scw.html"> <a href="../binaryclass/webspam_scw.html"> - <b>6.5.2.</b> + <b>6.6.2.</b> PA1, AROW, SCW @@ -1117,14 +1138,14 @@ </li> - <li class="chapter " data-level="6.6" data-path="../binaryclass/titanic_rf.html"> + <li class="chapter " data-level="6.7" data-path="../binaryclass/titanic_rf.html"> <a href="../binaryclass/titanic_rf.html"> - <b>6.6.</b> + <b>6.7.</b> - Kaggle Titanic + Kaggle Titanic tutorial </a> @@ -1135,7 +1156,7 @@ - <li class="header">Part VII - Multiclass classification tutorials</li> + <li class="header">Part VII - Multiclass classification</li> @@ -1146,7 +1167,7 @@ <b>7.1.</b> - News20 Multiclass + News20 Multiclass tutorial </a> @@ -1257,7 +1278,7 @@ <b>7.2.</b> - Iris + Iris tutorial </a> @@ -1319,18 +1340,33 @@ - <li class="header">Part VIII - Regression tutorials</li> + <li class="header">Part VIII - Regression</li> - <li class="chapter " data-level="8.1" data-path="../regression/e2006.html"> + <li class="chapter " data-level="8.1" data-path="../regression/general.html"> - <a href="../regression/e2006.html"> + <a href="../regression/general.html"> <b>8.1.</b> - E2006-tfidf regression + 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> @@ -1339,12 +1375,12 @@ <ul class="articles"> - <li class="chapter " data-level="8.1.1" data-path="../regression/e2006_dataset.html"> + <li class="chapter " data-level="8.2.1" data-path="../regression/e2006_dataset.html"> <a href="../regression/e2006_dataset.html"> - <b>8.1.1.</b> + <b>8.2.1.</b> Data preparation @@ -1354,12 +1390,12 @@ </li> - <li class="chapter " data-level="8.1.2" data-path="../regression/e2006_arow.html"> + <li class="chapter " data-level="8.2.2" data-path="../regression/e2006_arow.html"> <a href="../regression/e2006_arow.html"> - <b>8.1.2.</b> + <b>8.2.2.</b> Passive Aggressive, AROW @@ -1374,14 +1410,14 @@ </li> - <li class="chapter " data-level="8.2" data-path="../regression/kddcup12tr2.html"> + <li class="chapter " data-level="8.3" data-path="../regression/kddcup12tr2.html"> <a href="../regression/kddcup12tr2.html"> - <b>8.2.</b> + <b>8.3.</b> - KDDCup 2012 track 2 CTR prediction + KDDCup 2012 track 2 CTR prediction tutorial </a> @@ -1390,12 +1426,12 @@ <ul class="articles"> - <li class="chapter " data-level="8.2.1" data-path="../regression/kddcup12tr2_dataset.html"> + <li class="chapter " data-level="8.3.1" data-path="../regression/kddcup12tr2_dataset.html"> <a href="../regression/kddcup12tr2_dataset.html"> - <b>8.2.1.</b> + <b>8.3.1.</b> Data preparation @@ -1405,12 +1441,12 @@ </li> - <li class="chapter " data-level="8.2.2" data-path="../regression/kddcup12tr2_lr.html"> + <li class="chapter " data-level="8.3.2" data-path="../regression/kddcup12tr2_lr.html"> <a href="../regression/kddcup12tr2_lr.html"> - <b>8.2.2.</b> + <b>8.3.2.</b> Logistic Regression, Passive Aggressive @@ -1420,12 +1456,12 @@ </li> - <li class="chapter " data-level="8.2.3" data-path="../regression/kddcup12tr2_lr_amplify.html"> + <li class="chapter " data-level="8.3.3" data-path="../regression/kddcup12tr2_lr_amplify.html"> <a href="../regression/kddcup12tr2_lr_amplify.html"> - <b>8.2.3.</b> + <b>8.3.3.</b> Logistic Regression with Amplifier @@ -1435,12 +1471,12 @@ </li> - <li class="chapter " data-level="8.2.4" data-path="../regression/kddcup12tr2_adagrad.html"> + <li class="chapter " data-level="8.3.4" data-path="../regression/kddcup12tr2_adagrad.html"> <a href="../regression/kddcup12tr2_adagrad.html"> - <b>8.2.4.</b> + <b>8.3.4.</b> AdaGrad, AdaDelta @@ -2151,7 +2187,7 @@ Apache Hivemall is an effort undergoing incubation at The Apache Software Founda <script> var gitbook = gitbook || []; gitbook.push(function() { - gitbook.page.hasChanged({"page":{"title":"English/Japanese Text Tokenizer","level":"2.3","depth":1,"next":{"title":"Feature Scaling","level":"3.1","depth":1,"path":"ft_engineering/scaling.md","ref":"ft_engineering/scaling.md","articles":[]},"previous":{"title":"Efficient Top-K query processing","level":"2.2","depth":1,"path":"misc/topk.md","ref":"misc/topk.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitte r":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/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":{"select or":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/tokenizer.md","mtime":"2017-02-08T07:24:57.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2017-06-15T10:33:21.138Z"},"basePath":"..","book":{"language":""}}); + gitbook.page.hasChanged({"page":{"title":"English/Japanese Text Tokenizer","level":"2.3","depth":1,"next":{"title":"Feature Scaling","level":"3.1","depth":1,"path":"ft_engineering/scaling.md","ref":"ft_engineering/scaling.md","articles":[]},"previous":{"title":"Efficient Top-K query processing","level":"2.2","depth":1,"path":"misc/topk.md","ref":"misc/topk.md","articles":[]},"dir":"ltr"},"config":{"plugins":["theme-api","edit-link","github","splitter","sitemap","etoc","callouts","toggle-chapters","anchorjs","codeblock-filename","expandable-chapters","multipart","codeblock-filename","katex","emphasize","localized-footer"],"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"pluginsConfig":{"emphasize":{},"callouts":{},"etoc":{"h2lb":3,"header":1,"maxdepth":3,"mindepth":1,"notoc":true},"github":{"url":"https://github.com/apache/incubator-hivemall/"},"splitte r":{},"search":{},"downloadpdf":{"base":"https://github.com/apache/incubator-hivemall/docs/gitbook","label":"PDF","multilingual":false},"multipart":{},"localized-footer":{"filename":"FOOTER.md","hline":"true"},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"katex":{},"fontsettings":{"theme":"white","family":"sans","size":2,"font":"sans"},"highlight":{},"codeblock-filename":{},"sitemap":{"hostname":"http://hivemall.incubator.apache.org/"},"theme-api":{"languages":[],"split":false,"theme":"dark"},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"edit-link":{"label":"Edit","base":"https://github.com/apache/incubator-hivemall/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":{"select or":"h1,h2,h3,*:not(.callout) > h4,h5"},"toggle-chapters":{},"expandable-chapters":{}},"theme":"default","pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"variables":{},"title":"Hivemall User Manual","links":{"sidebar":{"<i class=\"fa fa-home\"></i> Home":"http://hivemall.incubator.apache.org/"}},"gitbook":"3.x.x","description":"User Manual for Apache Hivemall"},"file":{"path":"misc/tokenizer.md","mtime":"2016-12-02T08:02:42.000Z","type":"markdown"},"gitbook":{"version":"3.2.2","time":"2017-06-23T09:59:20.878Z"},"basePath":"..","book":{"language":""}}); }); </script> </div>
