PUB-511: Add tutorial for GBM

lib/resources/tutorials/gbm.iris/step1.html

@@ -0,0 +1,10 @@
+<p>This tutorial shows how to use the GBM method in H<sub>2</sub>O for model training and classification.</p>
+
+<p>GBM is a method for regression and classification that builds a forest of gradient boosted trees. The trees are built from a training dataset and can be used to make predictions on a test dataset.</p>
+
+<p>
+Vocabulary:
+<ul>
+  <li><a href="http://en.wikipedia.org/wiki/Gradient_boosting">Gradient boosting</a></li>
+</ul>
+</p>

lib/resources/tutorials/gbm.iris/step2.html

@@ -0,0 +1,16 @@
+<p>
+We will use the common <a href='http://archive.ics.uci.edu/ml/datasets/Iris'>Iris dataset</a> for training.
+</p>
+
+<p>
+The iris dataset is provided <a href="/datasets/iris.csv">here</a>.  Please, download it and save it on your disk.
+</p>
+
+<p>
+To upload the dataset into H<sub>2</sub>O application, please, use the menu option <span class='label mref'>Data &gt; Upload</span> or direct <a href="/Upload.html" target="_blank">link</a>.
+
+<p>
+Alternatively, Data can be imported from a URL directly into H<sub>2</sub>O application.
+Use the menu option <span class='label mref'>Data &gt; Import Files</span> or direct
+<a href="/2/ImportFiles2.html?path=https%3A%2F%2Fraw.github.com%2F0xdata%2Fh2o%2Fmaster%2Fsmalldata%2Firis%2Firis.csv" target="_blank">link</a>.
+</p>

lib/resources/tutorials/gbm.iris/step3.html

@@ -0,0 +1,5 @@
+<p>
+<!--To parse the uploaded dataset (most likely already done), use the menu option <span class='label mref'>Data &gt; Parse</span> or direct <a href="/2/Parse2.query?source_key=iris.csv" target="_blank">link</a>.-->
+    The uploaded dataset was automatically parsed during the previous step.
+    You can always use the menu option <span class='label mref'>Data &gt; Parse</span> to parse data.
+</p>

lib/resources/tutorials/gbm.iris/step4.html

@@ -0,0 +1,6 @@
+<p>
+    The parsed dataset can be inspected by the menu option <span class='label mref'>Data &gt; Inspect</span> or by direct
+    <a href="/2/Inspect2.html?src_key=iris.hex" target="_blank">link</a>.
+</p>
+
+<p>The inspect view shows the columns and rows for the dataset. For each column it displays its type, arity, basic statistical information (min/max/min/variance), and number of missing or invalid rows. The whole dataset can be explored row by row if desired.</p>

lib/resources/tutorials/gbm.iris/step5.html

@@ -0,0 +1,12 @@
+<p>
+Now that we have loaded the iris dataset into H<sub>2</sub>O, we can build a GBM
+model.  For this purpose, please use the menu option <span class='label
+mref'>Model &gt; GBM</span> or direct <a
+href="/2/GBM.query?source=iris.hex&destination_key=model&response=4&ntrees=20&ignore=&learn_rate=0.2"
+target="_blank">link</a>.
+<p>
+</p>
+The GBM method has multiple tuning parameters that can affect the model it will
+build.  For example, you can increase the number of trees, the maximum tree
+depth or the learning rate.
+</p>

lib/resources/tutorials/gbm.iris/step6.html

@@ -0,0 +1,4 @@
+<p>
+    Running GBM produces a model and its progress is displayed
+    <a href='2/GBMModelView.html?_modelKey=model' target='_blank'>here</a>.
+</p>

lib/resources/tutorials/gbm.iris/step7.html

@@ -0,0 +1,4 @@
+<p>
+    The model can be used to make a prediction on a test set via
+    the menu option <span class='label mref'>Score &gt; Predict</span> or direct <a href="/2/Predict.query?model=model&data=iris.hex&prediction=pred" target="_blank">link</a>.
+</p>

lib/resources/tutorials/gbm.iris/step8.html

@@ -0,0 +1,4 @@
+<p>
+    The prediction can now be scored via
+    the menu option <span class='label mref'>Score &gt; Confusion Matrix</span> or direct <a href="/2/ConfusionMatrix.query?actual=iris.hex&vactual=4&predict=pred&vpredict=predict" target="_blank">link</a>.
+</p>

src/main/java/water/api/RequestServer.java

@@ -128,6 +128,7 @@ public enum API_VERSION {
     // Help and Tutorials
     Request.addToNavbar(registerRequest(new Documentation()),       "H2O Documentation",      "Help", USE_NEW_TAB);
     Request.addToNavbar(registerRequest(new Tutorials()),           "Tutorials Home",         "Help", USE_NEW_TAB);
+    Request.addToNavbar(registerRequest(new TutorialGBM()),         "GBM Tutorial",           "Help", USE_NEW_TAB);
     Request.addToNavbar(registerRequest(new TutorialDeepLearning()),"Deep Learning Tutorial", "Help", USE_NEW_TAB);
     Request.addToNavbar(registerRequest(new TutorialRFIris()),      "Random Forest Tutorial", "Help", USE_NEW_TAB);
     Request.addToNavbar(registerRequest(new TutorialGLMProstate()), "GLM Tutorial",           "Help", USE_NEW_TAB);

src/main/java/water/api/TutorialGBM.java

@@ -0,0 +1,33 @@
+package water.api;
+
+/**
+ * Basic page introducing tutorial for GBM on Iris
+ */
+public class TutorialGBM extends TutorialWorkflow {
+
+  private final transient TutorWorkflow _wf;
+  private final static String[][] TUTORIAL_STEPS = new String[][]{
+    /*               Title     Short Summary     File containing step description */
+    new String[] { "Step 1", "Introduction", "/tutorials/gbm.iris/step1.html" },
+    new String[] { "Step 2", "Dataset inhale", "/tutorials/gbm.iris/step2.html" },
+    new String[] { "Step 3", "Parsing the dataset", "/tutorials/gbm.iris/step3.html" },
+    new String[] { "Step 4", "Inspecting the dataset", "/tutorials/gbm.iris/step4.html" },
+    new String[] { "Step 5", "Building the model", "/tutorials/gbm.iris/step5.html" },
+    new String[] { "Step 6", "Inspecting the model", "/tutorials/gbm.iris/step6.html" },
+    new String[] { "Step 7", "Predict on a test set", "/tutorials/gbm.iris/step7.html" },
+    new String[] { "Step 8", "Scoring the prediction", "/tutorials/gbm.iris/step8.html" },
+  };
+
+  public TutorialGBM() {
+    _wf = new TutorWorkflow("GBM Tutorial");
+    int i = 1;
+    for (String[] info : TUTORIAL_STEPS) {
+      _wf.addStep(i++, new FileTutorStep(info));
+    }
+  }
+
+  @Override
+  protected TutorWorkflow getWorkflow() {
+    return _wf;
+  }
+}

src/main/java/water/api/Tutorials.java

@@ -19,25 +19,31 @@ public class Tutorials extends HTMLOnlyRequest {
     + "</div>"
     + "<div class='row'>"
 
-    + "<div class='span3 col'>"
+    + "<div class='span2 col'>"
     + "  <h2>Random Forest</h2>"
-    +   "<p>Random Forest is a classical machine learning algorithm for classification and regression. Learn how to use it with H<sub>2</sub>O.</it></p>"
+    +   "<p>Random Forest is a classical machine learning method for classification and regression. Learn how to use it with H<sub>2</sub>O.</it></p>"
     +   "<a href='/TutorialRFIris.html' class='btn btn-primary'>Try it!</a>"
     + "</div>"
 
-    + "<div class='span3 col'>"
+    + "<div class='span2 col'>"
+    + "  <h2>GBM</h2>"
+    +   "<p>GBM uses gradient boosted regression trees for highly predictive regression and classification.</p>"
+    +   "<a href='/TutorialGBM.html' class='btn btn-primary'>Try it!</a>"
+    + "</div>"
+
+    + "<div class='span2 col'>"
     +   "<h2>GLM</h2>"
     +   "<p>Generalized linear model is a generalization of linear regression. Experience its unique power on top of H<sub>2</sub>O.</p>"
     +   "<a href='/TutorialGLMProstate.html' class='btn btn-primary'>Try it!</a>"
     + "</div>"
 
-    + "<div class='span3 col'>"
-    + "<h2>K-means</h2>"
+    + "<div class='span2 col'>"
+    + "<h2>K-Means</h2>"
     + "<p>Perform cluster analysis with H<sub>2</sub>O. It employs K-means, a highly scalable clustering algorithm.</p>"
     +   "<a href='/TutorialKMeans.html' class='btn btn-primary'>Try it!</a>"
     + "</div>"
 
-    + "<div class='span3 col'>"
+    + "<div class='span2 col'>"
     + "<h2>Deep Learning</h2>"
     + "<p>H<sub>2</sub>O's distributed Deep Learning models high-level abstractions in data with deep artificial neural networks.</p>"
     +   "<a href='/TutorialDeepLearning.html' class='btn btn-primary'>Try it!</a>"