Documentation fixes for the issues in #664 (#665)

* Documentation fixes described in issue #664

* this P: notation shouldn't matter, but it does.

* regenerating the CSharpAPi

* regenerating the entry points list and manifest

Author: sfilipi

src/Microsoft.ML.Data/Transforms/doc.xml

@@ -9,10 +9,10 @@
         This transform removes the entire row if any of the input columns have a missing value in that row.
         This preprocessing is required for many ML algorithms that cannot work with missing values.
         Useful if any missing entry invalidates the entire row.
-        If the <see cref="Microsoft.ML.Runtime.Data.NAFilter.Defaults.Complement"/> is set to true, this transform would do the exact opposite,
+        If the <see cref="P:Microsoft.ML.Transforms.MissingValuesRowDropper.Complement"/> is set to true, this transform would do the exact opposite,
         it will keep only the rows that have missing values.
       </remarks>
-      <seealso cref="Microsoft.ML.Runtime.Data.MetadataUtils.Kinds.HasMissingValues"></seealso>
+      <seealso cref="T:Microsoft.ML.Runtime.Data.MetadataUtils.Kinds.HasMissingValues"></seealso>
     </member>
     <example name="NAFilter">
       <example>
@@ -44,7 +44,7 @@
         <code language="csharp">
           pipeline.Add(new TextToKeyConverter((&quot;Column&quot;, &quot;OutColumn&quot;))
           { 
-            Sort = TermTransformSortOrder.Occurrence 
+              Sort = TermTransformSortOrder.Occurrence 
           });
         </code>
       </example>
@@ -82,15 +82,15 @@
           It can be changed to true for known length vectors, but it results in an error if changed to false for variable length vectors.
         </para>
       </remarks>
-      <seealso cref=" Microsoft.ML.Runtime.Data.MetadataUtils.Kinds.HasMissingValues"/>
+      <seealso cref="T:Microsoft.ML.Runtime.Data.MetadataUtils.Kinds.HasMissingValues"/>
       <seealso cref="T:Microsoft.ML.Data.DataKind"/>
     </member>
     <example name="NAHandle">
       <example>
         <code language="csharp">
           pipeline.Add(new MissingValueHandler(&quot;FeatureCol&quot;, &quot;CleanFeatureCol&quot;)
           {
-          ReplaceWith  = NAHandleTransformReplacementKind.Mean
+              ReplaceWith  = NAHandleTransformReplacementKind.Mean
           });
         </code>
       </example>

src/Microsoft.ML.FastTree/doc.xml

@@ -29,7 +29,7 @@
           <item><description>In case of a ranking problem, the instances are ordered by the output value of the ensemble.</description></item>
         </list>
         <para>For more information see:</para>
-        <list>
+        <list type="bullet">
           <item><description><a href='https://en.wikipedia.org/wiki/Gradient_boosting#Gradient_tree_boosting'>Wikipedia: Gradient boosting (Gradient tree boosting).</a></description></item>
           <item><description><a href='http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aos/1013203451'>Greedy function approximation: A gradient boosting machine.</a></description></item>
         </list>  

src/Microsoft.ML.HalLearners/SymSgdClassificationTrainer.cs

@@ -32,6 +32,7 @@ namespace Microsoft.ML.Runtime.SymSgd
 {
     using TPredictor = IPredictorWithFeatureWeights<Float>;
 
+    /// <include file='doc.xml' path='doc/members/member[@name="SymSGD"]/*' />
     public sealed class SymSgdClassificationTrainer :
         TrainerBase<TPredictor>,
         ITrainer<TPredictor>
@@ -173,7 +174,11 @@ private TPredictor CreatePredictor(VBuffer<Float> weights, Float bias)
             return new ParameterMixingCalibratedPredictor(Host, predictor, new PlattCalibrator(Host, -1, 0));
         }
 
-        [TlcModule.EntryPoint(Name = "Trainers.SymSgdBinaryClassifier", Desc = "Train a symbolic SGD.", UserName = SymSgdClassificationTrainer.UserNameValue, ShortName = SymSgdClassificationTrainer.ShortName)]
+        [TlcModule.EntryPoint(Name = "Trainers.SymSgdBinaryClassifier",
+            Desc = "Train a symbolic SGD.",
+            UserName = SymSgdClassificationTrainer.UserNameValue,
+            ShortName = SymSgdClassificationTrainer.ShortName,
+            XmlInclude = new[] { @"<include file='../Microsoft.ML.HalLearners/doc.xml' path='doc/members/member[@name=""SymSGD""]/*' />" })]
         public static CommonOutputs.BinaryClassificationOutput TrainSymSgd(IHostEnvironment env, Arguments input)
         {
             Contracts.CheckValue(env, nameof(env));

src/Microsoft.ML.Transforms/HashJoinTransform.cs

@@ -152,8 +152,7 @@ private static KeyType GetItemType(int hashBits)
 
         internal const string RegistrationName = "HashJoin";
 
-        internal const string Summary = "Converts column values into hashes. This transform accepts both numeric and text inputs, both single and vector-valued columns. "
-            + "This is a part of the Dracula transform.";
+        internal const string Summary = "Converts column values into hashes. This transform accepts both numeric and text inputs, both single and vector-valued columns. ";
 
         internal const string UserName = "Hash Join Transform";
 

src/Microsoft.ML.Transforms/Text/doc.xml

@@ -74,7 +74,7 @@
         The n-grams are represented as count vectors, with vector slots corresponding to n-grams.
         Embedding ngrams in a vector space allows their contents to be compared in an efficient manner. 
         The slot values in the vector can be weighted by the following factors:
-        <list>
+        <list type="bullet">
           <item>
             <term>term frequency</term>
             <description> the number of occurrences of the slot in the text</description>
@@ -169,7 +169,7 @@
         </para>
         <para>
           For more details please see original LightLDA paper, and its open source implementation. 
-          <list>
+          <list type="bullet">
             <item><description><a href="http://arxiv.org/abs/1412.1576"> LightLDA: Big Topic Models on Modest Computer Clusters</a></description></item>
             <item><description><a href=" https://github.com/Microsoft/LightLDA">LightLDA </a></description></item>
           </list>

src/Microsoft.ML.Transforms/doc.xml

@@ -29,10 +29,11 @@
         Converts the categorical value into an indicator array by building a dictionary of categories based on the data and using the id in the dictionary as the index in the array
       </summary>
       <remarks>
-        <para>The CategoricalOneHotVectorizer transform passes through a data set, operating on text columns, to
+        <para>
+        The CategoricalOneHotVectorizer transform passes through a data set, operating on text columns, to
         build a dictionary of categories.
-        For each row, the entire text string appearing in the input column is defined as a category.
-        The output of this transform is an indicator vector.</para>
+        For each row, the entire text string appearing in the input column is defined as a category.</para>
+        <para>The output of this transform is an indicator vector.</para>
         Each slot in this vector corresponds to a category in the dictionary, so its length is the size of the built dictionary.
         <para>The CategoricalOneHotVectorizer can be applied to one or more columns, in which case it builds and uses a separate dictionary
         for each column that it is applied to.</para>
@@ -171,7 +172,7 @@
         This transform can transform either scalars or vectors (both fixed and variable size),
         creating output columns that indicate, through the true/false booleans whether the row has a missing value.
       </summary>
-      <seealso cref=" Microsoft.ML.Runtime.Data.MetadataUtils.Kinds.HasMissingValues"></seealso>
+      <seealso cref="T:Microsoft.ML.Runtime.Data.MetadataUtils.Kinds.HasMissingValues"></seealso>
     </member>
     <example name="NAIndicator">
       <example>
@@ -192,14 +193,14 @@
         with either the default value, user input, or imputed values (min/max/mean are currently supported).
         Imputation modes are supported for vectors both by slot and across all slots.
       </remarks>
-      <seealso cref=" Microsoft.ML.Runtime.Data.MetadataUtils.Kinds.HasMissingValues"></seealso>
+      <seealso cref="T:Microsoft.ML.Runtime.Data.MetadataUtils.Kinds.HasMissingValues"></seealso>
     </member>
     <example name="NAReplace">
       <example>
         <code language="csharp">
           pipeline.Add(new MissingValueSubstitutor(&quot;FeatureCol&quot;)
           { 
-            ReplacementKind = NAReplaceTransformReplacementKind.Mean 
+              ReplacementKind = NAReplaceTransformReplacementKind.Mean 
           });
         </code>
       </example>
@@ -221,7 +222,7 @@
         <code language="csharp">
           pipeline.Add(new LpNormalizer(&quot;FeatureCol&quot;)
           { 
-            NormKind = LpNormNormalizerTransformNormalizerKind.L1Norm
+              NormKind = LpNormNormalizerTransformNormalizerKind.L1Norm
           });
         </code>
       </example>
@@ -235,14 +236,15 @@
        </summary>
       <remarks>
         Scaling inputs to unit norms is a common operation for text classification or clustering.
-        For more information see: <a href="http://www.cs.stanford.edu/~acoates/papers/coatesleeng_aistats_2011.pdf"></a>
+        For more information see: 
+        <a href="http://www.cs.stanford.edu/~acoates/papers/coatesleeng_aistats_2011.pdf">An Analysis of Single-Layer Networks in Unsupervised Feature Learning</a>
       </remarks>
       <seealso cref=" Microsoft.ML.Transforms.LpNormalizer"></seealso>
       <example>
         <code language="csharp">
           pipeline.Add(new GlobalContrastNormalizer(&quot;FeatureCol&quot;)
           { 
-            SubMean= false
+              SubMean= false
           });
         </code>
       </example>
@@ -334,7 +336,7 @@
         <code language="csharp">
           pipeline.Add(new CombinerByContiguousGroupId
           { 
-            GroupKey = new []{&quot;Key1&quot;, &quot;Key2&quot; } 
+              GroupKey = new []{&quot;Key1&quot;, &quot;Key2&quot; } 
           });
         </code>
       </example>

src/Microsoft.ML/CSharpApi.cs

@@ -9776,9 +9776,7 @@ public StochasticGradientDescentBinaryClassifierPipelineStep(Output output)
     namespace Trainers
     {
 
-        /// <summary>
-        /// Train a symbolic SGD.
-        /// </summary>
+        /// <include file='../Microsoft.ML.HalLearners/doc.xml' path='doc/members/member[@name="SymSGD"]/*' />
         public sealed partial class SymSgdBinaryClassifier : Microsoft.ML.Runtime.EntryPoints.CommonInputs.ITrainerInputWithLabel, Microsoft.ML.Runtime.EntryPoints.CommonInputs.ITrainerInput, Microsoft.ML.ILearningPipelineItem
         {
 

test/BaselineOutput/Common/EntryPoints/core_ep-list.tsv

@@ -88,7 +88,7 @@ Transforms.FeatureCombiner	Combines all the features into one feature column.	Mi
 Transforms.FeatureSelectorByCount	Selects the slots for which the count of non-default values is greater than or equal to a threshold.	Microsoft.ML.Runtime.EntryPoints.SelectFeatures	CountSelect	Microsoft.ML.Runtime.Data.CountFeatureSelectionTransform+Arguments	Microsoft.ML.Runtime.EntryPoints.CommonOutputs+TransformOutput
 Transforms.FeatureSelectorByMutualInformation	Selects the top k slots across all specified columns ordered by their mutual information with the label column.	Microsoft.ML.Runtime.EntryPoints.SelectFeatures	MutualInformationSelect	Microsoft.ML.Runtime.Data.MutualInformationFeatureSelectionTransform+Arguments	Microsoft.ML.Runtime.EntryPoints.CommonOutputs+TransformOutput
 Transforms.GlobalContrastNormalizer	Performs a global contrast normalization on input values: Y = (s * X - M) / D, where s is a scale, M is mean and D is either L2 norm or standard deviation.	Microsoft.ML.Runtime.Data.LpNormalization	GcNormalize	Microsoft.ML.Runtime.Data.LpNormNormalizerTransform+GcnArguments	Microsoft.ML.Runtime.EntryPoints.CommonOutputs+TransformOutput
-Transforms.HashConverter	Converts column values into hashes. This transform accepts both numeric and text inputs, both single and vector-valued columns. This is a part of the Dracula transform.	Microsoft.ML.Runtime.Data.HashJoin	Apply	Microsoft.ML.Runtime.Data.HashJoinTransform+Arguments	Microsoft.ML.Runtime.EntryPoints.CommonOutputs+TransformOutput
+Transforms.HashConverter	Converts column values into hashes. This transform accepts both numeric and text inputs, both single and vector-valued columns. 	Microsoft.ML.Runtime.Data.HashJoin	Apply	Microsoft.ML.Runtime.Data.HashJoinTransform+Arguments	Microsoft.ML.Runtime.EntryPoints.CommonOutputs+TransformOutput
 Transforms.ImageGrayscale	Convert image into grayscale.	Microsoft.ML.Runtime.ImageAnalytics.EntryPoints.ImageAnalytics	ImageGrayscale	Microsoft.ML.Runtime.ImageAnalytics.ImageGrayscaleTransform+Arguments	Microsoft.ML.Runtime.EntryPoints.CommonOutputs+TransformOutput
 Transforms.ImageLoader	Load images from files.	Microsoft.ML.Runtime.ImageAnalytics.EntryPoints.ImageAnalytics	ImageLoader	Microsoft.ML.Runtime.ImageAnalytics.ImageLoaderTransform+Arguments	Microsoft.ML.Runtime.EntryPoints.CommonOutputs+TransformOutput
 Transforms.ImagePixelExtractor	Extract color plane(s) from an image. Options include scaling, offset and conversion to floating point.	Microsoft.ML.Runtime.ImageAnalytics.EntryPoints.ImageAnalytics	ImagePixelExtractor	Microsoft.ML.Runtime.ImageAnalytics.ImagePixelExtractorTransform+Arguments	Microsoft.ML.Runtime.EntryPoints.CommonOutputs+TransformOutput

test/BaselineOutput/Common/EntryPoints/core_manifest.json

@@ -18062,7 +18062,7 @@
     },
     {
       "Name": "Transforms.HashConverter",
-      "Desc": "Converts column values into hashes. This transform accepts both numeric and text inputs, both single and vector-valued columns. This is a part of the Dracula transform.",
+      "Desc": "Converts column values into hashes. This transform accepts both numeric and text inputs, both single and vector-valued columns. ",
       "FriendlyName": "Hash Join Transform",
       "ShortName": "HashJoin",
       "Inputs": [