Adding LDA sample to Microsoft.ML.Samples

Author: abgoswam

docs/samples/Microsoft.ML.Samples/Dynamic/LdaTransform.cs

@@ -0,0 +1,66 @@
+using Microsoft.ML.Data;
+using Microsoft.ML.Runtime.Api;
+using Microsoft.ML.Runtime.Data;
+using System;
+using System.Collections.Generic;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+    public class LdaTransformExample
+    {
+        public static void LdaTransform()
+        {
+            // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
+            // as well as the source of randomness.
+            var ml = new MLContext();
+
+            // Get a small dataset as an IEnumerable.
+            IEnumerable<SamplesUtils.DatasetUtils.SampleTopicsData> data = SamplesUtils.DatasetUtils.GetTopicsData();
+            var trainData = ml.CreateStreamingDataView(data);
+
+            // Preview of one of the columns of the the topics data. 
+            // The Review column contains the keys associated with a particular body of text.  
+            //
+            // Review                               
+            // "animals birds cats dogs fish horse" 
+            // "horse birds house fish duck cats"   
+            // "car truck driver bus pickup"       
+            // "car truck driver bus pickup horse"
+
+            // A pipeline for featurizing the "Review" column
+            string ldaFeatures = "LdaFeatures";
+            var pipeline = ml.Transforms.Text.ProduceWordBags("Review").
+                Append(ml.Transforms.Text.LatentDirichletAllocation("Review", ldaFeatures, numTopic:3));
+
+            // The transformed data
+            var transformer = pipeline.Fit(trainData);
+            var transformed_data = transformer.Transform(trainData);
+
+            // Small helper to print the text inside the columns, in the console. 
+            Action<string, IEnumerable<VBuffer<float>>> printHelper = (columnName, column) =>
+            {
+                Console.WriteLine($"{columnName} column obtained post-transformation.");
+                foreach (var featureRow in column)
+                {
+                    foreach (var value in featureRow.GetValues())
+                        Console.Write($"{value} ");
+                    Console.WriteLine("");
+                }
+
+                Console.WriteLine("===================================================");
+            };
+
+            // Preview of the column obtained after processing the input.
+            var defaultColumn = transformed_data.GetColumn<VBuffer<float>>(ml, ldaFeatures);
+            printHelper(ldaFeatures, defaultColumn);
+
+            // LdaFeatures column obtained post-transformation.
+            // For LDA, we had specified numTopic:3. Hence each row of text has been featurized as a vector of floats with length 3.
+
+            //0.1818182 0.4545455 0.3636364
+            //0.3636364 0.1818182 0.4545455
+            //0.2222222 0.2222222 0.5555556
+            //0.2727273 0.09090909 0.6363636
+        }
+    }
+}

docs/samples/Microsoft.ML.Samples/Microsoft.ML.Samples.csproj

@@ -17,6 +17,7 @@
     <NativeAssemblyReference Include="CpuMathNative" />
     <NativeAssemblyReference Include="FastTreeNative" />
     <NativeAssemblyReference Include="MatrixFactorizationNative" />
+    <NativeAssemblyReference Include="LdaNative" />
 
     <ProjectReference Include="..\..\..\src\Microsoft.ML.Analyzer\Microsoft.ML.Analyzer.csproj">
       <ReferenceOutputAssembly>false</ReferenceOutputAssembly>

docs/samples/Microsoft.ML.Samples/Program.cs

@@ -6,7 +6,7 @@ internal static class Program
     {
         static void Main(string[] args)
         {
-            MatrixFactorizationExample.MatrixFactorizationInMemoryData();
+            LdaTransformExample.LdaTransform();
         }
     }
 }

src/Microsoft.ML.Transforms/Text/TextCatalog.cs

@@ -507,6 +507,13 @@ public static NgramHashEstimator ProduceHashedNgrams(this TransformsCatalog.Text
         /// <param name="numSummaryTermPerTopic">The number of words to summarize the topic.</param>
         /// <param name="numBurninIterations">The number of burn-in iterations.</param>
         /// <param name="resetRandomGenerator">Reset the random number generator for each document.</param>
+        /// <example>
+        /// <format type="text/markdown">
+        /// <![CDATA[
+        /// [!code-csharp[LatentDirichletAllocation](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/LdaTransform.cs)]
+        /// ]]>
+        /// </format>
+        /// </example>
         public static LatentDirichletAllocationEstimator LatentDirichletAllocation(this TransformsCatalog.TextTransforms catalog,
             string inputColumn,
             string outputColumn = null,