CollectionDataSource (train on top of memory collection instead of loading data from file)

ZBaselines/Common/EntryPoints/core_ep-list.tsv

@@ -1,3 +1,4 @@
+Data.DataViewReference	Pass dataview from memory to experiment	Microsoft.ML.Runtime.EntryPoints.InMemoryDataView	ImportData	Microsoft.ML.Runtime.EntryPoints.InMemoryDataView+Input	Microsoft.ML.Runtime.EntryPoints.InMemoryDataView+Output
 Data.IDataViewArrayConverter	Create and array variable	Microsoft.ML.Runtime.EntryPoints.CrossValidationBinaryMacro	MakeArray	Microsoft.ML.Runtime.EntryPoints.CrossValidationBinaryMacro+ArrayIDataViewInput	Microsoft.ML.Runtime.EntryPoints.CrossValidationBinaryMacro+ArrayIDataViewOutput
 Data.PredictorModelArrayConverter	Create and array variable	Microsoft.ML.Runtime.EntryPoints.CrossValidationBinaryMacro	MakeArray	Microsoft.ML.Runtime.EntryPoints.CrossValidationBinaryMacro+ArrayIPredictorModelInput	Microsoft.ML.Runtime.EntryPoints.CrossValidationBinaryMacro+ArrayIPredictorModelOutput
 Data.TextLoader	Import a dataset from a text file	Microsoft.ML.Runtime.EntryPoints.ImportTextData	ImportText	Microsoft.ML.Runtime.EntryPoints.ImportTextData+Input	Microsoft.ML.Runtime.EntryPoints.ImportTextData+Output

ZBaselines/Common/EntryPoints/core_manifest.json

@@ -1,5 +1,31 @@
 {
   "EntryPoints": [
+    {
+      "Name": "Data.DataViewReference",
+      "Desc": "Pass dataview from memory to experiment",
+      "FriendlyName": null,
+      "ShortName": null,
+      "Inputs": [
+        {
+          "Name": "Data",
+          "Type": "DataView",
+          "Desc": "Pointer to IDataView in memory",
+          "Aliases": [
+            "data"
+          ],
+          "Required": true,
+          "SortOrder": 1.0,
+          "IsNullable": false
+        }
+      ],
+      "Outputs": [
+        {
+          "Name": "Data",
+          "Type": "DataView",
+          "Desc": "The resulting data view"
+        }
+      ]
+    },
     {
       "Name": "Data.IDataViewArrayConverter",
       "Desc": "Create and array variable",

src/Microsoft.ML/CSharpApi.cs

@@ -53,11 +53,22 @@ public Microsoft.ML.Data.TextLoader.Output Add(Microsoft.ML.Data.TextLoader inpu
                 return output;
             }
 
+            public Microsoft.ML.Data.DataViewReference.Output Add(Microsoft.ML.Data.DataViewReference input)
+            {
+                var output = new Microsoft.ML.Data.DataViewReference.Output();
+                Add(input, output);
+                return output;
+            }
+
             public void Add(Microsoft.ML.Data.TextLoader input, Microsoft.ML.Data.TextLoader.Output output)
             {
                 _jsonNodes.Add(Serialize("Data.TextLoader", input, output));
             }
 
+            public void Add(Microsoft.ML.Data.DataViewReference input, Microsoft.ML.Data.DataViewReference.Output output)
+            {
+                _jsonNodes.Add(Serialize("Data.DataViewReference", input, output));
+            }
             public Microsoft.ML.Models.AnomalyDetectionEvaluator.Output Add(Microsoft.ML.Models.AnomalyDetectionEvaluator input)
             {
                 var output = new Microsoft.ML.Models.AnomalyDetectionEvaluator.Output();
@@ -1311,6 +1322,23 @@ public sealed partial class TextLoader
             public string CustomSchema { get; set; }
 
 
+            public sealed class Output
+            {
+                /// <summary>
+                /// The resulting data view
+                /// </summary>
+                public Var<Microsoft.ML.Runtime.Data.IDataView> Data { get; set; } = new Var<Microsoft.ML.Runtime.Data.IDataView>();
+
+            }
+        }
+
+        public sealed partial class DataViewReference
+        {
+            /// <summary>
+            /// Location of the input file
+            /// </summary>
+            public Var<Microsoft.ML.Runtime.Data.IDataView> Data { get; set; } = new Var<Microsoft.ML.Runtime.Data.IDataView>();
+
             public sealed class Output
             {
                 /// <summary>

src/Microsoft.ML/MemoryCollection.cs

@@ -0,0 +1,94 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+// See the LICENSE file in the project root for more information.
+
+using System.Collections.Generic;
+using Microsoft.ML.Runtime;
+using Microsoft.ML.Runtime.Api;
+using Microsoft.ML.Runtime.Data;
+using Microsoft.ML.Runtime.EntryPoints;
+using Microsoft.ML.Runtime.Internal.Utilities;
+
+namespace Microsoft.ML
+{
+    public class MemoryCollection
+    {
+        /// <summary>
+        /// Creates memory collection loader.
+        /// </summary>
+        public static MemoryCollectionLoader<T> Create<T>(IList<T> data) where T:class
+        {
+            return new MemoryCollectionLoader<T>(data);
+        }
+
+        /// <summary>
+        /// Creates memory collection loader.
+        /// </summary>
+        public static MemoryCollectionLoader<T> Create<T>(IEnumerable<T> data) where T : class
+        {
+            return new MemoryCollectionLoader<T>(data);
+        }
+    }
+
+    /// <summary>
+    /// Allows you to convert your memory collection into IDataview.
+    /// </summary>
+    /// <typeparam name="TInput"></typeparam>
+    public class MemoryCollectionLoader<TInput> : ILearningPipelineLoader
+        where TInput : class
+    {
+        public ILearningPipelineStep ApplyStep(ILearningPipelineStep previousStep, Experiment experiment)
+        {
+            Contracts.Assert(previousStep == null);
+            _dataViewEntryPoint = new Data.DataViewReference();
+            var importOutput = experiment.Add(_dataViewEntryPoint);
+            return new MemoryCollectionPipelineStep(importOutput.Data);
+        }
+
+        private readonly IList<TInput> _listCollection;
+        private readonly IEnumerable<TInput> _enumerableCollection;
+
+        private Data.DataViewReference _dataViewEntryPoint;
+        private IDataView _dataView;
+
+        /// <summary>
+        /// Creates IDataview on top of collection
+        /// </summary>
+        public MemoryCollectionLoader(IList<TInput> collection)
+        {
+            Contracts.CheckParamValue(Utils.Size(collection) > 0, collection, nameof(collection), "Must be non-empty");
+            _listCollection = collection;
+        }
+
+        /// <summary>
+        /// Creates IDataview on top of collection
+        /// </summary>
+        public MemoryCollectionLoader(IEnumerable<TInput> collection)
+        {
+            Contracts.CheckValue(collection,nameof(collection), "Must be non-null");
+            _enumerableCollection = collection;
+
+        }
+
+        public void SetInput(IHostEnvironment env, Experiment experiment)
+        {
+            if (_listCollection != null)
+                _dataView = ComponentCreation.CreateDataView(env, _listCollection);
+            if (_enumerableCollection != null)
+                _dataView = ComponentCreation.CreateStreamingDataView(env, _listCollection);
+            env.CheckValue(_dataView, nameof(_dataView));
+            experiment.SetInput(_dataViewEntryPoint.Data, _dataView);
+        }
+
+        private class MemoryCollectionPipelineStep : ILearningPipelineDataStep
+        {
+            public MemoryCollectionPipelineStep(Var<IDataView> data)
+            {
+                Data = data;
+            }
+
+            public Var<IDataView> Data { get; }
+            public Var<ITransformModel> Model  => null;
+        }
+    }
+}

src/Microsoft.ML/Runtime/EntryPoints/InMemoryDataView.cs

@@ -0,0 +1,37 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+// See the LICENSE file in the project root for more information.
+
+using Microsoft.ML.Runtime;
+using Microsoft.ML.Runtime.CommandLine;
+using Microsoft.ML.Runtime.Data;
+using Microsoft.ML.Runtime.EntryPoints;
+
+[assembly: LoadableClass(typeof(void), typeof(InMemoryDataView), null, typeof(SignatureEntryPointModule), "InMemoryDataView")]
+namespace Microsoft.ML.Runtime.EntryPoints
+{
+    public class InMemoryDataView
+    {
+        public sealed class Input
+        {
+            [Argument(ArgumentType.Required, ShortName = "data", HelpText = "Pointer to IDataView in memory", SortOrder = 1)]
+            public IDataView Data;
+        }
+
+        public sealed class Output
+        {
+            [TlcModule.Output(Desc = "The resulting data view", SortOrder = 1)]
+            public IDataView Data;
+        }
+
+        [TlcModule.EntryPoint(Name = "Data.DataViewReference", Desc = "Pass dataview from memory to experiment")]
+        public static Output ImportData(IHostEnvironment env, Input input)
+        {
+            Contracts.CheckValue(env, nameof(env));
+            var host = env.Register("DataViewReference");
+            env.CheckValue(input, nameof(input));
+            EntryPointUtils.CheckInputArgs(host, input);
+            return new Output { Data = input.Data };
+        }
+    }
+}

src/Microsoft.ML/TextLoader.cs

@@ -115,11 +115,10 @@ private class TextLoaderPipelineStep : ILearningPipelineDataStep
             public TextLoaderPipelineStep(Var<IDataView> data)
             {
                 Data = data;
-                Model = null;
             }
 
             public Var<IDataView> Data { get; }
-            public Var<ITransformModel> Model { get; }
+            public Var<ITransformModel> Model => null;
         }
     }
 }