DataOperationsCatalog.xml

<Type Name="DataOperationsCatalog" FullName="Microsoft.ML.DataOperationsCatalog">
  <TypeSignature Language="C#" Value="public sealed class DataOperationsCatalog" />
  <TypeSignature Language="ILAsm" Value=".class public auto ansi sealed beforefieldinit DataOperationsCatalog extends System.Object" />
  <TypeSignature Language="DocId" Value="T:Microsoft.ML.DataOperationsCatalog" />
  <TypeSignature Language="VB.NET" Value="Public NotInheritable Class DataOperationsCatalog" />
  <TypeSignature Language="F#" Value="type DataOperationsCatalog = class" />
  <AssemblyInfo>
    <AssemblyName>Microsoft.ML.Data</AssemblyName>
    <AssemblyVersion>1.0.0.0</AssemblyVersion>
  </AssemblyInfo>
  <Base>
    <BaseTypeName>System.Object</BaseTypeName>
  </Base>
  <Interfaces />
  <Docs>
    <summary>
            Class used to create components that operate on data, but are not part of the model training pipeline.
            Includes components to load, save, cache, filter, shuffle, and split data.
            </summary>
    <remarks>To be added.</remarks>
  </Docs>
  <Members>
    <Member MemberName="BootstrapSample">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView BootstrapSample (Microsoft.ML.IDataView input, int? seed = default, bool complement = false);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView BootstrapSample(class Microsoft.ML.IDataView input, valuetype System.Nullable`1&lt;int32&gt; seed, bool complement) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.BootstrapSample(Microsoft.ML.IDataView,System.Nullable{System.Int32},System.Boolean)" />
      <MemberSignature Language="VB.NET" Value="Public Function BootstrapSample (input As IDataView, Optional seed As Nullable(Of Integer) = Nothing, Optional complement As Boolean = false) As IDataView" />
      <MemberSignature Language="F#" Value="member this.BootstrapSample : Microsoft.ML.IDataView * Nullable&lt;int&gt; * bool -&gt; Microsoft.ML.IDataView" Usage="dataOperationsCatalog.BootstrapSample (input, seed, complement)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="input" Type="Microsoft.ML.IDataView" />
        <Parameter Name="seed" Type="System.Nullable&lt;System.Int32&gt;" />
        <Parameter Name="complement" Type="System.Boolean" />
      </Parameters>
      <Docs>
        <param name="input">The input data.</param>
        <param name="seed">The random seed. If unspecified, the random state will be instead derived from the <see cref="T:Microsoft.ML.MLContext" />.</param>
        <param name="complement">Whether this is the out-of-bag sample, that is, all those rows that are not selected by the transform.
            Can be used to create a complementary pair of samples by using the same seed.</param>
        <summary>
            Take an approximate bootstrap sample of <paramref name="input" />.
            </summary>
        <returns>To be added.</returns>
        <remarks>
            This sampler is a streaming version of <a href="https://en.wikipedia.org/wiki/Bootstrapping_(statistics)">bootstrap resampling</a>.
            Instead of taking the whole dataset into memory and resampling, <see cref="M:Microsoft.ML.DataOperationsCatalog.BootstrapSample(Microsoft.ML.IDataView,System.Nullable{System.Int32},System.Boolean)" /> streams through the dataset and
            uses a <a href="https://en.wikipedia.org/wiki/Poisson_distribution">Poisson</a>(1) distribution to select the number of times a
            given row will be added to the sample. The <paramref name="complement" /> parameter allows for the creation of a bootstap sample
            and complementary out-of-bag sample by using the same <paramref name="seed" />.
            </remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[BootstrapSample](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/BootstrapSample.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="Cache">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView Cache (Microsoft.ML.IDataView input, params string[] columnsToPrefetch);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView Cache(class Microsoft.ML.IDataView input, string[] columnsToPrefetch) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.Cache(Microsoft.ML.IDataView,System.String[])" />
      <MemberSignature Language="VB.NET" Value="Public Function Cache (input As IDataView, ParamArray columnsToPrefetch As String()) As IDataView" />
      <MemberSignature Language="F#" Value="member this.Cache : Microsoft.ML.IDataView * string[] -&gt; Microsoft.ML.IDataView" Usage="dataOperationsCatalog.Cache (input, columnsToPrefetch)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="input" Type="Microsoft.ML.IDataView" />
        <Parameter Name="columnsToPrefetch" Type="System.String[]">
          <Attributes>
            <Attribute>
              <AttributeName Language="C#">[System.ParamArray]</AttributeName>
              <AttributeName Language="F#">[&lt;System.ParamArray&gt;]</AttributeName>
            </Attribute>
          </Attributes>
        </Parameter>
      </Parameters>
      <Docs>
        <param name="input">The input data.</param>
        <param name="columnsToPrefetch">The columns that must be cached whenever anything is cached. An empty array or null
            value means that columns are cached upon their first access.</param>
        <summary>
            Creates a lazy in-memory cache of <paramref name="input" />.
            </summary>
        <returns>To be added.</returns>
        <remarks>
            Caching happens per-column. A column is only cached when it is first accessed.
            In addition, <paramref name="columnsToPrefetch" /> are considered 'always needed', so these columns
            will be cached the first time any data is requested.
            </remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[Cache](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/Cache.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="CreateEnumerable&lt;TRow&gt;">
      <MemberSignature Language="C#" Value="public System.Collections.Generic.IEnumerable&lt;TRow&gt; CreateEnumerable&lt;TRow&gt; (Microsoft.ML.IDataView data, bool reuseRowObject, bool ignoreMissingColumns = false, Microsoft.ML.Data.SchemaDefinition schemaDefinition = default) where TRow : class, new();" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class System.Collections.Generic.IEnumerable`1&lt;!!TRow&gt; CreateEnumerable&lt;class .ctor TRow&gt;(class Microsoft.ML.IDataView data, bool reuseRowObject, bool ignoreMissingColumns, class Microsoft.ML.Data.SchemaDefinition schemaDefinition) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.CreateEnumerable``1(Microsoft.ML.IDataView,System.Boolean,System.Boolean,Microsoft.ML.Data.SchemaDefinition)" />
      <MemberSignature Language="VB.NET" Value="Public Function CreateEnumerable(Of TRow As {Class, New}) (data As IDataView, reuseRowObject As Boolean, Optional ignoreMissingColumns As Boolean = false, Optional schemaDefinition As SchemaDefinition = Nothing) As IEnumerable(Of TRow)" />
      <MemberSignature Language="F#" Value="member this.CreateEnumerable : Microsoft.ML.IDataView * bool * bool * Microsoft.ML.Data.SchemaDefinition -&gt; seq&lt;'Row (requires 'Row : null and 'Row : (new : unit -&gt; 'Row))&gt; (requires 'Row : null and 'Row : (new : unit -&gt; 'Row))" Usage="dataOperationsCatalog.CreateEnumerable (data, reuseRowObject, ignoreMissingColumns, schemaDefinition)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>System.Collections.Generic.IEnumerable&lt;TRow&gt;</ReturnType>
      </ReturnValue>
      <TypeParameters>
        <TypeParameter Name="TRow">
          <Constraints>
            <ParameterAttribute>DefaultConstructorConstraint</ParameterAttribute>
            <ParameterAttribute>ReferenceTypeConstraint</ParameterAttribute>
          </Constraints>
        </TypeParameter>
      </TypeParameters>
      <Parameters>
        <Parameter Name="data" Type="Microsoft.ML.IDataView" />
        <Parameter Name="reuseRowObject" Type="System.Boolean" />
        <Parameter Name="ignoreMissingColumns" Type="System.Boolean" />
        <Parameter Name="schemaDefinition" Type="Microsoft.ML.Data.SchemaDefinition" />
      </Parameters>
      <Docs>
        <typeparam name="TRow">The user-defined item type.</typeparam>
        <param name="data">The underlying data view.</param>
        <param name="reuseRowObject">Whether to return the same object on every row, or allocate a new one per row.</param>
        <param name="ignoreMissingColumns">Whether to ignore the case when a requested column is not present in the data view.</param>
        <param name="schemaDefinition">Optional user-provided schema definition. If it is not present, the schema is inferred from the definition of T.</param>
        <summary>
            Convert an <see cref="T:Microsoft.ML.IDataView" /> into a strongly-typed <see cref="T:System.Collections.Generic.IEnumerable`1" />.
            </summary>
        <returns>The <see cref="T:System.Collections.Generic.IEnumerable`1" /> that holds the data in <paramref name="data" />. It can be enumerated multiple times.</returns>
        <remarks>To be added.</remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[CreateEnumerable](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/DataViewEnumerable.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="CrossValidationSplit">
      <MemberSignature Language="C#" Value="public System.Collections.Generic.IReadOnlyList&lt;Microsoft.ML.DataOperationsCatalog.TrainTestData&gt; CrossValidationSplit (Microsoft.ML.IDataView data, int numberOfFolds = 5, string samplingKeyColumnName = default, int? seed = default);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class System.Collections.Generic.IReadOnlyList`1&lt;valuetype Microsoft.ML.DataOperationsCatalog/TrainTestData&gt; CrossValidationSplit(class Microsoft.ML.IDataView data, int32 numberOfFolds, string samplingKeyColumnName, valuetype System.Nullable`1&lt;int32&gt; seed) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.CrossValidationSplit(Microsoft.ML.IDataView,System.Int32,System.String,System.Nullable{System.Int32})" />
      <MemberSignature Language="VB.NET" Value="Public Function CrossValidationSplit (data As IDataView, Optional numberOfFolds As Integer = 5, Optional samplingKeyColumnName As String = Nothing, Optional seed As Nullable(Of Integer) = Nothing) As IReadOnlyList(Of DataOperationsCatalog.TrainTestData)" />
      <MemberSignature Language="F#" Value="member this.CrossValidationSplit : Microsoft.ML.IDataView * int * string * Nullable&lt;int&gt; -&gt; System.Collections.Generic.IReadOnlyList&lt;Microsoft.ML.DataOperationsCatalog.TrainTestData&gt;" Usage="dataOperationsCatalog.CrossValidationSplit (data, numberOfFolds, samplingKeyColumnName, seed)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>System.Collections.Generic.IReadOnlyList&lt;Microsoft.ML.DataOperationsCatalog+TrainTestData&gt;</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="data" Type="Microsoft.ML.IDataView" />
        <Parameter Name="numberOfFolds" Type="System.Int32" />
        <Parameter Name="samplingKeyColumnName" Type="System.String" />
        <Parameter Name="seed" Type="System.Nullable&lt;System.Int32&gt;" />
      </Parameters>
      <Docs>
        <param name="data">The dataset to split.</param>
        <param name="numberOfFolds">Number of cross-validation folds.</param>
        <param name="samplingKeyColumnName">Name of a column to use for grouping rows. If two examples share the same value of the <paramref name="samplingKeyColumnName" />,
            they are guaranteed to appear in the same subset (train or test). This can be used to ensure no label leakage from the train to the test set.
            Note that when performing a Ranking Experiment, the <paramref name="samplingKeyColumnName" /> must be the GroupId column.
            If <see langword="null" /> no row grouping will be performed.</param>
        <param name="seed">Seed for the random number generator used to select rows for cross-validation folds.</param>
        <summary>
            Split the dataset into cross-validation folds of train set and test set.
            Respects the <paramref name="samplingKeyColumnName" /> if provided.
            </summary>
        <returns>To be added.</returns>
        <remarks>To be added.</remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[CrossValidationSplit](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/CrossValidationSplit.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="FilterRowsByColumn">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView FilterRowsByColumn (Microsoft.ML.IDataView input, string columnName, double lowerBound = -∞, double upperBound = ∞);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView FilterRowsByColumn(class Microsoft.ML.IDataView input, string columnName, float64 lowerBound, float64 upperBound) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.FilterRowsByColumn(Microsoft.ML.IDataView,System.String,System.Double,System.Double)" />
      <MemberSignature Language="VB.NET" Value="Public Function FilterRowsByColumn (input As IDataView, columnName As String, Optional lowerBound As Double = -∞, Optional upperBound As Double = ∞) As IDataView" />
      <MemberSignature Language="F#" Value="member this.FilterRowsByColumn : Microsoft.ML.IDataView * string * double * double -&gt; Microsoft.ML.IDataView" Usage="dataOperationsCatalog.FilterRowsByColumn (input, columnName, lowerBound, upperBound)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="input" Type="Microsoft.ML.IDataView" />
        <Parameter Name="columnName" Type="System.String" />
        <Parameter Name="lowerBound" Type="System.Double" />
        <Parameter Name="upperBound" Type="System.Double" />
      </Parameters>
      <Docs>
        <param name="input">The input data.</param>
        <param name="columnName">The name of a column to use for filtering.</param>
        <param name="lowerBound">The inclusive lower bound.</param>
        <param name="upperBound">The exclusive upper bound.</param>
        <summary>
            Filter the dataset by the values of a numeric column.
            </summary>
        <returns>To be added.</returns>
        <remarks>
            Keep only those rows that satisfy the range condition: the value of column <paramref name="columnName" />
            must be between <paramref name="lowerBound" /> (inclusive) and <paramref name="upperBound" /> (exclusive).
            </remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[FilterRowsByColumn](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/FilterRowsByColumn.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="FilterRowsByKeyColumnFraction">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView FilterRowsByKeyColumnFraction (Microsoft.ML.IDataView input, string columnName, double lowerBound = 0, double upperBound = 1);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView FilterRowsByKeyColumnFraction(class Microsoft.ML.IDataView input, string columnName, float64 lowerBound, float64 upperBound) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.FilterRowsByKeyColumnFraction(Microsoft.ML.IDataView,System.String,System.Double,System.Double)" />
      <MemberSignature Language="VB.NET" Value="Public Function FilterRowsByKeyColumnFraction (input As IDataView, columnName As String, Optional lowerBound As Double = 0, Optional upperBound As Double = 1) As IDataView" />
      <MemberSignature Language="F#" Value="member this.FilterRowsByKeyColumnFraction : Microsoft.ML.IDataView * string * double * double -&gt; Microsoft.ML.IDataView" Usage="dataOperationsCatalog.FilterRowsByKeyColumnFraction (input, columnName, lowerBound, upperBound)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="input" Type="Microsoft.ML.IDataView" />
        <Parameter Name="columnName" Type="System.String" />
        <Parameter Name="lowerBound" Type="System.Double" />
        <Parameter Name="upperBound" Type="System.Double" />
      </Parameters>
      <Docs>
        <param name="input">The input data.</param>
        <param name="columnName">The name of a column to use for filtering.</param>
        <param name="lowerBound">The inclusive lower bound.</param>
        <param name="upperBound">The exclusive upper bound.</param>
        <summary>
            Filter the dataset by the values of a <see cref="T:Microsoft.ML.Data.KeyDataViewType" /> column.
            </summary>
        <returns>To be added.</returns>
        <remarks>
            Keep only those rows that satisfy the range condition: the value of a key column <paramref name="columnName" />
            (treated as a fraction of the entire key range) must be between <paramref name="lowerBound" /> (inclusive) and <paramref name="upperBound" /> (exclusive).
            This filtering is useful if the <paramref name="columnName" /> is a key column obtained by some 'stable randomization',
            for example, hashing.
            </remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[FilterRowsByKeyColumnFraction](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/FilterRowsByKeyColumnFraction.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="FilterRowsByMissingValues">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView FilterRowsByMissingValues (Microsoft.ML.IDataView input, params string[] columns);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView FilterRowsByMissingValues(class Microsoft.ML.IDataView input, string[] columns) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.FilterRowsByMissingValues(Microsoft.ML.IDataView,System.String[])" />
      <MemberSignature Language="VB.NET" Value="Public Function FilterRowsByMissingValues (input As IDataView, ParamArray columns As String()) As IDataView" />
      <MemberSignature Language="F#" Value="member this.FilterRowsByMissingValues : Microsoft.ML.IDataView * string[] -&gt; Microsoft.ML.IDataView" Usage="dataOperationsCatalog.FilterRowsByMissingValues (input, columns)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="input" Type="Microsoft.ML.IDataView" />
        <Parameter Name="columns" Type="System.String[]">
          <Attributes>
            <Attribute>
              <AttributeName Language="C#">[System.ParamArray]</AttributeName>
              <AttributeName Language="F#">[&lt;System.ParamArray&gt;]</AttributeName>
            </Attribute>
          </Attributes>
        </Parameter>
      </Parameters>
      <Docs>
        <param name="input">The input data.</param>
        <param name="columns">Name of the columns to filter on. If a row is has a missing value in any of
            these columns, it will be dropped from the dataset.</param>
        <summary>
            Drop rows where any column in <paramref name="columns" /> contains a missing value.
            </summary>
        <returns>To be added.</returns>
        <remarks>To be added.</remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[FilterRowsByMissingValues](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/FilterRowsByMissingValues.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="LoadFromEnumerable&lt;TRow&gt;">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView LoadFromEnumerable&lt;TRow&gt; (System.Collections.Generic.IEnumerable&lt;TRow&gt; data, Microsoft.ML.Data.SchemaDefinition schemaDefinition = default) where TRow : class;" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView LoadFromEnumerable&lt;class TRow&gt;(class System.Collections.Generic.IEnumerable`1&lt;!!TRow&gt; data, class Microsoft.ML.Data.SchemaDefinition schemaDefinition) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.LoadFromEnumerable``1(System.Collections.Generic.IEnumerable{``0},Microsoft.ML.Data.SchemaDefinition)" />
      <MemberSignature Language="VB.NET" Value="Public Function LoadFromEnumerable(Of TRow As Class) (data As IEnumerable(Of TRow), Optional schemaDefinition As SchemaDefinition = Nothing) As IDataView" />
      <MemberSignature Language="F#" Value="member this.LoadFromEnumerable : seq&lt;'Row (requires 'Row : null)&gt; * Microsoft.ML.Data.SchemaDefinition -&gt; Microsoft.ML.IDataView (requires 'Row : null)" Usage="dataOperationsCatalog.LoadFromEnumerable (data, schemaDefinition)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <TypeParameters>
        <TypeParameter Name="TRow">
          <Constraints>
            <ParameterAttribute>ReferenceTypeConstraint</ParameterAttribute>
          </Constraints>
        </TypeParameter>
      </TypeParameters>
      <Parameters>
        <Parameter Name="data" Type="System.Collections.Generic.IEnumerable&lt;TRow&gt;" />
        <Parameter Name="schemaDefinition" Type="Microsoft.ML.Data.SchemaDefinition" />
      </Parameters>
      <Docs>
        <typeparam name="TRow">The user-defined item type.</typeparam>
        <param name="data">The enumerable data containing type <typeparamref name="TRow" /> to convert to a <see cref="T:Microsoft.ML.IDataView" />.</param>
        <param name="schemaDefinition">The optional schema definition of the data view to create. If <c>null</c>,
             the schema definition is inferred from <typeparamref name="TRow" />.</param>
        <summary>
             Create a new <see cref="T:Microsoft.ML.IDataView" /> over an enumerable of the items of user-defined type.
             The user maintains ownership of the <paramref name="data" /> and the resulting data view will
             never alter the contents of the <paramref name="data" />.
             Since <see cref="T:Microsoft.ML.IDataView" /> is assumed to be immutable, the user is expected to support
             multiple enumerations of the <paramref name="data" /> that would return the same results, unless
             the user knows that the data will only be cursored once.
            
             One typical usage for streaming data view could be: create the data view that lazily loads data
             as needed, then apply pre-trained transformations to it and cursor through it for transformation
             results.
             </summary>
        <returns>The constructed <see cref="T:Microsoft.ML.IDataView" />.</returns>
        <remarks>To be added.</remarks>
        <example>
          <format type="text/markdown"><![CDATA[
             [!code-csharp[LoadFromEnumerable](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/LoadFromEnumerable.cs)]
             ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="LoadFromEnumerable&lt;TRow&gt;">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView LoadFromEnumerable&lt;TRow&gt; (System.Collections.Generic.IEnumerable&lt;TRow&gt; data, Microsoft.ML.DataViewSchema schema) where TRow : class;" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView LoadFromEnumerable&lt;class TRow&gt;(class System.Collections.Generic.IEnumerable`1&lt;!!TRow&gt; data, class Microsoft.ML.DataViewSchema schema) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.LoadFromEnumerable``1(System.Collections.Generic.IEnumerable{``0},Microsoft.ML.DataViewSchema)" />
      <MemberSignature Language="VB.NET" Value="Public Function LoadFromEnumerable(Of TRow As Class) (data As IEnumerable(Of TRow), schema As DataViewSchema) As IDataView" />
      <MemberSignature Language="F#" Value="member this.LoadFromEnumerable : seq&lt;'Row (requires 'Row : null)&gt; * Microsoft.ML.DataViewSchema -&gt; Microsoft.ML.IDataView (requires 'Row : null)" Usage="dataOperationsCatalog.LoadFromEnumerable (data, schema)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <TypeParameters>
        <TypeParameter Name="TRow">
          <Constraints>
            <ParameterAttribute>ReferenceTypeConstraint</ParameterAttribute>
          </Constraints>
        </TypeParameter>
      </TypeParameters>
      <Parameters>
        <Parameter Name="data" Type="System.Collections.Generic.IEnumerable&lt;TRow&gt;" />
        <Parameter Name="schema" Type="Microsoft.ML.DataViewSchema" />
      </Parameters>
      <Docs>
        <typeparam name="TRow">The user-defined item type.</typeparam>
        <param name="data">The enumerable data containing type <typeparamref name="TRow" /> to convert to an <see cref="T:Microsoft.ML.IDataView" />.</param>
        <param name="schema">The schema of the returned <see cref="T:Microsoft.ML.IDataView" />.</param>
        <summary>
            Create a new <see cref="T:Microsoft.ML.IDataView" /> over an enumerable of the items of user-defined type using the provided <see cref="T:Microsoft.ML.DataViewSchema" />,
            which might contain more information about the schema than the type can capture.
            </summary>
        <returns>An <see cref="T:Microsoft.ML.IDataView" /> with the given <paramref name="schema" />.</returns>
        <remarks>
            The user maintains ownership of the <paramref name="data" /> and the resulting data view will
            never alter the contents of the <paramref name="data" />.
            Since <see cref="T:Microsoft.ML.IDataView" /> is assumed to be immutable, the user is expected to support
            multiple enumerations of the <paramref name="data" /> that would return the same results, unless
            the user knows that the data will only be cursored once.
            One typical usage for streaming data view could be: create the data view that lazily loads data
            as needed, then apply pre-trained transformations to it and cursor through it for transformation
            results.
            One practical usage of this would be to supply the feature column names through the <see cref="T:Microsoft.ML.DataViewSchema.Annotations" />.
            </remarks>
      </Docs>
    </Member>
    <Member MemberName="ShuffleRows">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView ShuffleRows (Microsoft.ML.IDataView input, int? seed = default, int shufflePoolSize = 1000, bool shuffleSource = true);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView ShuffleRows(class Microsoft.ML.IDataView input, valuetype System.Nullable`1&lt;int32&gt; seed, int32 shufflePoolSize, bool shuffleSource) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.ShuffleRows(Microsoft.ML.IDataView,System.Nullable{System.Int32},System.Int32,System.Boolean)" />
      <MemberSignature Language="VB.NET" Value="Public Function ShuffleRows (input As IDataView, Optional seed As Nullable(Of Integer) = Nothing, Optional shufflePoolSize As Integer = 1000, Optional shuffleSource As Boolean = true) As IDataView" />
      <MemberSignature Language="F#" Value="member this.ShuffleRows : Microsoft.ML.IDataView * Nullable&lt;int&gt; * int * bool -&gt; Microsoft.ML.IDataView" Usage="dataOperationsCatalog.ShuffleRows (input, seed, shufflePoolSize, shuffleSource)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="input" Type="Microsoft.ML.IDataView" />
        <Parameter Name="seed" Type="System.Nullable&lt;System.Int32&gt;" />
        <Parameter Name="shufflePoolSize" Type="System.Int32" />
        <Parameter Name="shuffleSource" Type="System.Boolean" />
      </Parameters>
      <Docs>
        <param name="input">The input data.</param>
        <param name="seed">The random seed. If unspecified, the random state will be instead derived from the <see cref="T:Microsoft.ML.MLContext" />.</param>
        <param name="shufflePoolSize">The number of rows to hold in the pool. Setting this to 1 will turn off pool shuffling and
            <see cref="M:Microsoft.ML.DataOperationsCatalog.ShuffleRows(Microsoft.ML.IDataView,System.Nullable{System.Int32},System.Int32,System.Boolean)" /> will only perform a shuffle by reading <paramref name="input" /> in a random order.</param>
        <param name="shuffleSource">If <see langword="false" />, the transform will not attempt to read <paramref name="input" /> in a random order and only use
            pooling to shuffle. This parameter has no effect if the <see cref="P:Microsoft.ML.IDataView.CanShuffle" /> property of <paramref name="input" /> is <see langword="false" />.
            </param>
        <summary>
            Shuffle the rows of <paramref name="input" />.
            </summary>
        <returns>To be added.</returns>
        <remarks>
          <see cref="M:Microsoft.ML.DataOperationsCatalog.ShuffleRows(Microsoft.ML.IDataView,System.Nullable{System.Int32},System.Int32,System.Boolean)" /> will shuffle the rows of any input <see cref="T:Microsoft.ML.IDataView" /> using a streaming approach.
            In order to not load the entire dataset in memory, a pool of <paramref name="shufflePoolSize" /> rows will be used
            to randomly select rows to output. The pool is constructed from the first <paramref name="shufflePoolSize" /> rows
            in <paramref name="input" />. Rows will then be randomly yielded from the pool and replaced with the next row from <paramref name="input" />
            until all the rows have been yielded, resulting in a new <see cref="T:Microsoft.ML.IDataView" /> of the same size as <paramref name="input" />
            but with the rows in a randomized order.
            If the <see cref="P:Microsoft.ML.IDataView.CanShuffle" /> property of <paramref name="input" /> is true, then it will also be read into the
            pool in a random order, offering two sources of randomness.
            </remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[ShuffleRows](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/ShuffleRows.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="SkipRows">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView SkipRows (Microsoft.ML.IDataView input, long count);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView SkipRows(class Microsoft.ML.IDataView input, int64 count) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.SkipRows(Microsoft.ML.IDataView,System.Int64)" />
      <MemberSignature Language="VB.NET" Value="Public Function SkipRows (input As IDataView, count As Long) As IDataView" />
      <MemberSignature Language="F#" Value="member this.SkipRows : Microsoft.ML.IDataView * int64 -&gt; Microsoft.ML.IDataView" Usage="dataOperationsCatalog.SkipRows (input, count)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="input" Type="Microsoft.ML.IDataView" />
        <Parameter Name="count" Type="System.Int64" />
      </Parameters>
      <Docs>
        <param name="input">The input data.</param>
        <param name="count">Number of rows to skip.</param>
        <summary>
            Skip <paramref name="count" /> rows in <paramref name="input" />.
            </summary>
        <returns>To be added.</returns>
        <remarks>
            Skips the first <paramref name="count" /> rows from <paramref name="input" /> and returns an <see cref="T:Microsoft.ML.IDataView" /> with all other rows.
            </remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[SkipRows](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/SkipRows.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="TakeRows">
      <MemberSignature Language="C#" Value="public Microsoft.ML.IDataView TakeRows (Microsoft.ML.IDataView input, long count);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance class Microsoft.ML.IDataView TakeRows(class Microsoft.ML.IDataView input, int64 count) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.TakeRows(Microsoft.ML.IDataView,System.Int64)" />
      <MemberSignature Language="VB.NET" Value="Public Function TakeRows (input As IDataView, count As Long) As IDataView" />
      <MemberSignature Language="F#" Value="member this.TakeRows : Microsoft.ML.IDataView * int64 -&gt; Microsoft.ML.IDataView" Usage="dataOperationsCatalog.TakeRows (input, count)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.IDataView</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="input" Type="Microsoft.ML.IDataView" />
        <Parameter Name="count" Type="System.Int64" />
      </Parameters>
      <Docs>
        <param name="input">The input data.</param>
        <param name="count">Number of rows to take.</param>
        <summary>
            Take <paramref name="count" /> rows from <paramref name="input" />.
            </summary>
        <returns>To be added.</returns>
        <remarks>
            Returns returns an <see cref="T:Microsoft.ML.IDataView" /> with the first <paramref name="count" /> rows from <paramref name="input" />.
            </remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[TakeRows](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/TakeRows.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
    <Member MemberName="TrainTestSplit">
      <MemberSignature Language="C#" Value="public Microsoft.ML.DataOperationsCatalog.TrainTestData TrainTestSplit (Microsoft.ML.IDataView data, double testFraction = 0.1, string samplingKeyColumnName = default, int? seed = default);" />
      <MemberSignature Language="ILAsm" Value=".method public hidebysig instance valuetype Microsoft.ML.DataOperationsCatalog/TrainTestData TrainTestSplit(class Microsoft.ML.IDataView data, float64 testFraction, string samplingKeyColumnName, valuetype System.Nullable`1&lt;int32&gt; seed) cil managed" />
      <MemberSignature Language="DocId" Value="M:Microsoft.ML.DataOperationsCatalog.TrainTestSplit(Microsoft.ML.IDataView,System.Double,System.String,System.Nullable{System.Int32})" />
      <MemberSignature Language="VB.NET" Value="Public Function TrainTestSplit (data As IDataView, Optional testFraction As Double = 0.1, Optional samplingKeyColumnName As String = Nothing, Optional seed As Nullable(Of Integer) = Nothing) As DataOperationsCatalog.TrainTestData" />
      <MemberSignature Language="F#" Value="member this.TrainTestSplit : Microsoft.ML.IDataView * double * string * Nullable&lt;int&gt; -&gt; Microsoft.ML.DataOperationsCatalog.TrainTestData" Usage="dataOperationsCatalog.TrainTestSplit (data, testFraction, samplingKeyColumnName, seed)" />
      <MemberType>Method</MemberType>
      <AssemblyInfo>
        <AssemblyName>Microsoft.ML.Data</AssemblyName>
        <AssemblyVersion>1.0.0.0</AssemblyVersion>
      </AssemblyInfo>
      <ReturnValue>
        <ReturnType>Microsoft.ML.DataOperationsCatalog+TrainTestData</ReturnType>
      </ReturnValue>
      <Parameters>
        <Parameter Name="data" Type="Microsoft.ML.IDataView" />
        <Parameter Name="testFraction" Type="System.Double" />
        <Parameter Name="samplingKeyColumnName" Type="System.String" />
        <Parameter Name="seed" Type="System.Nullable&lt;System.Int32&gt;" />
      </Parameters>
      <Docs>
        <param name="data">The dataset to split.</param>
        <param name="testFraction">The fraction of data to go into the test set.</param>
        <param name="samplingKeyColumnName">Name of a column to use for grouping rows. If two examples share the same value of the <paramref name="samplingKeyColumnName" />,
            they are guaranteed to appear in the same subset (train or test). This can be used to ensure no label leakage from the train to the test set.
            Note that when performing a Ranking Experiment, the <paramref name="samplingKeyColumnName" /> must be the GroupId column.
            If <see langword="null" /> no row grouping will be performed.</param>
        <param name="seed">Seed for the random number generator used to select rows for the train-test split.</param>
        <summary>
            Split the dataset into the train set and test set according to the given fraction.
            Respects the <paramref name="samplingKeyColumnName" /> if provided.
            </summary>
        <returns>To be added.</returns>
        <remarks>To be added.</remarks>
        <example>
          <format type="text/markdown"><![CDATA[
            [!code-csharp[TrainTestSplit](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/DataOperations/TrainTestSplit.cs)]
            ]]></format>
        </example>
      </Docs>
    </Member>
  </Members>
</Type>