CategoricalCatalog.OneHotEncoding Yöntem

public static Microsoft.ML.Transforms.OneHotEncodingEstimator OneHotEncoding (this Microsoft.ML.TransformsCatalog.CategoricalTransforms catalog, Microsoft.ML.InputOutputColumnPair[] columns, Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind outputKind = Microsoft.ML.Transforms.OneHotEncodingEstimator+OutputKind.Indicator, int maximumNumberOfKeys = 1000000, Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality keyOrdinality = Microsoft.ML.Transforms.ValueToKeyMappingEstimator+KeyOrdinality.ByOccurrence, Microsoft.ML.IDataView keyData = default);

static member OneHotEncoding : Microsoft.ML.TransformsCatalog.CategoricalTransforms * Microsoft.ML.InputOutputColumnPair[] * Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind * int * Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality * Microsoft.ML.IDataView -> Microsoft.ML.Transforms.OneHotEncodingEstimator

<Extension()>
Public Function OneHotEncoding (catalog As TransformsCatalog.CategoricalTransforms, columns As InputOutputColumnPair(), Optional outputKind As OneHotEncodingEstimator.OutputKind = Microsoft.ML.Transforms.OneHotEncodingEstimator+OutputKind.Indicator, Optional maximumNumberOfKeys As Integer = 1000000, Optional keyOrdinality As ValueToKeyMappingEstimator.KeyOrdinality = Microsoft.ML.Transforms.ValueToKeyMappingEstimator+KeyOrdinality.ByOccurrence, Optional keyData As IDataView = Nothing) As OneHotEncodingEstimator

Parametreler

Döndürülenler

Örnekler

using System;
using Microsoft.ML;

namespace Samples.Dynamic.Transforms.Categorical
{
    public static class OneHotEncodingMultiColumn
    {
        public static void Example()
        {
            // 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 mlContext = new MLContext();

            // Create a small dataset as an IEnumerable.
            var samples = new[]
            {
                new DataPoint {Education = "0-5yrs", ZipCode = "98005"},
                new DataPoint {Education = "0-5yrs", ZipCode = "98052"},
                new DataPoint {Education = "6-11yrs", ZipCode = "98005"},
                new DataPoint {Education = "6-11yrs", ZipCode = "98052"},
                new DataPoint {Education = "11-15yrs", ZipCode = "98005"}
            };

            // Convert training data to IDataView.
            IDataView data = mlContext.Data.LoadFromEnumerable(samples);

            // Multi column example: A pipeline for one hot encoding two columns
            // 'Education' and 'ZipCode'.
            var multiColumnKeyPipeline =
                mlContext.Transforms.Categorical.OneHotEncoding(
                    new[]
                    {
                        new InputOutputColumnPair("Education"),
                        new InputOutputColumnPair("ZipCode")
                    });

            // Fit and Transform data.
            IDataView transformedData =
                multiColumnKeyPipeline.Fit(data).Transform(data);

            var convertedData =
                mlContext.Data.CreateEnumerable<TransformedData>(transformedData,
                    true);

            Console.WriteLine(
                "One Hot Encoding of two columns 'Education' and 'ZipCode'.");

            // One Hot Encoding of two columns 'Education' and 'ZipCode'.

            foreach (TransformedData item in convertedData)
                Console.WriteLine("{0}\t\t\t{1}", string.Join(" ", item.Education),
                    string.Join(" ", item.ZipCode));

            // 1 0 0                   1 0
            // 1 0 0                   0 1
            // 0 1 0                   1 0
            // 0 1 0                   0 1
            // 0 0 1                   1 0
        }

        private class DataPoint
        {
            public string Education { get; set; }

            public string ZipCode { get; set; }
        }

        private class TransformedData
        {
            public float[] Education { get; set; }

            public float[] ZipCode { get; set; }
        }
    }
}

Açıklamalar

Tahmin aracına birden çok sütun geçirilirse, tüm sütunlar veriler üzerinden tek bir geçişte işlenir. Bu nedenle, birden çok sütuna sahip bir tahmin aracı belirtmek, her biri tek sütunlu birçok tahmin aracı belirtmekten daha verimlidir.

public static Microsoft.ML.Transforms.OneHotEncodingEstimator OneHotEncoding (this Microsoft.ML.TransformsCatalog.CategoricalTransforms catalog, string outputColumnName, string inputColumnName = default, Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind outputKind = Microsoft.ML.Transforms.OneHotEncodingEstimator+OutputKind.Indicator, int maximumNumberOfKeys = 1000000, Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality keyOrdinality = Microsoft.ML.Transforms.ValueToKeyMappingEstimator+KeyOrdinality.ByOccurrence, Microsoft.ML.IDataView keyData = default);

static member OneHotEncoding : Microsoft.ML.TransformsCatalog.CategoricalTransforms * string * string * Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind * int * Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality * Microsoft.ML.IDataView -> Microsoft.ML.Transforms.OneHotEncodingEstimator

<Extension()>
Public Function OneHotEncoding (catalog As TransformsCatalog.CategoricalTransforms, outputColumnName As String, Optional inputColumnName As String = Nothing, Optional outputKind As OneHotEncodingEstimator.OutputKind = Microsoft.ML.Transforms.OneHotEncodingEstimator+OutputKind.Indicator, Optional maximumNumberOfKeys As Integer = 1000000, Optional keyOrdinality As ValueToKeyMappingEstimator.KeyOrdinality = Microsoft.ML.Transforms.ValueToKeyMappingEstimator+KeyOrdinality.ByOccurrence, Optional keyData As IDataView = Nothing) As OneHotEncodingEstimator

Parametreler

Döndürülenler

Örnekler

using System;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Transforms;

namespace Samples.Dynamic.Transforms.Categorical
{
    public static class OneHotEncoding
    {
        public static void Example()
        {
            // 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 mlContext = new MLContext();

            // Create a small dataset as an IEnumerable.
            var samples = new[]
            {
                new DataPoint {Education = "0-5yrs"},
                new DataPoint {Education = "0-5yrs"},
                new DataPoint {Education = "6-11yrs"},
                new DataPoint {Education = "6-11yrs"},
                new DataPoint {Education = "11-15yrs"}
            };

            // Convert training data to IDataView.
            IDataView data = mlContext.Data.LoadFromEnumerable(samples);

            // A pipeline for one hot encoding the Education column.
            var pipeline = mlContext.Transforms.Categorical.OneHotEncoding(
                "EducationOneHotEncoded", "Education");

            // Fit and transform the data.
            IDataView oneHotEncodedData = pipeline.Fit(data).Transform(data);

            PrintDataColumn(oneHotEncodedData, "EducationOneHotEncoded");

            // We have 3 slots because there are three categories in the
            // 'Education' column.

            // 1 0 0
            // 1 0 0
            // 0 1 0
            // 0 1 0
            // 0 0 1

            // A pipeline for one hot encoding the Education column (using keying).
            var keyPipeline = mlContext.Transforms.Categorical.OneHotEncoding(
                "EducationOneHotEncoded", "Education",
                OneHotEncodingEstimator.OutputKind.Key);

            // Fit and Transform data.
            oneHotEncodedData = keyPipeline.Fit(data).Transform(data);

            var keyEncodedColumn =
                oneHotEncodedData.GetColumn<uint>("EducationOneHotEncoded");

            Console.WriteLine(
                "One Hot Encoding of single column 'Education', with key type " +
                "output.");

            // One Hot Encoding of single column 'Education', with key type output.

            foreach (uint element in keyEncodedColumn)
                Console.WriteLine(element);

            // 1
            // 1
            // 2
            // 2
            // 3
        }

        private static void PrintDataColumn(IDataView transformedData,
            string columnName)
        {
            var countSelectColumn = transformedData.GetColumn<float[]>(
                transformedData.Schema[columnName]);

            foreach (var row in countSelectColumn)
            {
                for (var i = 0; i < row.Length; i++)
                    Console.Write($"{row[i]}\t");

                Console.WriteLine();
            }
        }

        private class DataPoint
        {
            public string Education { get; set; }
        }
    }
}