Schema mismatch for feature column 'Features':

Question

Schema mismatch for feature column 'Features': expected Vector, got Vector Parameter name: inputSchema That error occur on following code

 static readonly string _dataPat=Path.Combine(Environment.CurrentDirectory, "Data", "train_data.csv"); 
static void Main(string[] args)
    {

            var mlContext = new MLContext(seed: 0);

        IDataView data = mlContext.Data.LoadFromTextFile<IrisData>(_dataPath, separatorChar: ',', hasHeader: true);

        string featuresColumnName = "Features";

            var pipeline = mlContext.Transforms
                .Concatenate(featuresColumnName,"Class", "Sex", "AgeGroup", "Embarked")
                .Append(mlContext.Clustering.Trainers.KMeans(featuresColumnName, numberOfClusters: 2));

            var model = pipeline.Fit(data);

Error is on line with Code

var model = pipeline.Fit(data);

my class IrisData

public class IrisData
{
    [LoadColumn(0)]
    public string Class;

    [LoadColumn(1)]
    public string Sex;

    [LoadColumn(2)]
    public string AgeGroup;

    [LoadColumn(3)]
    public string Embarked;
}

CSV file in my project

Try putting the second parameter for `Concatenate` to be an array of column names. — Jon, Aug 15 '19 at 19:45
@Jon Now error occur "Could not find input column 'Features' Parameter name: inputSchema'" — Ayesha Sheikh, Aug 16 '19 at 05:19
That error is due to adding csv file may be. I've updated my question and added picture of my csv file in my project — Ayesha Sheikh, Aug 16 '19 at 05:40
Instead of using `Concatenate` try using `FeaturizeText` instead. — Jon, Aug 19 '19 at 23:18

score 0 · Answer 1 · answered Aug 26 '19 at 18:21

Your Features column needs to be a Vector of floats. But you are creating a Vector of strings.

You will need to convert those strings to numbers. One way to do it is to use OneHotEncoding. See https://learn.microsoft.com/en-us/dotnet/machine-learning/how-to-guides/prepare-data-ml-net#work-with-categorical-data

Schema mismatch for feature column 'Features':

1 Answers1