c# - dynamic training/test classes with ML.NET

Question

This is a follow up from the question here Dynamic classes/objects ML.net's PredictionMoadel<TInput, TOutput> Train()

My system cannot use a predefined class at compile time, therefore I tried to feed a dynamic class into ML.NET like below

    // field data type
    public class Field
    {
        public string FieldName { get; set; }
        public Type FieldType { get; set; }
    }

    // dynamic class helper
    public class DynamicClass : DynamicObject
    {
        private readonly Dictionary<string, KeyValuePair<Type, object>> _fields;

        public DynamicClass(List<Field> fields)
        {
            _fields = new Dictionary<string, KeyValuePair<Type, object>>();
            fields.ForEach(x => _fields.Add(x.FieldName,
                new KeyValuePair<Type, object>(x.FieldType, null)));
        }

        public override bool TrySetMember(SetMemberBinder binder, object value)
        {
            if (_fields.ContainsKey(binder.Name))
            {
                var type = _fields[binder.Name].Key;
                if (value.GetType() == type)
                {
                    _fields[binder.Name] = new KeyValuePair<Type, object>(type, value);
                    return true;
                }
                else throw new Exception("Value " + value + " is not of type " + type.Name);
            }
            return false;
        }

        public override bool TryGetMember(GetMemberBinder binder, out object result)
        {
            result = _fields[binder.Name].Value;
            return true;
        }
    }

    private static void Main(string[] args)
    {
        var fields = new List<Field>
        {
            new Field {FieldName = "Name", FieldType = typeof(string)},
            new Field {FieldName = "Income", FieldType = typeof(float)}
        };

        dynamic obj1 = new DynamicClass(fields);
        obj1.Name = "John";
        obj1.Income = 100f;

        dynamic obj2 = new DynamicClass(fields);
        obj2.Name = "Alice";
        obj2.Income = 200f;

        var trainingData = new List<dynamic> {obj1, obj2};

        var env = new LocalEnvironment();
        var schemaDef = SchemaDefinition.Create(typeof(DynamicClass));
        schemaDef.Add(new SchemaDefinition.Column(null, "Name", TextType.Instance));
        schemaDef.Add(new SchemaDefinition.Column(null, "Income", NumberType.R4));
        var trainDataView = env.CreateStreamingDataView(trainingData, schemaDef);

        var pipeline = new CategoricalEstimator(env, "Name")
            .Append(new ConcatEstimator(env, "Features", "Name"))
            .Append(new FastTreeRegressionTrainer(env, "Income", "Features"));

        var model = pipeline.Fit(trainDataView);
    }

and got the error: "'No field or property with name 'Name' found in type 'System.Object'". I tried generating the class using Reflection only to run into the same problem.

Is there a workaround? Thanks

Answer 1

For those attempting to do this, I have a working solution that creates the schema and can be used to train data dynamically.

First, grab the code for DynamicTypeProperty and DynamicType from my other answer here.

The following code will create a schema dynamically:

var properties = new List<DynamicTypeProperty>()
{
    new DynamicTypeProperty("SepalLength", typeof(float)),
    new DynamicTypeProperty("SepalWidth", typeof(float)),
    new DynamicTypeProperty("PetalLength", typeof(float)),
    new DynamicTypeProperty("PetalWidth", typeof(float)),
};

// create the new type
var dynamicType = DynamicType.CreateDynamicType(properties);
var schema = SchemaDefinition.Create(dynamicType);

You'll then need to create list with the required data. This is done as follows:

var dynamicList = DynamicType.CreateDynamicList(dynamicType);

// get an action that will add to the list
var addAction = DynamicType.GetAddAction(dynamicList);

// call the action, with an object[] containing parameters in exact order added
addAction.Invoke(new object[] {1.1, 2.2, 3.3, 4.4});
// call add action again for each row.

Then you'll need to create an IDataView with the data, this requires using reflection, or the trainers won't infer the correct type.

            var mlContext = new MLContext();
            var dataType = mlContext.Data.GetType();
            var loadMethodGeneric = dataType.GetMethods().First(method => method.Name =="LoadFromEnumerable" && method.IsGenericMethod);
            var loadMethod = loadMethodGeneric.MakeGenericMethod(dynamicType);
            var trainData = (IDataView) loadMethod.Invoke(mlContext.Data, new[] {dynamicList, schema});

You then, should be able to run the trainData through your pipeline.

Good luck.