使用 ML.NET 的动态训练/测试类

Question

这是Dynamic classes/objects ML.net's PredictionMoadel<TInput, TOutput> Train()问题的后续

我的系统在编译时无法使用预定义的类，因此我尝试将动态类提供给 ML.NET，如下所示

    // 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);
    }

并得到错误：“在'System.Object'类型中找不到名称为'Name'的字段或属性”。我尝试使用反射生成类只是为了遇到同样的问题。

有解决方法吗？谢谢

Answer 1

对于那些尝试这样做的人，我有一个有效的解决方案，可以创建模式并可用于动态训练数据。

首先，从我这里的其他答案中获取 DynamicTypeProperty 和 DynamicType 的代码。

以下代码将动态创建架构：

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);

然后，您需要使用所需数据创建列表。这是按如下方式完成的：

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.

然后你需要用数据创建一个 IDataView，这需要使用反射，否则训练师不会推断出正确的类型。

            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});

然后，您应该能够运行整个trainData管道。

祝你好运。