public void Save_Model_Test_Json()
{
Tennis t = new Tennis
{
Humidity = Humidity.Normal,
Outlook = Outlook.Overcast,
Temperature = Temperature.Cool,
Windy = true
};
var model = (NeuralNetworkModel)BaseSupervised.Prediction <Tennis>(
new NeuralNetworkGenerator(),
Tennis.GetData(),
t,
p => p.Play
);
var file = GetPath();
Register.Type <Tennis>();
var model2 = SaveAndLoadJson(model);
Assert.Equal(model.Descriptor, model2.Descriptor);
AreEqual(model.Network, model2.Network);
}
static void Main(string[] args)
{
Tennis[] data = Tennis.GetData();
var d = Descriptor.Create <Tennis>();
var g = new DecisionTreeGenerator(d);
g.SetHint(false);
var model = Learner.Learn(data, 0.8, 1000, g);
Console.WriteLine(model);
Console.ReadKey();
}
public void Tennis_Naive_Bayes_Save_And_Load_Test()
{
var data = Tennis.GetData();
var description = Descriptor.Create <Tennis>();
var generator = new NaiveBayesGenerator(2);
var model = generator.Generate(description, data);
Serialize(model);
var lmodel = Deserialize <NaiveBayesModel>();
}
public void Tennis_Naive_Bayes_Save_And_Load_Test_Json()
{
var data = Tennis.GetData();
var description = Descriptor.Create <Tennis>();
var generator = new NaiveBayesGenerator(2);
var model = generator.Generate(description, data) as NaiveBayesModel;
var file = GetPath();
Register.Type <Tennis>();
var lmodel = SaveAndLoadJson(model);
Assert.Equal(model.Root, lmodel.Root);
}
public void TennisPrediction(IGenerator generator)
{
Tennis t = new Tennis
{
Humidity = Humidity.Normal,
Outlook = Outlook.Overcast,
Temperature = Temperature.Cool,
Windy = true
};
Prediction <Tennis>(
generator, // generator
Tennis.GetData(), // training data
t, // test object
p => p.Play // should be true
);
}
public void Tennis_DT_and_Prediction()
{
var data = Tennis.GetData();
var description = Descriptor.Create <Tennis>();
var generator = new DecisionTreeGenerator(50);
var model = generator.Generate(description, data);
Tennis t = new Tennis
{
Humidity = Humidity.Normal,
Outlook = Outlook.Overcast,
Temperature = Temperature.Cool,
Windy = true
};
model.Predict <Tennis>(t);
Assert.IsTrue(t.Play);
}
public void Main_Naive_Bayes_Test()
{
var data = Tennis.GetData();
var description = Descriptor.Create <Tennis>();
var generator = new NaiveBayesGenerator(2);
var model = generator.Generate(description, data);
Tennis t = new Tennis
{
Humidity = Humidity.Normal,
Outlook = Outlook.Overcast,
Temperature = Temperature.Cool,
Windy = true
};
model.Predict <Tennis>(t);
Assert.IsTrue(t.Play);
}
public void Save_Node_Test()
{
Tennis t = new Tennis
{
Humidity = Humidity.Normal,
Outlook = Outlook.Overcast,
Temperature = Temperature.Cool,
Windy = true
};
var model = (NeuralNetworkModel)BaseSupervised.Prediction <Tennis>(
new NeuralNetworkGenerator(),
Tennis.GetData(),
t,
p => p.Play
);
var node = model.Network.In[0].Out[0].Target;
Serialize(node);
}
public void Save_Network_Test()
{
Tennis t = new Tennis
{
Humidity = Humidity.Normal,
Outlook = Outlook.Overcast,
Temperature = Temperature.Cool,
Windy = true
};
var model = (NeuralNetworkModel)BaseSupervised.Prediction <Tennis>(
new NeuralNetworkGenerator(),
Tennis.GetData(),
t,
p => p.Play
);
var file = GetPath();
var network = SaveAndLoad(model.Network, file);
AreEqual(model.Network, network);
}
public void Save_Model_Test()
{
Tennis t = new Tennis
{
Humidity = Humidity.Normal,
Outlook = Outlook.Overcast,
Temperature = Temperature.Cool,
Windy = true
};
var model = (NeuralNetworkModel)BaseSupervised.Prediction <Tennis>(
new NeuralNetworkGenerator(),
Tennis.GetData(),
t,
p => p.Play
);
Serialize(model);
var model2 = Deserialize <NeuralNetworkModel>();
Assert.Equal(model.Descriptor, model2.Descriptor);
AreEqual(model.Network, model2.Network);
}
