static void Main(string[] args)
{
SaveRateToFileTrainData("USD");
SaveRateToFileTestData("USD");
Global.UseEngine(SiaNet.Backend.ArrayFire.SiaNetBackend.Instance, DeviceType.CUDA, true);
var train = PreparingExchangeRateData.LoadTrain();
var test = PreparingExchangeRateData.LoadTest();
var model = new Sequential();
model.EpochEnd += Model_EpochEnd;
model.Add(new Dense(60, ActType.Sigmoid));
model.Add(new Dense(60, ActType.Sigmoid));
model.Add(new Dense(1, ActType.Linear));
//Compile with Optimizer, Loss and Metric
model.Compile(OptimizerType.SGD, LossType.MeanSquaredError, MetricType.MSE);
// Train for 1000 epoch with batch size of 2
model.Train(train, epochs: 1000, batchSize: 32);
//Create prediction data to evaluate
DataFrame2D predX = new DataFrame2D(2);
predX.Load(0, 0, 0, 1, 1, 0, 1, 1); //Result should be 0, 1, 1, 0
var rawPred = model.Predict(test);
Console.ReadLine();
}
static void Main(string[] args)
{
//Setup Engine
Global.UseEngine(SiaNet.Backend.MxNetLib.SiaNetBackend.Instance, DeviceType.CPU);
//Prep Data
var(x, y) = PrepDataset();
x.Head();
DataFrameIter trainSet = new DataFrameIter(x, y);
//Build model with simple fully connected layers
var model = new Sequential();
model.EpochEnd += Model_EpochEnd;
model.Add(new Dense(64, ActType.ReLU));
model.Add(new Dense(1, ActType.Sigmoid));
//Compile with Optimizer, Loss and Metric
model.Compile(OptimizerType.SGD, LossType.MeanSquaredError, MetricType.BinaryAccurary);
// Train for 100 epoch with batch size of 2
model.Train(trainSet, 1000, 2);
//Create prediction data to evaluate
DataFrame2D predX = new DataFrame2D(2);
predX.Load(0, 0, 0, 1); //Result should be 0 and 1
var rawPred = model.Predict(predX);
Console.ReadLine();
}
public static DataFrame LoadTest()
{
//string projectDirectory = System.IO.Path.GetFullPath(@"..\..\..\");
//var frame = Frame.ReadCsv(projectDirectory + "/Data/USDRateTest.csv");
//frame.DropColumn("Date");
string projectDirectory = System.IO.Path.GetFullPath(@"..\..\..\");
List <float> datas = new List <float>();
using (StreamReader readFile = new StreamReader(projectDirectory + "/Data/USDRateTest.csv"))
{
string line;
string[] row;
while ((line = readFile.ReadLine()) != null)
{
row = line.Split('\t');
for (int i = 1; i < row.Length; i++)
{
datas.Add(float.Parse(row[i]));
}
}
}
//var data = frame.ToArray2D<float>().Cast<float>().ToArray();
DataFrame2D df = new DataFrame2D(8);
df.Load(datas.ToArray());
return(df);
}
private static DataFrame LoadTest()
{
var x = new DataFrame2D(2);
x.Load(new float[] { 0, 1, 1, 1 });
return(x);
}
public static (DataFrame2D, DataFrame2D) PrepareDataSet()
{
DataFrame2D x = new DataFrame2D(2);
x.Load(new float[] { 0, 0, 0, 1, 1, 0, 1, 1 });
DataFrame2D y = new DataFrame2D(1);
y.Load(new float[] { 0, 1, 1, 0 });
return(x, y);
}
private static (DataFrame, DataFrame) LoadTrain()
{
var x = new DataFrame2D(2);
x.Load(new float[] { 0, 0, 0, 1, 1, 0, 1, 1 });
var y = new DataFrame2D(1);
y.Load(new float[] { 0, 1, 1, 0 });
return(x, y);
}
private static (DataFrame2D, DataFrame2D) PrepDataset()
{
var K = Global.CurrentBackend;
Tensor x = K.RandomNormal(new long[] { 900, 10 }, 0.25f, 1);
Tensor y = K.RandomUniform(new long[] { 900, 1 }, 0, 25);
DataFrame2D X = new DataFrame2D(10);
DataFrame2D Y = new DataFrame2D(1);
X.Load(x.DataFloat);
Y.Load(y.DataFloat);
return(X, Y);
}
private static (DataFrame2D, DataFrame2D) PrepDataset()
{
// We will prepare XOR gate dataset which will be treated as classification problem.
// More about this: https://medium.com/@jayeshbahire/the-xor-problem-in-neural-networks-50006411840b
DataFrame2D x = new DataFrame2D(2);
x.Load(new float[] { 0, 0, 0, 1, 1, 0, 1, 1 });
DataFrame2D y = new DataFrame2D(1);
y.Load(new float[] { 0, 1, 1, 0 });
return(x, y);
}
private static DataFrame LoadTest()
{
//Using deedle which is similar to Pandas in python
var frame = Frame.ReadCsv("./BostonHousing/test.csv", true);
frame.DropColumn("ID");
//Load Deedle frame to Tensor frame
var data = frame.ToArray2D <float>().Cast <float>().ToArray();
var test = new DataFrame2D(frame.ColumnCount);
test.Load(data);
return(test);
}
private static DataFrame LoadTest()
{
//Using deedle which is similar to Pandas in python
var frame = Frame.ReadCsv("test.csv", true);
//Preprocess the data by handling missing values, converting string to numbers
frame = PreProcesData(frame, true);
//Load Deedle frame to Tensor frame
var data = frame.ToArray2D <float>().Cast <float>().ToArray();
DataFrame2D df = new DataFrame2D(frame.ColumnCount);
df.Load(data);
return(df);
}
private static DataFrameIter LoadTrain()
{
//Using deedle which is similar to Pandas in python
var frame = Frame.ReadCsv("train.csv", true);
//Preprocess the data by handling missing values, converting string to numbers
frame = PreProcesData(frame);
//Load Deedle frame to Tensor frame
var data = frame.ToArray2D <float>().Cast <float>().ToArray();
DataFrame2D df = new DataFrame2D(frame.ColumnCount);
df.Load(data);
//Split X and Y
var x = df[0, 6];
var y = df[7];
return(new DataFrameIter(x, y));
}
private static (DataFrame, DataFrame) LoadTrain()
{
//Using deedle which is similar to Pandas in python
var frame = Frame.ReadCsv("./BostonHousing/train.csv", true);
frame.DropColumn("ID");
//Load Deedle frame to Tensor frame
var yData = frame["medv"].Values.Select(i => ((float)i)).ToArray();
frame.DropColumn("medv");
var data = frame.ToArray2D <float>().Cast <float>().ToArray();
var x = new DataFrame2D(frame.ColumnCount);
x.Load(data);
var y = new DataFrame2D(1);
y.Load(yData);
return(x, y);
}