Problem with ML.NET RobustScaler #5237
Description
System information
- Windows 10 Enterprise 10.0 18363 Built 18363
- Visual Studio 2019, build 16.6.2
Source code
- I have put my reproduceable project on GitHUb at: https://github.com/CBrauer/Test_RobustScaler
Program output. Notice that RobustScaler produced an extra column for "vwapGain"
Source code
My test program looks like:
namespace Test_RobustScaller {
internal class Program {
#region MyHead
public static void MyHead(IDataView train, int numRows) {
var trainPreview = train.Preview(maxRows: numRows);
var nColumns = trainPreview.ColumnView.Length;
var maxCharInHeaderName = 0;
for (var k = 0; k < nColumns; k++) {
var columnName = trainPreview.Schema[k].Name;
maxCharInHeaderName = Math.Max(maxCharInHeaderName, columnName.Length);
}
var nSpaces = new int[nColumns];
for (var k = 0; k < nColumns; k++) {
var columnName = trainPreview.Schema[k].Name;
for (var j = 0; j < maxCharInHeaderName - columnName.Length + 1; j++) {
Console.Write(" ");
}
Console.Write("{0}", columnName);
nSpaces[k] = maxCharInHeaderName - columnName.Length + 1;
}
Console.Write("\n");
foreach (var row in trainPreview.RowView) {
for (var k = 0; k < row.Values.Length; k++) {
var field = string.Format("{0}", row.Values[k].Value);
var nSpace = maxCharInHeaderName - field.Length + 1;
for (var j = 0; j < nSpace; j++) {
Console.Write(" ");
}
Console.Write(row.Values[k].Value);
}
Console.Write("\n");
}
Console.Write("\n");
}
#endregion
public static void Run() {
var mlContext = new MLContext(seed: 1);
var df_full = DataFrame.LoadCsv("../../../data/model.csv");
var header_names = new List<string> {
"BoxRatio", "Thrust", "Acceleration", "Velocity",
"OnBalRun", "vwapGain", "Altitude"
};
var nColumns = header_names.Count;
var df_columns = new DataFrameColumn[nColumns];
for (var k = 0; k < nColumns; k++) {
var name = header_names[k];
df_columns[k] = df_full.Columns[name];
}
var df = new DataFrame(df_columns);
Console.WriteLine("Before transform:");
Console.WriteLine(df.Head(5));
var pipeline = mlContext.Transforms.RobustScaler("vwapGain");
var model = pipeline.Fit(df);
var transformed = model.Transform(df);
Console.WriteLine("After Transform:");
MyHead(transformed, 5);
}
static void Main() {
Run();
Console.WriteLine("Hit return to exit.");
Console.ReadKey();
}
}
}
Charles