public void TestBcLrSameModel()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var output = FileHelper.GetOutputFile("bc-lr.zip", methodName);
var name = FileHelper.GetOutputFile("bc.txt", methodName);
var df = DataFrameIO.ReadStr("Label,X1,X2,X3,X4,X5,X6,X7,X8,X9\n" +
"0,0.1,1.1,2.1,3.1,4.1,5.1,6.2,7.4,-5\n" +
"1,1.1,1.1,2.1,3.1,4.1,5.1,6.2,7.4,-5\n" +
"0,2.1,1.1,3.1,3.1,-4.1,5.1,6.2,7.4,-5\n" +
"1,3.1,1.1,4.1,3.1,4.1,-5.1,6.2,7.4,-5\n" +
"0,4.1,1.1,2.1,3.1,4.1,5.1,6.2,-7.4,-5");
df.ToCsv(name);
var cmd = string.Format("Train tr=lr data={0} out={1} loader=text{{col=Label:R4:0 col=Features:R4:1-* sep=, header=+}}",
name, output);
var stdout = new StringBuilder();
ILogWriter logout = new LogWriter((string s) => { stdout.Append(s); });
ILogWriter logerr = new LogWriter((string s) => { stdout.Append(s); });
/*using (*/
var env = new DelegateEnvironment(seed: 0, verbose: 2, outWriter: logout, errWriter: logerr);
MamlHelper.MamlScript(cmd, false, env);
var stout = stdout.ToString();
if (string.IsNullOrEmpty(stout))
{
throw new Exception(stout);
}
}
/// <summary>
/// Reads a string as a IDataView.
/// Follows pandas API.
/// </summary>
public static DataFrame ReadStr(string content, char sep = ',', bool header = true,
string[] names = null, int[] dtypes = null,
int nrows = -1, int guess_rows = 10, bool index = false)
{
var kinds = IntToColumnTypes(dtypes);
return(DataFrameIO.ReadStr(content, sep, header, names, kinds, nrows, guess_rows, index));
}
public void TestI_ScalerTransformNumericValuesMinMax()
{
using (var host = EnvHelper.NewTestEnvironment(conc: 1))
{
var raw = DataFrameIO.ReadStr("A,B\n1.0,2.0\n2.0,3.0\n10.0,11.0");
raw.SetShuffle(false);
var loader = host.CreateTransform("concat{col=X:A,B}", raw);
var data = host.CreateTransform("Scaler{col=X scale=minMax}", loader);
(data as ITrainableTransform).Estimate();
var res = DataFrameIO.ReadView(data);
var txt = res.ToString();
var exp = "A,B,X.0,X.1\n1.0,2.0,0.0,0.0\n2.0,3.0,0.11111111,0.11111111\n10.0,11.0,1.0,1.0";
var dfexp = DataFrameIO.ReadStr(exp);
Assert.AreEqual(0, dfexp.AlmostEquals(res, exc: true, printDf: true));
}
}
public void TestI_PolynomialTransformNumericValues()
{
using (var host = EnvHelper.NewTestEnvironment(conc: 1))
{
var raw = DataFrameIO.ReadStr("A,B\n1.0,2.0\n2.0,3.0\n10.0,11.0");
raw.SetShuffle(false);
var loader = host.CreateTransform("concat{col=X:A,B}", raw);
var data = host.CreateTransform("Poly{col=X}", loader);
var res = DataFrameIO.ReadView(data);
var txt = res.ToString();
Assert.IsFalse(string.IsNullOrEmpty(txt));
var exp = "A,B,X.0,X.1,X.2,X.3,X.4\n1.0,2.0,1.0,2.0,1.0,2.0,4.0\n2.0,3.0,2.0,3.0,4.0,6.0,9.0\n10.0,11.0,10.0,11.0,100.0,110.0,121.0";
var dfexp = DataFrameIO.ReadStr(exp);
Assert.AreEqual(0, dfexp.AlmostEquals(res, exc: true, printDf: true));
}
}
public void TestI_ScalerTransformNumericValuesMeanVar()
{
/*using (*/
var host = EnvHelper.NewTestEnvironment(conc: 1);
{
var raw = DataFrameIO.ReadStr("A,B\n1.0,2.0\n2.0,3.0\n10.0,11.0");
raw.SetShuffle(false);
var loader = host.CreateTransform("concat{col=X:A,B}", raw);
var data = host.CreateTransform("Scaler{col=X}", loader);
(data as ITrainableTransform).Estimate();
var res = DataFrameIO.ReadView(data);
var txt = res.ToString();
Assert.IsNotNull(txt);
var exp = "A,B,X.0,X.1\n1.0,2.0,-0.827605963,-0.827605963\n2.0,3.0,-0.5793242,-0.5793242\n10.0,11.0,1.40693,1.40693";
var dfexp = DataFrameIO.ReadStr(exp);
Assert.AreEqual(0, dfexp.AlmostEquals(res, exc: true, printDf: true, sortBy: "A"));
}
}
public void TestTimeSeriesFloatRegression()
{
var inputs = new[] {
new InputOutput()
{
X = 5f, time = 0f, one = 1f
},
new InputOutput()
{
X = 7f, time = 1f, one = 1f
},
new InputOutput()
{
X = 9f, time = 2f, one = 1f
},
new InputOutput()
{
X = 11f, time = 3f, one = 1f
},
new InputOutput()
{
X = 5f, time = 0f, one = 1f
},
new InputOutput()
{
X = 7f, time = 1f, one = 1f
},
new InputOutput()
{
X = 9f, time = 2f, one = 1f
},
new InputOutput()
{
X = 11f, time = 3f, one = 1f
},
new InputOutput()
{
X = 5f, time = 0f, one = 1f
},
new InputOutput()
{
X = 7f, time = 1f, one = 1f
},
new InputOutput()
{
X = 9f, time = 2f, one = 1f
},
new InputOutput()
{
X = 11f, time = 3f, one = 1f
},
};
using (var host = EnvHelper.NewTestEnvironment())
{
var data = host.CreateStreamingDataView(inputs);
using (var pipe = new ScikitPipeline(new[] { "concat{col=xt:time,one}" }, "sasdcar{iter=50}", host))
{
pipe.Train(data, feature: "xt", label: "X");
var view = pipe.Predict(data);
var df = DataFrameIO.ReadView(view).Head(4).Copy();
df["diff"] = df["Score"] - df["X"];
var exp = DataFrameIO.ReadStr("null\n0\n0\n0\n0");
df["diff"].AssertAlmostEqual(exp["null"].AsType(NumberType.R4), precision: 1e-1);
}
}
}
