public void TestI_Q_KMeansInnerAPIWithDataFrame()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var iris = FileHelper.GetTestFile("iris.txt");
using (var env = new ConsoleEnvironment(conc: 1))
{
ComponentHelper.AddStandardComponents(env);
var df = Scikit.ML.DataManipulation.DataFrameIO.ReadCsv(iris, sep: '\t', dtypes: new ColumnType[] { NumberType.R4 });
var conc = env.CreateTransform("Concat{col=Feature:Sepal_length,Sepal_width}", df);
var roleMap = env.CreateExamples(conc, "Feature", label: "Label");
var trainer = CreateTrainer(env, "km");
IPredictor model;
using (var ch = env.Start("test"))
model = TrainUtils.Train(env, ch, roleMap, trainer, null, 0);
using (var ch = env.Start("Save"))
using (var fs = File.Create(outModelFilePath))
TrainUtils.SaveModel(env, ch, fs, model, roleMap);
Predictor pred;
using (var fs = File.OpenRead(outModelFilePath))
pred = env.LoadPredictorOrNull(fs);
#pragma warning disable CS0618
var scorer = ScoreUtils.GetScorer(pred.GetPredictorObject() as IPredictor, roleMap, env, null);
#pragma warning restore CS0618
var dfout = Scikit.ML.DataManipulation.DataFrameIO.ReadView(scorer);
Assert.AreEqual(dfout.Shape, new Tuple <int, int>(150, 13));
}
}
public void TestScikitAPI_DelegateEnvironment()
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 1, 10, 100 }
},
new ExampleA()
{
X = new float[] { 2, 3, 5 }
}
};
var inputs2 = new[] {
new ExampleA()
{
X = new float[] { -1, -10, -100 }
},
new ExampleA()
{
X = new float[] { -2, -3, -5 }
}
};
var stdout = new List <string>();
var stderr = new List <string>();
ILogWriter logout = new LogWriter((string s) =>
{
stdout.Add(s);
});
ILogWriter logerr = new LogWriter((string s) =>
{
stderr.Add(s);
});
using (var host = new DelegateEnvironment(conc: 1, outWriter: logout, errWriter: logerr, verbose: 3))
using (var ch = host.Start("Train Pipeline"))
{
ComponentHelper.AddStandardComponents(host);
ch.Info(MessageSensitivity.All, "Polynomial");
var data = host.CreateStreamingDataView(inputs);
using (var pipe = new ScikitPipeline(new[] { "poly{col=X}" }, host: host))
{
var predictor = pipe.Train(data);
if (predictor == null)
{
throw new Exception("Predictor is null");
}
}
}
if (stdout.Count == 0)
{
throw new Exception("stdout is empty.");
}
if (stderr.Count != 0)
{
throw new Exception($"stderr not empty\n{string.Join("\n", stderr)}");
}
}
/// <summary>
/// Returns all kinds of models.
/// </summary>
public static string[] GetAllKinds()
{
using (var env = new ConsoleEnvironment())
{
ComponentHelper.AddStandardComponents(env);
var sigs = env.ComponentCatalog.GetAllSignatureTypes();
var typeSig = sigs.Select(t => ComponentCatalog.SignatureToString(t).ToLowerInvariant());
return(new HashSet <string>(typeSig.OrderBy(c => c)).ToArray());
}
}
public static IHostEnvironment CreateEnvironment(int seed = -1, int verbose = 0,
string sensitivity = "All", int conc = 0,
ILogWriter outWriter = null, ILogWriter errWriter = null)
{
var env = new DelegateEnvironment(seed: seed < 0 ? null : (int?)seed, verbose: verbose,
sensitivity: MessageSensitivityFromString(sensitivity),
conc: conc, outWriter: outWriter, errWriter: errWriter);
ComponentHelper.AddStandardComponents(env);
return(env);
}
public static Tuple <IHostEnvironment, StringBuilder, StringBuilder> CreateStoreEnvironment(int seed = -1, int verbose = 0,
string sensitivity = "All", int conc = 0)
{
ILogWriter logout, logerr;
var stout = new StringBuilder();
var sterr = new StringBuilder();
logout = new LogWriter((string s) => { stout.Append(s); });
logerr = new LogWriter((string s) => { sterr.Append(s); });
var env = new DelegateEnvironment(seed: seed < 0 ? null : (int?)seed, verbose: verbose,
sensitivity: MessageSensitivityFromString(sensitivity),
conc: conc, outWriter: logout, errWriter: logerr);
ComponentHelper.AddStandardComponents(env);
return(new Tuple <IHostEnvironment, StringBuilder, StringBuilder>(env, stout, sterr));
}
public static string[] GetLoadedAssemblies(bool env = true)
{
if (env)
{
using (var e = new ConsoleEnvironment())
{
ComponentHelper.AddStandardComponents(e);
var assemblies = AppDomain.CurrentDomain.GetAssemblies().Select(x => InfoAssembly(x)).OrderBy(c => c);
return(assemblies.ToArray());
}
}
else
{
var assemblies = AppDomain.CurrentDomain.GetAssemblies().Select(x => InfoAssembly(x)).OrderBy(c => c);
return(assemblies.ToArray());
}
}
public void TestScikitAPI_DelegateEnvironmentVerbose0()
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 1, 10, 100 }
},
new ExampleA()
{
X = new float[] { 2, 3, 5 }
}
};
var inputs2 = new[] {
new ExampleA()
{
X = new float[] { -1, -10, -100 }
},
new ExampleA()
{
X = new float[] { -2, -3, -5 }
}
};
var stdout = new List <string>();
var stderr = new List <string>();
ILogWriter logout = new LogWriter(s => stdout.Add(s));
ILogWriter logerr = new LogWriter(s => stderr.Add(s));
/*using (*/
var host = new DelegateEnvironment(seed: 0, outWriter: logout, errWriter: logerr, verbose: 0);
{
ComponentHelper.AddStandardComponents(host);
var data = DataViewConstructionUtils.CreateFromEnumerable(host, inputs);
using (var pipe = new ScikitPipeline(new[] { "poly{col=X}" }, "km{k=2}", host: host))
{
var predictor = pipe.Train(data, feature: "X");
Assert.IsTrue(predictor != null);
}
}
Assert.AreEqual(stdout.Count, 0);
Assert.AreEqual(stderr.Count, 0);
}
/// <summary>
/// Creates a new environment. It should be done
/// with <tt>using</tt>.
/// </summary>
public static ConsoleEnvironment NewTestEnvironment(int?seed = null, bool verbose = false,
MessageSensitivity sensitivity = (MessageSensitivity)(-1),
int conc = 0, TextWriter outWriter = null, TextWriter errWriter = null)
{
if (!seed.HasValue)
{
seed = 42;
}
if (outWriter == null)
{
outWriter = new StreamWriter(new MemoryStream());
}
if (errWriter == null)
{
errWriter = new StreamWriter(new MemoryStream());
}
var env = new ConsoleEnvironment(seed, verbose, sensitivity, conc, outWriter, errWriter);
ComponentHelper.AddStandardComponents(env);
return(env);
}
public static string[] GetLoadedAssembliesLocation(bool env = true)
{
if (env)
{
using (var e = new ConsoleEnvironment())
{
ComponentHelper.AddStandardComponents(e);
var assemblies = AppDomain.CurrentDomain.GetAssemblies()
.Select(x => GetAssemblyLocation(x))
.Where(x => !string.IsNullOrEmpty(x))
.ToArray();
return(assemblies.ToArray());
}
}
else
{
var assemblies = AppDomain.CurrentDomain.GetAssemblies()
.Select(x => GetAssemblyLocation(x))
.Where(x => !string.IsNullOrEmpty(x))
.ToArray();
return(assemblies.ToArray());
}
}
/// <summary>
/// Returns all kinds of models.
/// </summary>
public static IEnumerable <ComponentDescription> EnumerateComponents(string kind)
{
if (kind == "argument")
{
foreach (var comp in EnumerateComponentsParameter(false))
{
yield return(comp);
}
}
else if (kind == "command")
{
foreach (var comp in EnumerateComponentsParameter(true))
{
yield return(comp);
}
}
else
{
var kinds = GetAllKinds();
if (!string.IsNullOrEmpty(kind) && !kinds.Where(c => c == kind).Any())
{
throw new ArgumentException($"Unable to find kind '{kind}' in\n{string.Join("\n", kinds)}.");
}
using (var env = new ConsoleEnvironment())
{
ComponentHelper.AddStandardComponents(env);
var sigs = env.ComponentCatalog.GetAllSignatureTypes();
var typeRes = typeof(object);
Type[] typeSigs;
if (string.IsNullOrEmpty(kind))
{
typeSigs = sigs.ToArray();
}
else
{
typeSigs = new[] { sigs.FirstOrDefault(t => ComponentCatalog.SignatureToString(t).ToLowerInvariant() == kind) }
};
foreach (var typeSig in typeSigs)
{
var infos = env.ComponentCatalog.GetAllDerivedClasses(typeRes, typeSig)
.Where(x => !x.IsHidden)
.OrderBy(x => x.LoadNames[0].ToLowerInvariant());
foreach (var info in infos)
{
var args = info.CreateArguments();
if (args == null)
{
yield return(new ComponentDescription(info, args, null, null));
}
else
{
var asse = args.GetType().Assembly;
var parsedArgs = CmdParser.GetArgInfo(args.GetType(), args).Args;
var arguments = new List <ComponentDescription.Argument>();
foreach (var arg in parsedArgs)
{
var a = new ComponentDescription.Argument()
{
Name = arg.LongName,
ShortName = arg.ShortNames == null || !arg.ShortNames.Any() ? null : arg.ShortNames.First(),
DefaultValue = arg.DefaultValue == null ? null : arg.DefaultValue.ToString(),
Help = arg.HelpText,
Arg = arg,
};
arguments.Add(a);
}
var cmp = new ComponentDescription(info, args, asse, arguments);
yield return(cmp);
}
}
}
}
}
}
#endregion
}
/// <summary>
/// Runs a simple test.
/// </summary>
public static void TestScikitAPI()
{
var inputs = new[] {
new ExampleVector()
{
X = new float[] { 1, 10, 100 }
},
new ExampleVector()
{
X = new float[] { 2, 3, 5 }
},
new ExampleVector()
{
X = new float[] { 2, 4, 5 }
},
new ExampleVector()
{
X = new float[] { 2, 4, 7 }
},
};
var inputs2 = new[] {
new ExampleVector()
{
X = new float[] { -1, -10, -100 }
},
new ExampleVector()
{
X = new float[] { -2, -3, -5 }
},
new ExampleVector()
{
X = new float[] { 3, 4, 5 }
},
new ExampleVector()
{
X = new float[] { 3, 4, 7 }
},
};
using (var host = new ConsoleEnvironment(conc: 1))
{
ComponentHelper.AddStandardComponents(host);
var data = host.CreateStreamingDataView(inputs);
using (var pipe = new ScikitPipeline(new[] { "poly{col=X}" }, "km{k=2}", host))
{
var predictor = pipe.Train(data, feature: "X");
if (predictor == null)
{
throw new Exception("Test failed: no predictor.");
}
var data2 = host.CreateStreamingDataView(inputs2);
var predictions = pipe.Predict(data2);
var df = DataFrameIO.ReadView(predictions);
if (df.Shape.Item1 != 4 || df.Shape.Item2 != 12)
{
throw new Exception("Test failed: prediction failed.");
}
var dfs = df.ToString();
var dfs2 = dfs.Replace("\n", ";");
if (!dfs2.StartsWith("X.0,X.1,X.2,X.3,X.4,X.5,X.6,X.7,X.8,PredictedLabel,Score.0,Score.1;-1,-10,-100,1,10,100,100,1000,10000"))
{
throw new Exception("Test failed: prediction failed (header).");
}
}
}
}
public static string MamlScript(string script, bool catch_output,
int conc = 0, int verbose = 2, int sensitivity = -1,
bool skipFailLoading = false)
{
ILogWriter logout, logerr;
var stout = new StringBuilder();
var sterr = new StringBuilder();
if (catch_output)
{
logout = new LogWriter((string s) =>
{
stout.Append(s);
});
logerr = new LogWriter((string s) =>
{
sterr.Append(s);
});
}
else
{
logout = new LogWriter((string s) => { Console.Write(s); });
logerr = new LogWriter((string s) => { Console.Error.Write(s); });
}
using (var env = new DelegateEnvironment((int?)null, verbose, (MessageSensitivity)sensitivity, conc, logout, logerr))
{
if (skipFailLoading)
{
try
{
ComponentHelper.AddStandardComponents(env);
}
catch (Exception e)
{
sterr.Append($"Unable to load an assembly due to {e.ToString()}.\n");
}
}
else
{
ComponentHelper.AddStandardComponents(env);
}
string res = null;
try
{
res = MamlHelper.MamlScript(script, false, env);
if (!string.IsNullOrEmpty(res))
{
stout.Append(res);
}
}
catch (InvalidOperationException e)
{
if (!string.IsNullOrEmpty(res))
{
sterr.Append(res + "\n");
}
sterr.Append($"[PyMamlHelper-InvalidOperationException] catch_output={catch_output}\n" + e.ToString() + "\n");
}
catch (MamlException e)
{
if (!string.IsNullOrEmpty(res))
{
sterr.Append(res + "\n");
}
sterr.Append($"[PyMamlHelper-MamlException] catch_output={catch_output}\n" + e.ToString() + "\n");
}
if (sterr.Length > 0)
{
return(string.Format("---OUT---\n{0}\n---ERR---\n{1}", stout.ToString(), sterr.ToString()));
}
else
{
return(stout.ToString());
}
}
}
