static void TrainMultiToRankerPredictorDense(string modelName, int threads, bool checkError,
bool singleColumn, bool shift, bool useUint)
{
var methodName = string.Format("{0}-{1}-V{2}-T{3}-S{4}", System.Reflection.MethodBase.GetCurrentMethod().Name,
modelName, singleColumn ? "C" : "Vec", threads, shift ? "shift" : "std");
var dataFilePath = shift
? FileHelper.GetTestFile("mc_iris_shift.txt")
: FileHelper.GetTestFile("mc_iris.txt");
var trainFile = FileHelper.GetOutputFile("iris_train.idv", methodName);
var testFile = FileHelper.GetOutputFile("iris_test.idv", methodName);
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
using (var env = EnvHelper.NewTestEnvironment(conc: threads == 1 ? 1 : 0))
{
string labelType = useUint ? "U4[0-2]" : "R4";
string loadSettings = string.Format("Text{{col=Label:{0}:0 col=Slength:R4:1 col=Swidth:R4:2 col=Plength:R4:3 col=Pwidth:R4:4 header=+}}", labelType);
var loader = env.CreateLoader(loadSettings, new MultiFileSource(dataFilePath));
var concat = env.CreateTransform("Concat{col=Features:Slength,Swidth}", loader);
var roles = env.CreateExamples(concat, "Features", "Label");
string modelDef = threads <= 0 ? modelName : string.Format("{0}{{t={1}}}", modelName, threads);
string additionnal = modelName.Contains("xgbrk") ? " u4=+" : "";
string iova = string.Format("iovark{{p={0} sc={1}{2}}}", modelDef, singleColumn ? "+" : "-", additionnal);
var trainer = env.CreateTrainer(iova);
using (var ch = env.Start("train"))
{
var predictor = trainer.Train(env, ch, roles);
TestTrainerHelper.FinalizeSerializationTest(env, outModelFilePath, predictor, roles, outData, outData2,
PredictionKind.MultiClassClassification, checkError, ratio: 0.1f);
}
}
}
private void StartUp()
{
try
{
var factory = new CoreClientFactory(_loggerRef)
.SetEnv("Dev")
.SetApplication(Assembly.GetExecutingAssembly())
.SetProtocols(WcfConst.AllProtocolsStr)
.SetServers("localhost");
var client = factory.Create();
_clientRef = Reference <ICoreClient> .Create(client);
_cache = _clientRef.Target.CreateCache();
//_cache.SubscribeInfoOnly<Algorithm>(Expr.ALL);
// init controls
// - form title
var env = _clientRef.Target.ClientInfo.ConfigEnv;
Text += String.Format(" ({0})", EnvHelper.EnvName(env));
// - server port
int defaultPort = EnvHelper.SvcPort(env, SvcId.GridSwitch);
chkChangePort.Text = String.Format("Change server port from default ({0}) to:", defaultPort);
_syncContext.Post(OnClientStateChange, new CoreStateChange(CoreStateEnum.Initial, _clientRef.Target.CoreState));
_clientRef.Target.OnStateChange += _Client_OnStateChange;
}
catch (Exception excp)
{
_loggerRef.Target.Log(excp);
}
}
private void StartUp()
{
// default configuration
EnvId env = IntClient.Target.ClientInfo.ConfigEnv;
// derived configuration
_serverPort = OtherSettings.GetValue(WFPropName.Port, EnvHelper.SvcPort(env, SvcId.GridSwitch));
_nodeId = OtherSettings.GetValue(WFPropName.NodeId, Guid.NewGuid());
// create router/worker worksteps
Routers = GridWorksteps.Create().ToArray();
Workers = GridWorksteps.Create().ToArray();
// start discovery endpoint
string endpoint = ServiceHelper.FormatEndpoint(WcfConst.NetTcp, _serverPort);
string svcName = EnvHelper.SvcPrefix(SvcId.GridSwitch);
_discoServerHost = new CustomServiceHost <IDiscoverV111, DiscoverRecverV111>(
Logger, new DiscoverRecverV111(this), endpoint,
svcName, typeof(IDiscoverV111).Name, true);
IWorkContext context = new WorkContext(Logger, IntClient.Target, HostInstance, ServerInstance);
// start gridswitch endpoints - routers before workers
foreach (IWorkstep router in Routers)
{
router.Initialise(context);
router.EnableGrid(GridLevel.Router, _nodeId, _serverPort, null);
}
foreach (IWorkstep worker in Workers)
{
worker.Initialise(context);
worker.EnableGrid(GridLevel.Worker, _nodeId, _serverPort, null);
}
}
public LEMngIntegrationTests()
{
this.Services = DiHelper.GetServiceProvider();
Settings = Services.GetService <IOptions <AppSettings> >().Value;
EnvHelper.SetAzureAccessEnvironment();
}
private void PreCommand()
{
EnvHelper.GetGitConfig();
EnvHelper.GetBranchName();
EnvHelper.GetStash();
FileHelper.SaveAllFiles(_dte);
}
unsafe public InvokeData ReceiveInvoke(IDictionary initialEnvironmentVariables, RuntimeReceiveInvokeBuffers buffers)
{
Console.Error.WriteLine($"START RequestId: {context.RequestId} Version: {context.FunctionVersion}");
invoked = true;
curSBSharedMem = new SBSharedMem(sharedMem);
return(new InvokeData(curSBSharedMem)
{
RequestId = context.RequestId,
AwsCredentials = new AwsCredentials
{
AccessKeyId = EnvHelper.GetOrDefault("AWS_ACCESS_KEY_ID", "SOME_ACCESS_KEY_ID"),
SecretAccessKey = EnvHelper.GetOrDefault("AWS_SECRET_ACCESS_KEY", "SOME_SECRET_ACCESS_KEY"),
SessionToken = System.Environment.GetEnvironmentVariable("AWS_SESSION_TOKEN")
},
XAmznTraceId = EnvHelper.GetOrDefault("_X_AMZN_TRACE_ID", ""),
InputStream = context.InputStream,
OutputStream = new UnmanagedMemoryStream(curSBSharedMem.EventBody, 0, SBSharedMem.SizeOfEventBody, FileAccess.Write),
LambdaContextInternal = new LambdaContextInternal(
context.RemainingTime,
SendCustomerLogMessage,
new Lazy <CognitoClientContextInternal>(),
context.RequestId,
new Lazy <string>(context.Arn),
new Lazy <string>(string.Empty),
new Lazy <string>(string.Empty),
initialEnvironmentVariables
)
});
}
public void TestTagTrainOrScoreTransformCustomScorer()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var dataFilePath = FileHelper.GetTestFile("mc_iris.txt");
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
using (var env = EnvHelper.NewTestEnvironment())
{
var loader = env.CreateLoader("Text{col=Label:R4:0 col=Slength:R4:1 col=Swidth:R4:2 col=Plength:R4:3 col=Pwidth:R4:4 header=-}",
new MultiFileSource(dataFilePath));
using (var pipe = new ScikitPipeline(new[] {
"Concat{col=Feature:Slength,Swidth}",
"TagTrainScore{tr=iova{p=ft{nl=10 iter=1}} lab=Label feat=Feature tag=model scorer=MultiClassClassifierScorer{ex=AA}}"
}, host: env))
{
pipe.Train(loader);
var pred = pipe.Predict(loader);
var df = DataFrameIO.ReadView(pred);
Assert.AreEqual(df.Shape, new Tuple <int, int>(150, 11));
var dfs = df.Head().ToString();
Assert.IsTrue(dfs.StartsWith("Label,Slength,Swidth,Plength,Pwidth,Feature.0,Feature.1,PredictedLabelAA,ScoreAA.0,ScoreAA.1,ScoreAA.2"));
}
}
}
public MainLauncherWindow()
{
InitializeComponent();
fileService = new WinFileService();
dialogService = new WinDialogService();
freeLanDetectionService = new FreeLanDetectionService(fileService, dialogService);
windowsServices = new WindowsServices();
networkAdapters = new NetworkAdapters();
freeLanService = new FreeLanService(
windowsServices,
freeLanDetectionService,
dialogService
);
if (!EnvHelper.IsAdministrator())
{
MessageBox.Show("To use this application you will need administrator privileges!");
System.Environment.Exit(0);
}
UpdateWindow();
}
public void TestTagViewTransform()
{
using (var host = EnvHelper.NewTestEnvironment())
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 0, 1 }
},
new ExampleA()
{
X = new float[] { 2, 3 }
}
};
IDataView loader = host.CreateStreamingDataView(inputs);
var data = host.CreateTransform("Scaler{col=X1:X}", loader);
data = host.CreateTransform("tag{t=memory}", data);
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
TestTransformHelper.SerializationTestTransform(host, outModelFilePath, data, loader, outData, outData2);
}
}
public void TestChainTransformSerialize()
{
using (var host = EnvHelper.NewTestEnvironment())
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 1, 10, 100 }
},
new ExampleA()
{
X = new float[] { 2, 3, 5 }
}
};
IDataView loader = host.CreateStreamingDataView(inputs);
IDataTransform data = host.CreateTransform("Scaler{col=X4:X}", loader);
data = host.CreateTransform("ChainTrans{ xf1=Scaler{col=X2:X} xf2=Poly{col=X3:X2} }", data);
// We create a specific folder in build/UnitTest which will contain the output.
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
TestTransformHelper.SerializationTestTransform(host, outModelFilePath, data, loader, outData, outData2);
}
}
static void TrainPrePostProcessTrainer(string modelName, bool checkError, int threads, bool addpre)
{
var methodName = string.Format("{0}-{1}-T{2}", System.Reflection.MethodBase.GetCurrentMethod().Name, modelName, threads);
var dataFilePath = FileHelper.GetTestFile("mc_iris.txt");
var trainFile = FileHelper.GetOutputFile("iris_train.idv", methodName);
var testFile = FileHelper.GetOutputFile("iris_test.idv", methodName);
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
using (var env = EnvHelper.NewTestEnvironment(conc: threads == 1 ? 1 : 0))
{
var loader = env.CreateLoader("Text{col=Label:R4:0 col=Slength:R4:1 col=Swidth:R4:2 col=Plength:R4:3 col=Pwidth:R4:4 header=+}",
new MultiFileSource(dataFilePath));
var xf = env.CreateTransform("shuffle{force=+}", loader); // We shuffle because Iris is order by label.
xf = env.CreateTransform("concat{col=RawFeatures:Slength,Swidth}", xf);
var roles = env.CreateExamples(xf, "RawFeatures", "Label");
string pred = addpre ? "PrePost{pre=poly{col=Feature:RawFeatures} p=___ pret=Take{n=80}}" : "PrePost{p=___ pret=Take{n=80}}";
pred = pred.Replace("___", modelName);
var trainer = env.CreateTrainer(pred);
using (var ch = env.Start("Train"))
{
var predictor = trainer.Train(env, ch, roles);
TestTrainerHelper.FinalizeSerializationTest(env, outModelFilePath, predictor, roles, outData, outData2,
PredictionKind.MultiClassClassification, checkError, ratio: 0.15f);
}
}
}
public static void TrainMultiToRankerPredictorSparse(bool singleColumn, bool checkError)
{
var methodName = string.Format("{0}-{1}-V{2}", System.Reflection.MethodBase.GetCurrentMethod().Name,
"lr", singleColumn ? "C" : "Vec");
var trainFile = FileHelper.GetTestFile("Train-28x28_small.txt");
var testFile = FileHelper.GetTestFile("Test-28x28_small.txt");
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
using (var env = EnvHelper.NewTestEnvironment())
{
var loader = env.CreateLoader("Text", new MultiFileSource(trainFile));
var roles = env.CreateExamples(loader, "Features", "Label");
var iova = string.Format("iovark{{p=ftrank sc={0}}}", singleColumn ? "+" : "-");
loader = env.CreateLoader("Text", new MultiFileSource(testFile));
var trainer = env.CreateTrainer(iova);
using (var ch = env.Start("train"))
{
var predictor = trainer.Train(env, ch, roles);
TestTrainerHelper.FinalizeSerializationTest(env, outModelFilePath, predictor, roles, outData, outData2,
PredictionKind.MultiClassClassification, checkError, ratio: 0.1f);
}
}
}
public void TestI_ResampleSerialization()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var dataFilePath = FileHelper.GetTestFile("iris.txt");
var outputDataFilePath = FileHelper.GetOutputFile("outputDataFilePath.txt", methodName);
using (var env = EnvHelper.NewTestEnvironment(conc: 1))
{
var loader = env.CreateLoader("Text{col=Label:R4:0 col=Slength:R4:1 col=Swidth:R4:2 col=Plength:R4:3 " +
"col=Pwidth:R4:4 header=+ sep=tab}",
new MultiFileSource(dataFilePath));
var sorted = env.CreateTransform("resample{lambda=1 c=-}", loader);
DataViewHelper.ToCsv(env, sorted, outputDataFilePath);
var lines = File.ReadAllLines(outputDataFilePath);
int begin = 0;
for (; begin < lines.Length; ++begin)
{
if (lines[begin].StartsWith("Label"))
{
break;
}
}
lines = lines.Skip(begin).ToArray();
var linesSorted = lines.OrderBy(c => c).ToArray();
for (int i = 1; i < linesSorted.Length; ++i)
{
if (linesSorted[i - 1][0] > linesSorted[i][0])
{
throw new Exception("The output is not sorted.");
}
}
}
}
public static IServiceCollection AddMvcApi(this IServiceCollection services)
{
if (!EnvHelper.IsDevelopment())
{
services.AddResponseCaching();
services.AddElectMinResponse();
}
services.AddSingleton<IActionContextAccessor, ActionContextAccessor>();
services.AddSingleton<ITempDataProvider, CookieTempDataProvider>();
// Validation Filters
services.AddScoped<ApiValidationActionFilterAttribute>();
// Exception Filters
services.AddScoped<ApiExceptionFilterAttribute>();
services.AddScoped<RootExceptionFilterAttribute>();
// MVC
var mvcBuilder = services.AddMvc(options =>
{
options.RespectBrowserAcceptHeader = false; // false by default
options.Filters.Add(new ProducesAttribute(ContentType.Json));
options.Filters.Add(new ProducesAttribute(ContentType.Xml));
});
// Xml Config
mvcBuilder.AddXmlDataContractSerializerFormatters();
// Json Config
mvcBuilder.AddJsonOptions(options =>
{
options.SerializerSettings.ReferenceLoopHandling =
Formatting.JsonSerializerSettings.ReferenceLoopHandling;
options.SerializerSettings.NullValueHandling = Formatting.JsonSerializerSettings.NullValueHandling;
options.SerializerSettings.Formatting = Formatting.JsonSerializerSettings.Formatting;
options.SerializerSettings.ContractResolver = Formatting.JsonSerializerSettings.ContractResolver;
options.SerializerSettings.DateFormatString = Formatting.JsonSerializerSettings.DateFormatString;
options.SerializerSettings.Culture = Formatting.JsonSerializerSettings.Culture;
});
// Validation
mvcBuilder.AddViewOptions(options => { options.HtmlHelperOptions.ClientValidationEnabled = true; });
mvcBuilder.AddFluentValidation(fvc => { fvc.RegisterValidatorsFromAssemblyContaining<IValidator>(); });
// AreaName Support
services.Configure<RazorViewEngineOptions>(options =>
{
options.AreaViewLocationFormats.Clear();
options.AreaViewLocationFormats.Add("/" + AreaFolderName + "/{2}/Views/{1}/{0}.cshtml");
options.AreaViewLocationFormats.Add("/" + AreaFolderName + "/{2}/Views/Shared/{0}.cshtml");
options.AreaViewLocationFormats.Add("/Views/Shared/{0}.cshtml");
});
return services;
}
private IDataScorerTransform _TrainSentiment()
{
bool normalize = true;
var args = new TextLoader.Arguments()
{
Separator = "tab",
HasHeader = true,
Column = new[] {
new TextLoader.Column("Label", DataKind.BL, 0),
new TextLoader.Column("SentimentText", DataKind.Text, 1)
}
};
var args2 = new TextFeaturizingEstimator.Arguments()
{
Column = new TextFeaturizingEstimator.Column
{
Name = "Features",
Source = new[] { "SentimentText" }
},
KeepDiacritics = false,
KeepPunctuations = false,
TextCase = TextNormalizingEstimator.CaseNormalizationMode.Lower,
OutputTokens = true,
UsePredefinedStopWordRemover = true,
VectorNormalizer = normalize ? TextFeaturizingEstimator.TextNormKind.L2 : TextFeaturizingEstimator.TextNormKind.None,
CharFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments()
{
NgramLength = 3, AllLengths = false
},
WordFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments()
{
NgramLength = 2, AllLengths = true
},
};
var trainFilename = FileHelper.GetTestFile("wikipedia-detox-250-line-data.tsv");
using (var env = EnvHelper.NewTestEnvironment(seed: 1, conc: 1))
{
// Pipeline
var loader = new TextLoader(env, args).Read(new MultiFileSource(trainFilename));
var trans = TextFeaturizingEstimator.Create(env, args2, loader);
// Train
var trainer = new SdcaBinaryTrainer(env, new SdcaBinaryTrainer.Arguments
{
NumThreads = 1
});
var cached = new CacheDataView(env, trans, prefetch: null);
var predictor = trainer.Fit(cached);
var scoreRoles = new RoleMappedData(trans, label: "Label", feature: "Features");
var trainRoles = new RoleMappedData(cached, label: "Label", feature: "Features");
return(ScoreUtils.GetScorer(predictor.Model, scoreRoles, env, trainRoles.Schema));
}
}
public RabbitMQLogger(RabbitMQLoggerProvider rabbitMQLoggerProvider, string categoryName)
{
// Console.WriteLine("RabbitMQLogger - INIT LOGGER");
this._RabbitMQLoggerProvider = rabbitMQLoggerProvider;
this.categoryName = categoryName;
this.envModel = EnvHelper.GetEnv();
}
public ContextMenuCommands(OleMenuCommandService mcs, DTE dte,
OptionPageGrid generalOptions, EnvHelper envHelper)
{
_dte = dte;
_mcs = mcs;
_generalOptions = generalOptions;
_envHelper = envHelper;
}
private static async Task Initialize()
{
priceDb = new CosmosPriceRepository(EnvHelper.GetEnvironmentVariable("CosmosConnStr"));
itemDb = new CosmosItemRepository(EnvHelper.GetEnvironmentVariable("CosmosConnStr"));
items = await itemDb.GetAllItemsAsync();
emailSender = new SendGridEmailService();
}
public PredictionEngineExample(string modelName)
{
_env = EnvHelper.NewTestEnvironment();
var transformer = TransformerChain.LoadFromLegacy(_env, File.OpenRead(modelName));
var model = new ModelOperationsCatalog(_env);
_predictor = model.CreatePredictionEngine <FloatVectorInput, FloatOutput>(transformer);
}
/// <summary>
/// 生产外发字符串
/// </summary>
/// <returns></returns>
public string ToLogstashMessage()
{
string strPublishMessage = $"<{this.LogTime}> <{this.LogLevel}> <{this.LogId}> <{this.LogAttr}> <{this.LogCategory}> ";
strPublishMessage += $"<{ EnvHelper.GetEnv().APP_BUILD_NAME}> <{EnvHelper.GetLocalHostName()}> <{EnvHelper.GetLocalIPV4()}> <{this.LogMsg}>";
return(strPublishMessage);
}
public GitSVNMenuCommands(OleMenuCommandService mcs, DTE dte,
OptionPageGrid options, EnvHelper envHelper)
{
_mcs = mcs;
_options = options;
_dte = dte;
_envHelper = envHelper;
}
public void TestDBScanTransform()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var dataFilePath = FileHelper.GetTestFile("three_classes_2d.txt");
var outputDataFilePath = FileHelper.GetOutputFile("outputDataFilePath.txt", methodName);
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
using (var env = EnvHelper.NewTestEnvironment(conc: 1))
{
//var loader = env.CreateLoader("text{col=RowId:I4:0 col=Features:R4:1-2 header=+}", new MultiFileSource(dataFilePath));
var loader = TextLoader.Create(env, new TextLoader.Arguments()
{
HasHeader = true,
Column = new[] { TextLoader.Column.Parse("RowId:R4:0"),
TextLoader.Column.Parse("Features:R4:1-2") }
},
new MultiFileSource(dataFilePath));
var xf = env.CreateTransform("DBScan{col=Features}", loader);
string schema = SchemaHelper.ToString(xf.Schema);
if (string.IsNullOrEmpty(schema))
{
throw new Exception("Schema is null.");
}
if (!schema.Contains("Cluster"))
{
throw new Exception("Schema does not contain Cluster.");
}
if (!schema.Contains("Score"))
{
throw new Exception("Schema does not contain Score.");
}
StreamHelper.SaveModel(env, xf, outModelFilePath);
var saver = env.CreateSaver("Text{header=- schema=-}");
using (var fs2 = File.Create(outputDataFilePath))
saver.SaveData(fs2, TestTransformHelper.AddFlatteningTransform(env, xf),
StreamHelper.GetColumnsIndex(xf.Schema, new[] { "Features", "ClusterId", "Score" }));
// Checking the values.
var lines = File.ReadAllLines(outputDataFilePath).Select(c => c.Split('\t')).Where(c => c.Length == 4);
if (!lines.Any())
{
throw new Exception(string.Format("The output file is empty or not containing three columns '{0}'", outputDataFilePath));
}
var clusters = lines.Select(c => c[1]).Distinct();
if (clusters.Count() <= 1)
{
throw new Exception("Only one cluster, this is unexpected.");
}
// Serialization.
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
TestTransformHelper.SerializationTestTransform(env, outModelFilePath, xf, loader, outData, outData2);
}
}
public void TestSelectTagContactViewTransform()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var firstData = FileHelper.GetOutputFile("first.idv", methodName);
var outData = FileHelper.GetOutputFile("outData.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
using (var env = EnvHelper.NewTestEnvironment())
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 0, 1, 4 }
},
new ExampleA()
{
X = new float[] { 2, 3, 7 }
}
};
// Create IDV
IDataView loader = env.CreateStreamingDataView(inputs);
var saver = ComponentCreation.CreateSaver(env, "binary");
using (var ch = env.Start("save"))
{
using (var fs0 = env.CreateOutputFile(firstData))
DataSaverUtils.SaveDataView(ch, saver, loader, fs0, true);
// Create parallel pipeline
loader = env.CreateStreamingDataView(inputs);
var data = env.CreateTransform("Scaler{col=X1:X}", loader);
data = env.CreateTransform(string.Format("selecttag{{t=first s=second f={0}}}", firstData), data);
data = env.CreateTransform("Scaler{col=X1:X}", data);
var merged = env.CreateTransform("append{t=first}", data);
// Save the outcome
var text = env.CreateSaver("Text");
var columns = new int[merged.Schema.Count];
for (int i = 0; i < columns.Length; ++i)
{
columns[i] = i;
}
using (var fs2 = File.Create(outData))
text.SaveData(fs2, merged, columns);
// Final checking
var lines = File.ReadAllLines(outData);
if (!lines.Any())
{
throw new Exception("Empty file.");
}
if (lines.Length != 9)
{
throw new Exception("Some lines are missing.");
}
}
}
}
public void TestScikitAPI_SimplePredictor()
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 1, 10, 100 }
},
new ExampleA()
{
X = new float[] { 2, 3, 5 }
},
new ExampleA()
{
X = new float[] { 2, 4, 5 }
},
new ExampleA()
{
X = new float[] { 2, 4, 7 }
},
};
var inputs2 = new[] {
new ExampleA()
{
X = new float[] { -1, -10, -100 }
},
new ExampleA()
{
X = new float[] { -2, -3, -5 }
},
new ExampleA()
{
X = new float[] { 3, 4, 5 }
},
new ExampleA()
{
X = new float[] { 3, 4, 7 }
},
};
/*using (*/
var host = EnvHelper.NewTestEnvironment(conc: 1);
{
var data = DataViewConstructionUtils.CreateFromEnumerable(host, inputs);
using (var pipe = new ScikitPipeline(new[] { "poly{col=X}" }, "km{k=2}", host))
{
var predictor = pipe.Train(data, feature: "X");
Assert.IsTrue(predictor != null);
var data2 = new StreamingDataFrame(DataViewConstructionUtils.CreateFromEnumerable(host, inputs2));
var predictions = pipe.Predict(data2);
var df = DataFrameIO.ReadView(predictions);
Assert.AreEqual(df.Shape, new Tuple <int, int>(4, 12));
var dfs = df.ToString();
var dfs2 = dfs.Replace("\n", ";");
Assert.IsTrue(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"));
}
}
}
unsafe InvokeData ILambdaRuntime.ReceiveInvoke(IDictionary initialEnvironmentVariables, RuntimeReceiveInvokeBuffers buffers)
{
if (!invoked)
{
receivedInvokeAt = DateTimeOffset.Now;
invoked = true;
}
else
{
logs = "";
}
var result = client.GetAsync("http://127.0.0.1:9001/2018-06-01/runtime/invocation/next").Result;
if (result.StatusCode != HttpStatusCode.OK)
{
throw new Exception("Got a bad response from the bootstrap");
}
var requestId = result.Headers.GetValues("Lambda-Runtime-Aws-Request-Id").First();
var deadlineMs = result.Headers.GetValues("Lambda-Runtime-Deadline-Ms").First();
var functionArn = result.Headers.GetValues("Lambda-Runtime-Invoked-Function-Arn").First();
var xAmznTraceId = result.Headers.GetValues("Lambda-Runtime-Trace-Id").First();
var clientContext = HeaderHelper.GetFirstOrDefault(result.Headers, "Lambda-Runtime-Client-Context");
var cognitoIdentity = HeaderHelper.GetFirstOrDefault(result.Headers, "Lambda-Runtime-Cognito-Identity");
logTail = HeaderHelper.GetFirstOrDefault(result.Headers, "Docker-Lambda-Log-Type") == "Tail";
var body = result.Content.ReadAsStringAsync().Result;
context.RequestId = requestId;
context.DeadlineMs = long.Parse(deadlineMs);
context.Body = body;
curSBSharedMem = new SBSharedMem(sharedMem);
return(new InvokeData(curSBSharedMem)
{
RequestId = context.RequestId,
AwsCredentials = new AwsCredentials
{
AccessKeyId = EnvHelper.GetOrDefault("AWS_ACCESS_KEY_ID", "SOME_ACCESS_KEY_ID"),
SecretAccessKey = EnvHelper.GetOrDefault("AWS_SECRET_ACCESS_KEY", "SOME_SECRET_ACCESS_KEY"),
SessionToken = System.Environment.GetEnvironmentVariable("AWS_SESSION_TOKEN")
},
XAmznTraceId = xAmznTraceId,
InputStream = context.InputStream,
OutputStream = new UnmanagedMemoryStream(curSBSharedMem.EventBody, 0, SBSharedMem.SizeOfEventBody, FileAccess.Write),
LambdaContextInternal = new LambdaContextInternal(
context.RemainingTime,
SendCustomerLogMessage,
GetCognitoClientContextInternalLazy(clientContext),
context.RequestId,
new Lazy <string>(context.Arn),
GetCognitoIdentityIdLazy(cognitoIdentity),
GetCognitoIdentityPoolIdLazy(cognitoIdentity),
initialEnvironmentVariables
)
});
}
public void SolutionEvents_Opened()
{
EnvHelper.GetTortoiseGitProc();
EnvHelper.GetGit();
EnvHelper.GetSolutionDir(_dte);
EnvHelper.GetGitConfig();
EnvHelper.GetBranchName();
EnvHelper.GetStash();
}
private static IDataScorerTransform _TrainSentiment()
{
bool normalize = true;
var args = new TextLoader.Options()
{
Separators = new[] { '\t' },
HasHeader = true,
Columns = new[]
{
new TextLoader.Column("Label", DataKind.Boolean, 0),
new TextLoader.Column("SentimentText", DataKind.String, 1)
}
};
var args2 = new TextFeaturizingEstimator.Options()
{
KeepDiacritics = false,
KeepPunctuations = false,
CaseMode = TextNormalizingEstimator.CaseMode.Lower,
OutputTokensColumnName = "tokens",
Norm = normalize ? TextFeaturizingEstimator.NormFunction.L2 : TextFeaturizingEstimator.NormFunction.None,
CharFeatureExtractor = new WordBagEstimator.Options()
{
NgramLength = 3, UseAllLengths = false
},
WordFeatureExtractor = new WordBagEstimator.Options()
{
NgramLength = 2, UseAllLengths = true
},
};
var trainFilename = FileHelper.GetTestFile("wikipedia-detox-250-line-data.tsv");
/*using (*/
var env = EnvHelper.NewTestEnvironment(seed: 1, conc: 1);
{
// Pipeline
var loader = new TextLoader(env, args).Load(new MultiFileSource(trainFilename));
var trans = TextFeaturizingEstimator.Create(env, args2, loader);
// Train
var trainer = new SdcaLogisticRegressionBinaryTrainer(env, new SdcaLogisticRegressionBinaryTrainer.Options
{
LabelColumnName = "Label",
FeatureColumnName = "Features"
});
var cached = new Microsoft.ML.Data.CacheDataView(env, trans, prefetch: null);
var predictor = trainer.Fit(cached);
var trainRoles = new RoleMappedData(cached, label: "Label", feature: "Features");
var scoreRoles = new RoleMappedData(trans, label: "Label", feature: "Features");
return(ScoreUtils.GetScorer(predictor.Model, scoreRoles, env, trainRoles.Schema));
}
}
public StoreEngine(ILogger logger, ServerCfg serverCfg)
: base(PartNames.Store, logger)
{
_inboundCallQueue = new AsyncThreadQueue(Logger);
string connectionString = EnvHelper.FormatDbCfgStr(serverCfg.ModuleInfo.ConfigEnv, serverCfg.DbServer, serverCfg.DbPrefix);
Logger.LogDebug("Connection String: {0}", connectionString);
_state = new Guarded <StoreEngineState>(new StoreEngineState(serverCfg, connectionString));
}
public void TrainTestPipelinePredictTransform()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var dataFilePath = FileHelper.GetTestFile("mc_iris.txt");
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
using (var env = EnvHelper.NewTestEnvironment(conc: 1))
{
var loader = env.CreateLoader("Text{col=Label:R4:0 col=Slength:R4:1 col=Swidth:R4:2 col=Plength:R4:3 col=Pwidth:R4:4 header=+}",
new MultiFileSource(dataFilePath));
var pipe = env.CreateTransform("Concat{col=Features:Slength,Swidth}", loader);
pipe = env.CreateTransform("SplitTrainTest{col=base tag=train tag=test}", pipe);
pipe = env.CreateTransform("SelectTag{tag=unused selectTag=train}", pipe);
pipe = env.CreateTransform(string.Format("TagTrainScore{{tag=trainP out={0} tr=mlr}}", outModelFilePath), pipe);
pipe = env.CreateTransform("SelectTag{tag=scoredTrain selectTag=test}", pipe);
pipe = env.CreateTransform("TagPredict{in=trainP}", pipe);
string schema = SchemaHelper.ToString(pipe.Schema);
var cursor = pipe.GetRowCursor(i => true);
string schema2 = SchemaHelper.ToString(cursor.Schema);
if (schema != schema2)
{
throw new Exception("Schema mismatch.");
}
long count = DataViewUtils.ComputeRowCount(pipe);
if (count != 49)
{
throw new Exception(string.Format("Unexpected number of rows {0}", count));
}
// Checks the outputs.
var saver = env.CreateSaver("Text");
var columns = new string[pipe.Schema.Count];
for (int i = 0; i < columns.Length; ++i)
{
columns[i] = pipe.Schema[i].Name;
}
using (var fs2 = File.Create(outData))
saver.SaveData(fs2, pipe, StreamHelper.GetColumnsIndex(pipe.Schema));
var lines = File.ReadAllLines(outData);
if (lines.Length < 40)
{
throw new Exception("Something is missing:" + string.Join("\n", lines));
}
if (lines.Length > 70)
{
throw new Exception("Too much data:" + string.Join("\n", lines));
}
TestTransformHelper.SerializationTestTransform(env, outModelFilePath, pipe, loader, outData, outData2);
}
}
public PredictionEngineExample(string modelName)
{
_env = EnvHelper.NewTestEnvironment();
var view = DataViewConstructionUtils.CreateFromEnumerable(_env, new FloatVectorInput[] { });
var pipe = DataViewConstructionUtils.LoadPipeWithPredictor(_env, File.OpenRead(modelName),
new EmptyDataView(_env, view.Schema));
var transformer = new TransformWrapper(_env, pipe);
_predictor = _env.CreatePredictionEngine <FloatVectorInput, FloatOutput>(transformer);
}
