public string GetContent(int ifeat)
{
Contracts.Assert(0 <= ifeat && ifeat < Count);
DvText content = _content.GetItemOrDefault(ifeat);
return(content.HasChars ? content.ToString() : DatasetUtils.GetDefaultTransform(GetName(ifeat)));
}
public string GetName(int ifeat)
{
Contracts.Assert(0 <= ifeat && ifeat < Count);
DvText name = _names.GetItemOrDefault(ifeat);
return(name.HasChars ? name.ToString() : string.Format("f{0}", ifeat));
}
public void CanSuccessfullyRetrieveQuotedData()
{
string dataPath = GetDataPath("QuotingData.csv");
var loader = new Data.TextLoader(dataPath).CreateFrom <QuoteInput>(useHeader: true, separator: ',', allowQuotedStrings: true, supportSparse: false);
using (var environment = new TlcEnvironment())
{
Experiment experiment = environment.CreateExperiment();
ILearningPipelineDataStep output = loader.ApplyStep(null, experiment) as ILearningPipelineDataStep;
experiment.Compile();
loader.SetInput(environment, experiment);
experiment.Run();
IDataView data = experiment.GetOutput(output.Data);
Assert.NotNull(data);
using (var cursor = data.GetRowCursor((a => true)))
{
var IDGetter = cursor.GetGetter <float>(0);
var TextGetter = cursor.GetGetter <DvText>(1);
Assert.True(cursor.MoveNext());
float ID = 0;
IDGetter(ref ID);
Assert.Equal(1, ID);
DvText Text = new DvText();
TextGetter(ref Text);
Assert.Equal("This text contains comma, within quotes.", Text.ToString());
Assert.True(cursor.MoveNext());
ID = 0;
IDGetter(ref ID);
Assert.Equal(2, ID);
Text = new DvText();
TextGetter(ref Text);
Assert.Equal("This text contains extra punctuations and special characters.;*<>?!@#$%^&*()_+=-{}|[]:;'", Text.ToString());
Assert.True(cursor.MoveNext());
ID = 0;
IDGetter(ref ID);
Assert.Equal(3, ID);
Text = new DvText();
TextGetter(ref Text);
Assert.Equal("This text has no quotes", Text.ToString());
Assert.False(cursor.MoveNext());
}
}
}
private static Action <TRow> CreateTextToStringSetter(IRow input, int col, Delegate poke)
{
var getter = input.GetGetter <DvText>(col);
var typedPoke = poke as Poke <TRow, string>;
Contracts.AssertValue(typedPoke);
DvText value = default(DvText);
return(row =>
{
getter(ref value);
typedPoke(row, value.ToString());
});
}
protected override Delegate GetGetterCore(IChannel ch, IRow input, int iinfo, out Action disposer)
{
Host.AssertValue(ch, nameof(ch));
Host.AssertValue(input);
Host.Assert(0 <= iinfo && iinfo < Infos.Length);
disposer = null;
var getSrc = GetSrcGetter <DvText>(input, iinfo);
DvText src = default;
ValueGetter <Bitmap> del =
(ref Bitmap dst) =>
{
if (dst != null)
{
dst.Dispose();
dst = null;
}
getSrc(ref src);
if (src.Length > 0)
{
// Catch exceptions and pass null through. Should also log failures...
try
{
string path = src.ToString();
if (!string.IsNullOrWhiteSpace(_imageFolder))
{
path = Path.Combine(_imageFolder, path);
}
dst = new Bitmap(path);
}
catch (Exception e)
{
// REVIEW: We catch everything since the documentation for new Bitmap(string)
// appears to be incorrect. When the file isn't found, it throws an ArgumentException,
// while the documentation says FileNotFoundException. Not sure what it will throw
// in other cases, like corrupted file, etc.
// REVIEW : Log failures.
ch.Info(e.Message);
ch.Info(e.StackTrace);
dst = null;
}
}
};
return(del);
}
protected override Delegate MakeGetter(IRow input, int iinfo, out Action disposer)
{
Contracts.AssertValue(input);
Contracts.Assert(0 <= iinfo && iinfo < _parent.ColumnPairs.Length);
disposer = null;
var getSrc = input.GetGetter <DvText>(ColMapNewToOld[iinfo]);
DvText src = default;
ValueGetter <Bitmap> del =
(ref Bitmap dst) =>
{
if (dst != null)
{
dst.Dispose();
dst = null;
}
getSrc(ref src);
if (src.Length > 0)
{
// Catch exceptions and pass null through. Should also log failures...
try
{
string path = src.ToString();
if (!string.IsNullOrWhiteSpace(_parent.ImageFolder))
{
path = Path.Combine(_parent.ImageFolder, path);
}
dst = new Bitmap(path);
}
catch (Exception)
{
// REVIEW: We catch everything since the documentation for new Bitmap(string)
// appears to be incorrect. When the file isn't found, it throws an ArgumentException,
// while the documentation says FileNotFoundException. Not sure what it will throw
// in other cases, like corrupted file, etc.
// REVIEW : Log failures.
dst = null;
}
}
};
return(del);
}
public void CanSuccessfullyTrimSpaces()
{
string dataPath = GetDataPath("TrimData.csv");
var loader = new Data.TextLoader(dataPath).CreateFrom <QuoteInput>(useHeader: true, separator: ',', allowQuotedStrings: false, supportSparse: false, trimWhitespace: true);
using (var environment = new TlcEnvironment())
{
Experiment experiment = environment.CreateExperiment();
ILearningPipelineDataStep output = loader.ApplyStep(null, experiment) as ILearningPipelineDataStep;
experiment.Compile();
loader.SetInput(environment, experiment);
experiment.Run();
IDataView data = experiment.GetOutput(output.Data);
Assert.NotNull(data);
using (var cursor = data.GetRowCursor((a => true)))
{
var IDGetter = cursor.GetGetter <float>(0);
var TextGetter = cursor.GetGetter <DvText>(1);
Assert.True(cursor.MoveNext());
float ID = 0;
IDGetter(ref ID);
Assert.Equal(1, ID);
DvText Text = new DvText();
TextGetter(ref Text);
Assert.Equal("There is a space at the end", Text.ToString());
Assert.True(cursor.MoveNext());
ID = 0;
IDGetter(ref ID);
Assert.Equal(2, ID);
Text = new DvText();
TextGetter(ref Text);
Assert.Equal("There is no space at the end", Text.ToString());
Assert.False(cursor.MoveNext());
}
}
}
public static NumericColumn Operation(NumericColumn c1, DvText value)
{
switch (c1.Kind)
{
case DataKind.TX:
{
DvText[] a;
DataColumn <DvText> res;
Operation(c1, out a, out res);
for (int i = 0; i < res.Length; ++i)
{
res.Set(i, new DvText(a[i].ToString() + value.ToString()));
}
return(new NumericColumn(res));
}
default:
throw new DataTypeError(string.Format("{0} not implemented for column {1}.", OperationName, c1.Kind));
}
}
private bool?IsLookLikeHeader(DvText value)
{
var v = value.ToString();
if (v.Length > 100)
{
return(false);
}
var headerCandidates = new[] { "^Label", "^Feature", "^Market", "^m_", "^Weight" };
foreach (var candidate in headerCandidates)
{
if (Regex.IsMatch(v, candidate, RegexOptions.IgnoreCase))
{
return(true);
}
}
return(null);
}
public static PipelineResultRow[] ExtractResults(IHostEnvironment env, IDataView data, string graphColName, string metricColName, string idColName)
{
var results = new List <PipelineResultRow>();
var schema = data.Schema;
if (!schema.TryGetColumnIndex(graphColName, out var graphCol))
{
throw env.ExceptNotSupp($"Column name {graphColName} not found");
}
if (!schema.TryGetColumnIndex(metricColName, out var metricCol))
{
throw env.ExceptNotSupp($"Column name {metricColName} not found");
}
if (!schema.TryGetColumnIndex(idColName, out var pipelineIdCol))
{
throw env.ExceptNotSupp($"Column name {idColName} not found");
}
using (var cursor = data.GetRowCursor(col => true))
{
while (cursor.MoveNext())
{
var getter1 = cursor.GetGetter <double>(metricCol);
double metricValue = 0;
getter1(ref metricValue);
var getter2 = cursor.GetGetter <DvText>(graphCol);
DvText graphJson = new DvText();
getter2(ref graphJson);
var getter3 = cursor.GetGetter <DvText>(pipelineIdCol);
DvText pipelineId = new DvText();
getter3(ref pipelineId);
results.Add(new PipelineResultRow(graphJson.ToString(), metricValue, pipelineId.ToString()));
}
}
return(results.ToArray());
}
public void TestSaveImages()
{
using (var env = new ConsoleEnvironment())
{
var dataFile = GetDataPath("images/images.tsv");
var imageFolder = Path.GetDirectoryName(dataFile);
var data = env.CreateLoader("Text{col=ImagePath:TX:0 col=Name:TX:1}", new MultiFileSource(dataFile));
var images = ImageLoaderTransform.Create(env, new ImageLoaderTransform.Arguments()
{
Column = new ImageLoaderTransform.Column[1]
{
new ImageLoaderTransform.Column()
{
Source = "ImagePath", Name = "ImageReal"
}
},
ImageFolder = imageFolder
}, data);
IDataView cropped = ImageResizerTransform.Create(env, new ImageResizerTransform.Arguments()
{
Column = new ImageResizerTransform.Column[1] {
new ImageResizerTransform.Column()
{
Name = "ImageCropped", Source = "ImageReal", ImageHeight = 100, ImageWidth = 100, Resizing = ImageResizerTransform.ResizingKind.IsoPad
}
}
}, images);
cropped.Schema.TryGetColumnIndex("ImagePath", out int pathColumn);
cropped.Schema.TryGetColumnIndex("ImageCropped", out int cropBitmapColumn);
using (var cursor = cropped.GetRowCursor((x) => true))
{
var pathGetter = cursor.GetGetter <DvText>(pathColumn);
DvText path = default;
var bitmapCropGetter = cursor.GetGetter <Bitmap>(cropBitmapColumn);
Bitmap bitmap = default;
while (cursor.MoveNext())
{
pathGetter(ref path);
bitmapCropGetter(ref bitmap);
Assert.NotNull(bitmap);
var fileToSave = GetOutputPath(Path.GetFileNameWithoutExtension(path.ToString()) + ".cropped.jpg");
bitmap.Save(fileToSave, System.Drawing.Imaging.ImageFormat.Jpeg);
}
}
}
Done();
}
public static Type InferPredictorCategoryType(IDataView data, PurposeInference.Column[] columns)
{
List <PurposeInference.Column> labels = columns.Where(col => col.Purpose == ColumnPurpose.Label).ToList();
if (labels.Count == 0)
{
return(typeof(SignatureClusteringTrainer));
}
if (labels.Count > 1)
{
return(typeof(SignatureMultiOutputRegressorTrainer));
}
PurposeInference.Column label = labels.First();
HashSet <string> uniqueLabelValues = new HashSet <string>();
data = data.Take(1000);
using (var cursor = data.GetRowCursor(index => index == label.ColumnIndex))
{
ValueGetter <DvText> getter = DataViewUtils.PopulateGetterArray(cursor, new List <int> {
label.ColumnIndex
})[0];
while (cursor.MoveNext())
{
var currentLabel = new DvText();
getter(ref currentLabel);
string currentLabelString = currentLabel.ToString();
if (!String.IsNullOrEmpty(currentLabelString) && !uniqueLabelValues.Contains(currentLabelString))
{
uniqueLabelValues.Add(currentLabelString);
}
}
}
if (uniqueLabelValues.Count == 1)
{
return(typeof(SignatureAnomalyDetectorTrainer));
}
if (uniqueLabelValues.Count == 2)
{
return(typeof(SignatureBinaryClassifierTrainer));
}
if (uniqueLabelValues.Count > 2)
{
if ((label.ItemKind == DataKind.R4) &&
uniqueLabelValues.Any(val =>
{
float fVal;
return(float.TryParse(val, out fVal) && (fVal > 50 || fVal < 0 || val.Contains('.')));
}))
{
return(typeof(SignatureRegressorTrainer));
}
if (label.ItemKind == DataKind.R4 ||
label.ItemKind == DataKind.TX ||
data.Schema.GetColumnType(label.ColumnIndex).IsKey)
{
if (columns.Any(col => col.Purpose == ColumnPurpose.Group))
{
return(typeof(SignatureRankerTrainer));
}
else
{
return(typeof(SignatureMultiClassClassifierTrainer));
}
}
}
return(null);
}
private static ByteString StringToByteString(DvText str) => ByteString.CopyFrom(Encoding.UTF8.GetBytes(str.ToString()));
public static PipelineResultRow[] ExtractResults(IHostEnvironment env, IDataView data,
string graphColName, string metricColName, string idColName, string trainingMetricColName,
string firstInputColName, string predictorModelColName)
{
var results = new List <PipelineResultRow>();
var schema = data.Schema;
if (!schema.TryGetColumnIndex(graphColName, out var graphCol))
{
throw env.ExceptParam(nameof(graphColName), $"Column name {graphColName} not found");
}
if (!schema.TryGetColumnIndex(metricColName, out var metricCol))
{
throw env.ExceptParam(nameof(metricColName), $"Column name {metricColName} not found");
}
if (!schema.TryGetColumnIndex(trainingMetricColName, out var trainingMetricCol))
{
throw env.ExceptParam(nameof(trainingMetricColName), $"Column name {trainingMetricColName} not found");
}
if (!schema.TryGetColumnIndex(idColName, out var pipelineIdCol))
{
throw env.ExceptParam(nameof(idColName), $"Column name {idColName} not found");
}
if (!schema.TryGetColumnIndex(firstInputColName, out var firstInputCol))
{
throw env.ExceptParam(nameof(firstInputColName), $"Column name {firstInputColName} not found");
}
if (!schema.TryGetColumnIndex(predictorModelColName, out var predictorModelCol))
{
throw env.ExceptParam(nameof(predictorModelColName), $"Column name {predictorModelColName} not found");
}
using (var cursor = data.GetRowCursor(col => true))
{
var getter1 = cursor.GetGetter <double>(metricCol);
var getter2 = cursor.GetGetter <DvText>(graphCol);
var getter3 = cursor.GetGetter <DvText>(pipelineIdCol);
var getter4 = cursor.GetGetter <double>(trainingMetricCol);
var getter5 = cursor.GetGetter <DvText>(firstInputCol);
var getter6 = cursor.GetGetter <DvText>(predictorModelCol);
double metricValue = 0;
double trainingMetricValue = 0;
DvText graphJson = new DvText();
DvText pipelineId = new DvText();
DvText firstInput = new DvText();
DvText predictorModel = new DvText();
while (cursor.MoveNext())
{
getter1(ref metricValue);
getter2(ref graphJson);
getter3(ref pipelineId);
getter4(ref trainingMetricValue);
getter5(ref firstInput);
getter6(ref predictorModel);
results.Add(new PipelineResultRow(graphJson.ToString(),
metricValue, pipelineId.ToString(), trainingMetricValue,
firstInput.ToString(), predictorModel.ToString()));
}
}
return(results.ToArray());
}
public void CanSuccessfullyEnumerated()
{
var collection = CollectionDataSource.Create(new List <Input>()
{
new Input {
Number1 = 1, String1 = "1"
},
new Input {
Number1 = 2, String1 = "2"
},
new Input {
Number1 = 3, String1 = "3"
}
});
using (var environment = new TlcEnvironment())
{
Experiment experiment = environment.CreateExperiment();
ILearningPipelineDataStep output = collection.ApplyStep(null, experiment) as ILearningPipelineDataStep;
experiment.Compile();
collection.SetInput(environment, experiment);
experiment.Run();
IDataView data = experiment.GetOutput(output.Data);
Assert.NotNull(data);
using (var cursor = data.GetRowCursor((a => true)))
{
var IDGetter = cursor.GetGetter <float>(0);
var TextGetter = cursor.GetGetter <DvText>(1);
Assert.True(cursor.MoveNext());
float ID = 0;
IDGetter(ref ID);
Assert.Equal(1, ID);
DvText Text = new DvText();
TextGetter(ref Text);
Assert.Equal("1", Text.ToString());
Assert.True(cursor.MoveNext());
ID = 0;
IDGetter(ref ID);
Assert.Equal(2, ID);
Text = new DvText();
TextGetter(ref Text);
Assert.Equal("2", Text.ToString());
Assert.True(cursor.MoveNext());
ID = 0;
IDGetter(ref ID);
Assert.Equal(3, ID);
Text = new DvText();
TextGetter(ref Text);
Assert.Equal("3", Text.ToString());
Assert.False(cursor.MoveNext());
}
}
}
