// This example requires installation of additional nuget package <a href="https://www.nuget.org/packages/Microsoft.ML.FastTree/">Microsoft.ML.FastTree</a>.
public static void FastTreeBinaryClassification()
{
// Downloading a classification dataset from github.com/dotnet/machinelearning.
// It will be stored in the same path as the executable
string dataFilePath = SamplesUtils.DatasetUtils.DownloadAdultDataset();
// Data Preview
// 1. Column [Label]: IsOver50K (boolean)
// 2. Column: workclass (text/categorical)
// 3. Column: education (text/categorical)
// 4. Column: marital-status (text/categorical)
// 5. Column: occupation (text/categorical)
// 6. Column: relationship (text/categorical)
// 7. Column: ethnicity (text/categorical)
// 8. Column: sex (text/categorical)
// 9. Column: native-country-region (text/categorical)
// 10. Column: age (numeric)
// 11. Column: fnlwgt (numeric)
// 12. Column: education-num (numeric)
// 13. Column: capital-gain (numeric)
// 14. Column: capital-loss (numeric)
// 15. Column: hours-per-week (numeric)
// Creating the ML.Net IHostEnvironment object, needed for the pipeline
var mlContext = new MLContext();
// Creating Data Loader with the initial schema based on the format of the data
var loader = TextLoaderStatic.CreateLoader(
mlContext,
c => (
Age: c.LoadFloat(0),
Workclass: c.LoadText(1),
Fnlwgt: c.LoadFloat(2),
Education: c.LoadText(3),
EducationNum: c.LoadFloat(4),
MaritalStatus: c.LoadText(5),
Occupation: c.LoadText(6),
Relationship: c.LoadText(7),
Ethnicity: c.LoadText(8),
Sex: c.LoadText(9),
CapitalGain: c.LoadFloat(10),
CapitalLoss: c.LoadFloat(11),
HoursPerWeek: c.LoadFloat(12),
NativeCountry: c.LoadText(13),
IsOver50K: c.LoadBool(14)),
separator: ',',
hasHeader: true);
// Loader the data, and leave 10% out, so we can use them for testing
var data = loader.Load(dataFilePath);
var(trainData, testData) = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
// Create the Estimator
var learningPipeline = loader.MakeNewEstimator()
.Append(row => (
Features: row.Age.ConcatWith(
row.EducationNum,
row.MaritalStatus.OneHotEncoding(),
row.Occupation.OneHotEncoding(),
row.Relationship.OneHotEncoding(),
row.Ethnicity.OneHotEncoding(),
row.Sex.OneHotEncoding(),
row.HoursPerWeek,
row.NativeCountry.OneHotEncoding().SelectFeaturesBasedOnCount(count: 10)),
Label: row.IsOver50K))
.Append(row => (
Features: row.Features.Normalize(),
Label: row.Label,
Score: mlContext.BinaryClassification.Trainers.FastTree(
row.Label,
row.Features,
numberOfTrees: 100, // try: (int) 20-2000
numberOfLeaves: 20, // try: (int) 2-128
minimumExampleCountPerLeaf: 10, // try: (int) 1-100
learningRate: 0.2))) // try: (float) 0.025-0.4
.Append(row => (
Label: row.Label,
Score: row.Score,
PredictedLabel: row.Score.predictedLabel));
// Fit this Pipeline to the Training Data
var model = learningPipeline.Fit(trainData);
// Evaluate how the model is doing on the test data
var dataWithPredictions = model.Transform(testData);
var metrics = mlContext.BinaryClassification.Evaluate(dataWithPredictions, row => row.Label, row => row.Score);
Console.WriteLine($"Accuracy: {metrics.Accuracy}"); // 0.84
Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve}"); // 0.89
Console.WriteLine($"F1 Score: {metrics.F1Score}"); // 0.64
Console.WriteLine($"Negative Precision: {metrics.NegativePrecision}"); // 0.88
Console.WriteLine($"Negative Recall: {metrics.NegativeRecall}"); // 0.91
Console.WriteLine($"Positive Precision: {metrics.PositivePrecision}"); // 0.68
Console.WriteLine($"Positive Recall: {metrics.PositiveRecall}"); // 0.60
}
public void SimpleTextLoaderCopyColumnsTest()
{
var env = new MLContext(0);
const string data = "0 hello 3.14159 -0 2\n"
+ "1 1 2 4 15";
var dataSource = new BytesStreamSource(data);
var text = TextLoaderStatic.CreateLoader(env, ctx => (
label: ctx.LoadBool(0),
text: ctx.LoadText(1),
numericFeatures: ctx.LoadFloat(2, null)), // If fit correctly, this ought to be equivalent to max of 4, that is, length of 3.
dataSource, separator: ' ');
// While we have a type-safe wrapper for `IDataView` it is utterly useless except as an input to the `Fit` functions
// of the other statically typed wrappers. We perhaps ought to make it useful in its own right, but perhaps not now.
// For now, just operate over the actual `IDataView`.
var textData = text.Load(dataSource).AsDynamic;
Action <DataViewSchema, string> CheckSchemaHasColumn = (dataSchema, name) =>
{
Assert.True(dataSchema.GetColumnOrNull(name).HasValue, "Could not find column '" + name + "'");
};
var schema = textData.Schema;
// First verify that the columns are there. There ought to be at least one column corresponding to the identifiers in the tuple.
CheckSchemaHasColumn(schema, "label");
CheckSchemaHasColumn(schema, "text");
CheckSchemaHasColumn(schema, "numericFeatures");
// Next verify they have the expected types.
Assert.Equal(BooleanDataViewType.Instance, schema["label"].Type);
Assert.Equal(TextDataViewType.Instance, schema["text"].Type);
Assert.Equal(new VectorType(NumberDataViewType.Single, 3), schema["numericFeatures"].Type);
// Next actually inspect the data.
using (var cursor = textData.GetRowCursorForAllColumns())
{
var textGetter = cursor.GetGetter <ReadOnlyMemory <char> >(schema["text"]);
var numericFeaturesGetter = cursor.GetGetter <VBuffer <float> >(schema["numericFeatures"]);
ReadOnlyMemory <char> textVal = default;
var labelGetter = cursor.GetGetter <bool>(schema["label"]);
bool labelVal = default;
VBuffer <float> numVal = default;
void CheckValuesSame(bool bl, string tx, float v0, float v1, float v2)
{
labelGetter(ref labelVal);
textGetter(ref textVal);
numericFeaturesGetter(ref numVal);
Assert.True(tx.AsSpan().SequenceEqual(textVal.Span));
Assert.Equal((bool)bl, labelVal);
Assert.Equal(3, numVal.Length);
Assert.Equal(v0, numVal.GetItemOrDefault(0));
Assert.Equal(v1, numVal.GetItemOrDefault(1));
Assert.Equal(v2, numVal.GetItemOrDefault(2));
}
Assert.True(cursor.MoveNext(), "Could not move even to first row");
CheckValuesSame(false, "hello", 3.14159f, -0f, 2f);
Assert.True(cursor.MoveNext(), "Could not move to second row");
CheckValuesSame(true, "1", 2f, 4f, 15f);
Assert.False(cursor.MoveNext(), "Moved to third row, but there should have been only two");
}
// The next step where we shuffle the names around a little bit is one where we are
// testing out the implicit usage of copy columns.
var est = text.MakeNewEstimator().Append(r => (text: r.label, label: r.numericFeatures));
var newText = text.Append(est);
var newTextData = newText.Fit(dataSource).Load(dataSource);
schema = newTextData.AsDynamic.Schema;
// First verify that the columns are there. There ought to be at least one column corresponding to the identifiers in the tuple.
CheckSchemaHasColumn(schema, "label");
CheckSchemaHasColumn(schema, "text");
// Next verify they have the expected types.
Assert.Equal(BooleanDataViewType.Instance, schema["text"].Type);
Assert.Equal(new VectorType(NumberDataViewType.Single, 3), schema["label"].Type);
}
