Expose ML.NET SSA & IID spike & changepoint detectors.

src/DotNetBridge/Bridge.cs

@@ -17,6 +17,7 @@
 using Microsoft.ML.Trainers.FastTree;
 using Microsoft.ML.Trainers.LightGbm;
 using Microsoft.ML.Transforms;
+using Microsoft.ML.TimeSeries;
 
 namespace Microsoft.MachineLearning.DotNetBridge
 {
@@ -328,6 +329,7 @@ private static unsafe int GenericExec(EnvironmentBlock* penv, sbyte* psz, int cd
             //env.ComponentCatalog.RegisterAssembly(typeof(SaveOnnxCommand).Assembly);
             //env.ComponentCatalog.RegisterAssembly(typeof(TimeSeriesProcessingEntryPoints).Assembly);
             //env.ComponentCatalog.RegisterAssembly(typeof(ParquetLoader).Assembly);
+            env.ComponentCatalog.RegisterAssembly(typeof(ForecastExtensions).Assembly);
 
             using (var ch = host.Start("Executing"))
             {

src/DotNetBridge/DotNetBridge.csproj

@@ -41,5 +41,6 @@
     <PackageReference Include="Microsoft.ML.OnnxTransformer" Version="0.13.0" />
     <PackageReference Include="Microsoft.ML.TensorFlow" Version="0.13.0" />
     <PackageReference Include="Microsoft.ML.Ensemble" Version="0.13.0" />
+    <PackageReference Include="Microsoft.ML.TimeSeries" Version="0.13.0" />
   </ItemGroup>
 </Project>

src/Platforms/build.csproj

@@ -20,6 +20,7 @@
     <PackageReference Include="Microsoft.ML.OnnxTransformer" Version="0.13.0" />
     <PackageReference Include="Microsoft.ML.TensorFlow" Version="0.13.0" />
     <PackageReference Include="Microsoft.ML.Ensemble" Version="0.13.0" />
+    <PackageReference Include="Microsoft.ML.TimeSeries" Version="0.13.0" />
   </ItemGroup>
 
 </Project>

src/python/nimbusml.pyproj

@@ -88,6 +88,9 @@
     <Compile Include="nimbusml\examples\examples_from_dataframe\GamRegressor_airquality_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\GlobalContrastRowScaler_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\Handler_df.py" />
+    <Compile Include="nimbusml\examples\examples_from_dataframe\IidChangePointDetector_df.py" />
+    <Compile Include="nimbusml\examples\examples_from_dataframe\SsaChangePointDetector_df.py" />
+    <Compile Include="nimbusml\examples\examples_from_dataframe\SsaSpikeDetector_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\Image_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\Indicator_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\FromKey_df.py" />
@@ -109,6 +112,7 @@
     <Compile Include="nimbusml\examples\examples_from_dataframe\OneHotVectorizer_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\OnlineGradientDescentRegressor_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\OrdinaryLeastSquaresRegressor_df.py" />
+    <Compile Include="nimbusml\examples\examples_from_dataframe\IidSpikeDetector_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\PcaAnomalyDetector_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\PcaTransformer_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\RangeFilter_df.py" />
@@ -134,6 +138,9 @@
     <Compile Include="nimbusml\examples\GlobalContrastRowScaler.py" />
     <Compile Include="nimbusml\examples\Handler.py" />
     <Compile Include="nimbusml\examples\Hinge.py" />
+    <Compile Include="nimbusml\examples\IidChangePointDetector.py" />
+    <Compile Include="nimbusml\examples\SsaChangePointDetector.py" />
+    <Compile Include="nimbusml\examples\SsaSpikeDetector.py" />
     <Compile Include="nimbusml\examples\Image.py" />
     <Compile Include="nimbusml\examples\Indicator.py" />
     <Compile Include="nimbusml\examples\FromKey.py" />
@@ -159,6 +166,7 @@
     <Compile Include="nimbusml\examples\OneVsRestClassifier.py" />
     <Compile Include="nimbusml\examples\OnlineGradientDescentRegressor.py" />
     <Compile Include="nimbusml\examples\OrdinaryLeastSquaresRegressor.py" />
+    <Compile Include="nimbusml\examples\IidSpikeDetector.py" />
     <Compile Include="nimbusml\examples\PcaAnomalyDetector.py" />
     <Compile Include="nimbusml\examples\PcaTransformer.py" />
     <Compile Include="nimbusml\examples\PipelineWithGridSearchCV2.py" />
@@ -224,6 +232,11 @@
     <Compile Include="nimbusml\internal\core\preprocessing\schema\columnduplicator.py" />
     <Compile Include="nimbusml\internal\core\preprocessing\schema\columndropper.py" />
     <Compile Include="nimbusml\internal\core\preprocessing\tensorflowscorer.py" />
+    <Compile Include="nimbusml\internal\core\time_series\iidchangepointdetector.py" />
+    <Compile Include="nimbusml\internal\core\time_series\iidspikedetector.py" />
+    <Compile Include="nimbusml\internal\core\time_series\ssachangepointdetector.py" />
+    <Compile Include="nimbusml\internal\core\time_series\ssaspikedetector.py" />
+    <Compile Include="nimbusml\internal\core\time_series\__init__.py" />
     <Compile Include="nimbusml\internal\entrypoints\data_customtextloader.py" />
     <Compile Include="nimbusml\internal\entrypoints\data_dataviewreference.py" />
     <Compile Include="nimbusml\internal\entrypoints\data_idataviewarrayconverter.py" />
@@ -571,6 +584,16 @@
     <Compile Include="nimbusml\tests\feature_extraction\text\test_sentiment.py" />
     <Compile Include="nimbusml\tests\idv\__init__.py" />
     <Compile Include="nimbusml\tests\preprocessing\normalization\test_meanvariancescaler.py" />
+    <Compile Include="nimbusml\tests\time_series\test_iidchangepointdetector.py" />
+    <Compile Include="nimbusml\tests\time_series\test_ssachangepointdetector.py" />
+    <Compile Include="nimbusml\tests\time_series\test_ssaspikedetector.py" />
+    <Compile Include="nimbusml\tests\time_series\test_iidspikedetector.py" />
+    <Compile Include="nimbusml\tests\time_series\__init__.py" />
+    <Compile Include="nimbusml\time_series\iidchangepointdetector.py" />
+    <Compile Include="nimbusml\time_series\iidspikedetector.py" />
+    <Compile Include="nimbusml\time_series\ssachangepointdetector.py" />
+    <Compile Include="nimbusml\time_series\ssaspikedetector.py" />
+    <Compile Include="nimbusml\time_series\__init__.py" />
     <Compile Include="tests\test_estimator_checks.py" />
     <Compile Include="nimbusml\tests\feature_extraction\text\test_lightlda.py" />
     <Compile Include="nimbusml\tests\idv\test_idv.py" />
@@ -743,6 +766,7 @@
     <Folder Include="nimbusml\internal\core\preprocessing\normalization\" />
     <Folder Include="nimbusml\internal\core\preprocessing\schema\" />
     <Folder Include="nimbusml\internal\core\preprocessing\text\" />
+    <Folder Include="nimbusml\internal\core\time_series\" />
     <Folder Include="nimbusml\internal\entrypoints\" />
     <Folder Include="nimbusml\internal\utils\" />
     <Folder Include="nimbusml\linear_model\" />
@@ -764,6 +788,7 @@
     <Folder Include="nimbusml\tests\multiclass\" />
     <Folder Include="nimbusml\tests\model_summary\" />
     <Folder Include="nimbusml\tests\idv\" />
+    <Folder Include="nimbusml\tests\time_series\" />
     <Folder Include="nimbusml\tests\pipeline\" />
     <Folder Include="nimbusml\tests\feature_extraction\" />
     <Folder Include="nimbusml\tests\feature_extraction\categorical\" />
@@ -780,6 +805,7 @@
     <Folder Include="nimbusml\tests\preprocessing\text\" />
     <Folder Include="nimbusml\tests\scikit\" />
     <Folder Include="nimbusml\tests\utils\" />
+    <Folder Include="nimbusml\time_series\" />
     <Folder Include="nimbusml\utils\" />
     <Folder Include="tests\" />
     <Folder Include="tools\" />

src/python/nimbusml/examples/IidChangePointDetector.py

@@ -0,0 +1,38 @@
+###############################################################################
+# IidChangePointDetector
+from nimbusml import Pipeline, FileDataStream
+from nimbusml.datasets import get_dataset
+from nimbusml.time_series import IidChangePointDetector
+
+# data input (as a FileDataStream)
+path = get_dataset('timeseries').as_filepath()
+
+data = FileDataStream.read_csv(path)
+print(data.head())
+#      t1    t2      t3
+# 0  0.01  0.01  0.0100
+# 1  0.02  0.02  0.0200
+# 2  0.03  0.03  0.0200
+# 3  0.03  0.03  0.0250
+# 4  0.03  0.03  0.0005
+
+# define the training pipeline
+pipeline = Pipeline([
+    IidChangePointDetector(columns={'t2_cp': 't2'}, change_history_length=4)
+])
+
+result = pipeline.fit_transform(data)
+print(result)
+
+#      t1     t2       t3  t2_cp.Alert  t2_cp.Raw Score  t2_cp.P-Value Score  t2_cp.Martingale Score
+# 0  0.01   0.01   0.0100          0.0             0.01         5.000000e-01            1.212573e-03
+# 1  0.02   0.02   0.0200          0.0             0.02         4.960106e-01            1.221347e-03
+# 2  0.03   0.03   0.0200          0.0             0.03         1.139087e-02            3.672914e-02
+# 3  0.03   0.03   0.0250          0.0             0.03         2.058296e-01            8.164447e-02
+# 4  0.03   0.03   0.0005          0.0             0.03         2.804577e-01            1.373786e-01
+# 5  0.03   0.05   0.0100          1.0             0.05         1.448886e-06            1.315014e+04
+# 6  0.05   0.07   0.0500          0.0             0.07         2.616611e-03            4.941587e+04
+# 7  0.07   0.09   0.0900          0.0             0.09         3.053187e-02            2.752614e+05
+# 8  0.09  99.00  99.0000          0.0            99.00         1.000000e-08            1.389396e+12
+# 9  1.10   0.10   0.1000          1.0             0.10         3.778296e-01            1.854344e+07
+

src/python/nimbusml/examples/IidSpikeDetector.py

@@ -0,0 +1,37 @@
+###############################################################################
+# IidSpikeDetector
+from nimbusml import Pipeline, FileDataStream
+from nimbusml.datasets import get_dataset
+from nimbusml.time_series import IidSpikeDetector
+
+# data input (as a FileDataStream)
+path = get_dataset('timeseries').as_filepath()
+
+data = FileDataStream.read_csv(path)
+print(data.head())
+#      t1    t2      t3
+# 0  0.01  0.01  0.0100
+# 1  0.02  0.02  0.0200
+# 2  0.03  0.03  0.0200
+# 3  0.03  0.03  0.0250
+# 4  0.03  0.03  0.0005
+
+# define the training pipeline
+pipeline = Pipeline([
+    IidSpikeDetector(columns={'t2_spikes': 't2'}, pvalue_history_length=5)
+])
+
+result = pipeline.fit_transform(data)
+print(result)
+#      t1     t2       t3  t2_spikes.Alert  t2_spikes.Raw Score  t2_spikes.P-Value Score
+# 0  0.01   0.01   0.0100              0.0                 0.01             5.000000e-01
+# 1  0.02   0.02   0.0200              0.0                 0.02             4.960106e-01
+# 2  0.03   0.03   0.0200              0.0                 0.03             1.139087e-02
+# 3  0.03   0.03   0.0250              0.0                 0.03             2.058296e-01
+# 4  0.03   0.03   0.0005              0.0                 0.03             2.804577e-01
+# 5  0.03   0.05   0.0100              1.0                 0.05             3.743552e-03
+# 6  0.05   0.07   0.0500              1.0                 0.07             4.136079e-03
+# 7  0.07   0.09   0.0900              0.0                 0.09             2.242496e-02
+# 8  0.09  99.00  99.0000              1.0                99.00             1.000000e-08
+# 9  1.10   0.10   0.1000              0.0                 0.10             4.015681e-01
+

src/python/nimbusml/examples/SsaChangePointDetector.py

@@ -0,0 +1,40 @@
+###############################################################################
+# SsaChangePointDetector
+from nimbusml import Pipeline, FileDataStream
+from nimbusml.datasets import get_dataset
+from nimbusml.time_series import SsaChangePointDetector
+
+# data input (as a FileDataStream)
+path = get_dataset('timeseries').as_filepath()
+
+data = FileDataStream.read_csv(path)
+print(data.head())
+#      t1    t2      t3
+# 0  0.01  0.01  0.0100
+# 1  0.02  0.02  0.0200
+# 2  0.03  0.03  0.0200
+# 3  0.03  0.03  0.0250
+# 4  0.03  0.03  0.0005
+
+# define the training pipeline
+pipeline = Pipeline([
+    SsaChangePointDetector(columns={'t2_cp': 't2'},
+                           change_history_length=4,
+                           training_window_size=8,
+                           seasonal_window_size=3)
+])
+
+result = pipeline.fit_transform(data)
+print(result)
+
+#      t1     t2       t3  t2_cp.Alert  t2_cp.Raw Score  t2_cp.P-Value Score  t2_cp.Martingale Score
+# 0  0.01   0.01   0.0100          0.0        -0.111334         5.000000e-01                0.001213
+# 1  0.02   0.02   0.0200          0.0        -0.076755         4.862075e-01                0.001243
+# 2  0.03   0.03   0.0200          0.0        -0.034871         3.856320e-03                0.099119
+# 3  0.03   0.03   0.0250          0.0        -0.012559         8.617091e-02                0.482400
+# 4  0.03   0.03   0.0005          0.0        -0.015723         2.252377e-01                0.988788
+# 5  0.03   0.05   0.0100          0.0        -0.001133         1.767711e-01                2.457946
+# 6  0.05   0.07   0.0500          0.0         0.006265         9.170460e-02                0.141898
+# 7  0.07   0.09   0.0900          0.0         0.002383         2.701134e-01                0.050747
+# 8  0.09  99.00  99.0000          1.0        98.879520         1.000000e-08           210274.372059
+# 9  1.10   0.10   0.1000          0.0       -57.817568         6.635692e-02           507877.454862

src/python/nimbusml/examples/SsaSpikeDetector.py

@@ -0,0 +1,40 @@
+###############################################################################
+# SsaSpikeDetector
+from nimbusml import Pipeline, FileDataStream
+from nimbusml.datasets import get_dataset
+from nimbusml.time_series import SsaSpikeDetector
+
+# data input (as a FileDataStream)
+path = get_dataset('timeseries').as_filepath()
+
+data = FileDataStream.read_csv(path)
+print(data.head())
+#      t1    t2      t3
+# 0  0.01  0.01  0.0100
+# 1  0.02  0.02  0.0200
+# 2  0.03  0.03  0.0200
+# 3  0.03  0.03  0.0250
+# 4  0.03  0.03  0.0005
+
+# define the training pipeline
+pipeline = Pipeline([
+    SsaSpikeDetector(columns={'t2_spikes': 't2'},
+                     pvalue_history_length=4,
+                     training_window_size=8,
+                     seasonal_window_size=3)
+])
+
+result = pipeline.fit_transform(data)
+print(result)
+
+#      t1     t2       t3  t2_spikes.Alert  t2_spikes.Raw Score  t2_spikes.P-Value Score
+# 0  0.01   0.01   0.0100              0.0            -0.111334             5.000000e-01
+# 1  0.02   0.02   0.0200              0.0            -0.076755             4.862075e-01
+# 2  0.03   0.03   0.0200              0.0            -0.034871             3.856320e-03
+# 3  0.03   0.03   0.0250              0.0            -0.012559             8.617091e-02
+# 4  0.03   0.03   0.0005              0.0            -0.015723             2.252377e-01
+# 5  0.03   0.05   0.0100              0.0            -0.001133             1.767711e-01
+# 6  0.05   0.07   0.0500              0.0             0.006265             9.170460e-02
+# 7  0.07   0.09   0.0900              0.0             0.002383             2.701134e-01
+# 8  0.09  99.00  99.0000              1.0            98.879520             1.000000e-08
+# 9  1.10   0.10   0.1000              0.0           -57.817568             6.635692e-02

src/python/nimbusml/examples/examples_from_dataframe/IidChangePointDetector_df.py

@@ -0,0 +1,34 @@
+###############################################################################
+# IidChangePointDetector
+import pandas as pd
+from nimbusml.time_series import IidChangePointDetector
+
+# Create a sample series with a change
+input_data = [5, 5, 5, 5, 5, 5, 5, 5]
+input_data.extend([7, 7, 7, 7, 7, 7, 7, 7])
+
+X_train = pd.Series(input_data, name="ts")
+
+cpd = IidChangePointDetector(confidence=95, change_history_length=4) << {'result': 'ts'}
+data = cpd.fit_transform(X_train)
+
+print(data)
+
+#     ts  result.Alert  result.Raw Score  result.P-Value Score  result.Martingale Score
+# 0    5           0.0               5.0          5.000000e-01                 0.001213
+# 1    5           0.0               5.0          5.000000e-01                 0.001213
+# 2    5           0.0               5.0          5.000000e-01                 0.001213
+# 3    5           0.0               5.0          5.000000e-01                 0.001213
+# 4    5           0.0               5.0          5.000000e-01                 0.001213
+# 5    5           0.0               5.0          5.000000e-01                 0.001213
+# 6    5           0.0               5.0          5.000000e-01                 0.001213
+# 7    5           0.0               5.0          5.000000e-01                 0.001213
+# 8    7           1.0               7.0          1.000000e-08             10298.666376   <-- alert is on, predicted changepoint
+# 9    7           0.0               7.0          1.328455e-01             33950.164799
+# 10   7           0.0               7.0          2.613750e-01             60866.342063
+# 11   7           0.0               7.0          3.776152e-01             78362.038772
+# 12   7           0.0               7.0          5.000000e-01                 0.009226
+# 13   7           0.0               7.0          5.000000e-01                 0.002799
+# 14   7           0.0               7.0          5.000000e-01                 0.001561
+# 15   7           0.0               7.0          5.000000e-01                 0.001213
+

src/python/nimbusml/examples/examples_from_dataframe/IidSpikeDetector_df.py

@@ -0,0 +1,27 @@
+###############################################################################
+# IidSpikeDetector
+import numpy as np
+import pandas as pd
+from nimbusml.time_series import IidSpikeDetector
+
+X_train = pd.Series([5, 5, 5, 5, 5, 10, 5, 5, 5, 5, 5], name="ts")
+
+isd = IidSpikeDetector(confidence=95, pvalue_history_length=2.5) << {'result': 'ts'}
+
+isd.fit(X_train, verbose=1)
+data = isd.transform(X_train)
+
+print(data)
+
+#       ts  result.Alert  result.Raw Score  result.P-Value Score
+# 0    5.0           0.0               5.0          5.000000e-01
+# 1    5.0           0.0               5.0          5.000000e-01
+# 2    5.0           0.0               5.0          5.000000e-01
+# 3    5.0           0.0               5.0          5.000000e-01
+# 4    5.0           0.0               5.0          5.000000e-01
+# 5   10.0           1.0              10.0          1.000000e-08
+# 6    5.0           0.0               5.0          2.613750e-01
+# 7    5.0           0.0               5.0          2.613750e-01
+# 8    5.0           0.0               5.0          5.000000e-01
+# 9    5.0           0.0               5.0          5.000000e-01
+# 10   5.0           0.0               5.0          5.000000e-01