Update the documentation of 1.2 release

README.md

@@ -12,7 +12,7 @@ Documentation can be found [here](https://docs.microsoft.com/en-us/NimbusML/over
 
 `nimbusml` runs on Windows, Linux, and macOS. 
 
-`nimbusml` requires Python **2.7**, **3.5**, **3.6** 64 bit version only.
+`nimbusml` requires Python **2.7**, **3.5**, **3.6**, **3.7** 64 bit version only.
 
 Install `nimbusml` using `pip` with:
 

build.cmd

@@ -24,6 +24,7 @@ set RunTests=False
 set RunExtendedTests=False
 set BuildDotNetBridgeOnly=False
 set SkipDotNetBridge=False
+set AzureBuild=False
 
 :Arg_Loop
 if [%1] == [] goto :Build
@@ -45,17 +46,22 @@ if /i [%1] == [--buildDotNetBridgeOnly]     (
 if /i [%1] == [--skipDotNetBridge]     (
     set SkipDotNetBridge=True
     shift && goto :Arg_Loop
+)
+if /i [%1] == [--azureBuild]     (
+    set AzureBuild=True
+    shift && goto :Arg_Loop
 ) else goto :Usage
 
 :Usage
-echo "Usage: build.cmd [--configuration <Configuration>] [--runTests] [--includeExtendedTests] [--buildDotNetBridgeOnly] [--skipDotNetBridge]"
+echo "Usage: build.cmd [--configuration <Configuration>] [--runTests] [--includeExtendedTests] [--buildDotNetBridgeOnly] [--skipDotNetBridge] [--azureBuild]"
 echo ""
 echo "Options:"
 echo "  --configuration <Configuration>   Build Configuration (DbgWinPy3.7,DbgWinPy3.6,DbgWinPy3.5,DbgWinPy2.7,RlsWinPy3.7,RlsWinPy3.6,RlsWinPy3.5,RlsWinPy2.7)"
 echo "  --runTests                        Run tests after build"
 echo "  --includeExtendedTests            Include the extended tests if the tests are run"
 echo "  --buildDotNetBridgeOnly           Build only DotNetBridge"
 echo "  --skipDotNetBridge                Build everything except DotNetBridge"
+echo "  --azureBuild                      Building in azure devops (adds dotnet CLI to the path)"
 goto :Exit_Success
 
 :Configuration
@@ -153,12 +159,19 @@ if /i [%1] == [DbgWinPy2.7]     (
 echo Installing dotnet SDK ... 
 powershell -NoProfile -ExecutionPolicy unrestricted -Command "[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12; &([scriptblock]::Create((Invoke-WebRequest -useb 'https://dot.net/v1/dotnet-install.ps1'))) -Version 2.1.200 -InstallDir ./cli"
 
+set _dotnetRoot=%__currentScriptDir%cli
+
+if "%AzureBuild%" == "True" (
+    :: Add dotnet CLI root to the PATH in azure devops agent
+    echo ##vso[task.prependpath]%_dotnetRoot%
+)
+
 :: Build managed code
 echo ""
 echo "#################################"
 echo "Building DotNet Bridge ... "
 echo "#################################"
-set _dotnet=%__currentScriptDir%cli\dotnet.exe
+set _dotnet=%_dotnetRoot%\dotnet.exe
 
 if "%SkipDotNetBridge%" == "False" ( 
     call "%_dotnet%" build -c %Configuration% -o "%BuildOutputDir%%Configuration%"  --force "%__currentScriptDir%src\DotNetBridge\DotNetBridge.csproj"

build/signed_build_phase.yml

@@ -28,7 +28,7 @@ phases:
     continueOnError: false
     condition: and(succeeded(), in(variables._SignType, 'real', 'test'))
 
-  - script: ./build.cmd --buildDotNetBridgeOnly --configuration $(BuildConfig)
+  - script: ./build.cmd --buildDotNetBridgeOnly --azureBuild --configuration $(BuildConfig)
     displayName: Build DotNetBridgeOnly
 
   - task: MSBuild@1

docs/release-notes/release-1.2.0.md

@@ -0,0 +1,52 @@
+# [NimbusML](https://docs.microsoft.com/en-us/nimbusml/overview) 1.2.0
+
+## **New Features**
+
+- **Time Series Spike And Change Point Detection**
+
+   [PR#135](https://github.com/microsoft/NimbusML/pull/135) added support
+   for time series spike and change point detection using the Independent
+   and identically distributed (IID) and Singular Spectrum Analysis (SSA)
+   algorithms.
+
+   **Spike Detection Examples**
+
+   - [IID using a pandas Series](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/examples_from_dataframe/IidSpikeDetector_df.py)
+   - [SSA using a pandas Series](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/examples_from_dataframe/SsaSpikeDetector_df.py)
+   - [IID using a FileDataStream](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/IidSpikeDetector.py)
+   - [SSA using a FileDataStream](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/SsaSpikeDetector.py)
+
+   **Change Point Detection Examples**
+
+   - [IID using a pandas Series](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/examples_from_dataframe/IidChangePointDetector_df.py)
+   - [SSA using a pandas Series](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/examples_from_dataframe/SsaChangePointDetector_df.py)
+   - [IID using a FileDataStream](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/IidChangePointDetector.py)
+   - [SSA using a FileDataStream](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/SsaChangePointDetector.py)
+
+- **Time Series Forecasting**
+   [PR#164](https://github.com/microsoft/NimbusML/pull/164) exposes an API
+   for time series forecasting using Singular Spectrum Analysis(SSA).
+
+   **Forecasting Examples**
+   - [Using a pandas Series](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/examples_from_dataframe/SsaForecaster_df.py)
+   - [Using a FileDataStream](https://github.com/microsoft/NimbusML/tree/master/src/python/nimbusml/examples/SsaForecaster.py)
+
+## **Bug Fixes**
+
+None.
+
+## **Breaking Changes**
+
+None.
+
+## **Enhancements**
+
+None.
+
+## **Documentation and Samples**
+
+- Sample for CharTokenizer. [PR#153](https://github.com/microsoft/NimbusML/pull/153)
+
+## **Remarks**
+
+None.

release-next.md

@@ -0,0 +1,25 @@
+# [NimbusML](https://docs.microsoft.com/en-us/nimbusml/overview) Next
+
+## **New Features**
+
+None.
+
+## **Bug Fixes**
+
+None.
+
+## **Breaking Changes**
+
+None.
+
+## **Enhancements**
+
+None.
+
+## **Documentation and Samples**
+
+None.
+
+## **Remarks**
+
+None.

src/DotNetBridge/DotNetBridge.csproj

@@ -31,16 +31,16 @@
       <PrivateAssets>all</PrivateAssets>
       <IncludeAssets>runtime; build; native; contentfiles; analyzers</IncludeAssets>
     </PackageReference>
-    <PackageReference Include="Microsoft.ML" Version="1.1.0" />
-    <PackageReference Include="Microsoft.ML.CpuMath" Version="1.1.0" />    
-    <PackageReference Include="Microsoft.ML.EntryPoints" Version="0.13.0" />
-    <PackageReference Include="Microsoft.ML.Mkl.Components" Version="1.1.0" />
-    <PackageReference Include="Microsoft.ML.Mkl.Redist" Version="1.1.0" />
-    <PackageReference Include="Microsoft.ML.ImageAnalytics" Version="1.1.0" />
-    <PackageReference Include="Microsoft.ML.LightGBM" Version="1.1.0" />
-    <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" />
+    <PackageReference Include="Microsoft.ML" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.CpuMath" Version="1.2.0" />    
+    <PackageReference Include="Microsoft.ML.EntryPoints" Version="0.14.0" />
+    <PackageReference Include="Microsoft.ML.Mkl.Components" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.Mkl.Redist" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.ImageAnalytics" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.LightGBM" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.OnnxTransformer" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.TensorFlow" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.Ensemble" Version="0.14.0" />
+    <PackageReference Include="Microsoft.ML.TimeSeries" Version="1.2.0" />
   </ItemGroup>
 </Project>

src/Platforms/build.csproj

@@ -11,16 +11,16 @@
   </PropertyGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.ML" Version="1.1.0" />
-    <PackageReference Include="Microsoft.ML.CpuMath" Version="1.1.0" />    
-    <PackageReference Include="Microsoft.ML.EntryPoints" Version="0.13.0" />
-    <PackageReference Include="Microsoft.ML.Mkl.Components" Version="1.1.0" />
-    <PackageReference Include="Microsoft.ML.ImageAnalytics" Version="1.1.0" />
-    <PackageReference Include="Microsoft.ML.LightGBM" Version="1.1.0" />
-    <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" />
+    <PackageReference Include="Microsoft.ML" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.CpuMath" Version="1.2.0" />    
+    <PackageReference Include="Microsoft.ML.EntryPoints" Version="0.14.0" />
+    <PackageReference Include="Microsoft.ML.Mkl.Components" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.ImageAnalytics" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.LightGBM" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.OnnxTransformer" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.TensorFlow" Version="1.2.0" />
+    <PackageReference Include="Microsoft.ML.Ensemble" Version="0.14.0" />
+    <PackageReference Include="Microsoft.ML.TimeSeries" Version="1.2.0" />
   </ItemGroup>
 
 </Project>

src/python/nimbusml.pyproj

@@ -231,6 +231,7 @@
     <Compile Include="nimbusml\internal\core\timeseries\_iidchangepointdetector.py" />
     <Compile Include="nimbusml\internal\core\timeseries\_iidspikedetector.py" />
     <Compile Include="nimbusml\internal\core\timeseries\_ssachangepointdetector.py" />
+    <Compile Include="nimbusml\internal\core\timeseries\_ssaforecaster.py" />
     <Compile Include="nimbusml\internal\core\timeseries\_ssaspikedetector.py" />
     <Compile Include="nimbusml\internal\core\timeseries\__init__.py" />
     <Compile Include="nimbusml\internal\core\preprocessing\filter\_skipfilter.py" />

src/python/nimbusml/__init__.py

@@ -2,7 +2,7 @@
 Microsoft Machine Learning for Python
 """
 
-__version__ = '1.1.0'
+__version__ = '1.2.0'
 
 # CoreCLR version of MicrosoftML is built on Windows.
 # But file permissions are not preserved when it's copied to Linux.

src/python/nimbusml/_pipeline.py

@@ -2210,18 +2210,26 @@ def _validate_model_summary(self, model_summary):
                 "is expected ".format(
                     type(model_summary)))
 
-        str_bias = 'Bias'
-        str_classnames = 'ClassNames'
-        str_coefficients = 'Coefficients'
-        str_weights = 'Weights'
-        str_gains = 'Gains'
-        str_support_vectors = 'Support vectors.'
+        col_names = [
+            'Bias',
+            'ClassNames',
+            'Coefficients',
+            'PredictorName',
+            'Summary',
+            'VectorName'
+        ]
+
+        col_name_prefixes = [
+            'Weights',
+            'Gains',
+            'Support vectors.',
+            'VectorData'
+        ]
 
         for col in model_summary.columns:
-            if col in (str_bias, str_classnames, str_coefficients):
+            if col in col_names:
                 pass
-            elif col.startswith(str_weights) or col.startswith(
-                    str_gains) or col.startswith(str_support_vectors):
+            elif any([col.startswith(pre) for pre in col_name_prefixes]):
                 pass
             else:
                 raise TypeError(

src/python/nimbusml/ensemble/_lightgbmbinaryclassifier.py

@@ -156,7 +156,7 @@ def __init__(
             unbalanced_sets=False,
             weight_of_positive_examples=1.0,
             sigmoid=0.5,
-            evaluation_metric='Logloss',
+            evaluation_metric='Default',
             maximum_bin_count_per_feature=255,
             verbose=False,
             silent=True,

src/python/nimbusml/ensemble/_lightgbmclassifier.py

@@ -78,6 +78,9 @@ class LightGbmClassifier(core, BasePredictor, ClassifierMixin):
 
     :param caching: Whether trainer should cache input training data.
 
+    :param unbalanced_sets: Use for multi-class classification when training
+        data is not balanced.
+
     :param use_softmax: Use softmax loss for the multi classification.
 
     :param sigmoid: Parameter for the sigmoid function.
@@ -145,9 +148,10 @@ def __init__(
             booster=None,
             normalize='Auto',
             caching='Auto',
+            unbalanced_sets=False,
             use_softmax=None,
             sigmoid=0.5,
-            evaluation_metric='Error',
+            evaluation_metric='Default',
             maximum_bin_count_per_feature=255,
             verbose=False,
             silent=True,
@@ -198,6 +202,7 @@ def __init__(
             booster=booster,
             normalize=normalize,
             caching=caching,
+            unbalanced_sets=unbalanced_sets,
             use_softmax=use_softmax,
             sigmoid=sigmoid,
             evaluation_metric=evaluation_metric,

src/python/nimbusml/ensemble/_lightgbmranker.py

@@ -150,7 +150,7 @@ def __init__(
             caching='Auto',
             custom_gains=[0, 3, 7, 15, 31, 63, 127, 255, 511, 1023, 2047, 4095],
             sigmoid=0.5,
-            evaluation_metric='NormalizedDiscountedCumulativeGain',
+            evaluation_metric='Default',
             maximum_bin_count_per_feature=255,
             verbose=False,
             silent=True,

src/python/nimbusml/ensemble/_lightgbmregressor.py

@@ -141,7 +141,7 @@ def __init__(
             booster=None,
             normalize='Auto',
             caching='Auto',
-            evaluation_metric='RootMeanSquaredError',
+            evaluation_metric='Default',
             maximum_bin_count_per_feature=255,
             verbose=False,
             silent=True,

src/python/nimbusml/examples/SsaForecaster.py

@@ -19,13 +19,10 @@
 
 # define the training pipeline
 pipeline = Pipeline([
-    SsaForecaster(forcasting_confident_lower_bound_column_name="cmin",
-                  forcasting_confident_upper_bound_column_name="cmax",
-                  series_length=6,
+    SsaForecaster(series_length=6,
                   train_size=8,
                   window_size=3,
                   horizon=2,
-                  # max_growth={'TimeSpan': 1, 'Growth': 1}
                   columns={'t2_fc': 't2'})
 ])
 
@@ -35,15 +32,15 @@
 print(result)
 
 # Output
-#     t1    t2    t3  t2_fc.0  t2_fc.1  cmin.0  cmin.1  cmax.0  cmax.1
-# 0 0.01  0.01  0.01     0.10     0.12    0.09    0.11    0.11    0.13
-# 1 0.02  0.02  0.02     0.06     0.08    0.06    0.07    0.07    0.09
-# 2 0.03  0.03  0.02     0.04     0.05    0.03    0.04    0.05    0.07
-# 3 0.03  0.03  0.03     0.05     0.06    0.04    0.05    0.05    0.07
-# 4 0.03  0.03  0.00     0.05     0.07    0.04    0.05    0.06    0.08
-# 5 0.03  0.05  0.01     0.06     0.08    0.05    0.07    0.07    0.10
-# 6 0.05  0.07  0.05     0.09     0.12    0.08    0.10    0.10    0.13
-# 7 0.07  0.09  0.09     0.12     0.16    0.11    0.15    0.13    0.17
-# 8 0.09 99.00 99.00    57.92    82.88   57.91   82.87   57.93   82.89
-# 9 1.10  0.10  0.10    60.50    77.18   60.49   77.17   60.50   77.19
-
+#
+#     t1    t2    t3  t2_fc.0  t2_fc.1
+# 0 0.01  0.01  0.01     0.10     0.12
+# 1 0.02  0.02  0.02     0.06     0.08
+# 2 0.03  0.03  0.02     0.04     0.05
+# 3 0.03  0.03  0.03     0.05     0.06
+# 4 0.03  0.03  0.00     0.05     0.07
+# 5 0.03  0.05  0.01     0.06     0.08
+# 6 0.05  0.07  0.05     0.09     0.12
+# 7 0.07  0.09  0.09     0.12     0.16
+# 8 0.09 99.00 99.00    57.92    82.88
+# 9 1.10  0.10  0.10    60.50    77.18