Final updates for release 1.2.0

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

@@ -2,30 +2,7 @@
 
 ## **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).
+None.
 
 ## **Bug Fixes**
 
@@ -41,7 +18,7 @@ None.
 
 ## **Documentation and Samples**
 
-TBD.
+None.
 
 ## **Remarks**
 

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/__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/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/internal/core/ensemble/lightgbmbinaryclassifier.py

@@ -145,7 +145,7 @@ 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/internal/core/ensemble/lightgbmclassifier.py

@@ -70,6 +70,9 @@ class LightGbmClassifier(
 
     :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.
@@ -137,9 +140,10 @@ 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,
@@ -165,6 +169,7 @@ def __init__(
         self.booster = booster
         self.normalize = normalize
         self.caching = caching
+        self.unbalanced_sets = unbalanced_sets
         self.use_softmax = use_softmax
         self.sigmoid = sigmoid
         self.evaluation_metric = evaluation_metric
@@ -201,6 +206,7 @@ def _get_node(self, **all_args):
             booster=self.booster,
             normalize_features=self.normalize,
             caching=self.caching,
+            unbalanced_sets=self.unbalanced_sets,
             use_softmax=self.use_softmax,
             sigmoid=self.sigmoid,
             evaluation_metric=self.evaluation_metric,

src/python/nimbusml/internal/core/ensemble/lightgbmranker.py

@@ -140,7 +140,7 @@ 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/internal/core/ensemble/lightgbmregressor.py

@@ -133,7 +133,7 @@ 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/internal/entrypoints/trainers_lightgbmbinaryclassifier.py

@@ -26,7 +26,7 @@ def trainers_lightgbmbinaryclassifier(
         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/internal/entrypoints/trainers_lightgbmclassifier.py

@@ -23,9 +23,10 @@ def trainers_lightgbmclassifier(
         row_group_column_name=None,
         normalize_features='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,
@@ -65,6 +66,8 @@ def trainers_lightgbmclassifier(
         column (inputs).
     :param caching: Whether trainer should cache input training data
         (inputs).
+    :param unbalanced_sets: Use for multi-class classification when
+        training data is not balanced (inputs).
     :param use_softmax: Use softmax loss for the multi
         classification. (inputs).
     :param sigmoid: Parameter for the sigmoid function. (inputs).
@@ -174,6 +177,11 @@ def trainers_lightgbmclassifier(
                 'Auto',
                 'Memory',
                 'None'])
+    if unbalanced_sets is not None:
+        inputs['UnbalancedSets'] = try_set(
+            obj=unbalanced_sets,
+            none_acceptable=True,
+            is_of_type=bool)
     if use_softmax is not None:
         inputs['UseSoftmax'] = try_set(
             obj=use_softmax,

src/python/nimbusml/internal/entrypoints/trainers_lightgbmranker.py

@@ -25,7 +25,7 @@ def trainers_lightgbmranker(
         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/internal/entrypoints/trainers_lightgbmregressor.py

@@ -23,7 +23,7 @@ def trainers_lightgbmregressor(
         row_group_column_name=None,
         normalize_features='Auto',
         caching='Auto',
-        evaluation_metric='RootMeanSquaredError',
+        evaluation_metric='Default',
         maximum_bin_count_per_feature=255,
         verbose=False,
         silent=True,

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(