Update to the latest entry point version of SsaForecaster. Fix a few

naming issues and remove the confidence lower and upper bounds from
the examples.

Author: [email protected]

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 +32,16 @@
 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
 

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

@@ -54,35 +54,33 @@
 training_seasons = 3
 training_size = seasonality_size * training_seasons
 
-forecaster = SsaForecaster(forcasting_confident_lower_bound_column_name="cmin",
-                           forcasting_confident_upper_bound_column_name="cmax",
-                           series_length=8,
+forecaster = SsaForecaster(series_length=8,
                            train_size=training_size,
                            window_size=seasonality_size + 1,
-                           horizon=4,
-                           # max_growth={'TimeSpan': 1, 'Growth': 1}
-                           ) <<   {'fc': 'ts'}
+                           horizon=4) <<   {'fc': 'ts'}
 
 forecaster.fit(X_train, verbose=1)
 data = forecaster.transform(x_test)
 
 pd.set_option('display.float_format', lambda x: '%.2f' % x)
 print(data)
 
-# Output
-#      ts  fc.0  fc.1  fc.2  fc.3  cmin.0  cmin.1  cmin.2  cmin.3  cmax.0  cmax.1  cmax.2  cmax.3
-# 0     0  1.00  2.00  3.00  4.00    1.00    2.00    3.00    4.00    1.00    2.00    3.00    4.00
-# 1     1  2.00  3.00  4.00 -0.00    2.00    3.00    4.00   -0.00    2.00    3.00    4.00    0.00
-# 2     2  3.00  4.00 -0.00  1.00    3.00    4.00   -0.00    1.00    3.00    4.00    0.00    1.00
-# 3     3  4.00 -0.00  1.00  2.00    4.00   -0.00    1.00    2.00    4.00    0.00    1.00    2.00
-# 4     4 -0.00  1.00  2.00  3.00   -0.00    1.00    2.00    3.00    0.00    1.00    2.00    3.00
-# 5     0  1.00  2.00  3.00  4.00    1.00    2.00    3.00    4.00    1.00    2.00    3.00    4.00
-# 6     1  2.00  3.00  4.00 -0.00    2.00    3.00    4.00   -0.00    2.00    3.00    4.00    0.00
-# 7     2  3.00  4.00 -0.00  1.00    3.00    4.00   -0.00    1.00    3.00    4.00    0.00    1.00
-# 8     3  4.00 -0.00  1.00  2.00    4.00   -0.00    1.00    2.00    4.00    0.00    1.00    2.00
-# 9     4 -0.00  1.00  2.00  3.00   -0.00    1.00    2.00    3.00    0.00    1.00    2.00    3.00
-# 10    0  1.00  2.00  3.00  4.00    1.00    2.00    3.00    4.00    1.00    2.00    3.00    4.00
-# 11    1  2.00  3.00  4.00 -0.00    2.00    3.00    4.00   -0.00    2.00    3.00    4.00    0.00
-# 12  100  3.00  4.00  0.00  1.00    3.00    4.00   -0.00    1.00    3.00    4.00    0.00    1.00
-# 13  110  4.00 -0.00  1.00 75.50    4.00   -0.00    1.00   75.50    4.00   -0.00    1.00   75.50
-# 14  120 -0.00  1.00 83.67 83.25   -0.00    1.00   83.67   83.25   -0.00    1.00   83.67   83.25
+# The fc.x columns are the forecasts
+# given the input in the ts column.
+#
+#      ts  fc.0  fc.1  fc.2  fc.3
+# 0     0  1.00  2.00  3.00  4.00
+# 1     1  2.00  3.00  4.00 -0.00
+# 2     2  3.00  4.00 -0.00  1.00
+# 3     3  4.00 -0.00  1.00  2.00
+# 4     4 -0.00  1.00  2.00  3.00
+# 5     0  1.00  2.00  3.00  4.00
+# 6     1  2.00  3.00  4.00 -0.00
+# 7     2  3.00  4.00 -0.00  1.00
+# 8     3  4.00 -0.00  1.00  2.00
+# 9     4 -0.00  1.00  2.00  3.00
+# 10    0  1.00  2.00  3.00  4.00
+# 11    1  2.00  3.00  4.00 -0.00
+# 12  100  3.00  4.00  0.00  1.00
+# 13  110  4.00 -0.00  1.00 75.50
+# 14  120 -0.00  1.00 83.67 83.25

src/python/nimbusml/internal/core/timeseries/ssaforecaster.py

@@ -37,11 +37,11 @@ class SsaForecaster(BasePipelineItem, DefaultSignature):
     :param variable_horizon: Set this to true horizon will change at prediction
         time.
 
-    :param forcasting_confident_lower_bound_column_name: The name of the
-        confidence interval lower bound column.
+    :param lower_bound_confidence_column: The name of the confidence interval
+        lower bound column.
 
-    :param forcasting_confident_upper_bound_column_name: The name of the
-        confidence interval upper bound column.
+    :param upper_bound_confidence_column: The name of the confidence interval
+        upper bound column.
 
     :param rank_selection_method: The rank selection method.
 
@@ -54,7 +54,7 @@ class SsaForecaster(BasePipelineItem, DefaultSignature):
         process. If not provided (i.e. set to null), it is set to windowSize -
         1.
 
-    :param should_stablize: The flag determining whether the model should be
+    :param should_stabilize: The flag determining whether the model should be
         stabilized.
 
     :param should_maintain_info: The flag determining whether the meta
@@ -80,12 +80,12 @@ def __init__(
             horizon=0,
             confidence_level=0.95,
             variable_horizon=False,
-            forcasting_confident_lower_bound_column_name=None,
-            forcasting_confident_upper_bound_column_name=None,
+            lower_bound_confidence_column=None,
+            upper_bound_confidence_column=None,
             rank_selection_method='Exact',
             rank=None,
             max_rank=None,
-            should_stablize=True,
+            should_stabilize=True,
             should_maintain_info=False,
             max_growth=None,
             discount_factor=1.0,
@@ -100,12 +100,12 @@ def __init__(
         self.horizon = horizon
         self.confidence_level = confidence_level
         self.variable_horizon = variable_horizon
-        self.forcasting_confident_lower_bound_column_name = forcasting_confident_lower_bound_column_name
-        self.forcasting_confident_upper_bound_column_name = forcasting_confident_upper_bound_column_name
+        self.lower_bound_confidence_column = lower_bound_confidence_column
+        self.upper_bound_confidence_column = upper_bound_confidence_column
         self.rank_selection_method = rank_selection_method
         self.rank = rank
         self.max_rank = max_rank
-        self.should_stablize = should_stablize
+        self.should_stabilize = should_stabilize
         self.should_maintain_info = should_maintain_info
         self.max_growth = max_growth
         self.discount_factor = discount_factor
@@ -126,12 +126,12 @@ def _get_node(self, **all_args):
             horizon=self.horizon,
             confidence_level=self.confidence_level,
             variable_horizon=self.variable_horizon,
-            forcasting_confident_lower_bound_column_name=self.forcasting_confident_lower_bound_column_name,
-            forcasting_confident_upper_bound_column_name=self.forcasting_confident_upper_bound_column_name,
+            lower_bound_confidence_column=self.lower_bound_confidence_column,
+            upper_bound_confidence_column=self.upper_bound_confidence_column,
             rank_selection_method=self.rank_selection_method,
             rank=self.rank,
             max_rank=self.max_rank,
-            should_stablize=self.should_stablize,
+            should_stabilize=self.should_stabilize,
             should_maintain_info=self.should_maintain_info,
             max_growth=self.max_growth,
             discount_factor=self.discount_factor,

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

@@ -21,12 +21,12 @@ def timeseriesprocessingentrypoints_ssaforecasting(
         horizon=0,
         confidence_level=0.95,
         variable_horizon=False,
-        forcasting_confident_lower_bound_column_name=None,
-        forcasting_confident_upper_bound_column_name=None,
+        lower_bound_confidence_column=None,
+        upper_bound_confidence_column=None,
         rank_selection_method='Exact',
         rank=None,
         max_rank=None,
-        should_stablize=True,
+        should_stabilize=True,
         should_maintain_info=False,
         max_growth=None,
         discount_factor=1.0,
@@ -50,10 +50,10 @@ def timeseriesprocessingentrypoints_ssaforecasting(
         forecasting. (inputs).
     :param variable_horizon: Set this to true horizon will change at
         prediction time. (inputs).
-    :param forcasting_confident_lower_bound_column_name: The name of
-        the confidence interval lower bound column. (inputs).
-    :param forcasting_confident_upper_bound_column_name: The name of
-        the confidence interval upper bound column. (inputs).
+    :param lower_bound_confidence_column: The name of the confidence
+        interval lower bound column. (inputs).
+    :param upper_bound_confidence_column: The name of the confidence
+        interval upper bound column. (inputs).
     :param rank_selection_method: The rank selection method.
         (inputs).
     :param rank: The desired rank of the subspace used for SSA
@@ -64,7 +64,7 @@ def timeseriesprocessingentrypoints_ssaforecasting(
     :param max_rank: The maximum rank considered during the rank
         selection process. If not provided (i.e. set to null), it is
         set to windowSize - 1. (inputs).
-    :param should_stablize: The flag determining whether the model
+    :param should_stabilize: The flag determining whether the model
         should be stabilized. (inputs).
     :param should_maintain_info: The flag determining whether the
         meta information for the model needs to be maintained.
@@ -130,15 +130,15 @@ def timeseriesprocessingentrypoints_ssaforecasting(
             obj=variable_horizon,
             none_acceptable=True,
             is_of_type=bool)
-    if forcasting_confident_lower_bound_column_name is not None:
-        inputs['ForcastingConfidentLowerBoundColumnName'] = try_set(
-            obj=forcasting_confident_lower_bound_column_name,
+    if lower_bound_confidence_column is not None:
+        inputs['LowerBoundConfidenceColumn'] = try_set(
+            obj=lower_bound_confidence_column,
             none_acceptable=True,
             is_of_type=str,
             is_column=True)
-    if forcasting_confident_upper_bound_column_name is not None:
-        inputs['ForcastingConfidentUpperBoundColumnName'] = try_set(
-            obj=forcasting_confident_upper_bound_column_name,
+    if upper_bound_confidence_column is not None:
+        inputs['UpperBoundConfidenceColumn'] = try_set(
+            obj=upper_bound_confidence_column,
             none_acceptable=True,
             is_of_type=str,
             is_column=True)
@@ -161,9 +161,9 @@ def timeseriesprocessingentrypoints_ssaforecasting(
             obj=max_rank,
             none_acceptable=True,
             is_of_type=numbers.Real)
-    if should_stablize is not None:
-        inputs['ShouldStablize'] = try_set(
-            obj=should_stablize,
+    if should_stabilize is not None:
+        inputs['ShouldStabilize'] = try_set(
+            obj=should_stabilize,
             none_acceptable=True,
             is_of_type=bool)
     if should_maintain_info is not None:

src/python/nimbusml/tests/timeseries/test_ssaforecaster.py

@@ -26,9 +26,7 @@ def test_simple_forecast(self):
         training_seasons = 3
         training_size = seasonality_size * training_seasons
 
-        forecaster = SsaForecaster(forcasting_confident_lower_bound_column_name="cmin",
-                                   forcasting_confident_upper_bound_column_name="cmax",
-                                   series_length=8,
+        forecaster = SsaForecaster(series_length=8,
                                    train_size=training_size,
                                    window_size=seasonality_size + 1,
                                    horizon=2) <<   {'fc': 'ts'}
@@ -48,9 +46,7 @@ def test_multiple_user_specified_columns_is_not_allowed(self):
 
         try:
             pipeline = Pipeline([
-                SsaForecaster(forcasting_confident_lower_bound_column_name="cmin",
-                              forcasting_confident_upper_bound_column_name="cmax",
-                              series_length=8,
+                SsaForecaster(series_length=8,
                               train_size=15,
                               window_size=5,
                               horizon=2,

src/python/nimbusml/timeseries/ssaforecaster.py

@@ -40,11 +40,11 @@ class SsaForecaster(core, BaseTransform, TransformerMixin):
     :param variable_horizon: Set this to true horizon will change at prediction
         time.
 
-    :param forcasting_confident_lower_bound_column_name: The name of the
-        confidence interval lower bound column.
+    :param lower_bound_confidence_column: The name of the confidence interval
+        lower bound column.
 
-    :param forcasting_confident_upper_bound_column_name: The name of the
-        confidence interval upper bound column.
+    :param upper_bound_confidence_column: The name of the confidence interval
+        upper bound column.
 
     :param rank_selection_method: The rank selection method.
 
@@ -57,7 +57,7 @@ class SsaForecaster(core, BaseTransform, TransformerMixin):
         process. If not provided (i.e. set to null), it is set to windowSize -
         1.
 
-    :param should_stablize: The flag determining whether the model should be
+    :param should_stabilize: The flag determining whether the model should be
         stabilized.
 
     :param should_maintain_info: The flag determining whether the meta
@@ -83,12 +83,12 @@ def __init__(
             horizon=0,
             confidence_level=0.95,
             variable_horizon=False,
-            forcasting_confident_lower_bound_column_name=None,
-            forcasting_confident_upper_bound_column_name=None,
+            lower_bound_confidence_column=None,
+            upper_bound_confidence_column=None,
             rank_selection_method='Exact',
             rank=None,
             max_rank=None,
-            should_stablize=True,
+            should_stabilize=True,
             should_maintain_info=False,
             max_growth=None,
             discount_factor=1.0,
@@ -107,12 +107,12 @@ def __init__(
             horizon=horizon,
             confidence_level=confidence_level,
             variable_horizon=variable_horizon,
-            forcasting_confident_lower_bound_column_name=forcasting_confident_lower_bound_column_name,
-            forcasting_confident_upper_bound_column_name=forcasting_confident_upper_bound_column_name,
+            lower_bound_confidence_column=lower_bound_confidence_column,
+            upper_bound_confidence_column=upper_bound_confidence_column,
             rank_selection_method=rank_selection_method,
             rank=rank,
             max_rank=max_rank,
-            should_stablize=should_stablize,
+            should_stabilize=should_stabilize,
             should_maintain_info=should_maintain_info,
             max_growth=max_growth,
             discount_factor=discount_factor,

src/python/tests/test_estimator_checks.py

@@ -200,9 +200,7 @@
                                    window_size=2,
                                    series_length=5,
                                    train_size=5,
-                                   horizon=1,
-                                   forcasting_confident_lower_bound_column_name="cmin",
-                                   forcasting_confident_upper_bound_column_name="cmax"),
+                                   horizon=1),
     'TensorFlowScorer': TensorFlowScorer(
         model_location=os.path.join(
             this,

src/python/tools/manifest.json

@@ -4095,7 +4095,7 @@
           "Default": false
         },
         {
-          "Name": "ForcastingConfidentLowerBoundColumnName",
+          "Name": "LowerBoundConfidenceColumn",
           "Type": "String",
           "Desc": "The name of the confidence interval lower bound column.",
           "Aliases": [
@@ -4107,7 +4107,7 @@
           "Default": null
         },
         {
-          "Name": "ForcastingConfidentUpperBoundColumnName",
+          "Name": "UpperBoundConfidenceColumn",
           "Type": "String",
           "Desc": "The name of the confidence interval upper bound column.",
           "Aliases": [
@@ -4153,7 +4153,7 @@
           "Default": null
         },
         {
-          "Name": "ShouldStablize",
+          "Name": "ShouldStabilize",
           "Type": "Bool",
           "Desc": "The flag determining whether the model should be stabilized.",
           "Required": false,