Integration runs, no tests

evalml/automl/automl_algorithm/default_algorithm.py

@@ -81,6 +81,7 @@ class DefaultAlgorithm(AutoMLAlgorithm):
             model families. Run evalml.pipelines.components.utils.allowed_model_families("binary") to see options. Change `binary`
             to `multiclass` or `regression` depending on the problem type.
         excluded_model_families (list[ModelFamily]): A list of model families to exclude from the estimators used when building pipelines. For default algorithm, this only excludes estimators in the non-naive batches.
+        is_multiseries (bool): Whether or not the problem is a multiseries time series problem. Defaults to False.
     """
 
     def __init__(
@@ -105,6 +106,7 @@ def __init__(
         run_feature_selection=True,
         verbose=False,
         exclude_featurizers=None,
+        is_multiseries=False,
     ):
         super().__init__(
             allowed_pipelines=[],
@@ -138,6 +140,7 @@ def __init__(
         self.run_feature_selection = run_feature_selection
         self.ensembling = ensembling
         self.exclude_featurizers = exclude_featurizers or []
+        self.is_multiseries = is_multiseries
 
         if allowed_model_families is not None and excluded_model_families is not None:
             raise ValueError(
@@ -170,6 +173,8 @@ def default_max_batches(self):
         """Returns the number of max batches AutoMLSearch should run by default."""
         if self.ensembling:
             return 3
+        elif self.is_multiseries:
+            return 1
         else:
             return 2
 
@@ -217,6 +222,7 @@ def _non_naive_estimators(self):
                 self.problem_type,
                 model_families=self.allowed_model_families,
                 excluded_model_families=self.excluded_model_families,
+                is_multiseries=self.is_multiseries,
             )
             if est not in self._naive_estimators()
         ]
@@ -265,6 +271,7 @@ def _create_naive_pipelines(self, use_features=False):
                 ),
                 features=self.features,
                 exclude_featurizers=self.exclude_featurizers,
+                is_multiseries=self.is_multiseries,
             )
             for estimator in estimators
         ]
@@ -293,6 +300,7 @@ def _add_without_pipelines(self, pipelines, estimators, feature_selector=[]):
                     features=self.features,
                     exclude_featurizers=self.exclude_featurizers,
                     include_decomposer=False,
+                    is_multiseries=self.is_multiseries,
                 )
                 for estimator in estimators
             ]
@@ -432,6 +440,7 @@ def _make_pipelines_helper(self, estimators):
                     ),
                     features=self.features,
                     exclude_featurizers=self.exclude_featurizers,
+                    is_multiseries=self.is_multiseries,
                 )
                 for estimator in estimators
             ]
@@ -472,11 +481,17 @@ def next_batch(self):
                 )
         # this logic needs to be updated once time series also supports ensembling
         elif is_time_series(self.problem_type):
-            if self._batch_number == 0:
+            # Skip the naive batch for multiseries time series
+            batch = (
+                self._batch_number
+                if not self.is_multiseries
+                else self._batch_number + 1
+            )
+            if batch == 0:
                 next_batch = self._create_naive_pipelines()
-            elif self._batch_number == 1:
+            elif batch == 1:
                 next_batch = self._create_fast_final()
-            elif self.batch_number == 2:
+            elif batch == 2:
                 next_batch = self._create_long_exploration(n=self.top_n)
             else:
                 next_batch = self._create_n_pipelines(
@@ -664,6 +679,7 @@ def _make_split_pipeline(self, estimator, pipeline_name=None):
                 extra_components_before=[SelectColumns],
                 use_estimator=False,
                 exclude_featurizers=self.exclude_featurizers,
+                is_multiseries=self.is_multiseries,
             )
 
             numeric_pipeline = make_pipeline(
@@ -677,6 +693,7 @@ def _make_split_pipeline(self, estimator, pipeline_name=None):
                 extra_components_after=[SelectColumns],
                 use_estimator=False,
                 exclude_featurizers=self.exclude_featurizers,
+                is_multiseries=self.is_multiseries,
             )
             pre_pipeline_components = (
                 {"DFS Transformer": ["DFS Transformer", "X", "y"]}
@@ -728,6 +745,7 @@ def _make_split_pipeline(self, estimator, pipeline_name=None):
                 extra_components_before=[SelectColumns],
                 features=self.features,
                 exclude_featurizers=self.exclude_featurizers,
+                is_multiseries=self.is_multiseries,
             )
             return categorical_pipeline
         elif self.run_feature_selection:
@@ -744,6 +762,7 @@ def _make_split_pipeline(self, estimator, pipeline_name=None):
                 extra_components_after=[SelectColumns],
                 features=self.features,
                 exclude_featurizers=self.exclude_featurizers,
+                is_multiseries=self.is_multiseries,
             )
             return numeric_pipeline
 
@@ -755,5 +774,6 @@ def _make_split_pipeline(self, estimator, pipeline_name=None):
                 self.problem_type,
                 sampler_name=self.sampler_name,
                 exclude_featurizers=self.exclude_featurizers,
+                is_multiseries=self.is_multiseries,
             )
             return pipeline

evalml/automl/automl_algorithm/iterative_algorithm.py

@@ -69,6 +69,7 @@ class IterativeAlgorithm(AutoMLAlgorithm):
         verbose (boolean): Whether or not to display logging information regarding pipeline building. Defaults to False.
         exclude_featurizers (list[str]): A list of featurizer components to exclude from the pipelines built by IterativeAlgorithm.
             Valid options are "DatetimeFeaturizer", "EmailFeaturizer", "URLFeaturizer", "NaturalLanguageFeaturizer", "TimeSeriesFeaturizer"
+        is_multiseries (bool): Whether or not the problem is a multiseries time series problem. Defaults to False.
     """
 
     def __init__(
@@ -95,6 +96,7 @@ def __init__(
         features=None,
         verbose=False,
         exclude_featurizers=None,
+        is_multiseries=False,
     ):
         self.X = infer_feature_types(X)
         self.y = infer_feature_types(y)
@@ -129,6 +131,7 @@ def __init__(
         self.features = features
         self._set_additional_pipeline_params()
         self.exclude_featurizers = exclude_featurizers
+        self.is_multiseries = is_multiseries
 
         super().__init__(
             allowed_pipelines=self.allowed_pipelines,
@@ -156,6 +159,7 @@ def _create_pipelines(self):
                 self.problem_type,
                 model_families=self.allowed_model_families,
                 excluded_model_families=self.excluded_model_families,
+                is_multiseries=self.is_multiseries,
             )
             allowed_estimators = self._filter_estimators(
                 allowed_estimators,
@@ -184,6 +188,7 @@ def _create_pipelines(self):
                         ).get("known_in_advance", None),
                         features=self.features,
                         exclude_featurizers=self.exclude_featurizers,
+                        is_multiseries=self.is_multiseries,
                     )
                     for estimator in allowed_estimators
                 ]
@@ -207,6 +212,7 @@ def _create_pipelines(self):
                             features=self.features,
                             exclude_featurizers=self.exclude_featurizers,
                             include_decomposer=False,
+                            is_multiseries=self.is_multiseries,
                         )
                         for estimator in allowed_estimators
                     ]

evalml/automl/automl_search.py

@@ -403,6 +403,7 @@ class AutoMLSearch:
 
         problem_configuration (dict, None): Additional parameters needed to configure the search. For example,
             in time series problems, values should be passed in for the time_index, gap, forecast_horizon, and max_delay variables.
+            For multiseries time series problems, the values passed in should also include the name of a series_id column.
 
         train_best_pipeline (boolean): Whether or not to train the best pipeline before returning it. Defaults to True.
 
@@ -624,6 +625,10 @@ def __init__(
         self.problem_configuration = self._validate_problem_configuration(
             problem_configuration,
         )
+        self.is_multiseries = (
+            is_time_series(self.problem_type)
+            and "series_id" in self.problem_configuration
+        )
         self._train_best_pipeline = train_best_pipeline
         self._best_pipeline = None
         self._searched = False
@@ -933,6 +938,7 @@ def _is_imbalanced(X, y, problem_type):
                 features=features,
                 verbose=self.verbose,
                 exclude_featurizers=self.exclude_featurizers,
+                is_multiseries=self.is_multiseries,
             )
         elif automl_algorithm == "default":
             self.automl_algorithm = DefaultAlgorithm(
@@ -953,6 +959,7 @@ def _is_imbalanced(X, y, problem_type):
                 verbose=self.verbose,
                 n_jobs=self.n_jobs,
                 exclude_featurizers=self.exclude_featurizers,
+                is_multiseries=self.is_multiseries,
             )
         else:
             raise ValueError("Please specify a valid automl algorithm.")
@@ -1355,6 +1362,7 @@ def _get_baseline_pipeline(self):
             gap = self.problem_configuration["gap"]
             forecast_horizon = self.problem_configuration["forecast_horizon"]
             time_index = self.problem_configuration["time_index"]
+            series_id = self.problem_configuration.get("series_id", None)
             exclude_timeseries_featurizer = (
                 "TimeSeriesFeaturizer" in self.exclude_featurizers
             )
@@ -1364,6 +1372,8 @@ def _get_baseline_pipeline(self):
                 forecast_horizon,
                 time_index,
                 exclude_timeseries_featurizer,
+                self.is_multiseries,
+                series_id,
             )
         return baseline
 

evalml/automl/utils.py

@@ -87,12 +87,14 @@ def make_data_splitter(
             raise ValueError(
                 "problem_configuration is required for time series problem types",
             )
+        series_id = problem_configuration.get("series_id")
         return TimeSeriesSplit(
             n_splits=n_splits,
             gap=problem_configuration.get("gap"),
             max_delay=problem_configuration.get("max_delay"),
             time_index=problem_configuration.get("time_index"),
             forecast_horizon=problem_configuration.get("forecast_horizon"),
+            n_series=len(X[series_id].unique()) if series_id is not None else None,
         )
     if X.shape[0] > _LARGE_DATA_ROW_THRESHOLD:
         return TrainingValidationSplit(

evalml/pipelines/components/estimators/regressors/varmax_regressor.py

@@ -59,7 +59,7 @@ def __init__(
         trend: Optional[str] = "c",
         random_seed: Union[int, float] = 0,
         maxiter: int = 10,
-        use_covariates: bool = True,
+        use_covariates: bool = False,
         **kwargs,
     ):
         self.preds_95_upper = None

evalml/pipelines/components/utils.py

@@ -14,7 +14,7 @@
 from evalml.pipelines.components.component_base import ComponentBase
 from evalml.pipelines.components.estimators.estimator import Estimator
 from evalml.pipelines.components.transformers.transformer import Transformer
-from evalml.problem_types import ProblemTypes, handle_problem_types
+from evalml.problem_types import ProblemTypes, handle_problem_types, is_time_series
 from evalml.utils import get_importable_subclasses
 
 
@@ -56,7 +56,19 @@ def allowed_model_families(problem_type):
     return list(set([e.model_family for e in estimators]))
 
 
-def get_estimators(problem_type, model_families=None, excluded_model_families=None):
+def _filter_multiseries_estimators(estimators, is_multiseries):
+    if is_multiseries:
+        return [estimator for estimator in estimators if estimator.is_multiseries]
+    else:
+        return [estimator for estimator in estimators if not estimator.is_multiseries]
+
+
+def get_estimators(
+    problem_type,
+    model_families=None,
+    excluded_model_families=None,
+    is_multiseries=False,
+):
     """Returns the estimators allowed for a particular problem type.
 
     Can also optionally filter by a list of model types.
@@ -65,6 +77,7 @@ def get_estimators(problem_type, model_families=None, excluded_model_families=No
         problem_type (ProblemTypes or str): Problem type to filter for.
         model_families (list[ModelFamily] or list[str]): Model families to filter for.
         excluded_model_families (list[ModelFamily]): A list of model families to exclude from the results.
+        is_multiseries (bool): Whether to return only estimators that support multiseries data.
 
     Returns:
         list[class]: A list of estimator subclasses.
@@ -111,6 +124,11 @@ def get_estimators(problem_type, model_families=None, excluded_model_families=No
         if estimator_class.model_family not in model_families:
             continue
         estimator_classes.append(estimator_class)
+    if is_time_series(problem_type):
+        estimator_classes = _filter_multiseries_estimators(
+            estimator_classes,
+            is_multiseries,
+        )
     return estimator_classes