Merge pull request #19 from alteryx/tempo-env-checkmates-refactoring

Tempo env checkmates refactoring

checkmates/exceptions/__init__.py

@@ -5,4 +5,6 @@
     ValidationErrorCode,
     ObjectiveCreationError,
     ObjectiveNotFoundError,
+    MethodPropertyNotFoundError,
+    ComponentNotYetFittedError,
 )

checkmates/exceptions/exceptions.py

@@ -14,6 +14,18 @@ class ObjectiveNotFoundError(Exception):
     pass
 
 
+class MethodPropertyNotFoundError(Exception):
+    """Exception to raise when a class is does not have an expected method or property."""
+
+    pass
+
+
+class ComponentNotYetFittedError(Exception):
+    """An exception to be raised when predict/predict_proba/transform is called on a component without fitting first."""
+
+    pass
+
+
 class ObjectiveCreationError(Exception):
     """Exception when get_objective tries to instantiate an objective and required args are not provided."""
 

checkmates/objectives/__init__.py

@@ -3,10 +3,13 @@
 from checkmates.objectives.objective_base import ObjectiveBase
 from checkmates.objectives.regression_objective import RegressionObjective
 
-from checkmates.objectives.utils import get_objective
-from checkmates.objectives.utils import get_default_primary_search_objective
-from checkmates.objectives.utils import get_non_core_objectives
-from checkmates.objectives.utils import get_core_objectives
+from checkmates.objectives.utils import (
+    get_objective,
+    get_default_primary_search_objective,
+    get_non_core_objectives,
+    get_core_objectives,
+    get_problem_type,
+)
 
 
 from checkmates.objectives.standard_metrics import RootMeanSquaredLogError

checkmates/objectives/utils.py

@@ -1,9 +1,16 @@
 """Utility methods for CheckMates objectives."""
+from typing import Optional
+
+import pandas as pd
+
 from checkmates import objectives
 from checkmates.exceptions import ObjectiveCreationError, ObjectiveNotFoundError
 from checkmates.objectives.objective_base import ObjectiveBase
-from checkmates.problem_types import handle_problem_types
+from checkmates.problem_types import ProblemTypes, handle_problem_types
 from checkmates.utils.gen_utils import _get_subclasses
+from checkmates.utils.logger import get_logger
+
+logger = get_logger(__file__)
 
 
 def get_non_core_objectives():
@@ -90,6 +97,35 @@ def get_objective(objective, return_instance=False, **kwargs):
     return objective_class
 
 
+def get_problem_type(
+    input_problem_type: Optional[str],
+    target_data: pd.Series,
+) -> ProblemTypes:
+    """Helper function to determine if classification problem is binary or multiclass dependent on target variable values."""
+    if not input_problem_type:
+        raise ValueError("problem type is required")
+    if input_problem_type.lower() == "classification":
+        values: pd.Series = target_data.value_counts()
+        if values.size == 2:
+            return ProblemTypes.BINARY
+        elif values.size > 2:
+            return ProblemTypes.MULTICLASS
+        else:
+            message: str = "The target field contains less than two unique values. It cannot be used for modeling."
+            logger.error(message, exc_info=True)
+            raise ValueError(message)
+
+    if input_problem_type.lower() == "regression":
+        return ProblemTypes.REGRESSION
+
+    if input_problem_type.lower() == "time series regression":
+        return ProblemTypes.TIME_SERIES_REGRESSION
+
+    message = f"Unexpected problem type provided in configuration: {input_problem_type}"
+    logger.error(message, exc_info=True)
+    raise ValueError(message)
+
+
 def get_default_primary_search_objective(problem_type):
     """Get the default primary search objective for a problem type.
 

checkmates/pipelines/__init__.py

@@ -0,0 +1,19 @@
+"""General CheckMates pipelines."""
+
+from checkmates.pipelines.component_base_meta import ComponentBaseMeta
+from checkmates.pipelines.component_base import ComponentBase
+from checkmates.pipelines.transformers import Transformer
+from checkmates.pipelines.components import (  # noqa: F401
+    DropColumns,
+    DropRowsTransformer,
+    PerColumnImputer,
+    TargetImputer,
+    TimeSeriesImputer,
+    TimeSeriesRegularizer,
+)
+from checkmates.pipelines.utils import (
+    _make_component_list_from_actions,
+    split_data,
+    drop_infinity,
+)
+from checkmates.pipelines.training_validation_split import TrainingValidationSplit