REFACTOR-#2467: Convert internal base dataframe objects to ABC (#2468)

Signed-off-by: Devin Petersohn <devin.petersohn@gmail.com>
modin-project · Nov 26, 2020 · 0aada32 · 0aada32
1 parent e5556b5
commit 0aada32
Show file tree

Hide file tree

Showing 3 changed files with 41 additions and 33 deletions.
diff --git a/modin/engines/base/frame/axis_partition.py b/modin/engines/base/frame/axis_partition.py
@@ -11,13 +11,12 @@
 # ANY KIND, either express or implied. See the License for the specific language
 # governing permissions and limitations under the License.
 
+from abc import ABC
 import pandas
 from modin.data_management.utils import split_result_of_axis_func_pandas
 
-NOT_IMPLMENTED_MESSAGE = "Must be implemented in child class"
 
-
-class BaseFrameAxisPartition(object):  # pragma: no cover
+class BaseFrameAxisPartition(ABC):  # pragma: no cover
     """An abstract class that represents the Parent class for any `ColumnPartition` or `RowPartition` class.
 
     This class is intended to simplify the way that operations are performed.
@@ -73,7 +72,7 @@ def apply(
         -------
             A list of `BaseFramePartition` objects.
         """
-        raise NotImplementedError(NOT_IMPLMENTED_MESSAGE)
+        pass
 
     def shuffle(self, func, lengths, **kwargs):
         """Shuffle the order of the data in this axis based on the `lengths`.
@@ -86,7 +85,7 @@ def shuffle(self, func, lengths, **kwargs):
         -------
             A list of RemotePartition objects split by `lengths`.
         """
-        raise NotImplementedError(NOT_IMPLMENTED_MESSAGE)
+        pass
 
     # Child classes must have these in order to correctly subclass.
     instance_type = None

diff --git a/modin/engines/base/frame/partition.py b/modin/engines/base/frame/partition.py
@@ -11,25 +11,18 @@
 # ANY KIND, either express or implied. See the License for the specific language
 # governing permissions and limitations under the License.
 
-NOT_IMPLEMENTED_MESSAGE = "Must be implemented in child class"
+from abc import ABC
 
 
-class BaseFramePartition(object):  # pragma: no cover
+class BaseFramePartition(ABC):  # pragma: no cover
     """An abstract class that holds the data and metadata for a single partition.
 
-    The methods required for implementing this abstract class are listed in
-    the section immediately following this.
-
-    The API exposed by the children of this object is used in
-    `BaseFrameManager`.
+    The public API exposed by the children of this object is used in `BaseFrameManager`.
 
     Note: These objects are treated as immutable by `BaseFrameManager`
     subclasses. There is no logic for updating inplace.
     """
 
-    # Abstract methods and fields. These must be implemented in order to
-    # properly subclass this object. There are also some abstract classmethods
-    # to implement.
     def get(self):
         """Return the object wrapped by this one to the original format.
 
@@ -41,7 +34,7 @@ def get(self):
         -------
             The object that was `put`.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     def apply(self, func, **kwargs):
         """Apply some callable function to the data in this partition.
@@ -50,26 +43,38 @@ def apply(self, func, **kwargs):
             an important part of many implementations. As of right now, they
             are not serialized.
 
-        Args:
-            func: The lambda to apply (may already be correctly formatted)
+        Args
+        ----
+        func : callable
+            The function to apply.
 
         Returns
         -------
              A new `BaseFramePartition` containing the object that has had `func`
              applied to it.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     def add_to_apply_calls(self, func, **kwargs):
         """Add the function to the apply function call stack.
 
-        This function will be executed when apply is called. It will be executed
+        Note: This function will be executed when apply is called. It will be executed
         in the order inserted; apply's func operates the last and return
+
+        Args
+        ----
+        func : callable
+            The function to apply.
+
+        Returns
+        -------
+            A new `BaseFramePartition` with the function added to the call queue.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     def drain_call_queue(self):
         """Execute all functionality stored in the call queue."""
+        pass
 
     def to_pandas(self):
         """Convert the object stored in this partition to a Pandas DataFrame.
@@ -81,7 +86,7 @@ def to_pandas(self):
         -------
             A Pandas DataFrame.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     def to_numpy(self, **kwargs):
         """Convert the object stored in this partition to a NumPy array.
@@ -93,7 +98,7 @@ def to_numpy(self, **kwargs):
         -------
             A NumPy array.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     def mask(self, row_indices, col_indices):
         """Lazily create a mask that extracts the indices provided.
@@ -106,21 +111,22 @@ def mask(self, row_indices, col_indices):
         -------
             A `BaseFramePartition` object.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     @classmethod
     def put(cls, obj):
         """Format a given object.
 
         Parameters
         ----------
-            obj: An object.
+        obj: object
+            An object.
 
         Returns
         -------
             A `BaseFramePartition` object.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     @classmethod
     def preprocess_func(cls, func):
@@ -131,14 +137,16 @@ def preprocess_func(cls, func):
             deploy a preprocessed function to multiple `BaseFramePartition`
             objects.
 
-        Args:
-            func: The function to preprocess.
+        Args
+        ----
+        func : callable
+            The function to preprocess.
 
         Returns
         -------
             An object that can be accepted by `apply`.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     @classmethod
     def length_extraction_fn(cls):
@@ -148,7 +156,7 @@ def length_extraction_fn(cls):
         -------
             A callable function.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     @classmethod
     def width_extraction_fn(cls):
@@ -158,7 +166,7 @@ def width_extraction_fn(cls):
         -------
             A callable function.
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
 
     _length_cache = None
     _width_cache = None
@@ -189,4 +197,4 @@ def empty(cls):
         -------
             An empty partition
         """
-        raise NotImplementedError(NOT_IMPLEMENTED_MESSAGE)
+        pass
diff --git a/modin/engines/base/frame/partition_manager.py b/modin/engines/base/frame/partition_manager.py
@@ -11,6 +11,7 @@
 # ANY KIND, either express or implied. See the License for the specific language
 # governing permissions and limitations under the License.
 
+from abc import ABC
 import numpy as np
 import pandas
 
@@ -19,7 +20,7 @@
 from pandas.api.types import union_categoricals
 
 
-class BaseFrameManager(object):
+class BaseFrameManager(ABC):
     """Partition class is the class to use for storing each partition. It must extend the `BaseFramePartition` class.
 
     It is the base class for managing the dataframe data layout and operators.