FIX-modin-project#2054: Moved non-dependent on modin.DataFrame utils …

…to modin/utils.py (modin-project#2055)

Signed-off-by: Dmitry Chigarev <[email protected]>

modin/backends/pandas/query_compiler.py

@@ -23,7 +23,7 @@
 
 from modin.backends.base.query_compiler import BaseQueryCompiler
 from modin.error_message import ErrorMessage
-from modin.pandas.utils import try_cast_to_pandas, wrap_udf_function
+from modin.utils import try_cast_to_pandas, wrap_udf_function
 from modin.data_management.functions import (
     FoldFunction,
     MapFunction,

modin/data_management/functions/groupby_function.py

@@ -14,7 +14,7 @@
 import pandas
 
 from .mapreducefunction import MapReduceFunction
-from modin.pandas.utils import try_cast_to_pandas
+from modin.utils import try_cast_to_pandas
 
 
 class GroupbyReduceFunction(MapReduceFunction):

modin/pandas/base.py

@@ -31,8 +31,9 @@
 import warnings
 import pickle as pkl
 
+from modin.utils import try_cast_to_pandas
 from modin.error_message import ErrorMessage
-from modin.pandas.utils import try_cast_to_pandas, is_scalar
+from modin.pandas.utils import is_scalar
 
 # Similar to pandas, sentinel value to use as kwarg in place of None when None has
 # special meaning and needs to be distinguished from a user explicitly passing None.

modin/pandas/dataframe.py

@@ -33,12 +33,10 @@
 import warnings
 
 from modin.error_message import ErrorMessage
+from modin.utils import _inherit_docstrings, to_pandas, hashable
 from .utils import (
     from_pandas,
     from_non_pandas,
-    to_pandas,
-    _inherit_docstrings,
-    hashable,
 )
 from .iterator import PartitionIterator
 from .series import Series

modin/pandas/general.py

@@ -17,7 +17,7 @@
 from .base import BasePandasDataset
 from .dataframe import DataFrame
 from .series import Series
-from .utils import to_pandas
+from modin.utils import to_pandas
 
 
 def isna(obj):

modin/pandas/groupby.py

@@ -18,8 +18,7 @@
 import pandas.core.common as com
 
 from modin.error_message import ErrorMessage
-
-from .utils import _inherit_docstrings, wrap_udf_function, try_cast_to_pandas
+from modin.utils import _inherit_docstrings, wrap_udf_function, try_cast_to_pandas
 from .series import Series
 
 

modin/pandas/io.py

@@ -485,7 +485,7 @@ def return_handler(*args, **kwargs):
                         A Modin DataFrame in place of a pandas DataFrame, or the same
                         return type as pandas.ExcelFile.
                     """
-                    from .utils import to_pandas
+                    from modin.utils import to_pandas
 
                     # We don't want to constantly be giving this error message for
                     # internal methods.
@@ -554,7 +554,7 @@ def return_handler(*args, **kwargs):
                         A Modin DataFrame in place of a pandas DataFrame, or the same
                         return type as pandas.HDFStore.
                     """
-                    from .utils import to_pandas
+                    from modin.utils import to_pandas
 
                     # We don't want to constantly be giving this error message for
                     # internal methods.

modin/pandas/plotting.py

@@ -13,7 +13,7 @@
 
 from pandas import plotting as pdplot
 
-from .utils import to_pandas
+from modin.utils import to_pandas
 from .dataframe import DataFrame
 
 

modin/pandas/reshape.py

@@ -15,7 +15,7 @@
 
 from .dataframe import DataFrame
 from .series import Series
-from .utils import to_pandas
+from modin.utils import to_pandas
 from modin.error_message import ErrorMessage
 
 

modin/pandas/series.py

@@ -24,10 +24,10 @@
 import sys
 import warnings
 
+from modin.utils import _inherit_docstrings, to_pandas
 from .base import BasePandasDataset
 from .iterator import PartitionIterator
-from .utils import _inherit_docstrings
-from .utils import from_pandas, to_pandas, is_scalar
+from .utils import from_pandas, is_scalar
 
 if sys.version_info[0] == 3 and sys.version_info[1] >= 7:
     # Python >= 3.7

modin/pandas/test/dataframe/test_default.py

@@ -17,7 +17,7 @@
 import os
 import matplotlib
 import modin.pandas as pd
-from modin.pandas.utils import to_pandas
+from modin.utils import to_pandas
 from numpy.testing import assert_array_equal
 import io
 

modin/pandas/test/dataframe/test_join_sort.py

@@ -16,7 +16,7 @@
 import pandas
 import matplotlib
 import modin.pandas as pd
-from modin.pandas.utils import to_pandas
+from modin.utils import to_pandas
 
 from modin.pandas.test.utils import (
     random_state,

modin/pandas/test/test_groupby.py

@@ -15,7 +15,8 @@
 import pandas
 import numpy as np
 import modin.pandas as pd
-from modin.pandas.utils import from_pandas, to_pandas, try_cast_to_pandas
+from modin.utils import try_cast_to_pandas, to_pandas
+from modin.pandas.utils import from_pandas
 from .utils import (
     df_equals,
     check_df_columns_have_nans,

modin/pandas/test/test_io.py

@@ -16,7 +16,8 @@
 import pandas
 from pandas.errors import ParserWarning
 from collections import OrderedDict
-from modin.pandas.utils import to_pandas, from_arrow
+from modin.utils import to_pandas
+from modin.pandas.utils import from_arrow
 from pathlib import Path
 import pyarrow as pa
 import pyarrow.parquet as pq

modin/pandas/test/test_series.py

@@ -20,7 +20,7 @@
 from numpy.testing import assert_array_equal
 import sys
 
-from modin.pandas.utils import to_pandas
+from modin.utils import to_pandas
 from .utils import (
     random_state,
     RAND_LOW,

modin/pandas/test/utils.py

@@ -20,7 +20,7 @@
     assert_categorical_equal,
 )
 import modin.pandas as pd
-from modin.pandas.utils import to_pandas
+from modin.utils import to_pandas
 from io import BytesIO
 
 random_state = np.random.RandomState(seed=42)

modin/pandas/utils.py

@@ -11,8 +11,6 @@
 # ANY KIND, either express or implied. See the License for the specific language
 # governing permissions and limitations under the License.
 
-import pandas
-
 
 def from_non_pandas(df, index, columns, dtype):
     from modin.data_management.dispatcher import EngineDispatcher
@@ -58,105 +56,6 @@ def from_arrow(at):
     return DataFrame(query_compiler=EngineDispatcher.from_arrow(at))
 
 
-def to_pandas(modin_obj):
-    """Converts a Modin DataFrame/Series to a pandas DataFrame/Series.
-
-    Args:
-        obj {modin.DataFrame, modin.Series}: The Modin DataFrame/Series to convert.
-
-    Returns:
-        A new pandas DataFrame or Series.
-    """
-    return modin_obj._to_pandas()
-
-
-def _inherit_docstrings(parent, excluded=[]):
-    """Creates a decorator which overwrites a decorated class' __doc__
-    attribute with parent's __doc__ attribute. Also overwrites __doc__ of
-    methods and properties defined in the class with the __doc__ of matching
-    methods and properties in parent.
-
-    Args:
-        parent (object): Class from which the decorated class inherits __doc__.
-        excluded (list): List of parent objects from which the class does not
-            inherit docstrings.
-
-    Returns:
-        function: decorator which replaces the decorated class' documentation
-            parent's documentation.
-    """
-
-    def decorator(cls):
-        if parent not in excluded:
-            cls.__doc__ = parent.__doc__
-        for attr, obj in cls.__dict__.items():
-            parent_obj = getattr(parent, attr, None)
-            if parent_obj in excluded or (
-                not callable(parent_obj) and not isinstance(parent_obj, property)
-            ):
-                continue
-            if callable(obj):
-                obj.__doc__ = parent_obj.__doc__
-            elif isinstance(obj, property) and obj.fget is not None:
-                p = property(obj.fget, obj.fset, obj.fdel, parent_obj.__doc__)
-                setattr(cls, attr, p)
-        return cls
-
-    return decorator
-
-
-def try_cast_to_pandas(obj):
-    """
-    Converts obj and all nested objects from modin to pandas if it is possible,
-    otherwise returns obj
-
-    Parameters
-    ----------
-        obj : object,
-            object to convert from modin to pandas
-
-    Returns
-    -------
-        Converted object
-    """
-    if hasattr(obj, "_to_pandas"):
-        return obj._to_pandas()
-    if isinstance(obj, (list, tuple)):
-        return type(obj)([try_cast_to_pandas(o) for o in obj])
-    if isinstance(obj, dict):
-        return {k: try_cast_to_pandas(v) for k, v in obj.items()}
-    if callable(obj):
-        module_hierarchy = getattr(obj, "__module__", "").split(".")
-        fn_name = getattr(obj, "__name__", None)
-        if fn_name and module_hierarchy[0] == "modin":
-            return (
-                getattr(pandas.DataFrame, fn_name, obj)
-                if module_hierarchy[-1] == "dataframe"
-                else getattr(pandas.Series, fn_name, obj)
-            )
-    return obj
-
-
-def wrap_udf_function(func):
-    def wrapper(*args, **kwargs):
-        result = func(*args, **kwargs)
-        # if user accidently returns modin DataFrame or Series
-        # casting it back to pandas to properly process
-        return try_cast_to_pandas(result)
-
-    wrapper.__name__ = func.__name__
-    return wrapper
-
-
-def hashable(obj):
-    """Return whether the object is hashable."""
-    try:
-        hash(obj)
-    except TypeError:
-        return False
-    return True
-
-
 def is_scalar(obj):
     """
     Return True if given object is scalar.

modin/utils.py

@@ -0,0 +1,113 @@
+# Licensed to Modin Development Team under one or more contributor license agreements.
+# See the NOTICE file distributed with this work for additional information regarding
+# copyright ownership.  The Modin Development Team licenses this file to you under the
+# Apache License, Version 2.0 (the "License"); you may not use this file except in
+# compliance with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software distributed under
+# the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
+# ANY KIND, either express or implied. See the License for the specific language
+# governing permissions and limitations under the License.
+
+import pandas
+
+
+def _inherit_docstrings(parent, excluded=[]):
+    """Creates a decorator which overwrites a decorated class' __doc__
+    attribute with parent's __doc__ attribute. Also overwrites __doc__ of
+    methods and properties defined in the class with the __doc__ of matching
+    methods and properties in parent.
+
+    Args:
+        parent (object): Class from which the decorated class inherits __doc__.
+        excluded (list): List of parent objects from which the class does not
+            inherit docstrings.
+
+    Returns:
+        function: decorator which replaces the decorated class' documentation
+            parent's documentation.
+    """
+
+    def decorator(cls):
+        if parent not in excluded:
+            cls.__doc__ = parent.__doc__
+        for attr, obj in cls.__dict__.items():
+            parent_obj = getattr(parent, attr, None)
+            if parent_obj in excluded or (
+                not callable(parent_obj) and not isinstance(parent_obj, property)
+            ):
+                continue
+            if callable(obj):
+                obj.__doc__ = parent_obj.__doc__
+            elif isinstance(obj, property) and obj.fget is not None:
+                p = property(obj.fget, obj.fset, obj.fdel, parent_obj.__doc__)
+                setattr(cls, attr, p)
+        return cls
+
+    return decorator
+
+
+def to_pandas(modin_obj):
+    """Converts a Modin DataFrame/Series to a pandas DataFrame/Series.
+
+    Args:
+        obj {modin.DataFrame, modin.Series}: The Modin DataFrame/Series to convert.
+
+    Returns:
+        A new pandas DataFrame or Series.
+    """
+    return modin_obj._to_pandas()
+
+
+def hashable(obj):
+    """Return whether the object is hashable."""
+    try:
+        hash(obj)
+    except TypeError:
+        return False
+    return True
+
+
+def try_cast_to_pandas(obj):
+    """
+    Converts obj and all nested objects from modin to pandas if it is possible,
+    otherwise returns obj
+
+    Parameters
+    ----------
+        obj : object,
+            object to convert from modin to pandas
+
+    Returns
+    -------
+        Converted object
+    """
+    if hasattr(obj, "_to_pandas"):
+        return obj._to_pandas()
+    if isinstance(obj, (list, tuple)):
+        return type(obj)([try_cast_to_pandas(o) for o in obj])
+    if isinstance(obj, dict):
+        return {k: try_cast_to_pandas(v) for k, v in obj.items()}
+    if callable(obj):
+        module_hierarchy = getattr(obj, "__module__", "").split(".")
+        fn_name = getattr(obj, "__name__", None)
+        if fn_name and module_hierarchy[0] == "modin":
+            return (
+                getattr(pandas.DataFrame, fn_name, obj)
+                if module_hierarchy[-1] == "dataframe"
+                else getattr(pandas.Series, fn_name, obj)
+            )
+    return obj
+
+
+def wrap_udf_function(func):
+    def wrapper(*args, **kwargs):
+        result = func(*args, **kwargs)
+        # if user accidently returns modin DataFrame or Series
+        # casting it back to pandas to properly process
+        return try_cast_to_pandas(result)
+
+    wrapper.__name__ = func.__name__
+    return wrapper