Deprecate ignoring empty objects in concat

python/cudf/cudf/core/dataframe.py

@@ -910,7 +910,9 @@ def _init_from_series_list(self, data, columns, index):
 
             transpose = self.T
         else:
-            concat_df = cudf.concat(data, axis=1)
+            with warnings.catch_warnings():
+                warnings.simplefilter("ignore", FutureWarning)
+                concat_df = cudf.concat(data, axis=1)
 
             cols = concat_df._data.to_pandas_index()
             if cols.dtype == "object":
@@ -1920,9 +1922,11 @@ def _get_renderable_dataframe(self):
             lower_left = self.tail(lower_rows).iloc[:, :left_cols]
             lower_right = self.tail(lower_rows).iloc[:, right_cols:]
 
-            upper = cudf.concat([upper_left, upper_right], axis=1)
-            lower = cudf.concat([lower_left, lower_right], axis=1)
-            output = cudf.concat([upper, lower])
+            with warnings.catch_warnings():
+                warnings.simplefilter("ignore", FutureWarning)
+                upper = cudf.concat([upper_left, upper_right], axis=1)
+                lower = cudf.concat([lower_left, lower_right], axis=1)
+                output = cudf.concat([upper, lower])
 
         output = self._clean_nulls_from_dataframe(output)
         output._index = output._index._clean_nulls_from_index()
@@ -5154,14 +5158,17 @@ def describe(
                 None,
             )
 
-            return cudf.concat(
-                [
-                    series.reindex(names, copy=False)
-                    for series in describe_series_list
-                ],
-                axis=1,
-                sort=False,
-            )
+            with warnings.catch_warnings():
+                warnings.simplefilter("ignore", FutureWarning)
+                res = cudf.concat(
+                    [
+                        series.reindex(names, copy=False)
+                        for series in describe_series_list
+                    ],
+                    axis=1,
+                    sort=False,
+                )
+            return res
 
     @_cudf_nvtx_annotate
     def to_pandas(self, *, nullable: bool = False) -> pd.DataFrame:
@@ -6258,7 +6265,10 @@ def mode(self, axis=0, numeric_only=False, dropna=True):
         if len(mode_results) == 0:
             return DataFrame()
 
-        df = cudf.concat(mode_results, axis=1)
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", FutureWarning)
+            df = cudf.concat(mode_results, axis=1)
+
         if isinstance(df, Series):
             df = df.to_frame()
 

python/cudf/cudf/core/groupby/groupby.py

@@ -1319,13 +1319,17 @@ def _post_process_chunk_results(
             # group is a row-like "Series" where the index labels
             # are the same as the original calling DataFrame
             if _is_row_of(chunk_results[0], self.obj):
-                result = cudf.concat(chunk_results, axis=1).T
+                with warnings.catch_warnings():
+                    warnings.simplefilter("ignore", FutureWarning)
+                    result = cudf.concat(chunk_results, axis=1).T
                 result.index = group_names
                 result.index.names = self.grouping.names
             # When the UDF is like df.x + df.y, the result for each
             # group is the same length as the original group
             elif len(self.obj) == sum(len(chk) for chk in chunk_results):
-                result = cudf.concat(chunk_results)
+                with warnings.catch_warnings():
+                    warnings.simplefilter("ignore", FutureWarning)
+                    result = cudf.concat(chunk_results)
                 index_data = group_keys._data.copy(deep=True)
                 index_data[None] = grouped_values.index._column
                 result.index = cudf.MultiIndex._from_data(index_data)
@@ -1336,7 +1340,9 @@ def _post_process_chunk_results(
                     f"type {type(chunk_results[0])}"
                 )
         else:
-            result = cudf.concat(chunk_results)
+            with warnings.catch_warnings():
+                warnings.simplefilter("ignore", FutureWarning)
+                result = cudf.concat(chunk_results)
             if self._group_keys:
                 index_data = group_keys._data.copy(deep=True)
                 index_data[None] = grouped_values.index._column

python/cudf/cudf/core/index.py

@@ -1103,6 +1103,16 @@ def _values(self):
     @_cudf_nvtx_annotate
     def _concat(cls, objs):
         non_empties = [index for index in objs if len(index)]
+        if len(objs) != len(non_empties):
+            # Do not remove until pandas-3.0 support is added.
+            warnings.warn(
+                "The behavior of array concatenation with empty entries is "
+                "deprecated. In a future version, this will no longer exclude "
+                "empty items when determining the result dtype. "
+                "To retain the old behavior, exclude the empty entries before "
+                "the concat operation.",
+                FutureWarning,
+            )
         if all(isinstance(obj, RangeIndex) for obj in non_empties):
             result = _concat_range_index(non_empties)
         else:
@@ -1300,7 +1310,9 @@ def __repr__(self):
             top = self[0:mr]
             bottom = self[-1 * mr :]
 
-            preprocess = cudf.concat([top, bottom])
+            with warnings.catch_warnings():
+                warnings.simplefilter("ignore", FutureWarning)
+                preprocess = cudf.concat([top, bottom])
         else:
             preprocess = self
 

python/cudf/cudf/core/join/_join_helpers.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import warnings
 from collections import abc
 from typing import TYPE_CHECKING, Any, Tuple, cast
 
@@ -170,9 +171,11 @@ def _match_categorical_dtypes_both(
         return lcol, rcol.astype(ltype)
     else:
         # merge categories
-        merged_categories = cudf.concat(
-            [ltype.categories, rtype.categories]
-        ).unique()
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", FutureWarning)
+            merged_categories = cudf.concat(
+                [ltype.categories, rtype.categories]
+            ).unique()
         common_type = cudf.CategoricalDtype(
             categories=merged_categories, ordered=False
         )

python/cudf/cudf/core/multiindex.py

@@ -6,6 +6,7 @@
 import numbers
 import operator
 import pickle
+import warnings
 from collections import abc
 from functools import cached_property
 from numbers import Integral
@@ -717,15 +718,17 @@ def _compute_validity_mask(self, index, row_tuple, max_length):
                 continue
             lookup[i] = cudf.Series(row)
         frame = cudf.DataFrame(dict(enumerate(index._data.columns)))
-        data_table = cudf.concat(
-            [
-                frame,
-                cudf.DataFrame(
-                    {"idx": cudf.Series(column.arange(len(frame)))}
-                ),
-            ],
-            axis=1,
-        )
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", FutureWarning)
+            data_table = cudf.concat(
+                [
+                    frame,
+                    cudf.DataFrame(
+                        {"idx": cudf.Series(column.arange(len(frame)))}
+                    ),
+                ],
+                axis=1,
+            )
         # Sort indices in pandas compatible mode
         # because we want the indices to be fetched
         # in a deterministic order.

python/cudf/cudf/core/reshape.py

@@ -5,6 +5,7 @@
 from typing import Dict, Optional
 
 import cupy
+import warnings
 import numpy as np
 import pandas as pd
 
@@ -320,9 +321,20 @@ def concat(objs, axis=0, join="outer", ignore_index=False, sort=None):
         df = cudf.DataFrame()
         _normalize_series_and_dataframe(objs, axis=axis)
 
+        any_empty = any(obj.empty for obj in objs)
+        if any_empty:
+            # Do not remove until pandas-3.0 support is added.
+            warnings.warn(
+                "The behavior of array concatenation with empty entries is "
+                "deprecated. In a future version, this will no longer exclude "
+                "empty items when determining the result dtype. "
+                "To retain the old behavior, exclude the empty entries before "
+                "the concat operation.",
+                FutureWarning,
+            )
         # Inner joins involving empty data frames always return empty dfs, but
         # We must delay returning until we have set the column names.
-        empty_inner = any(obj.empty for obj in objs) and join == "inner"
+        empty_inner = any_empty and join == "inner"
 
         objs = [obj for obj in objs if obj.shape != (0, 0)]
 

python/cudf/cudf/core/series.py

@@ -1429,7 +1429,9 @@ def __repr__(self):
         if max_rows not in (0, None) and len(self) > max_rows:
             top = self.head(int(max_rows / 2 + 1))
             bottom = self.tail(int(max_rows / 2 + 1))
-            preprocess = cudf.concat([top, bottom])
+            with warnings.catch_warnings():
+                warnings.simplefilter("ignore", FutureWarning)
+                preprocess = cudf.concat([top, bottom])
         else:
             preprocess = self.copy()
         preprocess.index = preprocess.index._clean_nulls_from_index()

python/cudf/cudf/io/parquet.py

@@ -794,13 +794,15 @@ def _parquet_to_frame(
                         dtype=_dtype,
                     )
 
-    # Concatenate dfs and return.
-    # Assume we can ignore the index if it has no name.
-    return (
-        cudf.concat(dfs, ignore_index=dfs[-1].index.name is None)
-        if len(dfs) > 1
-        else dfs[0]
-    )
+    if len(dfs) > 1:
+        # Concatenate dfs and return.
+        # Assume we can ignore the index if it has no name.
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", FutureWarning)
+            res = cudf.concat(dfs, ignore_index=dfs[-1].index.name is None)
+        return res
+    else:
+        return dfs[0]
 
 
 @_cudf_nvtx_annotate