From b554b999f7f4b4e542985a1f3a0a4b19680f502f Mon Sep 17 00:00:00 2001
From: Matthew Murray <matthewmurray711@gmail.com>
Date: Mon, 16 Sep 2024 16:14:22 -0700
Subject: [PATCH 1/5] improve pylibcudf docs

---
 python/pylibcudf/pylibcudf/binaryop.pyx        |  2 +-
 .../pylibcudf/pylibcudf/column_factories.pyx   | 18 ++++++++++++++++++
 python/pylibcudf/pylibcudf/lists.pyx           | 12 ++++++++++++
 3 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/python/pylibcudf/pylibcudf/binaryop.pyx b/python/pylibcudf/pylibcudf/binaryop.pyx
index 5a67f4d6cdb..5f9d145139a 100644
--- a/python/pylibcudf/pylibcudf/binaryop.pyx
+++ b/python/pylibcudf/pylibcudf/binaryop.pyx
@@ -94,7 +94,7 @@ cpdef bool is_supported_operation(
 ):
     """Check if an operation is supported for the given data types.
 
-    For details, see :cpp:func::is_supported_operation`.
+    For details, see :cpp:func::`is_supported_operation`.
 
     Parameters
     ----------
diff --git a/python/pylibcudf/pylibcudf/column_factories.pyx b/python/pylibcudf/pylibcudf/column_factories.pyx
index 4601cba515a..e9085e3ea02 100644
--- a/python/pylibcudf/pylibcudf/column_factories.pyx
+++ b/python/pylibcudf/pylibcudf/column_factories.pyx
@@ -18,6 +18,20 @@ from .types import MaskState, TypeId
 
 
 cpdef Column make_empty_column(MakeEmptyColumnOperand type_or_id):
+    """Creates an empty column of the specified type.
+
+    For details, see :cpp:func::`make_empty_column`.
+
+    Parameters
+    ----------
+    type_or_id : Union[DataType, type_id, object]
+        The column data type.
+
+    Returns
+    -------
+    Column
+        An empty Column
+    """
     cdef unique_ptr[column] result
     cdef type_id id
 
@@ -60,7 +74,11 @@ cpdef Column make_numeric_column(
     size_type size,
     MaskArg mstate
 ):
+    """Creates an empty numeric column.
+
+    For details, see :cpp:func::`make_numeric_column`.
 
+    """
     cdef unique_ptr[column] result
     cdef mask_state state
 
diff --git a/python/pylibcudf/pylibcudf/lists.pyx b/python/pylibcudf/pylibcudf/lists.pyx
index 947caddc485..6f82124d06e 100644
--- a/python/pylibcudf/pylibcudf/lists.pyx
+++ b/python/pylibcudf/pylibcudf/lists.pyx
@@ -52,6 +52,8 @@ cpdef Table explode_outer(Table input, size_type explode_column_idx):
 
     All other columns will be duplicated for each element in the list.
 
+    For details, see :cpp:func:`explode_outer`.
+
     Parameters
     ----------
     input : Table
@@ -75,6 +77,8 @@ cpdef Table explode_outer(Table input, size_type explode_column_idx):
 cpdef Column concatenate_rows(Table input):
     """Concatenate multiple lists columns into a single lists column row-wise.
 
+    For details, see :cpp:func:`concatenate_list_elements`.
+
     Parameters
     ----------
     input : Table
@@ -96,6 +100,8 @@ cpdef Column concatenate_rows(Table input):
 cpdef Column concatenate_list_elements(Column input, bool dropna):
     """Concatenate multiple lists on the same row into a single list.
 
+    For details, see :cpp:func:`concatenate_list_elements`.
+
     Parameters
     ----------
     input : Column
@@ -168,6 +174,8 @@ cpdef Column contains_nulls(Column input):
     """Create a column of bool values indicating whether
     each row in the lists column contains a null value.
 
+    For details, see :cpp:func:`contains_nulls`.
+
     Parameters
     ----------
     input : Column
@@ -290,6 +298,8 @@ cpdef Column segmented_gather(Column input, Column gather_map_list):
 cpdef Column extract_list_element(Column input, ColumnOrSizeType index):
     """Create a column of extracted list elements.
 
+    For details, see :cpp:func:`extract_list_element`.
+
     Parameters
     ----------
     input : Column
@@ -318,6 +328,8 @@ cpdef Column count_elements(Column input):
     list element in the given lists column.
     For details, see :cpp:func:`count_elements`.
 
+    For details, see :cpp:func:`count_elements`.
+
     Parameters
     ----------
     input : Column

From da11ff3b9933d0dd930fb18d5e8f5837f422daa2 Mon Sep 17 00:00:00 2001
From: Matthew Murray <matthewmurray711@gmail.com>
Date: Fri, 20 Sep 2024 13:09:22 -0700
Subject: [PATCH 2/5] add missing libcudf doc links

---
 python/pylibcudf/pylibcudf/expressions.pyx    |  4 ++--
 python/pylibcudf/pylibcudf/filling.pyx        |  2 +-
 python/pylibcudf/pylibcudf/groupby.pyx        |  2 +-
 python/pylibcudf/pylibcudf/io/avro.pyx        |  2 ++
 python/pylibcudf/pylibcudf/io/parquet.pyx     |  4 ++++
 python/pylibcudf/pylibcudf/labeling.pyx       |  2 ++
 python/pylibcudf/pylibcudf/merge.pyx          |  2 ++
 python/pylibcudf/pylibcudf/quantiles.pyx      |  4 ++++
 python/pylibcudf/pylibcudf/reshape.pyx        |  4 ++++
 python/pylibcudf/pylibcudf/search.pyx         |  6 ++++++
 python/pylibcudf/pylibcudf/sorting.pyx        | 20 +++++++++++++++++++
 .../pylibcudf/pylibcudf/stream_compaction.pyx | 18 +++++++++++++++++
 python/pylibcudf/pylibcudf/transform.pyx      |  2 ++
 13 files changed, 68 insertions(+), 4 deletions(-)

diff --git a/python/pylibcudf/pylibcudf/expressions.pyx b/python/pylibcudf/pylibcudf/expressions.pyx
index a44c9e25987..caf57128c86 100644
--- a/python/pylibcudf/pylibcudf/expressions.pyx
+++ b/python/pylibcudf/pylibcudf/expressions.pyx
@@ -198,8 +198,8 @@ cdef class ColumnNameReference(Expression):
         Name of this column in the table metadata
         (provided when the expression is evaluated).
     """
-    def __cinit__(self, str name):
+    def __cinit__(self, str colmun_name):
         self.c_obj = <expression_ptr> \
             move(make_unique[libcudf_exp.column_name_reference](
-                <string>(name.encode("utf-8"))
+                <string>(column_name.encode("utf-8"))
             ))
diff --git a/python/pylibcudf/pylibcudf/filling.pyx b/python/pylibcudf/pylibcudf/filling.pyx
index 61b430e64aa..b4623ee90a1 100644
--- a/python/pylibcudf/pylibcudf/filling.pyx
+++ b/python/pylibcudf/pylibcudf/filling.pyx
@@ -89,7 +89,7 @@ cpdef void fill_in_place(
             dereference(value.c_obj)
         )
 
-cpdef Column sequence(size_type size, Scalar init, Scalar step):
+cpdef Column sequence(int size, Scalar init, Scalar step):
     """Create a sequence column of size ``size`` with initial value ``init`` and step
     ``step``.
 
diff --git a/python/pylibcudf/pylibcudf/groupby.pyx b/python/pylibcudf/pylibcudf/groupby.pyx
index ae5d33aaa46..afb95dba5b3 100644
--- a/python/pylibcudf/pylibcudf/groupby.pyx
+++ b/python/pylibcudf/pylibcudf/groupby.pyx
@@ -286,7 +286,7 @@ cdef class GroupBy:
 
         Returns
         -------
-        Tuple[List[int], Table, Table]]
+        Tuple[List[int], Table, Table]
             A tuple of tables containing three items:
                 - A list of integer offsets into the group keys/values
                 - A table of group keys
diff --git a/python/pylibcudf/pylibcudf/io/avro.pyx b/python/pylibcudf/pylibcudf/io/avro.pyx
index 667c67f4c36..438b0ff1634 100644
--- a/python/pylibcudf/pylibcudf/io/avro.pyx
+++ b/python/pylibcudf/pylibcudf/io/avro.pyx
@@ -20,6 +20,8 @@ cpdef TableWithMetadata read_avro(
     """
     Reads an Avro dataset into a :py:class:`~.types.TableWithMetadata`.
 
+    For details, see :cpp:func:`read_avro`.
+
     Parameters
     ----------
     source_info: SourceInfo
diff --git a/python/pylibcudf/pylibcudf/io/parquet.pyx b/python/pylibcudf/pylibcudf/io/parquet.pyx
index df1f1b14247..981ca7b8159 100644
--- a/python/pylibcudf/pylibcudf/io/parquet.pyx
+++ b/python/pylibcudf/pylibcudf/io/parquet.pyx
@@ -59,6 +59,8 @@ cdef class ChunkedParquetReader:
     """
     Reads chunks of a Parquet file into a :py:class:`~.types.TableWithMetadata`.
 
+    For details, see :cpp:class:`chunked_parquet_reader`.
+
     Parameters
     ----------
     source_info : SourceInfo
@@ -167,6 +169,8 @@ cpdef read_parquet(
 ):
     """Reads an Parquet file into a :py:class:`~.types.TableWithMetadata`.
 
+    For details, see :cpp:func:`read_parquet`.
+
     Parameters
     ----------
     source_info : SourceInfo
diff --git a/python/pylibcudf/pylibcudf/labeling.pyx b/python/pylibcudf/pylibcudf/labeling.pyx
index b5a7445df36..b3f6a92d85c 100644
--- a/python/pylibcudf/pylibcudf/labeling.pyx
+++ b/python/pylibcudf/pylibcudf/labeling.pyx
@@ -20,6 +20,8 @@ cpdef Column label_bins(
 ):
     """Labels elements based on membership in the specified bins.
 
+    For details see :cpp:func:`label_bins`.
+
     Parameters
     ----------
     input : Column
diff --git a/python/pylibcudf/pylibcudf/merge.pyx b/python/pylibcudf/pylibcudf/merge.pyx
index a7d43c9d158..6d707b67449 100644
--- a/python/pylibcudf/pylibcudf/merge.pyx
+++ b/python/pylibcudf/pylibcudf/merge.pyx
@@ -19,6 +19,8 @@ cpdef Table merge (
 ):
     """Merge a set of sorted tables.
 
+    For details see :cpp:func:`merge`.
+
     Parameters
     ----------
     tables_to_merge : list
diff --git a/python/pylibcudf/pylibcudf/quantiles.pyx b/python/pylibcudf/pylibcudf/quantiles.pyx
index b847ade774d..3a771fbe7ef 100644
--- a/python/pylibcudf/pylibcudf/quantiles.pyx
+++ b/python/pylibcudf/pylibcudf/quantiles.pyx
@@ -30,6 +30,8 @@ cpdef Column quantile(
     Computes the specified quantiles by interpolating values between which they lie,
     using the interpolation strategy specified in interp.
 
+    For details see :cpp:func:`quantile`.
+
     Parameters
     ----------
     input: Column
@@ -91,6 +93,8 @@ cpdef Table quantiles(
     specified quantiles. In the event a quantile lies in between rows, the specified
     interpolation strategy is used to pick between the rows.
 
+    For details see :cpp:func:`quantiles`.
+
     Parameters
     ----------
     input: Table
diff --git a/python/pylibcudf/pylibcudf/reshape.pyx b/python/pylibcudf/pylibcudf/reshape.pyx
index a99145be900..eb1499ebbea 100644
--- a/python/pylibcudf/pylibcudf/reshape.pyx
+++ b/python/pylibcudf/pylibcudf/reshape.pyx
@@ -23,6 +23,8 @@ cpdef Column interleave_columns(Table source_table):
     in     = [[A1, A2, A3], [B1, B2, B3]]
     return = [A1, B1, A2, B2, A3, B3]
 
+    For details, see :cpp:func:`interleave_columns`.
+
     Parameters
     ----------
     source_table: Table
@@ -44,6 +46,8 @@ cpdef Column interleave_columns(Table source_table):
 cpdef Table tile(Table source_table, size_type count):
     """Repeats the rows from input table count times to form a new table.
 
+    For details, see :cpp:func:`tile`.
+
     Parameters
     ----------
     source_table: Table
diff --git a/python/pylibcudf/pylibcudf/search.pyx b/python/pylibcudf/pylibcudf/search.pyx
index ff2468f3f9c..814bc6553d8 100644
--- a/python/pylibcudf/pylibcudf/search.pyx
+++ b/python/pylibcudf/pylibcudf/search.pyx
@@ -19,6 +19,8 @@ cpdef Column lower_bound(
 ):
     """Find smallest indices in haystack where needles may be inserted to retain order.
 
+    For details, see :cpp:func:`lower_bound`.
+
     Parameters
     ----------
     haystack : Table
@@ -58,6 +60,8 @@ cpdef Column upper_bound(
 ):
     """Find largest indices in haystack where needles may be inserted to retain order.
 
+    For details, see :cpp:func:`upper_bound`.
+
     Parameters
     ----------
     haystack : Table
@@ -92,6 +96,8 @@ cpdef Column upper_bound(
 cpdef Column contains(Column haystack, Column needles):
     """Check whether needles are present in haystack.
 
+    For details, see :cpp:func:`contains`.
+
     Parameters
     ----------
     haystack : Table
diff --git a/python/pylibcudf/pylibcudf/sorting.pyx b/python/pylibcudf/pylibcudf/sorting.pyx
index bd173eebacb..42289d54bca 100644
--- a/python/pylibcudf/pylibcudf/sorting.pyx
+++ b/python/pylibcudf/pylibcudf/sorting.pyx
@@ -16,6 +16,8 @@ from .table cimport Table
 cpdef Column sorted_order(Table source_table, list column_order, list null_precedence):
     """Computes the row indices required to sort the table.
 
+    For details, see :cpp:func:`sorted_order`.
+
     Parameters
     ----------
     source_table : Table
@@ -52,6 +54,8 @@ cpdef Column stable_sorted_order(
     """Computes the row indices required to sort the table,
     preserving order of equal elements.
 
+    For details, see :cpp:func:`stable_sorted_order`.
+
     Parameters
     ----------
     source_table : Table
@@ -90,6 +94,8 @@ cpdef Column rank(
 ):
     """Computes the rank of each element in the column.
 
+    For details, see :cpp:func:`rank`.
+
     Parameters
     ----------
     input_view : Column
@@ -128,6 +134,8 @@ cpdef Column rank(
 cpdef bool is_sorted(Table tbl, list column_order, list null_precedence):
     """Checks if the table is sorted.
 
+    For details, see :cpp:func:`is_sorted`.
+
     Parameters
     ----------
     tbl : Table
@@ -165,6 +173,8 @@ cpdef Table segmented_sort_by_key(
 ):
     """Sorts the table by key, within segments.
 
+    For details, see :cpp:func:`segmented_sort_by_key`.
+
     Parameters
     ----------
     values : Table
@@ -209,6 +219,8 @@ cpdef Table stable_segmented_sort_by_key(
     """Sorts the table by key preserving order of equal elements,
     within segments.
 
+    For details, see :cpp:func:`stable_segmented_sort_by_key`.
+
     Parameters
     ----------
     values : Table
@@ -251,6 +263,8 @@ cpdef Table sort_by_key(
 ):
     """Sorts the table by key.
 
+    For details, see :cpp:func:`sort_by_key`.
+
     Parameters
     ----------
     values : Table
@@ -290,6 +304,8 @@ cpdef Table stable_sort_by_key(
 ):
     """Sorts the table by key preserving order of equal elements.
 
+    For details, see :cpp:func:`stable_sort_by_key`.
+
     Parameters
     ----------
     values : Table
@@ -324,6 +340,8 @@ cpdef Table stable_sort_by_key(
 cpdef Table sort(Table source_table, list column_order, list null_precedence):
     """Sorts the table.
 
+    For details, see :cpp:func:`sort`.
+
     Parameters
     ----------
     source_table : Table
@@ -355,6 +373,8 @@ cpdef Table sort(Table source_table, list column_order, list null_precedence):
 cpdef Table stable_sort(Table source_table, list column_order, list null_precedence):
     """Sorts the table preserving order of equal elements.
 
+    For details, see :cpp:func:`stable_sort`.
+
     Parameters
     ----------
     source_table : Table
diff --git a/python/pylibcudf/pylibcudf/stream_compaction.pyx b/python/pylibcudf/pylibcudf/stream_compaction.pyx
index b574bfa9fa2..d5475ea79d5 100644
--- a/python/pylibcudf/pylibcudf/stream_compaction.pyx
+++ b/python/pylibcudf/pylibcudf/stream_compaction.pyx
@@ -25,6 +25,8 @@ from .table cimport Table
 cpdef Table drop_nulls(Table source_table, list keys, size_type keep_threshold):
     """Filters out rows from the input table based on the presence of nulls.
 
+    For details, see :cpp:func:`drop_nulls`.
+
     Parameters
     ----------
     source_table : Table
@@ -53,6 +55,8 @@ cpdef Table drop_nulls(Table source_table, list keys, size_type keep_threshold):
 cpdef Table drop_nans(Table source_table, list keys, size_type keep_threshold):
     """Filters out rows from the input table based on the presence of NaNs.
 
+    For details, see :cpp:func:`drop_nans`.
+
     Parameters
     ----------
     source_table : Table
@@ -81,6 +85,8 @@ cpdef Table drop_nans(Table source_table, list keys, size_type keep_threshold):
 cpdef Table apply_boolean_mask(Table source_table, Column boolean_mask):
     """Filters out rows from the input table based on a boolean mask.
 
+    For details, see :cpp:func:`apply_boolean_mask`.
+
     Parameters
     ----------
     source_table : Table
@@ -111,6 +117,8 @@ cpdef Table unique(
 ):
     """Filter duplicate consecutive rows from the input table.
 
+    For details, see :cpp:func:`unique`.
+
     Parameters
     ----------
     input : Table
@@ -153,6 +161,8 @@ cpdef Table distinct(
 ):
     """Get the distinct rows from the input table.
 
+    For details, see :cpp:func:`distinct`.
+
     Parameters
     ----------
     input : Table
@@ -191,6 +201,8 @@ cpdef Column distinct_indices(
 ):
     """Get the indices of the distinct rows from the input table.
 
+    For details, see :cpp:func:`distinct_indices`.
+
     Parameters
     ----------
     input : Table
@@ -226,6 +238,8 @@ cpdef Table stable_distinct(
 ):
     """Get the distinct rows from the input table, preserving input order.
 
+    For details, see :cpp:func:`stable_distinct`.
+
     Parameters
     ----------
     input : Table
@@ -263,6 +277,8 @@ cpdef size_type unique_count(
 ):
     """Returns the number of unique consecutive elements in the input column.
 
+    For details, see :cpp:func:`unique_count`.
+
     Parameters
     ----------
     source : Column
@@ -294,6 +310,8 @@ cpdef size_type distinct_count(
 ):
     """Returns the number of distinct elements in the input column.
 
+    For details, see :cpp:func:`distinct_count`.
+
     Parameters
     ----------
     source : Column
diff --git a/python/pylibcudf/pylibcudf/transform.pyx b/python/pylibcudf/pylibcudf/transform.pyx
index 100ccb580ce..45558fe2b2f 100644
--- a/python/pylibcudf/pylibcudf/transform.pyx
+++ b/python/pylibcudf/pylibcudf/transform.pyx
@@ -14,6 +14,8 @@ from .gpumemoryview cimport gpumemoryview
 cpdef tuple[gpumemoryview, int] nans_to_nulls(Column input):
     """Create a null mask preserving existing nulls and converting nans to null.
 
+    For details, see :cpp:func:`nans_to_nulls`.
+
     Parameters
     ----------
     input : Column

From d75df82a141c6f26b565106be73837a0b1c9a1b3 Mon Sep 17 00:00:00 2001
From: Matthew Murray <matthewmurray711@gmail.com>
Date: Sat, 21 Sep 2024 06:55:29 -0700
Subject: [PATCH 3/5] fix declaration, revert name change

---
 python/pylibcudf/pylibcudf/expressions.pyx | 4 ++--
 python/pylibcudf/pylibcudf/filling.pxd     | 2 +-
 python/pylibcudf/pylibcudf/filling.pyx     | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/python/pylibcudf/pylibcudf/expressions.pyx b/python/pylibcudf/pylibcudf/expressions.pyx
index caf57128c86..a44c9e25987 100644
--- a/python/pylibcudf/pylibcudf/expressions.pyx
+++ b/python/pylibcudf/pylibcudf/expressions.pyx
@@ -198,8 +198,8 @@ cdef class ColumnNameReference(Expression):
         Name of this column in the table metadata
         (provided when the expression is evaluated).
     """
-    def __cinit__(self, str colmun_name):
+    def __cinit__(self, str name):
         self.c_obj = <expression_ptr> \
             move(make_unique[libcudf_exp.column_name_reference](
-                <string>(column_name.encode("utf-8"))
+                <string>(name.encode("utf-8"))
             ))
diff --git a/python/pylibcudf/pylibcudf/filling.pxd b/python/pylibcudf/pylibcudf/filling.pxd
index b9345f8cd42..301b652b6ac 100644
--- a/python/pylibcudf/pylibcudf/filling.pxd
+++ b/python/pylibcudf/pylibcudf/filling.pxd
@@ -24,7 +24,7 @@ cpdef void fill_in_place(
 )
 
 cpdef Column sequence(
-    size_type size,
+    int size,
     Scalar init,
     Scalar step,
 )
diff --git a/python/pylibcudf/pylibcudf/filling.pyx b/python/pylibcudf/pylibcudf/filling.pyx
index b4623ee90a1..61b430e64aa 100644
--- a/python/pylibcudf/pylibcudf/filling.pyx
+++ b/python/pylibcudf/pylibcudf/filling.pyx
@@ -89,7 +89,7 @@ cpdef void fill_in_place(
             dereference(value.c_obj)
         )
 
-cpdef Column sequence(int size, Scalar init, Scalar step):
+cpdef Column sequence(size_type size, Scalar init, Scalar step):
     """Create a sequence column of size ``size`` with initial value ``init`` and step
     ``step``.
 

From 6941df606044293a5d1580a01b4faad21084b0fd Mon Sep 17 00:00:00 2001
From: Matthew Murray <matthewmurray711@gmail.com>
Date: Mon, 23 Sep 2024 05:25:12 -0700
Subject: [PATCH 4/5] update declaration

---
 python/pylibcudf/pylibcudf/filling.pxd | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/python/pylibcudf/pylibcudf/filling.pxd b/python/pylibcudf/pylibcudf/filling.pxd
index 301b652b6ac..b9345f8cd42 100644
--- a/python/pylibcudf/pylibcudf/filling.pxd
+++ b/python/pylibcudf/pylibcudf/filling.pxd
@@ -24,7 +24,7 @@ cpdef void fill_in_place(
 )
 
 cpdef Column sequence(
-    int size,
+    size_type size,
     Scalar init,
     Scalar step,
 )

From ca82992d91333c8b6fc356c2dcca06bf86fa4a7e Mon Sep 17 00:00:00 2001
From: Matthew Murray <matthewmurray711@gmail.com>
Date: Tue, 24 Sep 2024 21:04:41 -0700
Subject: [PATCH 5/5] update branch, fix typo in doc string

---
 python/pylibcudf/pylibcudf/strings/findall.pyx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/python/pylibcudf/pylibcudf/strings/findall.pyx b/python/pylibcudf/pylibcudf/strings/findall.pyx
index 03ecb13a50e..3a6b87504b3 100644
--- a/python/pylibcudf/pylibcudf/strings/findall.pyx
+++ b/python/pylibcudf/pylibcudf/strings/findall.pyx
@@ -13,7 +13,7 @@ cpdef Column findall(Column input, RegexProgram pattern):
     Returns a lists column of strings for each matching occurrence using
     the regex_program pattern within each string.
 
-    For details, see For details, see :cpp:func:`cudf::strings::findall`.
+    For details, see :cpp:func:`cudf::strings::findall`.
 
     Parameters
     ----------