Merge branch 'main' into jkew/add-hybrid-precheck

Author: sfc-gh-jkew

.github/workflows/create-test-branch-from-release.yml

@@ -1,22 +1,11 @@
 # This workflow automatically creates a test branch from a release tag
 # For example, when release v1.40.0 is published, it creates test-v1.40.0 branch
-# Can also be triggered manually to create a test branch from any existing tag
 
 name: Create Test Branch from Release
 
 on:
   release:
     types: [published]
-  workflow_dispatch:
-    inputs:
-      tag_name:
-        description: 'Tag name to create test branch from (e.g., v1.40.0)'
-        required: true
-        type: string
-      test_branch_name:
-        description: 'Test branch name (optional, defaults to test-<tag_name>)'
-        required: false
-        type: string
 
 permissions:
   contents: write
@@ -29,18 +18,8 @@ jobs:
     - name: Extract tag name
       id: extract_tag
       run: |
-        # Determine tag name based on trigger type
-        if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
-          TAG_NAME=${{ inputs.tag_name }}
-          if [ -n "${{ inputs.test_branch_name }}" ]; then
-            TEST_BRANCH_NAME=${{ inputs.test_branch_name }}
-          else
-            TEST_BRANCH_NAME="test-${TAG_NAME}"
-          fi
-        else
-          TAG_NAME=${{ github.event.release.tag_name }}
-          TEST_BRANCH_NAME="test-${TAG_NAME}"
-        fi
+        TAG_NAME=${{ github.event.release.tag_name }}
+        TEST_BRANCH_NAME="test-${TAG_NAME}"
 
         echo "tag_name=${TAG_NAME}" >> $GITHUB_OUTPUT
         echo "test_branch_name=${TEST_BRANCH_NAME}" >> $GITHUB_OUTPUT

CHANGELOG.md

@@ -26,6 +26,18 @@
 - Added support for mapping `np.percentile` with DataFrame and Series inputs to `Series.quantile`.
 - Added support for setting the `random_state` parameter to an integer when calling `DataFrame.sample` or `Series.sample`.
 
+#### Improvements
+
+- Enhanced autoswitching functionality from Snowflake to native Pandas for methods with unsupported argument combinations:
+  - `shift()` with `suffix` or non-integer `periods` parameters
+  - `sort_index()` with `axis=1` or `key` parameters
+  - `sort_values()` with `axis=1`
+  - `melt()` with `col_level` parameter
+  - `apply()` with `result_type` parameter for DataFrame
+  - `pivot_table()` with `sort=True`, non-string `index` list, non-string `columns` list, non-string `values` list, or `aggfunc` dict with non-string values
+  - `fillna()` with `downcast` parameter or using `limit` together with `value`
+  - `dropna()` with `axis=1`
+
 #### Bug Fixes
 
 - Fixed a bug in `DataFrameGroupBy.agg` where func is a list of tuples used to set the names of the output columns.

src/snowflake/snowpark/modin/plugin/_internal/pivot_utils.py

@@ -1866,3 +1866,58 @@ def generate_column_prefix_groupings(
         )
 
     return list(zip(margin_data_column_prefixes, margin_data_column_groupings))
+
+
+def check_pivot_table_unsupported_args(args: dict) -> Optional[str]:
+    """
+    Validate pivot_table arguments for unsupported conditions.
+
+    This helper function checks various argument combinations that are not yet
+    supported by Snowpark pandas pivot_table implementation.
+
+    Args:
+        args : dictionary of arguments passed to pivot_table
+
+    Returns:
+        Error message if an unsupported condition is found, None otherwise
+    """
+    # Check if index argument is a string or list of strings
+    index = args.get("index")
+    if (
+        index is not None
+        and not isinstance(index, str)
+        and not all(isinstance(v, str) for v in index)
+        and None not in index
+    ):
+        return "index argument should be a string or a list of strings"
+
+    # Check if columns argument is a string or list of strings
+    columns = args.get("columns")
+    if (
+        columns is not None
+        and not isinstance(columns, str)
+        and not all(isinstance(v, str) for v in columns)
+        and None not in columns
+    ):
+        return "columns argument should be a string or a list of strings"
+
+    # Check if values argument is a string or list of strings
+    values = args.get("values")
+    if (
+        values is not None
+        and not isinstance(values, str)
+        and not all(isinstance(v, str) for v in values)
+        and None not in values
+    ):
+        return "values argument should be a string or a list of strings"
+
+    # Check for dictionary aggfunc with non-string functions when index is None
+    aggfunc = args.get("aggfunc")
+    if (
+        isinstance(aggfunc, dict)
+        and any(not isinstance(af, str) for af in aggfunc.values())
+        and args.get("index") is None
+    ):
+        return "dictionary aggfunc with non-string aggregation functions is not yet supported for pivot_table when index is None"
+
+    return None