snowflake-snowpark-python 1.48.1__tar.gz → 1.50.0__tar.gz

{snowflake_snowpark_python-1.48.1 → snowflake_snowpark_python-1.50.0}/CHANGELOG.md

@@ -1,5 +1,55 @@
 # Release History
 
+## 1.50.0 (2026-04-23)
+
+### Snowpark Python API Updates
+
+#### New Features
+
+- Added `artifact_repository` support to `udtf_configs` in `session.read.dbapi()`, enabling users to specify a custom artifact repository (e.g. PyPI) for packages used by the internal UDTF during distributed ingestion.
+
+#### Bug Fixes
+
+- Fixed a bug where `TRY_CAST` reader option is ignored when calling `DataFrameReader.schema().csv()`.
+- Fixed a bug where `event_table_telemetry` is using incorrect resource attributes.
+- Fixed a bug where `value_contains_null` was not propagated for `MapType` in `_as_nested` function.
+- Fixed a bug where CTE optimization incorrectly deduplicated subtrees containing non-deterministic data generation functions (e.g. `uuid_string()`). 
+- Fixed a bug where vectorized UDFs using non-anaconda package repositories did not specify the pandas package by default.
+
+### Snowpark pandas API Updates
+
+#### Dependency Updates
+
+- Updated the supported `pandas` versions to <=2.4 (was previously <=2.3.1).
+
+## 1.49.0 (2026-04-13)
+
+### Snowpark Python API Updates
+
+#### New Features
+
+- Allow a user-specified schema when reading Parquet files from a stage.
+
+#### Improvements
+
+- Restored the following query improvements that were reverted in 1.47.0 due to bugs:
+  - Reduced the size of queries generated by certain `DataFrame.join` operations.
+  - Removed redundant aliases in generated queries (for example, `SELECT "A" AS "A"` is now always simplified to `SELECT "A"`).
+- Removed warning that `DataFrameReader.dbapi` feature was in private preview.
+
+#### Bug Fixes
+
+- Fixed a bug where `Session.create_dataframe` raised `TypeError` when a `StringType` column was given a non-string Python value (e.g. `int`, `float`, `bool`, `Decimal`) for a small local relation (below the array bind threshold); `VALUES` SQL generation now coerces these types to string literals, consistent with the large-data bind-parameter path.
+- Fixed a bug where `DataFrame.approxQuantile` did not accept a `Column` for the `col` parameter.
+
+### Snowpark Local Testing Updates
+
+#### Bug Fixes
+
+- Fixed a bug where `concat` produced extra NaN rows and mismatched values after a `filter` operation in local testing.
+- Fixed a bug where `dense_rank()` would fail with `ValueError` on NULL partition values.
+- Fixed a bug where `collect()` raised `KeyError` after `save_as_table(column_order="name")` when the source DataFrame omitted columns with types `VariantType`, `MapType`, or `ArrayType` that were present in the target table schema in local testing.
+
 ## 1.48.1 (2026-03-31)
 
 ### Snowpark Python API Updates
@@ -8,6 +58,7 @@
 
 - Fixed a bug where chained `DataFrame.filter()` calls with raw SQL text containing `OR` produced incorrect results.
 - Fixed a Snowflake platform compatibility issue where `concat(lit('"'), ...)` could lose the leading quote through chained set-operation plans.
+- Fixed a bug for XML schema inference session resolution in spark compatible mode.
 
 ## 1.48.0 (2026-03-23)
 

{snowflake_snowpark_python-1.48.1/src/snowflake_snowpark_python.egg-info → snowflake_snowpark_python-1.50.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: snowflake-snowpark-python
-Version: 1.48.1
+Version: 1.50.0
 Summary: Snowflake Snowpark for Python
 Home-page: https://www.snowflake.com/
 Author: Snowflake, Inc
@@ -33,7 +33,7 @@ Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: >=3.9, <3.14
+Requires-Python: >=3.9, <3.15
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
 Requires-Dist: setuptools>=40.6.0
@@ -50,7 +50,7 @@ Requires-Dist: snowflake-connector-python[pandas]<5.0.0,>=3.17.0; extra == "pand
 Provides-Extra: modin
 Requires-Dist: snowflake-connector-python[pandas]<5.0.0,>=3.17.0; extra == "modin"
 Requires-Dist: modin<0.38.0,>=0.36.0; extra == "modin"
-Requires-Dist: pandas<=2.3.1; extra == "modin"
+Requires-Dist: pandas<=2.4; extra == "modin"
 Requires-Dist: tqdm; extra == "modin"
 Requires-Dist: ipywidgets; extra == "modin"
 Provides-Extra: secure-local-storage
@@ -74,10 +74,11 @@ Requires-Dist: tox; extra == "development"
 Requires-Dist: snowflake.core<2,>=1.0.0; extra == "development"
 Requires-Dist: psutil; extra == "development"
 Requires-Dist: lxml; extra == "development"
+Requires-Dist: pyarrow; extra == "development"
 Provides-Extra: modin-development
 Requires-Dist: snowflake-connector-python[pandas]<5.0.0,>=3.17.0; extra == "modin-development"
 Requires-Dist: modin<0.38.0,>=0.36.0; extra == "modin-development"
-Requires-Dist: pandas<=2.3.1; extra == "modin-development"
+Requires-Dist: pandas<=2.4; extra == "modin-development"
 Requires-Dist: tqdm; extra == "modin-development"
 Requires-Dist: ipywidgets; extra == "modin-development"
 Requires-Dist: pytest<8.0.0; extra == "modin-development"
@@ -98,13 +99,14 @@ Requires-Dist: tox; extra == "modin-development"
 Requires-Dist: snowflake.core<2,>=1.0.0; extra == "modin-development"
 Requires-Dist: psutil; extra == "modin-development"
 Requires-Dist: lxml; extra == "modin-development"
-Requires-Dist: scipy<=1.16.0; extra == "modin-development"
+Requires-Dist: pyarrow; extra == "modin-development"
+Requires-Dist: scipy<=1.16.3; extra == "modin-development"
 Requires-Dist: statsmodels; extra == "modin-development"
 Requires-Dist: scikit-learn; extra == "modin-development"
 Requires-Dist: plotly<6.0.0; extra == "modin-development"
 Requires-Dist: snowflake-ml-python>=1.8.0; python_version < "3.12" and extra == "modin-development"
 Requires-Dist: s3fs; extra == "modin-development"
-Requires-Dist: ray; extra == "modin-development"
+Requires-Dist: ray; python_version < "3.14" and extra == "modin-development"
 Provides-Extra: localtest
 Requires-Dist: pandas; extra == "localtest"
 Requires-Dist: requests; extra == "localtest"

{snowflake_snowpark_python-1.48.1 → snowflake_snowpark_python-1.50.0}/setup.py

@@ -32,7 +32,7 @@ INSTALL_REQ_LIST = [
     "python-dateutil",  # Snowpark IR
     "tzlocal",  # Snowpark IR
 ]
-REQUIRED_PYTHON_VERSION = ">=3.9, <3.14"
+REQUIRED_PYTHON_VERSION = ">=3.9, <3.15"
 
 if os.getenv("SNOWFLAKE_IS_PYTHON_RUNTIME_TEST", False):
     REQUIRED_PYTHON_VERSION = ">=3.9"
@@ -43,7 +43,7 @@ PANDAS_REQUIREMENTS = [
 MODIN_REQUIREMENTS = [
     *PANDAS_REQUIREMENTS,
     f"modin{MODIN_DEPENDENCY_VERSION}",
-    "pandas<=2.3.1",
+    "pandas<=2.4",
     "tqdm",  # For progress bars during backend switching
     "ipywidgets",  # For enhanced progress bars in Jupyter notebooks
 ]
@@ -66,12 +66,13 @@ DEVELOPMENT_REQUIREMENTS = [
     "snowflake.core>=1.0.0, <2",  # Catalog
     "psutil",  # testing for telemetry
     "lxml",  # used in XML reader unit tests
+    "pyarrow",  # used in dataframe reader tests
 ]
 MODIN_DEVELOPMENT_REQUIREMENTS = [
     # Snowpark pandas 3rd party library testing. Cap the scipy version because
     # Snowflake cannot find newer versions of scipy for python 3.11+. See
     # SNOW-2452791.
-    "scipy<=1.16.0",
+    "scipy<=1.16.3",
     "statsmodels",  # Snowpark pandas 3rd party library testing
     "scikit-learn",  # Snowpark pandas 3rd party library testing
     # plotly version restricted due to foreseen change in query counts in version 6.0.0+
@@ -80,7 +81,8 @@ MODIN_DEVELOPMENT_REQUIREMENTS = [
     # snowflake-ml-python is available on python 3.12.
     "snowflake-ml-python>=1.8.0; python_version<'3.12'",
     "s3fs",  # Used in tests that read CSV files from s3
-    "ray",  # Used in data movement tests
+    # ray currently has no compatible wheels for Python 3.14.
+    "ray; python_version<'3.14'",  # Used in data movement tests
 ]
 
 # read the version

{snowflake_snowpark_python-1.48.1 → snowflake_snowpark_python-1.50.0}/src/snowflake/snowpark/_internal/analyzer/analyzer.py

@@ -763,10 +763,18 @@ class Analyzer:
                     for k, v in df_alias_dict.items():
                         if v == expr.child.name:
                             df_alias_dict[k] = updated_due_to_inheritance  # type: ignore
+            origin = self.analyze(
+                expr.child, df_aliased_col_name_to_real_col_name, parse_local_name
+            )
+            if (
+                isinstance(expr.child, (Attribute, UnresolvedAttribute))
+                and origin == quoted_name
+            ):
+                # If the column name matches the target of the alias (`quoted_name`),
+                # we can directly emit the column name without an AS clause.
+                return origin
             return alias_expression(
-                self.analyze(
-                    expr.child, df_aliased_col_name_to_real_col_name, parse_local_name
-                ),
+                origin,
                 quoted_name,
             )
 

{snowflake_snowpark_python-1.48.1 → snowflake_snowpark_python-1.50.0}/src/snowflake/snowpark/_internal/analyzer/datatype_mapper.py

@@ -401,6 +401,16 @@ def to_sql(
             else str_to_sql(value)
         )
 
+    if isinstance(datatype, StringType) and isinstance(
+        value, (bool, int, float, Decimal)
+    ):
+        # Coerce common Python scalars to str so that VALUES and bind-param
+        # paths produce identical string representations.  bool is a subclass
+        # of int so it must be checked first.  Use lowercase for bools to
+        # match Snowflake's BOOLEAN::STRING cast semantics.
+        s = str(value).lower() if isinstance(value, bool) else str(value)
+        return to_sql(s, datatype, from_values_statement=from_values_statement)
+
     if isinstance(datatype, _IntegralType):
         return f"{value} :: INT"
 

{snowflake_snowpark_python-1.48.1 → snowflake_snowpark_python-1.50.0}/src/snowflake/snowpark/_internal/analyzer/expression.py

@@ -2,7 +2,6 @@
 # Copyright (c) 2012-2025 Snowflake Computing Inc. All rights reserved.
 #
 
-import copy
 import uuid
 from typing import TYPE_CHECKING, AbstractSet, Any, Dict, List, Optional, Tuple
 
@@ -158,7 +157,9 @@ class NamedExpression:
         return self._expr_id
 
     def __copy__(self):
-        new = copy.copy(super())
+        cls = self.__class__
+        new = cls.__new__(cls)
+        new.__dict__.update(self.__dict__)
         new._expr_id = None  # type: ignore
         return new