snowflake-ml-python 1.16.0__tar.gz → 1.17.0__tar.gz

{snowflake_ml_python-1.16.0 → snowflake_ml_python-1.17.0}/CHANGELOG.md

@@ -1,5 +1,26 @@
 # Release History
 
+## 1.17.0
+
+### Bug Fixes
+
+* ML Job: Added support for retrieving details of deleted jobs, including status, compute pool, and target instances.
+
+### Behavior Changes
+
+### New Features
+
+* Support xgboost 3.x.
+* ML Job: Overhauled the `MLJob.result()` API with broader cross-version
+  compatibility and support for additional data types, namely:
+  * Pandas DataFrames
+  * PyArrow Tables
+  * NumPy arrays
+  * NOTE: Requires `snowflake-ml-python>=1.17.0` to be installed inside remote container environment.
+* ML Job: Enabled job submission v2 by default
+  * Jobs submitted using v2 will automatically use the latest Container Runtime image
+  * v1 behavior can be restored by setting environment variable `MLRS_USE_SUBMIT_JOB_V2` to `false`
+
 ## 1.16.0
 
 ### Bug Fixes
@@ -34,9 +55,10 @@ options = {
             "function_type": "TABLE_FUNCTION",
             "volatility": Volatility.VOLATILE,
         },
+    },
 }
 
-````
+```
 
 ## 1.15.0 (09-29-2025)
 

{snowflake_ml_python-1.16.0/snowflake_ml_python.egg-info → snowflake_ml_python-1.17.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: snowflake-ml-python
-Version: 1.16.0
+Version: 1.17.0
 Summary: The machine learning client library that is used for interacting with Snowflake to build machine learning solutions.
 Author-email: "Snowflake, Inc" <support@snowflake.com>
 License: 
@@ -253,13 +253,13 @@ Requires-Dist: s3fs<2026,>=2024.6.1
 Requires-Dist: scikit-learn<1.8
 Requires-Dist: scipy<2,>=1.9
 Requires-Dist: shap<1,>=0.46.0
-Requires-Dist: snowflake-connector-python[pandas]<4,>=3.16.0
+Requires-Dist: snowflake-connector-python[pandas]<4,>=3.17.0
 Requires-Dist: snowflake-snowpark-python!=1.26.0,<2,>=1.17.0
 Requires-Dist: snowflake.core<2,>=1.0.2
 Requires-Dist: sqlparse<1,>=0.4
 Requires-Dist: tqdm<5
 Requires-Dist: typing-extensions<5,>=4.1.0
-Requires-Dist: xgboost<3,>=1.7.3
+Requires-Dist: xgboost<4
 Provides-Extra: all
 Requires-Dist: altair<6,>=5; extra == "all"
 Requires-Dist: catboost<2,>=1.2.0; extra == "all"
@@ -406,6 +406,27 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 # Release History
 
+## 1.17.0
+
+### Bug Fixes
+
+* ML Job: Added support for retrieving details of deleted jobs, including status, compute pool, and target instances.
+
+### Behavior Changes
+
+### New Features
+
+* Support xgboost 3.x.
+* ML Job: Overhauled the `MLJob.result()` API with broader cross-version
+  compatibility and support for additional data types, namely:
+  * Pandas DataFrames
+  * PyArrow Tables
+  * NumPy arrays
+  * NOTE: Requires `snowflake-ml-python>=1.17.0` to be installed inside remote container environment.
+* ML Job: Enabled job submission v2 by default
+  * Jobs submitted using v2 will automatically use the latest Container Runtime image
+  * v1 behavior can be restored by setting environment variable `MLRS_USE_SUBMIT_JOB_V2` to `false`
+
 ## 1.16.0
 
 ### Bug Fixes
@@ -440,9 +461,10 @@ options = {
             "function_type": "TABLE_FUNCTION",
             "volatility": Volatility.VOLATILE,
         },
+    },
 }
 
-````
+```
 
 ## 1.15.0 (09-29-2025)
 

{snowflake_ml_python-1.16.0 → snowflake_ml_python-1.17.0}/pyproject.toml

@@ -8,7 +8,7 @@ description = "The machine learning client library that is used for interacting
 classifiers = [ "Development Status :: 5 - Production/Stable", "Environment :: Console", "Environment :: Other Environment", "Intended Audience :: Developers", "Intended Audience :: Education", "Intended Audience :: Information Technology", "Intended Audience :: System Administrators", "License :: OSI Approved :: Apache Software License", "Operating System :: OS Independent", "Programming Language :: Python :: 3.9", "Programming Language :: Python :: 3.10", "Programming Language :: Python :: 3.11", "Programming Language :: Python :: 3.12", "Topic :: Database", "Topic :: Software Development", "Topic :: Software Development :: Libraries", "Topic :: Software Development :: Libraries :: Application Frameworks", "Topic :: Software Development :: Libraries :: Python Modules", "Topic :: Scientific/Engineering :: Information Analysis",]
 requires-python = ">=3.9, <3.13"
 dynamic = [ "version", "readme",]
-dependencies = [ "anyio>=3.5.0,<5", "cachetools>=3.1.1,<6", "cloudpickle>=2.0.0", "cryptography", "fsspec[http]>=2024.6.1,<2026", "importlib_resources>=6.1.1, <7", "numpy>=1.23,<3", "packaging>=20.9,<25", "pandas>=2.1.4,<3", "platformdirs<5", "pyarrow<19.0.0", "pydantic>=2.8.2, <3", "pyjwt>=2.0.0, <3", "pytimeparse>=1.1.8,<2", "pyyaml>=6.0,<7", "retrying>=1.3.3,<2", "s3fs>=2024.6.1,<2026", "scikit-learn<1.8", "scipy>=1.9,<2", "shap>=0.46.0,<1", "snowflake-connector-python[pandas]>=3.16.0,<4", "snowflake-snowpark-python>=1.17.0,<2,!=1.26.0", "snowflake.core>=1.0.2,<2", "sqlparse>=0.4,<1", "tqdm<5", "typing-extensions>=4.1.0,<5", "xgboost>=1.7.3,<3",]
+dependencies = [ "anyio>=3.5.0,<5", "cachetools>=3.1.1,<6", "cloudpickle>=2.0.0", "cryptography", "fsspec[http]>=2024.6.1,<2026", "importlib_resources>=6.1.1, <7", "numpy>=1.23,<3", "packaging>=20.9,<25", "pandas>=2.1.4,<3", "platformdirs<5", "pyarrow<19.0.0", "pydantic>=2.8.2, <3", "pyjwt>=2.0.0, <3", "pytimeparse>=1.1.8,<2", "pyyaml>=6.0,<7", "retrying>=1.3.3,<2", "s3fs>=2024.6.1,<2026", "scikit-learn<1.8", "scipy>=1.9,<2", "shap>=0.46.0,<1", "snowflake-connector-python[pandas]>=3.17.0,<4", "snowflake-snowpark-python>=1.17.0,<2,!=1.26.0", "snowflake.core>=1.0.2,<2", "sqlparse>=0.4,<1", "tqdm<5", "typing-extensions>=4.1.0,<5", "xgboost<4",]
 [[project.authors]]
 name = "Snowflake, Inc"
 email = "support@snowflake.com"

{snowflake_ml_python-1.16.0 → snowflake_ml_python-1.17.0}/snowflake/ml/_internal/human_readable_id/adjectives.txt

@@ -1,3 +1,4 @@
+aerial
 afraid
 ancient
 angry
@@ -26,7 +27,6 @@ dull
 empty
 evil
 fast
-fat
 fluffy
 foolish
 fresh
@@ -57,10 +57,10 @@ lovely
 lucky
 massive
 mean
+metallic
 mighty
 modern
 moody
-nasty
 neat
 nervous
 new
@@ -85,7 +85,6 @@ rotten
 rude
 selfish
 serious
-shaggy
 sharp
 short
 shy
@@ -96,14 +95,15 @@ slippery
 smart
 smooth
 soft
+solid
 sour
 spicy
 splendid
 spotty
+squishy
 stale
 strange
 strong
-stupid
 sweet
 swift
 tall
@@ -116,7 +116,6 @@ tidy
 tiny
 tough
 tricky
-ugly
 warm
 weak
 wet
@@ -124,5 +123,6 @@ wicked
 wise
 witty
 wonderful
+wooden
 yellow
 young

{snowflake_ml_python-1.16.0 → snowflake_ml_python-1.17.0}/snowflake/ml/_internal/human_readable_id/animals.txt

@@ -1,10 +1,9 @@
 anaconda
 ant
-ape
-baboon
 badger
 bat
 bear
+beetle
 bird
 bobcat
 bulldog
@@ -73,7 +72,6 @@ lobster
 mayfly
 mamba
 mole
-monkey
 moose
 moth
 mouse
@@ -114,6 +112,7 @@ swan
 termite
 tiger
 treefrog
+tuna
 turkey
 turtle
 vampirebat
@@ -126,3 +125,4 @@ worm
 yak
 yeti
 zebra
+zebrafish

{snowflake_ml_python-1.16.0 → snowflake_ml_python-1.17.0}/snowflake/ml/jobs/__init__.py

@@ -1,3 +1,4 @@
+from snowflake.ml.jobs._interop.exception_utils import install_exception_display_hooks
 from snowflake.ml.jobs._utils.types import JOB_STATUS
 from snowflake.ml.jobs.decorators import remote
 from snowflake.ml.jobs.job import MLJob
@@ -10,6 +11,9 @@ from snowflake.ml.jobs.manager import (
     submit_from_stage,
 )
 
+# Initialize exception display hooks for remote job error handling
+install_exception_display_hooks()
+
 __all__ = [
     "remote",
     "submit_file",

snowflake_ml_python-1.17.0/snowflake/ml/jobs/_interop/data_utils.py

@@ -0,0 +1,124 @@
+import io
+import json
+from typing import Any, Literal, Optional, Protocol, Union, cast, overload
+
+from snowflake import snowpark
+from snowflake.ml.jobs._interop import dto_schema
+
+
+class StageFileWriter(io.IOBase):
+    """
+    A context manager IOBase implementation that proxies writes to an internal BytesIO
+    and uploads to Snowflake stage on close.
+    """
+
+    def __init__(self, session: snowpark.Session, path: str) -> None:
+        self._session = session
+        self._path = path
+        self._buffer = io.BytesIO()
+        self._closed = False
+        self._exception_occurred = False
+
+    def write(self, data: Union[bytes, bytearray]) -> int:
+        """Write data to the internal buffer."""
+        if self._closed:
+            raise ValueError("I/O operation on closed file")
+        return self._buffer.write(data)
+
+    def close(self, write_contents: bool = True) -> None:
+        """Close the file and upload the buffer contents to the stage."""
+        if not self._closed:
+            # Only upload if buffer has content and no exception occurred
+            if write_contents and self._buffer.tell() > 0:
+                self._buffer.seek(0)
+                self._session.file.put_stream(self._buffer, self._path)
+            self._buffer.close()
+            self._closed = True
+
+    def __enter__(self) -> "StageFileWriter":
+        return self
+
+    def __exit__(self, exc_type: Any, exc_val: Any, exc_tb: Any) -> None:
+        exception_occurred = exc_type is not None
+        self.close(write_contents=not exception_occurred)
+
+    @property
+    def closed(self) -> bool:
+        return self._closed
+
+    def writable(self) -> bool:
+        return not self._closed
+
+    def readable(self) -> bool:
+        return False
+
+    def seekable(self) -> bool:
+        return not self._closed
+
+
+def _is_stage_path(path: str) -> bool:
+    return path.startswith("@") or path.startswith("snow://")
+
+
+def open_stream(path: str, mode: str = "rb", session: Optional[snowpark.Session] = None) -> io.IOBase:
+    if _is_stage_path(path):
+        if session is None:
+            raise ValueError("Session is required when opening a stage path")
+        if "r" in mode:
+            stream: io.IOBase = session.file.get_stream(path)  # type: ignore[assignment]
+            return stream
+        elif "w" in mode:
+            return StageFileWriter(session, path)
+        else:
+            raise ValueError(f"Unsupported mode '{mode}' for stage path")
+    else:
+        result: io.IOBase = open(path, mode)  # type: ignore[assignment]
+        return result
+
+
+class DtoCodec(Protocol):
+    @overload
+    @staticmethod
+    def decode(stream: io.IOBase, as_dict: Literal[True]) -> dict[str, Any]:
+        ...
+
+    @overload
+    @staticmethod
+    def decode(stream: io.IOBase, as_dict: Literal[False] = False) -> dto_schema.ResultDTO:
+        ...
+
+    @staticmethod
+    def decode(stream: io.IOBase, as_dict: bool = False) -> Union[dto_schema.ResultDTO, dict[str, Any]]:
+        pass
+
+    @staticmethod
+    def encode(dto: dto_schema.ResultDTO) -> bytes:
+        pass
+
+
+class JsonDtoCodec(DtoCodec):
+    @overload
+    @staticmethod
+    def decode(stream: io.IOBase, as_dict: Literal[True]) -> dict[str, Any]:
+        ...
+
+    @overload
+    @staticmethod
+    def decode(stream: io.IOBase, as_dict: Literal[False] = False) -> dto_schema.ResultDTO:
+        ...
+
+    @staticmethod
+    def decode(stream: io.IOBase, as_dict: bool = False) -> Union[dto_schema.ResultDTO, dict[str, Any]]:
+        data = cast(dict[str, Any], json.load(stream))
+        if as_dict:
+            return data
+        return dto_schema.ResultDTO.model_validate(data)
+
+    @staticmethod
+    def encode(dto: dto_schema.ResultDTO) -> bytes:
+        # Temporarily extract the value to avoid accidentally applying model_dump() on it
+        result_value = dto.value
+        dto.value = None  # Clear value to avoid serializing it in the model_dump
+        result_dict = dto.model_dump()
+        result_dict["value"] = result_value  # Put back the value
+        return json.dumps(result_dict).encode("utf-8")

snowflake_ml_python-1.17.0/snowflake/ml/jobs/_interop/dto_schema.py

@@ -0,0 +1,95 @@
+from typing import Any, Optional, Union
+
+from pydantic import BaseModel, model_validator
+from typing_extensions import NotRequired, TypedDict
+
+
+class BinaryManifest(TypedDict):
+    """
+    Binary data manifest schema.
+    Contains one of: path, bytes, or base64 for the serialized data.
+    """
+
+    path: NotRequired[str]  # Path to file
+    bytes: NotRequired[bytes]  # In-line byte string (not supported with JSON codec)
+    base64: NotRequired[str]  # Base64 encoded string
+
+
+class ParquetManifest(TypedDict):
+    """Protocol manifest schema for parquet files."""
+
+    paths: list[str]  # File paths
+
+
+# Union type for all manifest types, including catch-all dict[str, Any] for backward compatibility
+PayloadManifest = Union[BinaryManifest, ParquetManifest, dict[str, Any]]
+
+
+class ProtocolInfo(BaseModel):
+    """
+    The protocol used to serialize the result and the manifest of the result.
+    """
+
+    name: str
+    version: Optional[str] = None
+    metadata: Optional[dict[str, str]] = None
+    manifest: Optional[PayloadManifest] = None
+
+    def __str__(self) -> str:
+        result = self.name
+        if self.version:
+            result += f"-{self.version}"
+        return result
+
+    def with_manifest(self, manifest: PayloadManifest) -> "ProtocolInfo":
+        """
+        Return a new ProtocolInfo object with the manifest.
+        """
+        return ProtocolInfo(
+            name=self.name,
+            version=self.version,
+            metadata=self.metadata,
+            manifest=manifest,
+        )
+
+
+class ResultMetadata(BaseModel):
+    """
+    The metadata of a result.
+    """
+
+    type: str
+    repr: str
+
+
+class ExceptionMetadata(ResultMetadata):
+    message: str
+    traceback: str
+
+
+class ResultDTO(BaseModel):
+    """
+    A JSON representation of an execution result.
+
+    Args:
+        success: Whether the execution was successful.
+        value: The value of the execution or the exception if the execution failed.
+        protocol: The protocol used to serialize the result.
+        metadata: The metadata of the result.
+    """
+
+    success: bool
+    value: Optional[Any] = None
+    protocol: Optional[ProtocolInfo] = None
+    metadata: Optional[Union[ResultMetadata, ExceptionMetadata]] = None
+    serialize_error: Optional[str] = None
+
+    @model_validator(mode="before")
+    @classmethod
+    def validate_fields(cls, data: Any) -> Any:
+        """Ensure at least one of value, protocol, or metadata keys is specified."""
+        if isinstance(data, dict):
+            required_fields = {"value", "protocol", "metadata"}
+            if not any(field in data for field in required_fields):
+                raise ValueError("At least one of 'value', 'protocol', or 'metadata' must be specified")
+        return data