snowflake-ml-python 1.10.0__tar.gz → 1.12.0__tar.gz

{snowflake_ml_python-1.10.0 → snowflake_ml_python-1.12.0}/CHANGELOG.md

@@ -1,13 +1,94 @@
 # Release History
 
-## 1.10.0
+## 1.12.0
+
+### Bug Fixes
+
+* Registry: Fixed an issue where the string representation of dictionary-type output columns was being incorrectly
+  created during structured output deserialization. Now, the original data type is properly preserved.
+
+### Behavior Changes
+
+### New Features
+
+* Registry: Add OpenAI chat completion compatible signature option for `text-generation` models.
+
+```python
+from snowflake.ml.model import openai_signatures
+import pandas as pd
+
+mv = snowflake_registry.log_model(
+    model=generator,
+    model_name=...,
+    ...,
+    signatures=openai_signatures.OPENAI_CHAT_SIGNATURE,
+)
+
+# create a pd.DataFrame with openai.client.chat.completions arguments like below:
+x_df = pd.DataFrame.from_records(
+    [
+        {
+            "messages": [
+                {"role": "system", "content": "Complete the sentence."},
+                {
+                    "role": "user",
+                    "content": "A descendant of the Lost City of Atlantis, who swam to Earth while saying, ",
+                },
+            ],
+            "max_completion_tokens": 250,
+            "temperature": 0.9,
+            "stop": None,
+            "n": 3,
+            "stream": False,
+            "top_p": 1.0,
+            "frequency_penalty": 0.1,
+            "presence_penalty": 0.2,
+        }
+    ],
+)
+
+# OpenAI Chat Completion compatible output
+output_df = mv.run(X=x_df)
+```
+
+* Model Monitoring: Added support for segment columns to enable filtered analysis.
+  * Added `segment_columns` parameter to `ModelMonitorSourceConfig` to specify columns for segmenting monitoring data
+  * Segment columns must be of STRING type and exist in the source table
+  * Added methods to dynamically manage segments:
+    * `add_segment_column()`: Add a new segment column to an existing monitor
+    * `drop_segment_column()`: Remove a segment column from an existing monitor
+* Experiment Tracking (PrPr): Support for logging artifacts (files and directories) with `log_artifact`
+* Experiment Tracking (PrPr): Support for listing artifacts in a run with `list_artifacts`
+* Experiment Tracking (PrPr): Support for downloading artifacts in a run with `download_artifacts`
+
+## 1.11.0 (08-12-2025)
 
 ### Bug Fixes
 
+* ML Job: Fix `Error: Unable to retrieve head IP address` if not all instances start within the timeout.
+* ML Job: Fix `TypeError: SnowflakeCursor.execute() got an unexpected keyword argument '_force_qmark_paramstyle'`
+  when running inside Stored Procedures.
+
 ### Behavior Changes
 
 ### New Features
 
+* `ModelVersion.create_service()`: Made `image_repo` argument optional. By
+  default it will use a default image repo, which is
+  being rolled out in server version 9.22+.
+* Experiment Tracking (PrPr): Automatically log the model, metrics, and parameters while training Keras models with
+  `snowflake.ml.experiment.callback.keras.SnowflakeKerasCallback`.
+
+## 1.10.0
+
+### Behavior Changes
+
+* Experiment Tracking (PrPr): The import paths for the auto-logging callbacks have changed to
+  `snowflake.ml.experiment.callback.xgboost.SnowflakeXgboostCallback` and
+  `snowflake.ml.experiment.callback.lightgbm.SnowflakeLightgbmCallback`.
+
+### New Features
+
 * Registry: add progress bars for `ModelVersion.create_service` and `ModelVersion.log_model`.
 * ModelRegistry: Logs emitted during `ModelVersion.create_service` will be written to a file. The file location
   will be shown in the console.
@@ -26,13 +107,13 @@
 
 ```python
 from snowflake.ml.experiment import ExperimentTracking
+from snowflake.ml.experiment.callback import SnowflakeXgboostCallback, SnowflakeLightgbmCallback
 
 exp = ExperimentTracking(session=sp_session, database_name="ML", schema_name="PUBLIC")
 
 exp.set_experiment("MY_EXPERIMENT")
 
 # XGBoost
-from snowflake.ml.experiment.callback.xgboost import SnowflakeXgboostCallback
 callback = SnowflakeXgboostCallback(
   exp, log_model=True, log_metrics=True, log_params=True, model_name="model_name", model_signature=sig
 )
@@ -41,7 +122,6 @@ with exp.start_run():
   model.fit(X, y, eval_set=[(X_test, y_test)])
 
 # LightGBM
-from snowflake.ml.experiment.callback.lightgbm import SnowflakeLightgbmCallback
 callback = SnowflakeLightgbmCallback(
   exp, log_model=True, log_metrics=True, log_params=True, model_name="model_name", model_signature=sig
 )

{snowflake_ml_python-1.10.0/snowflake_ml_python.egg-info → snowflake_ml_python-1.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: snowflake-ml-python
-Version: 1.10.0
+Version: 1.12.0
 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: 
@@ -244,17 +244,17 @@ Requires-Dist: numpy<3,>=1.23
 Requires-Dist: packaging<25,>=20.9
 Requires-Dist: pandas<3,>=2.1.4
 Requires-Dist: platformdirs<5
-Requires-Dist: pyarrow
+Requires-Dist: pyarrow<19.0.0
 Requires-Dist: pydantic<3,>=2.8.2
 Requires-Dist: pyjwt<3,>=2.0.0
 Requires-Dist: pytimeparse<2,>=1.1.8
 Requires-Dist: pyyaml<7,>=6.0
 Requires-Dist: retrying<2,>=1.3.3
 Requires-Dist: s3fs<2026,>=2024.6.1
-Requires-Dist: scikit-learn<1.6
+Requires-Dist: scikit-learn<1.7
 Requires-Dist: scipy<2,>=1.9
 Requires-Dist: shap<1,>=0.46.0
-Requires-Dist: snowflake-connector-python[pandas]<4,>=3.15.0
+Requires-Dist: snowflake-connector-python[pandas]<4,>=3.16.0
 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
@@ -410,14 +410,95 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 # Release History
 
-## 1.10.0
+## 1.12.0
+
+### Bug Fixes
+
+* Registry: Fixed an issue where the string representation of dictionary-type output columns was being incorrectly
+  created during structured output deserialization. Now, the original data type is properly preserved.
+
+### Behavior Changes
+
+### New Features
+
+* Registry: Add OpenAI chat completion compatible signature option for `text-generation` models.
+
+```python
+from snowflake.ml.model import openai_signatures
+import pandas as pd
+
+mv = snowflake_registry.log_model(
+    model=generator,
+    model_name=...,
+    ...,
+    signatures=openai_signatures.OPENAI_CHAT_SIGNATURE,
+)
+
+# create a pd.DataFrame with openai.client.chat.completions arguments like below:
+x_df = pd.DataFrame.from_records(
+    [
+        {
+            "messages": [
+                {"role": "system", "content": "Complete the sentence."},
+                {
+                    "role": "user",
+                    "content": "A descendant of the Lost City of Atlantis, who swam to Earth while saying, ",
+                },
+            ],
+            "max_completion_tokens": 250,
+            "temperature": 0.9,
+            "stop": None,
+            "n": 3,
+            "stream": False,
+            "top_p": 1.0,
+            "frequency_penalty": 0.1,
+            "presence_penalty": 0.2,
+        }
+    ],
+)
+
+# OpenAI Chat Completion compatible output
+output_df = mv.run(X=x_df)
+```
+
+* Model Monitoring: Added support for segment columns to enable filtered analysis.
+  * Added `segment_columns` parameter to `ModelMonitorSourceConfig` to specify columns for segmenting monitoring data
+  * Segment columns must be of STRING type and exist in the source table
+  * Added methods to dynamically manage segments:
+    * `add_segment_column()`: Add a new segment column to an existing monitor
+    * `drop_segment_column()`: Remove a segment column from an existing monitor
+* Experiment Tracking (PrPr): Support for logging artifacts (files and directories) with `log_artifact`
+* Experiment Tracking (PrPr): Support for listing artifacts in a run with `list_artifacts`
+* Experiment Tracking (PrPr): Support for downloading artifacts in a run with `download_artifacts`
+
+## 1.11.0 (08-12-2025)
 
 ### Bug Fixes
 
+* ML Job: Fix `Error: Unable to retrieve head IP address` if not all instances start within the timeout.
+* ML Job: Fix `TypeError: SnowflakeCursor.execute() got an unexpected keyword argument '_force_qmark_paramstyle'`
+  when running inside Stored Procedures.
+
 ### Behavior Changes
 
 ### New Features
 
+* `ModelVersion.create_service()`: Made `image_repo` argument optional. By
+  default it will use a default image repo, which is
+  being rolled out in server version 9.22+.
+* Experiment Tracking (PrPr): Automatically log the model, metrics, and parameters while training Keras models with
+  `snowflake.ml.experiment.callback.keras.SnowflakeKerasCallback`.
+
+## 1.10.0
+
+### Behavior Changes
+
+* Experiment Tracking (PrPr): The import paths for the auto-logging callbacks have changed to
+  `snowflake.ml.experiment.callback.xgboost.SnowflakeXgboostCallback` and
+  `snowflake.ml.experiment.callback.lightgbm.SnowflakeLightgbmCallback`.
+
+### New Features
+
 * Registry: add progress bars for `ModelVersion.create_service` and `ModelVersion.log_model`.
 * ModelRegistry: Logs emitted during `ModelVersion.create_service` will be written to a file. The file location
   will be shown in the console.
@@ -436,13 +517,13 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 ```python
 from snowflake.ml.experiment import ExperimentTracking
+from snowflake.ml.experiment.callback import SnowflakeXgboostCallback, SnowflakeLightgbmCallback
 
 exp = ExperimentTracking(session=sp_session, database_name="ML", schema_name="PUBLIC")
 
 exp.set_experiment("MY_EXPERIMENT")
 
 # XGBoost
-from snowflake.ml.experiment.callback.xgboost import SnowflakeXgboostCallback
 callback = SnowflakeXgboostCallback(
   exp, log_model=True, log_metrics=True, log_params=True, model_name="model_name", model_signature=sig
 )
@@ -451,7 +532,6 @@ with exp.start_run():
   model.fit(X, y, eval_set=[(X_test, y_test)])
 
 # LightGBM
-from snowflake.ml.experiment.callback.lightgbm import SnowflakeLightgbmCallback
 callback = SnowflakeLightgbmCallback(
   exp, log_model=True, log_metrics=True, log_params=True, model_name="model_name", model_signature=sig
 )

{snowflake_ml_python-1.10.0 → snowflake_ml_python-1.12.0}/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 = [ "absl-py>=0.15,<2", "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", "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<1.6", "scipy>=1.9,<2", "shap>=0.46.0,<1", "snowflake-connector-python[pandas]>=3.15.0,<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 = [ "absl-py>=0.15,<2", "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<1.7", "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",]
 [[project.authors]]
 name = "Snowflake, Inc"
 email = "support@snowflake.com"

{snowflake_ml_python-1.10.0 → snowflake_ml_python-1.12.0}/snowflake/cortex/_complete.py

@@ -88,7 +88,7 @@ class MidStreamException(Exception):
             message = reason
         if http_resp:
             message = f"Error in stream (HTTP Response: {http_resp.status}) - {http_resp.reason}"
-        if request_id != "":
+        if request_id is not None and request_id != "":
             # add request_id to error message
             message += f" (Request ID: {request_id})"
         super().__init__(message)
@@ -327,7 +327,8 @@ def _return_stream_response(
             # This is the case of midstream errors which were introduced specifically for structured output.
             # TODO: discuss during code review
             if parsed_resp.get("error"):
-                raise MidStreamException(reason=response.text, request_id=request_id)
+                error_info = parsed_resp["error"]
+                raise MidStreamException(reason=str(error_info), request_id=request_id)
             else:
                 pass
 

{snowflake_ml_python-1.10.0 → snowflake_ml_python-1.12.0}/snowflake/ml/_internal/utils/service_logger.py

@@ -9,8 +9,33 @@ from typing import Optional
 
 import platformdirs
 
+
+class ProgressBarAwareConsoleHandler(logging.StreamHandler):  # type: ignore[type-arg]
+    """A logging handler that adapts to different progress bar systems to avoid interfering with display."""
+
+    def emit(self, record: logging.LogRecord) -> None:
+        try:
+            msg = self.format(record)
+
+            # Check if tqdm progress bars are active - use tqdm.write() to avoid interference
+            try:
+                import tqdm
+
+                if hasattr(tqdm.tqdm, "_instances") and tqdm.tqdm._instances:
+                    tqdm.tqdm.write(msg, file=self.stream)
+                    return
+            except (ImportError, AttributeError):
+                pass
+
+            # Fallback to regular stream writing (works for all contexts including Streamlit)
+            self.stream.write(msg + "\n")
+            self.flush()
+        except Exception:
+            self.handleError(record)
+
+
 # Module-level logger for operational messages that should appear on console
-stdout_handler = logging.StreamHandler(sys.stdout)
+stdout_handler = ProgressBarAwareConsoleHandler(sys.stdout)
 stdout_handler.setFormatter(logging.Formatter("%(message)s"))
 
 console_logger = logging.getLogger(__name__)

snowflake_ml_python-1.12.0/snowflake/ml/experiment/_client/artifact.py

@@ -0,0 +1,76 @@
+import os
+import posixpath
+from typing import NamedTuple
+
+
+class ArtifactInfo(NamedTuple):
+    name: str
+    size: int
+    md5: str
+    last_modified: str
+
+
+def get_put_path_pairs(local_path: str, artifact_path: str) -> list[tuple[str, str]]:
+    """Enumerate files to upload and their destination subdirectories.
+
+    Expands a local path (file or directory) into a list of pairs used for uploading
+    artifacts to the stage.
+
+    Args:
+        local_path: Absolute or relative path to a local file or directory to upload.
+        artifact_path: Destination subdirectory under the run's artifact root in the
+            stage. If empty, files are uploaded to the root. When uploading a
+            directory, this value is prepended to each file's relative path.
+
+    Returns:
+        A list of tuples ``(local_file_path, destination_artifact_subdir)``. For a
+        single file, the list contains one entry with ``destination_artifact_subdir``
+        set to ``artifact_path``. For directories, one entry per file is produced and
+        subdirectories are preserved using POSIX separators.
+
+    Raises:
+        FileNotFoundError: If ``local_path`` does not exist.
+    """
+    if not os.path.exists(local_path):
+        raise FileNotFoundError(f"Local path does not exist: {local_path}")
+
+    if os.path.isfile(local_path):
+        return [(local_path, artifact_path)]
+
+    pairs: list[tuple[str, str]] = []
+    base_dir = local_path
+    for root, _, files in os.walk(base_dir):
+        if not files:
+            continue
+        rel_dir = os.path.relpath(root, base_dir)
+        rel_dir_posix = "" if rel_dir in (".", "") else rel_dir.replace(os.sep, "/")
+        dest_artifact_path = posixpath.join(artifact_path, rel_dir_posix) if rel_dir_posix else artifact_path
+        for filename in files:
+            file_path = os.path.join(root, filename)
+            pairs.append((file_path, dest_artifact_path))
+    return pairs
+
+
+def get_download_path_pairs(artifacts: list[ArtifactInfo], base_target_dir: str) -> list[tuple[str, str]]:
+    """Given artifact metadata entries, computes where each artifact should be written
+    locally.
+
+    Args:
+        artifacts: List of artifact metadata where ``name`` is a POSIX-style path
+            relative to the run's artifact root (e.g., ``"file.txt"`` or
+            ``"nested/dir/file.txt"``).
+        base_target_dir: Local base directory to download into. If empty, the
+            current working directory is used. Directories will be created as
+            needed.
+
+    Returns:
+        A list of tuples ``(artifact_relative_path, local_directory)``. Each tuple
+        provides the relative path to request from the stage and the local directory
+        where the file should be written.
+    """
+    planned: list[tuple[str, str]] = []
+    for info in artifacts:
+        rel_dir = os.path.dirname(info.name)
+        local_dir = base_target_dir if rel_dir in ("", ".") else os.path.join(base_target_dir, rel_dir)
+        planned.append((info.name, local_dir))
+    return planned

{snowflake_ml_python-1.10.0 → snowflake_ml_python-1.12.0}/snowflake/ml/experiment/_client/experiment_tracking_sql_client.py

@@ -1,9 +1,10 @@
 from typing import Optional
 
 from snowflake.ml._internal.utils import query_result_checker, sql_identifier
+from snowflake.ml.experiment._client import artifact
 from snowflake.ml.model._client.sql import _base
 from snowflake.ml.utils import sql_client
-from snowflake.snowpark import row, session
+from snowflake.snowpark import file_operation, row, session
 
 
 class ExperimentTrackingSQLClient(_base._BaseSQLClient):
@@ -88,6 +89,59 @@ class ExperimentTrackingSQLClient(_base._BaseSQLClient):
             f"ALTER EXPERIMENT {experiment_fqn} MODIFY RUN {run_name} SET METADATA=$${run_metadata}$$",
         ).has_dimensions(expected_rows=1, expected_cols=1).validate()
 
+    def put_artifact(
+        self,
+        *,
+        experiment_name: sql_identifier.SqlIdentifier,
+        run_name: sql_identifier.SqlIdentifier,
+        artifact_path: str,
+        file_path: str,
+        auto_compress: bool = False,
+    ) -> file_operation.PutResult:
+        return self._session.file.put(
+            local_file_name=file_path,
+            stage_location=self._build_snow_uri(experiment_name, run_name, artifact_path),
+            overwrite=True,
+            auto_compress=auto_compress,
+        )[0]
+
+    def list_artifacts(
+        self,
+        *,
+        experiment_name: sql_identifier.SqlIdentifier,
+        run_name: sql_identifier.SqlIdentifier,
+        artifact_path: str,
+    ) -> list[artifact.ArtifactInfo]:
+        results = (
+            query_result_checker.SqlResultValidator(
+                self._session, f"LIST {self._build_snow_uri(experiment_name, run_name, artifact_path)}"
+            )
+            .has_dimensions(expected_cols=4)
+            .validate()
+        )
+        return [
+            artifact.ArtifactInfo(
+                name=str(result.name).removeprefix(f"/versions/{run_name}/"),
+                size=result.size,
+                md5=result.md5,
+                last_modified=result.last_modified,
+            )
+            for result in results
+        ]
+
+    def get_artifact(
+        self,
+        *,
+        experiment_name: sql_identifier.SqlIdentifier,
+        run_name: sql_identifier.SqlIdentifier,
+        artifact_path: str,
+        target_path: str,
+    ) -> file_operation.GetResult:
+        return self._session.file.get(
+            stage_location=self._build_snow_uri(experiment_name, run_name, artifact_path),
+            target_directory=target_path,
+        )[0]
+
     def show_runs_in_experiment(
         self, *, experiment_name: sql_identifier.SqlIdentifier, like: Optional[str] = None
     ) -> list[row.Row]:
@@ -96,3 +150,12 @@ class ExperimentTrackingSQLClient(_base._BaseSQLClient):
         return query_result_checker.SqlResultValidator(
             self._session, f"SHOW RUNS {like_clause} IN EXPERIMENT {experiment_fqn}"
         ).validate()
+
+    def _build_snow_uri(
+        self, experiment_name: sql_identifier.SqlIdentifier, run_name: sql_identifier.SqlIdentifier, artifact_path: str
+    ) -> str:
+        experiment_fqn = self.fully_qualified_object_name(self._database_name, self._schema_name, experiment_name)
+        uri = f"snow://experiment/{experiment_fqn}/versions/{run_name}"
+        if artifact_path:
+            uri += f"/{artifact_path}"
+        return uri

snowflake_ml_python-1.12.0/snowflake/ml/experiment/callback/keras.py

@@ -0,0 +1,63 @@
+import json
+from typing import TYPE_CHECKING, Any, Optional
+from warnings import warn
+
+import keras
+
+from snowflake.ml.experiment import utils
+
+if TYPE_CHECKING:
+    from snowflake.ml.experiment.experiment_tracking import ExperimentTracking
+    from snowflake.ml.model.model_signature import ModelSignature
+
+
+class SnowflakeKerasCallback(keras.callbacks.Callback):
+    def __init__(
+        self,
+        experiment_tracking: "ExperimentTracking",
+        log_model: bool = True,
+        log_metrics: bool = True,
+        log_params: bool = True,
+        log_every_n_epochs: int = 1,
+        model_name: Optional[str] = None,
+        model_signature: Optional["ModelSignature"] = None,
+    ) -> None:
+        self._experiment_tracking = experiment_tracking
+        self.log_model = log_model
+        self.log_metrics = log_metrics
+        self.log_params = log_params
+        if log_every_n_epochs < 1:
+            raise ValueError("`log_every_n_epochs` must be positive.")
+        self.log_every_n_epochs = log_every_n_epochs
+        self.model_name = model_name
+        self.model_signature = model_signature
+
+    def on_train_begin(self, logs: Optional[dict[str, Any]] = None) -> None:
+        if self.log_params:
+            params = json.loads(self.model.to_json())
+            self._experiment_tracking.log_params(utils.flatten_nested_params(params))
+
+    def on_epoch_end(self, epoch: int, logs: Optional[dict[str, Any]] = None) -> None:
+        if self.log_metrics and logs and epoch % self.log_every_n_epochs == 0:
+            for key, value in logs.items():
+                try:
+                    value = float(value)
+                except Exception:
+                    pass
+                else:
+                    self._experiment_tracking.log_metric(key=key, value=value, step=epoch)
+
+    def on_train_end(self, logs: Optional[dict[str, Any]] = None) -> None:
+        if self.log_model:
+            if not self.model_signature:
+                warn(
+                    "Model will not be logged because model signature is missing. "
+                    "To autolog the model, please specify `model_signature` when constructing SnowflakeKerasCallback."
+                )
+                return
+            model_name = self.model_name or self._experiment_tracking._get_or_set_experiment().name + "_model"
+            self._experiment_tracking.log_model(  # type: ignore[call-arg]
+                model=self.model,
+                model_name=model_name,
+                signatures={"predict": self.model_signature},
+            )

{snowflake_ml_python-1.10.0 → snowflake_ml_python-1.12.0}/snowflake/ml/experiment/callback/lightgbm.py

@@ -15,6 +15,7 @@ class SnowflakeLightgbmCallback(lgb.callback._RecordEvaluationCallback):
         log_model: bool = True,
         log_metrics: bool = True,
         log_params: bool = True,
+        log_every_n_epochs: int = 1,
         model_name: Optional[str] = None,
         model_signature: Optional["ModelSignature"] = None,
     ) -> None:
@@ -22,6 +23,9 @@ class SnowflakeLightgbmCallback(lgb.callback._RecordEvaluationCallback):
         self.log_model = log_model
         self.log_metrics = log_metrics
         self.log_params = log_params
+        if log_every_n_epochs < 1:
+            raise ValueError("`log_every_n_epochs` must be positive.")
+        self.log_every_n_epochs = log_every_n_epochs
         self.model_name = model_name
         self.model_signature = model_signature
 
@@ -32,7 +36,7 @@ class SnowflakeLightgbmCallback(lgb.callback._RecordEvaluationCallback):
             if env.iteration == env.begin_iteration:  # Log params only at the first iteration
                 self._experiment_tracking.log_params(env.params)
 
-        if self.log_metrics:
+        if self.log_metrics and env.iteration % self.log_every_n_epochs == 0:
             super().__call__(env)
             for dataset_name, metrics in self.eval_result.items():
                 for metric_name, log in metrics.items():

{snowflake_ml_python-1.10.0 → snowflake_ml_python-1.12.0}/snowflake/ml/experiment/callback/xgboost.py

@@ -18,6 +18,7 @@ class SnowflakeXgboostCallback(xgb.callback.TrainingCallback):
         log_model: bool = True,
         log_metrics: bool = True,
         log_params: bool = True,
+        log_every_n_epochs: int = 1,
         model_name: Optional[str] = None,
         model_signature: Optional["ModelSignature"] = None,
     ) -> None:
@@ -25,6 +26,9 @@ class SnowflakeXgboostCallback(xgb.callback.TrainingCallback):
         self.log_model = log_model
         self.log_metrics = log_metrics
         self.log_params = log_params
+        if log_every_n_epochs < 1:
+            raise ValueError("`log_every_n_epochs` must be positive.")
+        self.log_every_n_epochs = log_every_n_epochs
         self.model_name = model_name
         self.model_signature = model_signature
 
@@ -36,7 +40,7 @@ class SnowflakeXgboostCallback(xgb.callback.TrainingCallback):
         return model
 
     def after_iteration(self, model: Any, epoch: int, evals_log: dict[str, dict[str, Any]]) -> bool:
-        if self.log_metrics:
+        if self.log_metrics and epoch % self.log_every_n_epochs == 0:
             for dataset_name, metrics in evals_log.items():
                 for metric_name, log in metrics.items():
                     metric_key = dataset_name + ":" + metric_name