sagemaker-core 1.0.62__py3-none-any.whl → 2.1.1__py3-none-any.whl

sagemaker/core/model_monitor/cron_expression_generator.py

@@ -0,0 +1,82 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You
+# may not use this file except in compliance with the License. A copy of
+# the License is located at
+#
+#     http://aws.amazon.com/apache2.0/
+#
+# or in the "license" file accompanying this file. This file is
+# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
+# ANY KIND, either express or implied. See the License for the specific
+# language governing permissions and limitations under the License.
+"""This module contains code related to the CronExpressionGenerator class.
+
+Codes are used for generating cron expressions compatible with Amazon SageMaker Model
+Monitoring Schedules.
+"""
+from __future__ import print_function, absolute_import
+
+
+class CronExpressionGenerator(object):
+    """Generates cron expression strings for the SageMaker Model Monitoring Schedule API."""
+
+    @staticmethod
+    def hourly():
+        """Generates hourly cron expression that denotes that a job runs at the top of every hour.
+
+        Returns:
+            str: The cron expression format accepted by the Amazon SageMaker Model Monitoring
+                Schedule API.
+
+        """
+        return "cron(0 * ? * * *)"
+
+    @staticmethod
+    def daily(hour=0):
+        """Generates daily cron expression that denotes that a job runs at the top of every hour.
+
+        Args:
+            hour (int): The hour in HH24 format (UTC) to run the job at, on a daily schedule.
+                Examples:
+                    - 00
+                    - 12
+                    - 17
+                    - 23
+
+        Returns:
+            str: The cron expression format accepted by the Amazon SageMaker Model Monitoring
+                Schedule API.
+
+        """
+        return "cron(0 {} ? * * *)".format(hour)
+
+    @staticmethod
+    def daily_every_x_hours(hour_interval, starting_hour=0):
+        """Generates "daily every x hours" cron expression.
+
+        That denotes that a job runs every day at the specified hour, and then every x hours,
+        as specified in hour_interval.
+
+         Example:
+             >>> daily_every_x_hours(hour_interval=2, starting_hour=0)
+             This will run every 2 hours starting at midnight.
+
+             >>> daily_every_x_hours(hour_interval=10, starting_hour=0)
+             This will run at midnight, 10am, and 8pm every day.
+
+        Args:
+            hour_interval (int): The hour interval to run the job at.
+            starting_hour (int): The hour at which to begin in HH24 format (UTC).
+
+        Returns:
+            str: The cron expression format accepted by the Amazon SageMaker Model Monitoring
+                Schedule API.
+
+        """
+        return "cron(0 {}/{} ? * * *)".format(starting_hour, hour_interval)
+
+    @staticmethod
+    def now():
+        """Returns the string used to depict the one-time schedule"""
+        return "NOW"

sagemaker/core/model_monitor/data_capture_config.py

@@ -0,0 +1,115 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You
+# may not use this file except in compliance with the License. A copy of
+# the License is located at
+#
+#     http://aws.amazon.com/apache2.0/
+#
+# or in the "license" file accompanying this file. This file is
+# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
+# ANY KIND, either express or implied. See the License for the specific
+# language governing permissions and limitations under the License.
+"""This module contains code related to the DataCaptureConfig class.
+
+Codes are used for configuring capture, collection, and storage, for prediction requests and
+responses for models hosted on SageMaker Endpoints.
+"""
+from __future__ import print_function, absolute_import
+
+from sagemaker.core import s3
+from sagemaker.core.config.config_schema import ENDPOINT_CONFIG_DATA_CAPTURE_KMS_KEY_ID_PATH
+from sagemaker.core.helper.session_helper import Session
+from sagemaker.core.common_utils import resolve_value_from_config
+
+_MODEL_MONITOR_S3_PATH = "model-monitor"
+_DATA_CAPTURE_S3_PATH = "data-capture"
+
+
+class DataCaptureConfig(object):
+    """Configuration object passed in when deploying models to Amazon SageMaker Endpoints.
+
+    This object specifies configuration related to endpoint data capture for use with
+    Amazon SageMaker Model Monitoring.
+    """
+
+    API_MAPPING = {"REQUEST": "Input", "RESPONSE": "Output"}
+
+    def __init__(
+        self,
+        enable_capture,
+        sampling_percentage=20,
+        destination_s3_uri=None,
+        kms_key_id=None,
+        capture_options=None,
+        csv_content_types=None,
+        json_content_types=None,
+        sagemaker_session=None,
+    ):
+        """Initialize a DataCaptureConfig object for capturing data from Amazon SageMaker Endpoints.
+
+        Args:
+            enable_capture (bool): Required. Whether data capture should be enabled or not.
+            sampling_percentage (int): Optional. Default=20. The percentage of data to sample.
+                Must be between 0 and 100.
+            destination_s3_uri (str): Optional. Defaults to "s3://<default-session-bucket>/
+                model-monitor/data-capture".
+            kms_key_id (str): Optional. Default=None. The kms key to use when writing to S3.
+            capture_options ([str]): Optional. Must be a list containing any combination of the
+                following values: "REQUEST", "RESPONSE". Default=["REQUEST", "RESPONSE"]. Denotes
+                which data to capture between request and response.
+            csv_content_types ([str]): Optional. Default=["text/csv"].
+            json_content_types([str]): Optional. Default=["application/json"].
+            sagemaker_session (sagemaker.core.helper.session.Session): A SageMaker Session
+                object, used for SageMaker interactions (default: None). If not
+                specified, one is created using the default AWS configuration
+                chain.
+        """
+        self.enable_capture = enable_capture
+        self.sampling_percentage = sampling_percentage
+        self.destination_s3_uri = destination_s3_uri
+        sagemaker_session = sagemaker_session or Session()
+        if self.destination_s3_uri is None:
+            self.destination_s3_uri = s3.s3_path_join(
+                "s3://",
+                sagemaker_session.default_bucket(),
+                sagemaker_session.default_bucket_prefix,
+                _MODEL_MONITOR_S3_PATH,
+                _DATA_CAPTURE_S3_PATH,
+            )
+
+        self.kms_key_id = resolve_value_from_config(
+            kms_key_id,
+            ENDPOINT_CONFIG_DATA_CAPTURE_KMS_KEY_ID_PATH,
+            sagemaker_session=sagemaker_session,
+        )
+        self.capture_options = capture_options or ["REQUEST", "RESPONSE"]
+        self.csv_content_types = csv_content_types or ["text/csv"]
+        self.json_content_types = json_content_types or ["application/json"]
+
+    def _to_request_dict(self):
+        """Generates a request dictionary using the parameters provided to the class."""
+        request_dict = {
+            "EnableCapture": self.enable_capture,
+            "InitialSamplingPercentage": self.sampling_percentage,
+            "DestinationS3Uri": self.destination_s3_uri,
+            "CaptureOptions": [
+                #  Convert to API values or pass value directly through if unable to convert.
+                {"CaptureMode": self.API_MAPPING.get(capture_option.upper(), capture_option)}
+                for capture_option in self.capture_options
+            ],
+        }
+
+        if self.kms_key_id is not None:
+            request_dict["KmsKeyId"] = self.kms_key_id
+
+        if self.csv_content_types is not None or self.json_content_types is not None:
+            request_dict["CaptureContentTypeHeader"] = {}
+
+        if self.csv_content_types is not None:
+            request_dict["CaptureContentTypeHeader"]["CsvContentTypes"] = self.csv_content_types
+
+        if self.json_content_types is not None:
+            request_dict["CaptureContentTypeHeader"]["JsonContentTypes"] = self.json_content_types
+
+        return request_dict

sagemaker/core/model_monitor/data_quality_monitoring_config.py

@@ -0,0 +1,66 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You
+# may not use this file except in compliance with the License. A copy of
+# the License is located at
+#
+#     http://aws.amazon.com/apache2.0/
+#
+# or in the "license" file accompanying this file. This file is
+# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
+# ANY KIND, either express or implied. See the License for the specific
+# language governing permissions and limitations under the License.
+"""This module contains code related to the MonitoringConfig of constraints file.
+
+Code is used to represent the Monitoring Config object and its parameters suggested
+in constraints file by Model Monitor Container in data quality analysis.
+"""
+from __future__ import print_function, absolute_import
+
+CHI_SQUARED_METHOD = "ChiSquared"
+L_INFINITY_METHOD = "LInfinity"
+
+
+class DataQualityDistributionConstraints:
+    """Represents the distribution_constraints object of monitoring_config in constraints file."""
+
+    def __init__(self, categorical_drift_method: str = None):
+        self.categorical_drift_method = categorical_drift_method
+
+    @staticmethod
+    def valid_distribution_constraints(distribution_constraints):
+        """Checks whether distribution_constraints are valid or not."""
+
+        if not distribution_constraints:
+            return True
+
+        return DataQualityDistributionConstraints.valid_categorical_drift_method(
+            distribution_constraints.categorical_drift_method
+        )
+
+    @staticmethod
+    def valid_categorical_drift_method(categorical_drift_method):
+        """Checks whether categorical_drift_method is valid or not."""
+
+        if not categorical_drift_method:
+            return True
+
+        return categorical_drift_method in [CHI_SQUARED_METHOD, L_INFINITY_METHOD]
+
+
+class DataQualityMonitoringConfig:
+    """Represents monitoring_config object in constraints file."""
+
+    def __init__(self, distribution_constraints: DataQualityDistributionConstraints = None):
+        self.distribution_constraints = distribution_constraints
+
+    @staticmethod
+    def valid_monitoring_config(monitoring_config):
+        """Checks whether monitoring_config is valid or not."""
+
+        if not monitoring_config:
+            return True
+
+        return DataQualityDistributionConstraints.valid_distribution_constraints(
+            monitoring_config.distribution_constraints
+        )

sagemaker/core/model_monitor/dataset_format.py

@@ -0,0 +1,102 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You
+# may not use this file except in compliance with the License. A copy of
+# the License is located at
+#
+#     http://aws.amazon.com/apache2.0/
+#
+# or in the "license" file accompanying this file. This file is
+# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
+# ANY KIND, either express or implied. See the License for the specific
+# language governing permissions and limitations under the License.
+"""This module contains code related to the DatasetFormat class.
+
+Codes are used for managing the constraints JSON file generated and consumed by Amazon SageMaker
+Model Monitoring Schedules.
+"""
+from __future__ import print_function, absolute_import
+
+
+class DatasetFormat(object):
+    """Represents a Dataset Format that is used when calling a DefaultModelMonitor."""
+
+    @staticmethod
+    def csv(header=True, output_columns_position="START"):
+        """Returns a DatasetFormat JSON string for use with a DefaultModelMonitor.
+
+        Args:
+            header (bool): Whether the csv dataset to baseline and monitor has a header.
+                Default: True.
+            output_columns_position (str): The position of the output columns.
+                Must be one of ("START", "END"). Default: "START".
+
+        Returns:
+            dict: JSON string containing DatasetFormat to be used by DefaultModelMonitor.
+
+        """
+        return {"csv": {"header": header, "output_columns_position": output_columns_position}}
+
+    @staticmethod
+    def json(lines=True):
+        """Returns a DatasetFormat JSON string for use with a DefaultModelMonitor.
+
+        Args:
+            lines (bool): Whether the file should be read as a json object per line. Default: True.
+
+        Returns:
+            dict: JSON string containing DatasetFormat to be used by DefaultModelMonitor.
+
+        """
+        return {"json": {"lines": lines}}
+
+    @staticmethod
+    def sagemaker_capture_json():
+        """Returns a DatasetFormat SageMaker Capture Json string for use with a DefaultModelMonitor.
+
+        Returns:
+            dict: JSON string containing DatasetFormat to be used by DefaultModelMonitor.
+
+        """
+        return {"sagemakerCaptureJson": {}}
+
+
+class MonitoringDatasetFormat(object):
+    """Represents a Dataset Format that is used when calling a DefaultModelMonitor."""
+
+    @staticmethod
+    def csv(header=True):
+        """Returns a DatasetFormat JSON string for use with a DefaultModelMonitor.
+
+        Args:
+            header (bool): Whether the csv dataset to baseline and monitor has a header.
+                Default: True.
+
+        Returns:
+            dict: JSON string containing DatasetFormat to be used by DefaultModelMonitor.
+
+        """
+        return {"Csv": {"Header": header}}
+
+    @staticmethod
+    def json(lines=True):
+        """Returns a DatasetFormat JSON string for use with a DefaultModelMonitor.
+
+        Args:
+            lines (bool): Whether the file should be read as a json object per line. Default: True.
+
+        Returns:
+            dict: JSON string containing DatasetFormat to be used by DefaultModelMonitor.
+
+        """
+        return {"Json": {"Line": lines}}
+
+    @staticmethod
+    def parquet():
+        """Returns a DatasetFormat SageMaker Capture Json string for use with a DefaultModelMonitor.
+
+        Returns:
+            dict: JSON string containing DatasetFormat to be used by DefaultModelMonitor.
+
+        """
+        return {"Parquet": {}}