bring back validate_great_expectations

validate_great_expectations/README.md

@@ -0,0 +1,53 @@
+# Great Expectations Validation
+![Great Expectations Logo](doc/great-expectations-logo-full-size.png)
+
+Run data validation via Great Expectations. Will validate a given dataset with a given set of expectations, run the validation, and log the output HTML data doc in MLRun.
+
+## Prerequisites
+
+See [1_set_expectations.ipynb](1_set_expectations.ipynb) for a full example.
+
+- Initialized a Great Expectations project
+- Configured at least one Datasource i.e. `my_datasource`
+- Created at least one Expectation Suite i.e. `my_suite`
+- Created a Checkpoint i.e. `my_checkpoint`
+
+## Usage
+
+See [2_validate_expectations.ipynb](2_validate_expectations.ipynb) for a full example.
+
+```python
+import mlrun
+
+fn = mlrun.import_function("hub://great_expectations")
+run = fn.run(
+    inputs={"data": "https://s3.wasabisys.com/iguazio/data/iris/iris.data.raw.csv"},
+    params={
+        "expectation_suite_name": "test_suite",
+        "data_asset_name": "iris_dataset",
+    },
+)
+```
+
+## All Configuration
+Inputs
+```rst
+:param data:                   Data to validate. Can be local or remote link.
+```
+
+Parameters
+```rst
+:param expectation_suite_name: Name of expectation suite to validate against.
+:param data_asset_name:        Name of dataset in Great Expectations.
+:param datasource_name:        Name of datasource to use for validation.
+:param data_connector_name:    Name of data connector to use for validation.
+:param datasource_config:      Full configuration for datasource. For use with custom
+                               data sources other than the default pandas datasource.
+:param batch_identifiers:      Custom metadata for identifying particular batches of
+                               data. For use when not using the default batch identifiers.
+:param root_directory:         Path to underlying Great Expectations project. Defaults to
+                               MLRun project artifact path if not specified.
+:param checkpoint_name:        Name of checkpoint to use for validation.
+:param checkpoint_config:      Full configuration for checkpoint. For use with custome
+                               checkpoint config other than the default.
+```

validate_great_expectations/function.yaml

@@ -0,0 +1,170 @@
+kind: job
+metadata:
+  name: validate-great-expectations
+  tag: ''
+  hash: 82d0b647d443eb6e643d9dbfc8c0a650d74da018
+  project: ''
+  labels:
+    author: nicks
+    framework: great-expectations
+  categories:
+  - data-validation
+  - data-analysis
+spec:
+  command: ''
+  args: []
+  image: ''
+  build:
+    functionSourceCode: import os
import shutil

import mlrun

from great_expectations.core.batch import RuntimeBatchRequest
from great_expectations.data_context import BaseDataContext
from great_expectations.data_context.types.base import (
    DataContextConfig,
    FilesystemStoreBackendDefaults,
)
from great_expectations.checkpoint.types.checkpoint_result import CheckpointResult


def get_default_datasource_config(
    datasource_name: str, data_connector_name: str
) -> dict:
    """
    Convenience function to get the default pandas datasource config
    for use in validating expectations.

    :param datasource_name:     Name of datasource.
    :param data_connector_name: Name of data connector.

    :returns: Configuration for default datasource.
    """
    default_datasource_config = {
        "name": f"{datasource_name}",
        "class_name": "Datasource",
        "module_name": "great_expectations.datasource",
        "execution_engine": {
            "module_name": "great_expectations.execution_engine",
            "class_name": "PandasExecutionEngine",
        },
        "data_connectors": {
            f"{data_connector_name}": {
                "class_name": "RuntimeDataConnector",
                "module_name": "great_expectations.datasource.data_connector",
                "batch_identifiers": ["default_identifier_name"],
            },
        },
    }
    return default_datasource_config


def get_default_checkpoint_config(checkpoint_name: str) -> dict:
    """
    Convenience function to get the default checkpoint config for
    use in validating expectations.

    :param checkpoint_name: Name of checkpoint.

    :returns: Configuration for default checkpoint.
    """
    return {
        "name": checkpoint_name,
        "config_version": 1.0,
        "class_name": "SimpleCheckpoint",
        "run_name_template": "%Y%m%d-%H%M%S-my-run-name-template",
    }


def get_data_doc_path(checkpoint_result: CheckpointResult) -> str:
    """
    Convenience function to get the path of the output
    data doc from a checkpoint result.

    :param checkpoint_result: Great Expectations checkpoint result.

    :returns: Absolute path to new data doc.
    """
    result_id = checkpoint_result.list_validation_result_identifiers()[0]
    data_doc_path = checkpoint_result["run_results"][result_id]["actions_results"][
        "update_data_docs"
    ]["local_site"]
    data_doc_path = data_doc_path.replace("file://", "")
    return data_doc_path


def validate_expectations(
    context: mlrun.MLClientCtx,
    data: mlrun.DataItem,
    expectation_suite_name: str,
    data_asset_name: str,
    datasource_name: str = "pandas_datasource",
    data_connector_name: str = "default_runtime_data_connector_name",
    datasource_config: dict = None,
    batch_identifiers: dict = None,
    root_directory: str = None,
    checkpoint_name: str = None,
    checkpoint_config: dict = None,
) -> None:
    """
    Main function to validate an input dataset, datasource, data connector,
    and expectation suite.

    Runs the Great Expectation validation and logs
    whether the validation was a success as well as the output page
    of the data docs.

    :param context:                MLRun context.
    :param data:                   Data to validate. Can be local or remote link.
    :param expectation_suite_name: Name of expectation suite to validate against.
    :param data_asset_name:        Name of dataset in Great Expectations.
    :param datasource_name:        Name of datasource to use for validation.
    :param data_connector_name:    Name of data connector to use for validation.
    :param datasource_config:      Full configuration for datasource. For use with custom
                                   data sources other than the default pandas datasource.
    :param batch_identifiers:      Custom metadata for identifying particular batches of
                                   data. For use when not using the default batch identifiers.
    :param root_directory:         Path to underlying Great Expectations project. Defaults to
                                   MLRun project artifact path if not specified.
    :param checkpoint_name:        Name of checkpoint to use for validation.
    :param checkpoint_config:      Full configuration for checkpoint. For use with custome
                                   checkpoint config other than the default.
    """

    # Get data
    df = data.as_df()

    # Use default root directory for project if not specified
    root_directory = (
        root_directory
        if root_directory
        else f"/v3io/projects/{context.project}/great_expectations"
    )

    # Load great expectations context
    ge_context = BaseDataContext(
        project_config=DataContextConfig(
            store_backend_defaults=FilesystemStoreBackendDefaults(
                root_directory=root_directory
            )
        )
    )

    # Get expectation suite
    ge_context.get_expectation_suite(expectation_suite_name=expectation_suite_name)

    # Add default data source if not specified
    datasource_config = (
        datasource_config
        if datasource_config
        else get_default_datasource_config(datasource_name, data_connector_name)
    )
    ge_context.add_datasource(**datasource_config)

    # Get data batch
    batch_identifiers = (
        batch_identifiers
        if batch_identifiers
        else {"default_identifier_name": "default_identifier"}
    )
    batch_request = RuntimeBatchRequest(
        datasource_name=datasource_name,
        data_connector_name=data_connector_name,
        data_asset_name=data_asset_name,
        runtime_parameters={"batch_data": df},
        batch_identifiers=batch_identifiers,
    )

    # Get validator
    validator = ge_context.get_validator(
        batch_request=batch_request,
        expectation_suite_name=expectation_suite_name,
    )

    # Use default checkpoint name and config if not specified
    checkpoint_name = (
        checkpoint_name if checkpoint_name else f"{data_asset_name}_checkpoint"
    )
    checkpoint_config = (
        checkpoint_config
        if checkpoint_config
        else get_default_checkpoint_config(checkpoint_name)
    )

    # Add checkpoint
    ge_context.add_checkpoint(**checkpoint_config)

    # Run expectation suite on checkpoint
    checkpoint_result = ge_context.run_checkpoint(
        checkpoint_name=checkpoint_name,
        validations=[
            {
                "batch_request": batch_request,
                "expectation_suite_name": expectation_suite_name,
            }
        ],
    )

    # Log success
    context.log_result("validated", checkpoint_result["success"])

    # Log data doc
    data_doc_path = get_data_doc_path(checkpoint_result)
    context.log_artifact("validation_results", target_path=data_doc_path)

+    base_image: mlrun/mlrun
+    commands:
+    - python -m pip install great-expectations==0.15.41
+    code_origin: https://github.com/igz-us-sales/functions.git#c7b44af35294494a531a014f3d02a28eff3f4105:/User/functions/validate_great_expectations/validate_great_expectations.py
+    origin_filename: /User/functions/validate_great_expectations/validate_great_expectations.py
+  entry_points:
+    get_default_datasource_config:
+      name: get_default_datasource_config
+      doc: 'Convenience function to get the default pandas datasource config
+
+        for use in validating expectations.'
+      parameters:
+      - name: datasource_name
+        type: str
+        doc: Name of datasource.
+        default: ''
+      - name: data_connector_name
+        type: str
+        doc: Name of data connector.
+        default: ''
+      outputs:
+      - default: ''
+        doc: Configuration for default datasource.
+        type: dict
+      lineno: 15
+    get_default_checkpoint_config:
+      name: get_default_checkpoint_config
+      doc: 'Convenience function to get the default checkpoint config for
+
+        use in validating expectations.'
+      parameters:
+      - name: checkpoint_name
+        type: str
+        doc: Name of checkpoint.
+        default: ''
+      outputs:
+      - default: ''
+        doc: Configuration for default checkpoint.
+        type: dict
+      lineno: 46
+    get_data_doc_path:
+      name: get_data_doc_path
+      doc: 'Convenience function to get the path of the output
+
+        data doc from a checkpoint result.'
+      parameters:
+      - name: checkpoint_result
+        type: CheckpointResult
+        doc: Great Expectations checkpoint result.
+        default: ''
+      outputs:
+      - default: ''
+        doc: Absolute path to new data doc.
+        type: str
+      lineno: 63
+    validate_expectations:
+      name: validate_expectations
+      doc: 'Main function to validate an input dataset, datasource, data connector,
+
+        and expectation suite.
+
+
+        Runs the Great Expectation validation and logs
+
+        whether the validation was a success as well as the output page
+
+        of the data docs.'
+      parameters:
+      - name: context
+        type: MLClientCtx
+        doc: MLRun context.
+        default: ''
+      - name: data
+        type: DataItem
+        doc: Data to validate. Can be local or remote link.
+        default: ''
+      - name: expectation_suite_name
+        type: str
+        doc: Name of expectation suite to validate against.
+        default: ''
+      - name: data_asset_name
+        type: str
+        doc: Name of dataset in Great Expectations.
+        default: ''
+      - name: datasource_name
+        type: str
+        doc: Name of datasource to use for validation.
+        default: pandas_datasource
+      - name: data_connector_name
+        type: str
+        doc: Name of data connector to use for validation.
+        default: default_runtime_data_connector_name
+      - name: datasource_config
+        type: dict
+        doc: Full configuration for datasource. For use with custom data sources other
+          than the default pandas datasource.
+        default: null
+      - name: batch_identifiers
+        type: dict
+        doc: Custom metadata for identifying particular batches of data. For use when
+          not using the default batch identifiers.
+        default: null
+      - name: root_directory
+        type: str
+        doc: Path to underlying Great Expectations project. Defaults to MLRun project
+          artifact path if not specified.
+        default: null
+      - name: checkpoint_name
+        type: str
+        doc: Name of checkpoint to use for validation.
+        default: null
+      - name: checkpoint_config
+        type: dict
+        doc: Full configuration for checkpoint. For use with custome checkpoint config
+          other than the default.
+        default: null
+      outputs:
+      - default: ''
+      lineno: 80
+  description: Validate a dataset using Great Expectations
+  default_handler: validate_expectations
+  disable_auto_mount: false
+  env: []
+  resources:
+    requests:
+      memory: 1Mi
+      cpu: 25m
+    limits:
+      memory: 20Gi
+      cpu: '2'
+  priority_class_name: igz-workload-medium
+  preemption_mode: prevent
+  affinity:
+    nodeAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        nodeSelectorTerms:
+        - matchExpressions:
+          - key: app.iguazio.com/lifecycle
+            operator: NotIn
+            values:
+            - preemptible
+          - key: eks.amazonaws.com/capacityType
+            operator: NotIn
+            values:
+            - SPOT
+          - key: node-lifecycle
+            operator: NotIn
+            values:
+            - spot
+  tolerations: null
+  security_context: {}
+verbose: false

validate_great_expectations/item.yaml

@@ -0,0 +1,26 @@
+apiVersion: v1
+categories:
+- data-validation
+- data-analysis
+description: Validate a dataset using Great Expectations
+doc: ''
+example: validate_great_expectations.ipynb
+generationDate: 2022-04-26:12-28
+hidden: false
+icon: ''
+labels:
+  author: nicks
+  framework: great-expectations
+maintainers: []
+marketplaceType: ''
+mlrunVersion: 1.1.0
+name: validate-great-expectations
+platformVersion: 3.5.2
+spec:
+  filename: validate_great_expectations.py
+  handler: validate_expectations
+  image: mlrun/mlrun
+  kind: job
+  requirements: [great-expectations==0.15.41]
+url: ''
+version: 1.1.0

validate_great_expectations/requirements.txt

@@ -0,0 +1 @@
+great-expectations==0.15.41