Update evidently integration to support NumPy 2.0

docs/book/component-guide/data-validators/evidently.md

@@ -100,11 +100,11 @@ text_data_report = evidently_report_step.with_options(
 The configuration shown in the example is the equivalent of running the following Evidently code inside the step:
 
 ```python
-from evidently.metrics import ColumnRegExpMetric
-from evidently.metric_preset import DataQualityPreset, TextOverviewPreset
-from evidently import ColumnMapping
-from evidently.report import Report
-from evidently.metrics.base_metric import generate_column_metrics
+from evidently.legacy.metrics import ColumnRegExpMetric
+from evidently.legacy.metric_preset import DataQualityPreset, TextOverviewPreset
+from evidently.legacy.pipeline.column_mapping import ColumnMapping
+from evidently.legacy.report import Report
+from evidently.legacy.metrics.base_metric import generate_column_metrics
 import nltk
 
 nltk.download("words")
@@ -154,11 +154,11 @@ We configure the `evidently_report_step` using parameters that you would normall
 There are several ways you can reference the Evidently metrics when configuring `EvidentlyMetricConfig` items:
 
 * by class name: this is the easiest way to reference an Evidently metric. You can use the name of a metric or metric preset class as it appears in the Evidently documentation (e.g.`"DataQualityPreset"`, `"DatasetDriftMetric"`).
-* by full class path: you can also use the full Python class path of the metric or metric preset class ( e.g. `"evidently.metric_preset.DataQualityPreset"`, `"evidently.metrics.DatasetDriftMetric"`). This is useful if you want to use metrics or metric presets that are not included in Evidently library.
+* by full class path: you can also use the full Python class path of the metric or metric preset class ( e.g. `"evidently.legacy.metric_preset.DataQualityPreset"`, `"evidently.legacy.metrics.DatasetDriftMetric"`). This is useful if you want to use metrics or metric presets that are not included in Evidently library.
 *   by passing in the class itself: you can also import and pass in an Evidently metric or metric preset class itself, e.g.:
 
     ```python
-    from evidently.metrics import DatasetDriftMetric
+    from evidently.legacy.metrics import DatasetDriftMetric
 
     ...
 
@@ -221,7 +221,7 @@ text_data_report = evidently_report_step.with_options(
     parameters=dict(
         report_options = [
             (
-                "evidently.options.ColorOptions", {
+                "evidently.legacy.options.ColorOptions", {
                     "primary_color": "#5a86ad",
                     "fill_color": "#fff4f2",
                     "zero_line_color": "#016795",
@@ -289,11 +289,11 @@ text_data_test = evidently_test_step.with_options(
 The configuration shown in the example is the equivalent of running the following Evidently code inside the step:
 
 ```python
-from evidently.tests import TestColumnRegExp
-from evidently.test_preset import DataQualityTestPreset
-from evidently import ColumnMapping
-from evidently.test_suite import TestSuite
-from evidently.tests.base_test import generate_column_tests
+from evidently.legacy.tests import TestColumnRegExp
+from evidently.legacy.test_preset import DataQualityTestPreset
+from evidently.legacy.pipeline.column_mapping import ColumnMapping
+from evidently.legacy.test_suite import TestSuite
+from evidently.legacy.tests.base_test import generate_column_tests
 import nltk
 
 nltk.download("words")
@@ -342,11 +342,11 @@ We configure the `evidently_test_step` using parameters that you would normally
 There are several ways you can reference the Evidently tests when configuring `EvidentlyTestConfig` items, similar to how you reference them in an `EvidentlyMetricConfig` object:
 
 * by class name: this is the easiest way to reference an Evidently test. You can use the name of a test or test preset class as it appears in the Evidently documentation (e.g.`"DataQualityTestPreset"`, `"TestColumnRegExp"`).
-* by full class path: you can also use the full Python class path of the test or test preset class ( e.g. `"evidently.test_preset.DataQualityTestPreset"`, `"evidently.tests.TestColumnRegExp"`). This is useful if you want to use tests or test presets that are not included in Evidently library.
+* by full class path: you can also use the full Python class path of the test or test preset class ( e.g. `"evidently.legacy.test_preset.DataQualityTestPreset"`, `"evidently.legacy.tests.TestColumnRegExp"`). This is useful if you want to use tests or test presets that are not included in Evidently library.
 *   by passing in the class itself: you can also import and pass in an Evidently test or test preset class itself, e.g.:
 
     ```python
-    from evidently.tests import TestColumnRegExp
+    from evidently.legacy.tests import TestColumnRegExp
 
     ...
 
@@ -398,7 +398,7 @@ text_data_test = evidently_test_step.with_options(
     parameters=dict(
         test_options = [
             (
-                "evidently.options.ColorOptions", {
+                "evidently.legacy.options.ColorOptions", {
                     "primary_color": "#5a86ad",
                     "fill_color": "#fff4f2",
                     "zero_line_color": "#016795",
@@ -423,7 +423,7 @@ All you have to do is call the Evidently Data Validator methods when you need to
 from typing import Annotated
 from typing import Tuple
 import pandas as pd
-from evidently.pipeline.column_mapping import ColumnMapping
+from evidently.legacy.pipeline.column_mapping import ColumnMapping
 from zenml.integrations.evidently.data_validators import EvidentlyDataValidator
 from zenml.integrations.evidently.metrics import EvidentlyMetricConfig
 from zenml.integrations.evidently.tests import EvidentlyTestConfig
@@ -544,11 +544,11 @@ You can use the Evidently library directly in your custom pipeline steps, e.g.:
 from typing import Annotated
 from typing import Tuple
 import pandas as pd
-from evidently.report import Report
-import evidently.metric_preset as metric_preset
-from evidently.test_suite import TestSuite
-import evidently.test_preset as test_preset
-from evidently.pipeline.column_mapping import ColumnMapping
+from evidently.legacy.report import Report
+from evidently.legacy.metric_preset import DataQualityPreset
+from evidently.legacy.test_suite import TestSuite
+from evidently.legacy.test_preset import DataQualityTestPreset
+from evidently.legacy.pipeline.column_mapping import ColumnMapping
 from zenml.types import HTMLString
 from zenml import step
 
@@ -571,7 +571,7 @@ def data_profiler(
 
     # pre-processing (e.g. dataset preparation) can take place here
 
-    report = Report(metrics=[metric_preset.DataQualityPreset()])
+    report = Report(metrics=[DataQualityPreset()])
     report.run(
         current_data=dataset,
         reference_data=dataset,
@@ -600,8 +600,8 @@ def data_tester(
 
     # pre-processing (e.g. dataset preparation) can take place here
 
-    test_suite = TestSuite(metrics=[test_preset.DataQualityTestPreset()])
-    report.run(
+    test_suite = TestSuite(tests=[DataQualityTestPreset()])
+    test_suite.run(
         current_data=dataset,
         reference_data=dataset,
     )

src/zenml/integrations/evidently/__init__.py

@@ -54,9 +54,8 @@ class EvidentlyIntegration(Integration):
 
     NAME = EVIDENTLY
     REQUIREMENTS = [
-        "evidently>=0.4.16,<=0.4.22",
+        "evidently>=0.5.0,<1.0",
         "tenacity!=8.4.0",  # https://github.com/jd/tenacity/issues/471
-        "numpy<2.0.0",  # evidently is not compatible with NumPy 2.0
     ]
     REQUIREMENTS_IGNORED_ON_UNINSTALL = ["tenacity", "pandas"]
 
@@ -75,8 +74,9 @@ def get_requirements(
         """
         from zenml.integrations.pandas import PandasIntegration
 
-        return cls.REQUIREMENTS + \
-            PandasIntegration.get_requirements(target_os=target_os, python_version=python_version)
+        return cls.REQUIREMENTS + PandasIntegration.get_requirements(
+            target_os=target_os, python_version=python_version
+        )
 
     @classmethod
     def flavors(cls) -> List[Type[Flavor]]:

src/zenml/integrations/evidently/column_mapping.py

@@ -15,7 +15,9 @@
 
 from typing import List, Optional, Sequence, Union
 
-from evidently import ColumnMapping  # type: ignore[import-untyped]
+from evidently.legacy.pipeline.column_mapping import (  # type: ignore[import-untyped]
+    ColumnMapping,
+)
 from pydantic import BaseModel, ConfigDict, Field
 
 

src/zenml/integrations/evidently/data_validators/evidently_data_validator.py

@@ -15,6 +15,7 @@
 
 import os
 from typing import (
+    TYPE_CHECKING,
     Any,
     ClassVar,
     Dict,
@@ -25,19 +26,27 @@
 )
 
 import pandas as pd
-from evidently.pipeline.column_mapping import ColumnMapping  # type: ignore
-from evidently.report import Report  # type: ignore
-from evidently.test_suite import TestSuite  # type: ignore
+
+if TYPE_CHECKING:
+    from evidently.legacy.pipeline.column_mapping import (  # type: ignore[import-untyped]
+        ColumnMapping,
+    )
+    from evidently.legacy.report import Report  # type: ignore[import-untyped]
+    from evidently.legacy.test_suite import (  # type: ignore[import-untyped]
+        TestSuite,
+    )
 
 from zenml.data_validators import BaseDataValidator, BaseDataValidatorFlavor
 from zenml.integrations.evidently.flavors.evidently_data_validator_flavor import (
     EvidentlyDataValidatorFlavor,
 )
-from zenml.integrations.evidently.metrics import EvidentlyMetricConfig
-from zenml.integrations.evidently.tests import EvidentlyTestConfig
 from zenml.logger import get_logger
 from zenml.utils import source_utils
 
+if TYPE_CHECKING:
+    from zenml.integrations.evidently.metrics import EvidentlyMetricConfig
+    from zenml.integrations.evidently.tests import EvidentlyTestConfig
+
 logger = get_logger(__name__)
 
 
@@ -69,7 +78,7 @@ class with Evidently options
         ```python
             options = [
                 (
-                    "evidently.options.ColorOptions",{
+                    "evidently.legacy.options.ColorOptions",{
                         "primary_color": "#5a86ad",
                         "fill_color": "#fff4f2",
                         "zero_line_color": "#016795",
@@ -83,7 +92,7 @@ class with Evidently options
         This is the same as saying:
 
         ```python
-        from evidently.options import ColorOptions
+        from evidently.legacy.options import ColorOptions
 
         color_scheme = ColorOptions()
         color_scheme.primary_color = "#5a86ad"
@@ -166,12 +175,12 @@ def data_profiling(
         self,
         dataset: pd.DataFrame,
         comparison_dataset: Optional[pd.DataFrame] = None,
-        profile_list: Optional[Sequence[EvidentlyMetricConfig]] = None,
-        column_mapping: Optional[ColumnMapping] = None,
+        profile_list: Optional[Sequence["EvidentlyMetricConfig"]] = None,
+        column_mapping: Optional["ColumnMapping"] = None,
         report_options: Sequence[Tuple[str, Dict[str, Any]]] = [],
         download_nltk_data: bool = False,
         **kwargs: Any,
-    ) -> Report:
+    ) -> "Report":
         """Analyze a dataset and generate a data report with Evidently.
 
         The method takes in an optional list of Evidently options to be passed
@@ -183,7 +192,7 @@ def data_profiling(
         ```python
         options = [
             (
-                "evidently.options.ColorOptions",{
+                "evidently.legacy.options.ColorOptions",{
                     "primary_color": "#5a86ad",
                     "fill_color": "#fff4f2",
                     "zero_line_color": "#016795",
@@ -213,6 +222,10 @@ def data_profiling(
         Returns:
             The Evidently Report as JSON object and as HTML.
         """
+        from evidently.legacy.report import Report
+
+        from zenml.integrations.evidently.metrics import EvidentlyMetricConfig
+
         self._set_nltk_data_path()
         if download_nltk_data:
             self._download_nltk_data()
@@ -236,12 +249,12 @@ def data_validation(
         self,
         dataset: Any,
         comparison_dataset: Optional[Any] = None,
-        check_list: Optional[Sequence[EvidentlyTestConfig]] = None,
+        check_list: Optional[Sequence["EvidentlyTestConfig"]] = None,
         test_options: Sequence[Tuple[str, Dict[str, Any]]] = [],
-        column_mapping: Optional[ColumnMapping] = None,
+        column_mapping: Optional["ColumnMapping"] = None,
         download_nltk_data: bool = False,
         **kwargs: Any,
-    ) -> TestSuite:
+    ) -> "TestSuite":
         """Validate a dataset with Evidently.
 
         Args:
@@ -262,6 +275,10 @@ def data_validation(
         Returns:
             The Evidently Test Suite as JSON object and as HTML.
         """
+        from evidently.legacy.test_suite import TestSuite
+
+        from zenml.integrations.evidently.tests import EvidentlyTestConfig
+
         if download_nltk_data:
             self._download_nltk_data()
 

src/zenml/integrations/evidently/metrics.py

@@ -22,15 +22,18 @@
     Union,
 )
 
-from evidently import metric_preset, metrics  # type: ignore[import-untyped]
-from evidently.metric_preset.metric_preset import (  # type: ignore[import-untyped]
+from evidently.legacy import (  # type: ignore[import-untyped]
+    metric_preset,
+    metrics,
+)
+from evidently.legacy.metric_preset.metric_preset import (  # type: ignore[import-untyped]
     MetricPreset,
 )
-from evidently.metrics.base_metric import (  # type: ignore[import-untyped]
+from evidently.legacy.metrics.base_metric import (  # type: ignore[import-untyped]
     Metric,
     generate_column_metrics,
 )
-from evidently.utils.generators import (  # type: ignore[import-untyped]
+from evidently.legacy.utils.generators import (  # type: ignore[import-untyped]
     BaseGenerator,
 )
 from pydantic import BaseModel, ConfigDict, Field
@@ -170,15 +173,15 @@ def metric_generator(
         # Configure an Evidently Metric generator using a full Metric class
         # path
         config = EvidentlyMetric.metric_generator(
-            "evidently.metrics.ColumnSummaryMetric", columns=["age", "name"]
+            "evidently.legacy.metrics.ColumnSummaryMetric", columns=["age", "name"]
         )
         ```
 
         ```python
         from zenml.integrations.evidently.data_validators import EvidentlyMetric
 
         # Configure an Evidently Metric generator using a Metric class
-        from evidently.metrics import ColumnDriftMetric
+        from evidently.legacy.metrics import ColumnDriftMetric
         config = EvidentlyMetric.metric_generator(
             ColumnDriftMetric, columns="all", skip_id_column=True
         )
@@ -253,7 +256,7 @@ def metric(
 
         # Configure an Evidently MetricPreset using its full class path
         config = EvidentlyMetric.metric(
-            "evidently.metric_preset.DataDriftPreset"
+            "evidently.legacy.metric_preset.DataDriftPreset"
         )
         ```
 
@@ -262,7 +265,7 @@ def metric(
 
         # Configure an Evidently Metric using its class and pass additional
         # parameters
-        from evidently.metrics import ColumnSummaryMetric
+        from evidently.legacy.metrics import ColumnSummaryMetric
         config = EvidentlyMetric.metric(
             ColumnSummaryMetric, column_name="age"
         )

src/zenml/integrations/evidently/steps/evidently_report.py

@@ -108,4 +108,4 @@ def evidently_report_step(
         report_options=report_options or [],
         download_nltk_data=download_nltk_data,
     )
-    return report.json(), HTMLString(report.show(mode="inline").data)
+    return report.json(), HTMLString(report.get_html())

src/zenml/integrations/evidently/steps/evidently_test.py

@@ -104,5 +104,5 @@ def evidently_test_step(
     )
     return (
         test_suite.json(),
-        HTMLString(test_suite.show(mode="inline").data),
+        HTMLString(test_suite.get_html()),
     )