Add exclude_detection_period_from_training flag to column/dimension anomaly tests

integration_tests/tests/test_all_columns_anomalies.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timedelta
+from datetime import datetime, timedelta, timezone
 from typing import Any, Dict, List
 
 import pytest
@@ -153,3 +153,123 @@ def test_anomalyless_all_columns_anomalies_all_monitors_sanity(
         test_id, DBT_TEST_NAME, test_args, data=data, multiple_results=True
     )
     assert all([res["status"] == "pass" for res in test_results])
+
+
+# Anomalies currently not supported on ClickHouse
+@pytest.mark.skip_targets(["clickhouse"])
+def test_exclude_detection_from_training_all_columns(
+    test_id: str, dbt_project: DbtProject
+):
+    """
+    Test the exclude_detection_period_from_training flag functionality for column anomalies.
+
+    Scenario:
+    - 30 days of normal data with variance in null_count pattern (8, 10, 12 nulls per day)
+    - 7 days of anomalous data (20 nulls per day) in detection period
+    - Without exclusion: anomaly gets included in training baseline, test passes (misses anomaly)
+    - With exclusion: anomaly excluded from training, test fails (detects anomaly)
+    """
+    utc_now = datetime.now(timezone.utc)
+
+    # Generate 30 days of normal data with variance in null_count (8, 10, 12 pattern)
+    normal_pattern = [8, 10, 12]
+    normal_data = []
+    for i in range(30):
+        date = utc_now - timedelta(days=37 - i)
+        null_count = normal_pattern[i % 3]
+        normal_data.extend(
+            [
+                {TIMESTAMP_COLUMN: date.strftime(DATE_FORMAT), "superhero": None}
+                for _ in range(null_count)
+            ]
+        )
+        normal_data.extend(
+            [
+                {
+                    TIMESTAMP_COLUMN: date.strftime(DATE_FORMAT),
+                    "superhero": "Superman" if i % 2 == 0 else "Batman",
+                }
+                for _ in range(40 - null_count)
+            ]
+        )
+
+    # Generate 7 days of anomalous data (20 nulls per day) - 100% increase from mean
+    anomalous_data = []
+    for i in range(7):
+        date = utc_now - timedelta(days=7 - i)
+        anomalous_data.extend(
+            [
+                {TIMESTAMP_COLUMN: date.strftime(DATE_FORMAT), "superhero": None}
+                for _ in range(20)
+            ]
+        )
+        anomalous_data.extend(
+            [
+                {
+                    TIMESTAMP_COLUMN: date.strftime(DATE_FORMAT),
+                    "superhero": "Superman" if i % 2 == 0 else "Batman",
+                }
+                for _ in range(20)  # Keep total rows similar
+            ]
+        )
+
+    all_data = normal_data + anomalous_data
+
+    # Test 1: WITHOUT exclusion (should pass - misses the anomaly because it's included in training)
+    test_args_without_exclusion = {
+        "timestamp_column": TIMESTAMP_COLUMN,
+        "column_anomalies": ["null_count"],
+        "training_period": {"period": "day", "count": 30},
+        "detection_period": {"period": "day", "count": 7},
+        "time_bucket": {"period": "day", "count": 1},
+        "sensitivity": 5,  # Higher sensitivity to allow anomaly to be absorbed
+        # exclude_detection_period_from_training is not set (defaults to False/None)
+    }
+
+    test_results_without_exclusion = dbt_project.test(
+        test_id + "_f",
+        DBT_TEST_NAME,
+        test_args_without_exclusion,
+        data=all_data,
+        multiple_results=True,
+    )
+
+    # This should PASS because the anomaly is included in training, making it part of the baseline
+    superhero_result = next(
+        (
+            res
+            for res in test_results_without_exclusion
+            if res["column_name"].lower() == "superhero"
+        ),
+        None,
+    )
+    assert (
+        superhero_result and superhero_result["status"] == "pass"
+    ), "Test should pass when anomaly is included in training"
+
+    # Test 2: WITH exclusion (should fail - detects the anomaly because it's excluded from training)
+    test_args_with_exclusion = {
+        **test_args_without_exclusion,
+        "exclude_detection_period_from_training": True,
+    }
+
+    test_results_with_exclusion = dbt_project.test(
+        test_id + "_t",
+        DBT_TEST_NAME,
+        test_args_with_exclusion,
+        data=all_data,
+        multiple_results=True,
+    )
+
+    # This should FAIL because the anomaly is excluded from training, so it's detected as anomalous
+    superhero_result = next(
+        (
+            res
+            for res in test_results_with_exclusion
+            if res["column_name"].lower() == "superhero"
+        ),
+        None,
+    )
+    assert (
+        superhero_result and superhero_result["status"] == "fail"
+    ), "Test should fail when anomaly is excluded from training"

macros/edr/tests/test_all_columns_anomalies.sql

@@ -1,4 +1,4 @@
-{% test all_columns_anomalies(model, column_anomalies, exclude_prefix, exclude_regexp, timestamp_column, where_expression, anomaly_sensitivity, anomaly_direction, min_training_set_size, time_bucket, days_back, backfill_days, seasonality, sensitivity,ignore_small_changes, fail_on_zero, detection_delay, anomaly_exclude_metrics, detection_period, training_period, dimensions) %}
+{% test all_columns_anomalies(model, column_anomalies, exclude_prefix, exclude_regexp, timestamp_column, where_expression, anomaly_sensitivity, anomaly_direction, min_training_set_size, time_bucket, days_back, backfill_days, seasonality, sensitivity,ignore_small_changes, fail_on_zero, detection_delay, anomaly_exclude_metrics, detection_period, training_period, dimensions, exclude_detection_period_from_training=false) %}
     {{ config(tags = ['elementary-tests']) }}
     {%- if execute and elementary.is_test_command() and elementary.is_elementary_enabled() %}
         {% set model_relation = elementary.get_model_relation_for_test(model, elementary.get_test_model()) %}
@@ -37,7 +37,8 @@
                                                                                                    anomaly_exclude_metrics=anomaly_exclude_metrics,
                                                                                                    detection_period=detection_period,
                                                                                                    training_period=training_period,
-                                                                                                   dimensions=dimensions) %}
+                                                                                                   dimensions=dimensions,
+                                                                                                   exclude_detection_period_from_training=exclude_detection_period_from_training) %}
 
         {%- if not test_configuration %}
             {{ exceptions.raise_compiler_error("Failed to create test configuration dict for test `{}`".format(test_table_name)) }}

macros/edr/tests/test_column_anomalies.sql

@@ -1,4 +1,4 @@
-{% test column_anomalies(model, column_name, column_anomalies, timestamp_column, where_expression, anomaly_sensitivity, anomaly_direction, min_training_set_size, time_bucket, days_back, backfill_days, seasonality, sensitivity,ignore_small_changes, fail_on_zero, detection_delay, anomaly_exclude_metrics, detection_period, training_period, dimensions) %}
+{% test column_anomalies(model, column_name, column_anomalies, timestamp_column, where_expression, anomaly_sensitivity, anomaly_direction, min_training_set_size, time_bucket, days_back, backfill_days, seasonality, sensitivity,ignore_small_changes, fail_on_zero, detection_delay, anomaly_exclude_metrics, detection_period, training_period, dimensions, exclude_detection_period_from_training=false) %}
     {{ config(tags = ['elementary-tests']) }}
     {%- if execute and elementary.is_test_command() and elementary.is_elementary_enabled() %}
         {% set model_relation = elementary.get_model_relation_for_test(model, elementary.get_test_model()) %}
@@ -36,7 +36,8 @@
                                                                                                    anomaly_exclude_metrics=anomaly_exclude_metrics,
                                                                                                    detection_period=detection_period,
                                                                                                    training_period=training_period,
-                                                                                                   dimensions=dimensions) %}
+                                                                                                   dimensions=dimensions,
+                                                                                                   exclude_detection_period_from_training=exclude_detection_period_from_training) %}
 
         {%- if not test_configuration %}
             {{ exceptions.raise_compiler_error("Failed to create test configuration dict for test `{}`".format(test_table_name)) }}

macros/edr/tests/test_dimension_anomalies.sql

@@ -1,4 +1,4 @@
-{% test dimension_anomalies(model, dimensions, timestamp_column, where_expression, anomaly_sensitivity, anomaly_direction, min_training_set_size, time_bucket, days_back, backfill_days, seasonality, sensitivity,ignore_small_changes, fail_on_zero, detection_delay, anomaly_exclude_metrics, detection_period, training_period, exclude_final_results) %}
+{% test dimension_anomalies(model, dimensions, timestamp_column, where_expression, anomaly_sensitivity, anomaly_direction, min_training_set_size, time_bucket, days_back, backfill_days, seasonality, sensitivity,ignore_small_changes, fail_on_zero, detection_delay, anomaly_exclude_metrics, detection_period, training_period, exclude_final_results, exclude_detection_period_from_training=false) %}
     {{ config(tags = ['elementary-tests']) }}
     {%- if execute and elementary.is_test_command() and elementary.is_elementary_enabled() %}
         {% set model_relation = elementary.get_model_relation_for_test(model, elementary.get_test_model()) %}
@@ -39,7 +39,8 @@
                                                                                                    anomaly_exclude_metrics=anomaly_exclude_metrics,
                                                                                                    detection_period=detection_period,
                                                                                                    training_period=training_period,
-                                                                                                   exclude_final_results=exclude_final_results) %}
+                                                                                                   exclude_final_results=exclude_final_results,
+                                                                                                   exclude_detection_period_from_training=exclude_detection_period_from_training) %}
 
         {%- if not test_configuration %}
             {{ exceptions.raise_compiler_error("Failed to create test configuration dict for test `{}`".format(test_table_name)) }}