Merge branch 'develop' of https://dev.azure.com/imagetemplates/documa…

…ti.io/_git/dqoado into develop

dqops/sampledata/.~lock.house_price_prediction_treated_dataset.csv#

@@ -0,0 +1 @@
+,DESKTOP-A6A380Q/lyftrondev,DESKTOP-A6A380Q,30.10.2024 09:22,file:///C:/Users/lyftrondev/AppData/Roaming/LibreOffice/4;

examples/data-consistency/detect-data-type-changes/.DQO_USER_HOME

@@ -0,0 +1 @@
+This is a marker file to identify a DQO_USER_HOME folder. Please check this file to Git.

examples/data-consistency/detect-data-type-changes/.gitignore

@@ -0,0 +1,8 @@
+.credentials/
+.data/
+.index/
+.logs/
+bin/
+jars/
+.venv/
+.localsettings.dqosettings.yaml

examples/data-consistency/detect-data-type-changes/patterns/Detect anomalies in the count of distinct values.dqocolumnpattern.yaml

@@ -0,0 +1,19 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  description: Monitors the count of distinct values in a column and raises an issue
+    when an anomaly is detected.
+  monitoring_checks:
+    daily:
+      uniqueness:
+        daily_distinct_count_anomaly:
+          warning:
+            anomaly_percent: 0.1
+  partitioned_checks:
+    daily:
+      uniqueness:
+        daily_partition_distinct_count_anomaly:
+          warning:
+            anomaly_percent: 0.1

examples/data-consistency/detect-data-type-changes/patterns/Detect anomalies in the percentage of null values.dqocolumnpattern.yaml

@@ -0,0 +1,19 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  description: Monitors the scale of null values in columns and raises an issue when
+    the day-to-day change is significant.
+  monitoring_checks:
+    daily:
+      nulls:
+        daily_nulls_percent_anomaly:
+          warning:
+            anomaly_percent: 0.1
+  partitioned_checks:
+    daily:
+      nulls:
+        daily_partition_nulls_percent_anomaly:
+          warning:
+            anomaly_percent: 0.1

examples/data-consistency/detect-data-type-changes/patterns/Detect anomalies in the sum and average of numeric values at a partition level.dqocolumnpattern.yaml

@@ -0,0 +1,17 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  description: Monitors the sum and average (mean) aggregated values of numeric values
+    and raises a data quality issue when the value changes too much between daily
+    partitions.
+  partitioned_checks:
+    daily:
+      anomaly:
+        daily_partition_sum_anomaly:
+          warning:
+            anomaly_percent: 0.05
+        daily_partition_mean_anomaly:
+          warning:
+            anomaly_percent: 0.05

examples/data-consistency/detect-data-type-changes/patterns/Detect anomalies in the sum and average of numeric values.dqocolumnpattern.yaml

@@ -0,0 +1,16 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  description: Monitors the sum and average (mean) aggregated values of numeric values
+    and raises a data quality issue when the value changes too much day-to-day.
+  monitoring_checks:
+    daily:
+      anomaly:
+        daily_sum_anomaly:
+          warning:
+            anomaly_percent: 0.05
+        daily_mean_anomaly:
+          warning:
+            anomaly_percent: 0.05

examples/data-consistency/detect-data-type-changes/patterns/Detect big day-to-day data volume changes.dqotablepattern.yaml

@@ -0,0 +1,13 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/TableLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_table_checks
+spec:
+  priority: 1000
+  description: Monitors data volume of the whole table daily and raises an issue when
+    the volume has increased of decreased significantly.
+  monitoring_checks:
+    daily:
+      volume:
+        daily_row_count_change:
+          warning:
+            max_percent: 10.0

examples/data-consistency/detect-data-type-changes/patterns/Detect change of the data type of values in text columns.dqocolumnpattern.yaml

@@ -0,0 +1,18 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  description: Detects when the values stored in a text column change their type.
+    This policy should be activated on raw tables in the landing zones for table that
+    store all values (also numeric an dates) in text columns.
+  monitoring_checks:
+    daily:
+      datatype:
+        daily_detected_datatype_in_text_changed:
+          warning: {}
+  partitioned_checks:
+    daily:
+      datatype:
+        daily_partition_detected_datatype_in_text_changed:
+          warning: {}

examples/data-consistency/detect-data-type-changes/patterns/Detect column schema changes.dqocolumnpattern.yaml

@@ -0,0 +1,14 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  description: "Monitors the schema of columns registered in DQOps. Raises a data\
+    \ quality issue when the column is missing, or its data has changed."
+  monitoring_checks:
+    daily:
+      schema:
+        daily_column_exists:
+          warning: {}
+        daily_column_type_changed:
+          warning: {}

examples/data-consistency/detect-data-type-changes/patterns/Detect columns containing any null values.dqocolumnpattern.yaml

@@ -0,0 +1,20 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  disabled: true
+  description: Detects columns containing any null values using both monitoring checks
+    and daily partitioned checks.
+  monitoring_checks:
+    daily:
+      nulls:
+        daily_nulls_count:
+          warning:
+            max_count: 0
+  partitioned_checks:
+    daily:
+      nulls:
+        daily_partition_nulls_count:
+          warning:
+            max_count: 0

examples/data-consistency/detect-data-type-changes/patterns/Detect data freshness anomalies daily.dqotablepattern.yaml

@@ -0,0 +1,12 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/TableLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_table_checks
+spec:
+  priority: 1000
+  description: Monitors data freshness anomalies daily.
+  monitoring_checks:
+    daily:
+      timeliness:
+        daily_data_freshness_anomaly:
+          warning:
+            anomaly_percent: 0.1

examples/data-consistency/detect-data-type-changes/patterns/Detect data volume anomalies.dqotablepattern.yaml

@@ -0,0 +1,19 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/TableLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_table_checks
+spec:
+  priority: 1000
+  description: "Monitors data volume of the whole table (using daily monitoring checks)\
+    \ and for each daily partition, using daily partition checks."
+  monitoring_checks:
+    daily:
+      volume:
+        daily_row_count_anomaly:
+          warning:
+            anomaly_percent: 0.1
+  partitioned_checks:
+    daily:
+      volume:
+        daily_partition_row_count_anomaly:
+          warning:
+            anomaly_percent: 0.1

examples/data-consistency/detect-data-type-changes/patterns/Detect empty columns.dqocolumnpattern.yaml

@@ -0,0 +1,18 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  disabled: true
+  description: Detects empty columns using both monitoring checks an daily partitioned
+    checks.
+  monitoring_checks:
+    daily:
+      nulls:
+        daily_empty_column_found:
+          warning: {}
+  partitioned_checks:
+    daily:
+      nulls:
+        daily_partition_empty_column_found:
+          warning: {}

examples/data-consistency/detect-data-type-changes/patterns/Detect empty tables daily.dqotablepattern.yaml

@@ -0,0 +1,12 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/TableLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_table_checks
+spec:
+  priority: 1000
+  description: Detects empty tables using daily monitoring checks.
+  monitoring_checks:
+    daily:
+      volume:
+        daily_row_count:
+          warning:
+            min_count: 1

examples/data-consistency/detect-data-type-changes/patterns/Detect outliers in numeric values across daily partitions.dqocolumnpattern.yaml

@@ -0,0 +1,18 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  disabled: true
+  description: Monitors numeric columns to detect new smallest (min) or biggest (max)
+    value for each daily partition. Raises a data quality issue when the partition
+    contains a big or small value that exceeds regular ranges.
+  partitioned_checks:
+    daily:
+      anomaly:
+        daily_partition_min_anomaly:
+          warning:
+            anomaly_percent: 0.1
+        daily_partition_max_anomaly:
+          warning:
+            anomaly_percent: 0.1

examples/data-consistency/detect-data-type-changes/patterns/Detect outliers in numeric values.dqocolumnpattern.yaml

@@ -0,0 +1,16 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  description: "Monitors numeric columns to detect new smallest (min) or biggest (max)\
+    \ value, which must be an anomaly."
+  monitoring_checks:
+    daily:
+      anomaly:
+        daily_min_anomaly:
+          warning:
+            anomaly_percent: 0.1
+        daily_max_anomaly:
+          warning:
+            anomaly_percent: 0.1

examples/data-consistency/detect-data-type-changes/patterns/Detect significant changes in the percentage of null values.dqocolumnpattern.yaml

@@ -0,0 +1,20 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  disabled: true
+  description: Monitors the percentage of null values in columns and raises an issue
+    when the day-to-day change is above a threshold.
+  monitoring_checks:
+    daily:
+      nulls:
+        daily_nulls_percent_change:
+          warning:
+            max_percent: 10.0
+  partitioned_checks:
+    daily:
+      nulls:
+        daily_partition_nulls_percent_change:
+          warning:
+            max_percent: 10.0

examples/data-consistency/detect-data-type-changes/patterns/Detect table availability issues daily.dqotablepattern.yaml

@@ -0,0 +1,12 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/TableLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_table_checks
+spec:
+  priority: 1000
+  description: Monitors table availability issues daily.
+  monitoring_checks:
+    daily:
+      availability:
+        daily_table_availability:
+          warning:
+            max_failures: 0

examples/data-consistency/detect-data-type-changes/patterns/Detect table schema changes.dqotablepattern.yaml

@@ -0,0 +1,18 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/TableLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_table_checks
+spec:
+  priority: 1000
+  description: Monitors the table schema and raises issues when the schema of the
+    table was changed.
+  monitoring_checks:
+    daily:
+      schema:
+        daily_column_count_changed:
+          warning: {}
+        daily_column_list_changed:
+          warning: {}
+        daily_column_list_or_order_changed:
+          warning: {}
+        daily_column_types_changed:
+          warning: {}

examples/data-consistency/detect-data-type-changes/patterns/Profile text columns to detect PII values (sensitive data).dqocolumnpattern.yaml

@@ -0,0 +1,12 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 1000
+  description: "Activates data profiling checks on all text columns to detect if they\
+    \ contain sensitive data (emails, phone numbers). Enabling this policy allows\
+    \ the data quality rule miner to set up PII checks when sensitive values are identified."
+  profiling_checks:
+    pii:
+      profile_contains_usa_phone_percent: {}
+      profile_contains_email_percent: {}

examples/data-consistency/detect-data-type-changes/patterns/Track the count and percentage of null values.dqocolumnpattern.yaml

@@ -0,0 +1,17 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/ColumnLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_column_checks
+spec:
+  priority: 2000
+  description: Monitors the count and the percentage of null values without raising
+    data quality issues.
+  monitoring_checks:
+    daily:
+      nulls:
+        daily_nulls_count: {}
+        daily_nulls_percent: {}
+  partitioned_checks:
+    daily:
+      nulls:
+        daily_partition_nulls_count: {}
+        daily_partition_nulls_percent: {}

examples/data-consistency/detect-data-type-changes/patterns/Track volume of daily partitions.dqotablepattern.yaml

@@ -0,0 +1,10 @@
+# yaml-language-server: $schema=https://cloud.dqops.com/dqo-yaml-schema/TableLevelDataQualityPolicyYaml-schema.json
+apiVersion: dqo/v1
+kind: default_table_checks
+spec:
+  priority: 1000
+  description: Monitors volume (row count) of daily partitions.
+  partitioned_checks:
+    daily:
+      volume:
+        daily_partition_row_count: {}

examples/data-consistency/detect-data-type-changes/rules/requirements.txt

@@ -0,0 +1 @@
+# packages in this file are installed when DQOps starts

examples/data-consistency/detect-data-type-changes/run_dqo.cmd

@@ -0,0 +1,2 @@
+@echo off
+..\..\..\dqo.cmd

examples/data-consistency/detect-data-type-changes/run_dqo.sh

@@ -0,0 +1,2 @@
+#!/bin/sh
+../../../dqo