dbt run works on clickhouse

Author: Michael Myaskovsky

dbt_project.yml

@@ -3,6 +3,9 @@ version: "0.18.1"
 
 require-dbt-version: [">=1.0.0", "<2.0.0"]
 
+flags:
+  require_explicit_package_overrides_for_builtin_materializations: false
+  
 config-version: 2
 profile: "elementary"
 

macros/edr/data_monitoring/monitors/column_numeric_monitors.sql

@@ -23,9 +23,17 @@
 {% endmacro %}
 
 {% macro standard_deviation(column_name) -%}
+    {{ adapter.dispatch('standard_deviation', 'elementary')(column_name) }}
+{%- endmacro %}
+
+{% macro default__standard_deviation(column_name) -%}
     stddev(cast({{ column_name }} as {{ elementary.edr_type_float() }}))
 {%- endmacro %}
 
+{% macro clickhouse__standard_deviation(column_name) -%}
+    stddevPop(cast({{ column_name }} as {{ elementary.edr_type_float() }}))
+{%- endmacro %}
+
 {% macro variance(column_name) -%}
     variance(cast({{ column_name }} as {{ elementary.edr_type_float() }}))
 {%- endmacro %}

macros/edr/dbt_artifacts/upload_artifacts_to_table.sql

@@ -1,7 +1,6 @@
 {% macro upload_artifacts_to_table(table_relation, artifacts, flatten_artifact_callback, append=False, should_commit=False, metadata_hashes=None, on_query_exceed=none) %}
     {% set context_name = 'upload_artifacts_to_table[' ~ table_relation.name ~ ']'%}
     {% do elementary.begin_duration_measure_context(context_name) %}
-
     {% set flatten_artifact_dicts = [] %}
     {% do elementary.file_log("[{}] Flattening the artifacts.".format(table_relation.identifier)) %}
     {% do elementary.begin_duration_measure_context('artifacts_flatten') %}
@@ -18,8 +17,10 @@
 
     {% if append %}
         {# In append mode, just insert, and no need to be atomic #}
+
         {% do elementary.insert_rows(table_relation, flatten_artifact_dicts, should_commit, elementary.get_config_var('dbt_artifacts_chunk_size'), on_query_exceed) %}
     {% else %}
+
         {% set upload_artifact_method = get_upload_artifact_method(table_relation, metadata_hashes) %}
         {% if upload_artifact_method.type == "diff" %}
             {% do elementary.file_log("[{}] Comparing the artifacts state.".format(table_relation.identifier)) %}

macros/utils/cross_db_utils/current_timestamp.sql

@@ -22,6 +22,9 @@
     cast(current_timestamp() as timestamp)
 {% endmacro %}
 
+{% macro clickhouse__edr_current_timestamp() %}
+    now()
+{% endmacro %}
 
 {% macro edr_current_timestamp_in_utc() -%}
     {{ adapter.dispatch('edr_current_timestamp_in_utc','elementary')() }}
@@ -47,6 +50,10 @@
     cast(unix_timestamp() as timestamp)
 {% endmacro %}
 
+{% macro clickhouse__edr_current_timestamp_in_utc() %}
+    now('UTC')
+{% endmacro %}
+
 {% macro athena__edr_current_timestamp() -%}
     CURRENT_TIMESTAMP
 {%- endmacro -%}

macros/utils/table_operations/delete_and_insert.sql

@@ -54,6 +54,28 @@
     {% do return([query]) %}
 {% endmacro %}
 
+{% macro clickhouse__get_delete_and_insert_queries(relation, insert_relation, delete_relation, delete_column_key) %}
+    {% set queries = [] %}
+
+    {% if delete_relation %}
+        {% set delete_query %}
+            alter table {{ relation }} delete where
+            {{ delete_column_key }} is null
+            or {{ delete_column_key }} in (select {{ delete_column_key }} from {{ delete_relation }});
+        {% endset %}
+        {% do queries.append(delete_query) %}
+    {% endif %}
+
+    {% if insert_relation %}
+        {% set insert_query %}
+            insert into {{ relation }} select * from {{ insert_relation }};
+        {% endset %}
+        {% do queries.append(insert_query) %}
+    {% endif %}
+
+    {% do return(queries) %}
+{% endmacro %}
+
 {% macro spark__get_delete_and_insert_queries(relation, insert_relation, delete_relation, delete_column_key) %}
     {% set queries = [] %}
 

models/edr/data_monitoring/anomaly_detection/metrics_anomaly_score.sql

@@ -27,7 +27,7 @@ time_window_aggregation as (
         bucket_duration_hours,
         updated_at,
         avg(metric_value) over (partition by metric_name, full_table_name, column_name order by bucket_start asc rows between unbounded preceding and current row) as training_avg,
-        stddev(metric_value) over (partition by metric_name, full_table_name, column_name order by bucket_start asc rows between unbounded preceding and current row) as training_stddev,
+        {{ elementary.standard_deviation('metric_value') }} over (partition by metric_name, full_table_name, column_name order by bucket_start asc rows between unbounded preceding and current row) as training_stddev,
         count(metric_value) over (partition by metric_name, full_table_name, column_name order by bucket_start asc rows between unbounded preceding and current row) as training_set_size,
         last_value(bucket_end) over (partition by metric_name, full_table_name, column_name order by bucket_start asc rows between unbounded preceding and current row) training_end,
         first_value(bucket_end) over (partition by metric_name, full_table_name, column_name order by bucket_start asc rows between unbounded preceding and current row) as training_start