gitea_admin/sientia-dataops-laborious-legacy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SIENTIAPDE-1646

Browse Source 
Refactor ModelMetrics to utilize DriftAnalysis for drift detection

- Replaced ModelAnalysis with DriftAnalysis in the ModelMetrics class to enhance drift detection capabilities.
- Updated method signatures and documentation to reflect the changes in target_name and return values.
- Adjusted data handling to ensure compatibility with the new analysis methods and improved clarity in the drift metrics dataframe preparation.
This commit is contained in:
Vitor Pimentel dos Santos
2026-05-08 16:39:12 -03:00
parent e6018af23f
commit 10c7e292b9
29 changed files with 843 additions and 1266 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
e2e/scenario_inputs/drift_base.json
View File

@@ -2,9 +2,9 @@
"schedule_name": "test-schedule",
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"schema": "predictions_schema",
"schema": "sientia_data",
"source_table_name": "laborious_data",
"target_table_name": "drift",
"target_table_name": "drift_metrics",
"interval": 60,
"drift_metrics": ["kolmogorov_smirnov", "jensen_shannon", "wasserstein"],
"chunk_period": "min",

4
e2e/scenario_inputs/format_export_base.json
View File

@@ -2,8 +2,8 @@
"schedule_name": "test-schedule",
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "predictions_schema",
"query": "SELECT timestamp, variable, value, created_at FROM sientia_data.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "sientia_data",
"table_name": "predictions",
"transform_table_name": "transformed_data",
"input_filters": {

4
e2e/scenario_inputs/main_happy_path.json
View File

@@ -10,8 +10,8 @@
"schedule_name": "test-schedule",
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "predictions_schema",
"query": "SELECT timestamp, variable, value, created_at FROM sientia_data.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "sientia_data",
"table_name": "predictions",
"transform_table_name": "transformed_data",
"input_filters": {

4
e2e/scenario_inputs/main_invalid_datetime.json
View File

@@ -10,8 +10,8 @@
"schedule_name": "test-schedule",
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"query": "SELECT timestamp, variable, value FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "predictions_schema",
"query": "SELECT timestamp, variable, value FROM sientia_data.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "sientia_data",
"table_name": "predictions",
"transform_table_name": "transformed_data",
"input_filters": {

2
e2e/scenario_inputs/main_missing_required.json
View File

@@ -10,7 +10,7 @@
"schedule_name": "test-schedule",
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"schema": "predictions_schema",
"schema": "sientia_data",
"table_name": "predictions",
"transform_table_name": "transformed_data"
}

2
e2e/scenario_inputs/main_sql_error.json
View File

@@ -11,7 +11,7 @@
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"query": "SELECT * FROM nonexistent_table WHERE invalid_syntax =",
"schema": "predictions_schema",
"schema": "sientia_data",
"table_name": "predictions",
"transform_table_name": "transformed_data",
"input_filters": {

6
e2e/scenario_inputs/minimal_retrain_base.json
View File

@@ -2,9 +2,9 @@
"schedule_name": "test-schedule",
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "predictions_schema",
"table_name": "retrain_reports",
"query": "SELECT timestamp, variable, value, created_at FROM sientia_data.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "sientia_data",
"table_name": "log_retrain",
"datetime_columns": ["timestamp", "created_at"],
"model_config": {
"target": "sensor_1"

2
e2e/scenario_inputs/minio_offload_load_query.json
View File

@@ -5,7 +5,7 @@
"model_id": "{{MODEL_ID}}",
"workflow_name": "predictions_batch"
},
"query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
"query": "SELECT timestamp, variable, value, created_at FROM sientia_data.laborious_data WHERE model_id = {{MODEL_ID}}",
"model_name": "test_model",
"datetime_columns": ["timestamp", "created_at"]
}

4
e2e/scenario_inputs/minio_offload_workflow.json
View File

@@ -2,8 +2,8 @@
"schedule_name": "test-schedule",
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "predictions_schema",
"query": "SELECT timestamp, variable, value, created_at FROM sientia_data.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "sientia_data",
"table_name": "predictions",
"transform_table_name": "transformed_data",
"input_filters": {

4
e2e/scenario_inputs/prediction_process_base.json
View File

@@ -2,8 +2,8 @@
"schedule_name": "test-schedule",
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "predictions_schema",
"query": "SELECT timestamp, variable, value, created_at FROM sientia_data.laborious_data WHERE model_id = {{MODEL_ID}}",
"schema": "sientia_data",
"table_name": "predictions",
"transform_table_name": "transformed_data",
"input_filters": {

4
e2e/scenario_inputs/simple_metrics_base.json
View File

@@ -2,10 +2,10 @@
"schedule_name": "test-schedule",
"model_name": "test_model",
"model_id": "{{MODEL_ID}}",
"schema": "predictions_schema",
"schema": "sientia_data",
"predictions_table_name": "predictions",
"data_table_name": "laborious_data",
"target_table_name": "simple_metrics_data",
"target_table_name": "simple_metrics",
"interval_minutes": 60,
"metrics": ["rmse", "mse", "mae", "r2"],
"model_config": {