gitea_admin/sientia-dataops-orchestrator_temporal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
08e28441dc87a636936a9670d2b01d19e7d08640
sientia-dataops-orchestrato…/test.ipynb
vitor-aignosi c9b5e98726 SIENTIAPDE-1273 
Implement drift monitoring configuration and update formatters to support drift workflows. Add drift function to orchestrator utilities and enhance tests for drift functionality.
2025-11-14 09:22:24 -03:00

2687 lines
104 KiB
Plaintext
Raw Blame History

{
"cells": [
{
"cell_type": "code",
"execution_count": 4,
"id": "a287fa45",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Initializing Couchbase connection...\n",
"Awaiting Couchbase connection...\n",
"Couchbase connection ready\n"
]
}
],
"source": [
"from orchestrator.activities.couchbase import Couchbase\n",
"from unittest.mock import MagicMock\n",
"logger = MagicMock(info=MagicMock(side_effect=print), debug=MagicMock(side_effect=print))\n",
"couchbase = Couchbase(\n",
" connection_string=\"couchbase://localhost\",\n",
" username=\"sientia\",\n",
" password=\"sientia\",\n",
" logger=logger,\n",
" notification_handler=MagicMock()\n",
")\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "d9a0f9c4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Executing couchbase query: %s \n",
"SELECT\n",
" pipelines.*,\n",
" models as model\n",
"FROM\n",
" `pipelines`\n",
"JOIN\n",
" `models` ON KEYS pipelines.model_id;\n",
"\n",
"Fetched %d rows from couchbase 1\n",
"Rows: \n",
" %s [\n",
" {\n",
" \"filters\": [\n",
" {\n",
" \"filter_name\": \"OUT_OF_BOUNDS_FILTER\",\n",
" \"policy\": \"DISCARD\"\n",
" },\n",
" {\n",
" \"filter_name\": \"NULL_VALUES_FILTER\",\n",
" \"policy\": \"DISCARD\"\n",
" }\n",
" ],\n",
" \"frequency\": \"5s\",\n",
" \"max_retry_policy\": 1,\n",
" \"model\": {\n",
" \"name\": \"Demo Model-Demo2\"\n",
" },\n",
" \"model_id\": \"1\",\n",
" \"name\": \"scouter-opcua-pipeline\",\n",
" \"read_tags\": [\n",
" {\n",
" \"aggr_func\": \"avg\",\n",
" \"data_range\": [\n",
" -100,\n",
" 100\n",
" ],\n",
" \"tag_name\": \"Counter\"\n",
" }\n",
" ],\n",
" \"tag_retention_minutes\": 60,\n",
" \"workflow_type\": \"scouter\"\n",
" }\n",
"]\n",
"[{'filters': [{'filter_name': 'OUT_OF_BOUNDS_FILTER', 'policy': 'DISCARD'}, {'filter_name': 'NULL_VALUES_FILTER', 'policy': 'DISCARD'}], 'frequency': '5s', 'max_retry_policy': 1, 'model': {'name': 'Demo Model-Demo2'}, 'model_id': '1', 'name': 'scouter-opcua-pipeline', 'read_tags': [{'aggr_func': 'avg', 'data_range': [-100, 100], 'tag_name': 'Counter'}], 'tag_retention_minutes': 60, 'workflow_type': 'scouter'}]\n"
]
}
],
"source": [
"query = \"\"\"\n",
"SELECT\n",
" pipelines.*,\n",
" models as model\n",
"FROM\n",
" `pipelines`\n",
"JOIN\n",
" `models` ON KEYS pipelines.model_id;\n",
"\"\"\"\n",
"if __name__ == \"__main__\":\n",
"\n",
"\n",
" result = await couchbase.load_query_from_couchbase({\n",
" \"query\": query\n",
" })\n",
"\n",
" print(result)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "7d01f160",
"metadata": {},
"outputs": [],
"source": [
"from temporalio import client\n",
"from orchestrator.activities.temporal_manager import TemporalManager\n",
"import os\n",
"from unittest.mock import MagicMock\n",
"\n",
"host = \"localhost:7233\"\n",
"logger = MagicMock(info=MagicMock(side_effect=print), debug=MagicMock(side_effect=print))\n",
"\n",
"temporal_client = await client.Client.connect(\n",
" target_host=host,\n",
" namespace=os.getenv('TEMPORAL_NAMESPACE', 'default')\n",
")\n",
"\n",
" "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bb750ae6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<temporalio.client.ScheduleHandle at 0x7700871c6150>"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import asyncio\n",
"from datetime import timedelta\n",
"from temporalio.client import (\n",
" Client,\n",
" Schedule,\n",
" ScheduleActionStartWorkflow,\n",
" ScheduleIntervalSpec,\n",
" ScheduleSpec,\n",
")\n",
"from temporalio.common import TypedSearchAttributes, SearchAttributeKey, SearchAttributePair\n",
"\n",
"# temporal operator search-attribute create --namespace scouter --name model_id --type Text && temporal operator search-attribute create --namespace scouter --name orchestrated --type Text && temporal operator search-attribute create --namespace scouter --name model_name --type Text && temporal operator search-attribute create --namespace laborious --name model_id --type Text && temporal operator search-attribute create --namespace laborious --name orchestrated --type Text && temporal operator search-attribute create --namespace laborious --name model_name --type Text\n",
"\n",
"\n",
"\n",
"await temporal_client.create_schedule(\n",
" \"orchestrator\",\n",
" Schedule(\n",
" action=ScheduleActionStartWorkflow(\n",
" 'orchestrator',\n",
" {\n",
" \"schedule_name\": \"orchestrator-test\",\n",
" \"pipelines_query\": {\n",
" \"collection\": \"pipelines\",\n",
" \"aggregation\": [\n",
" {\n",
" \"$lookup\": {\n",
" \"from\": \"models\",\n",
" \"localField\": \"model_id\",\n",
" \"foreignField\": \"id\",\n",
" \"as\": \"model_docs\"\n",
" }\n",
" },\n",
" {\n",
" \"$match\": {\n",
" \"active\": True\n",
" }\n",
" },\n",
" {\n",
" \"$addFields\": {\n",
" \"models\": {\n",
" \"$arrayElemAt\": [\n",
" \"$model_docs\",\n",
" 0\n",
" ]\n",
" }\n",
" }\n",
" },\n",
" {\n",
" \"$match\": {\n",
" \"models.active\": True\n",
" }\n",
" },\n",
" {\n",
" \"$project\": {\n",
" \"model_docs\": 0\n",
" }\n",
" }\n",
" ]\n",
" },\n",
" \"opc_servers_query\": {\n",
" \"collection\": \"opc-servers\",\n",
" \"filters\": {\n",
"\n",
" }\n",
" }\n",
" },\n",
" id=\"orchestrator\",\n",
" task_queue=\"orchestrator-queue\",\n",
" execution_timeout=timedelta(minutes=600)\n",
" ),\n",
" spec=ScheduleSpec(\n",
" intervals=[ScheduleIntervalSpec(every=timedelta(minutes=60))]\n",
" )\n",
" )\n",
")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b840347d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Error deleting schedule scouter-load-test-1: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-2: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-3: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-4: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-5: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-6: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-7: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-8: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-9: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-10: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-11: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-12: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-13: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-14: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-15: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-16: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-17: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-18: workflow execution already completed\n",
"Error deleting schedule scouter-load-test-19: workflow execution already completed\n"
]
}
],
"source": [
"# Delete schedule by ID\n",
"schedule_id = \"scouter-load-test-num\"\n",
"\n",
"for i in range(0, 70):\n",
"\n",
" try:\n",
" handle = temporal_client.get_schedule_handle(\n",
" schedule_id.replace(\"num\", str(i)))\n",
" \n",
" await handle.delete()\n",
" except Exception as e:\n",
" print(f\"Error deleting schedule {schedule_id.replace('num', str(i))}: {e}\")\n",
"\n",
"# Delete schedule by ID\n",
"schedule_id = \"laborious-load-test-num\"\n",
"\n",
"for i in range(0, 70):\n",
"\n",
" try:\n",
" handle = temporal_client.get_schedule_handle(\n",
" schedule_id.replace(\"num\", str(i)))\n",
" \n",
" await handle.delete()\n",
" except Exception as e:\n",
" print(f\"Error deleting schedule {schedule_id.replace('num', str(i))}: {e}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "374b5b0e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"scouter-load-test-num\n"
]
}
],
"source": [
"schedule_id = \"scouter-load-test-num\"\n",
"schedule_id.replace(\"-\", \"_\")\n",
"\n",
"print(schedule_id)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1bd82225",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Getting orchestrated schedules...\n"
]
}
],
"source": [
"schedules = await manager.load_schedule()"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "1948670e",
"metadata": {},
"outputs": [],
"source": [
"from google.protobuf.json_format import MessageToDict\n",
"import base64\n",
"import json\n",
"for arg in schedules.schedule.action.args:\n",
" data = MessageToDict(arg)\n",
" data = base64.b64decode(data['data']).decode('utf-8')"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "a4c777dd",
"metadata": {},
"outputs": [],
"source": [
"from google.protobuf.json_format import MessageToDict\n",
"import base64\n",
"import json\n",
"\n",
"schedules_config = {}\n",
"async for schedule in await temporal_client.list_schedules():\n",
" id = schedule.id\n",
"\n",
" handle = temporal_client.get_schedule_handle(id)\n",
"\n",
" desc = await handle.describe()\n",
"\n",
" for arg in desc.schedule.action.args:\n",
" data = MessageToDict(arg)['data']\n",
" data = base64.b64decode(data).decode('utf-8')\n",
"\n",
" frequency = desc.schedule.spec.intervals[0].every.seconds\n",
"\n",
" schedules_config[id] = {\n",
" 'frequency': frequency,\n",
" 'data': json.loads(data),\n",
" 'handle': handle\n",
" }\n",
" \n",
" \n",
" \n",
" "
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "f81b3728",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'id': 'orchestrator', 'schedule': ScheduleListSchedule(action=ScheduleListActionStartWorkflow(workflow='orchestrator'), spec=ScheduleSpec(calendars=[], intervals=[ScheduleIntervalSpec(every=datetime.timedelta(seconds=3600), offset=None)], cron_expressions=[], skip=[], start_at=None, end_at=None, jitter=None, time_zone_name=None), state=ScheduleListState(note=None, paused=False)), 'info': ScheduleListInfo(recent_actions=[ScheduleActionResult(scheduled_at=datetime.datetime(2025, 7, 14, 9, 0, tzinfo=datetime.timezone.utc), started_at=datetime.datetime(2025, 7, 14, 9, 0, 0, 165083, tzinfo=datetime.timezone.utc), action=ScheduleActionExecutionStartWorkflow(workflow_id='orchestrator-2025-07-14T09:00:00Z', first_execution_run_id='01980829-9700-771a-9c9d-2450eecc9af4')), ScheduleActionResult(scheduled_at=datetime.datetime(2025, 7, 14, 10, 0, tzinfo=datetime.timezone.utc), started_at=datetime.datetime(2025, 7, 14, 10, 0, 0, 125309, tzinfo=datetime.timezone.utc), action=ScheduleActionExecutionStartWorkflow(workflow_id='orchestrator-2025-07-14T10:00:00Z', first_execution_run_id='01980860-8578-759d-97fa-dbdfc784f88a')), ScheduleActionResult(scheduled_at=datetime.datetime(2025, 7, 14, 11, 0, tzinfo=datetime.timezone.utc), started_at=datetime.datetime(2025, 7, 14, 11, 0, 0, 124356, tzinfo=datetime.timezone.utc), action=ScheduleActionExecutionStartWorkflow(workflow_id='orchestrator-2025-07-14T11:00:00Z', first_execution_run_id='01980897-73f7-7e83-a7a6-20eaac38e7d4')), ScheduleActionResult(scheduled_at=datetime.datetime(2025, 7, 14, 12, 0, tzinfo=datetime.timezone.utc), started_at=datetime.datetime(2025, 7, 14, 12, 0, 0, 167329, tzinfo=datetime.timezone.utc), action=ScheduleActionExecutionStartWorkflow(workflow_id='orchestrator-2025-07-14T12:00:00Z', first_execution_run_id='019808ce-62a2-75d6-b11d-c5387cfa258f')), ScheduleActionResult(scheduled_at=datetime.datetime(2025, 7, 14, 13, 0, tzinfo=datetime.timezone.utc), started_at=datetime.datetime(2025, 7, 14, 13, 0, 0, 167575, tzinfo=datetime.timezone.utc), action=ScheduleActionExecutionStartWorkflow(workflow_id='orchestrator-2025-07-14T13:00:00Z', first_execution_run_id='01980905-5122-7807-90ae-3782d0332e79'))], next_action_times=[datetime.datetime(2025, 7, 14, 14, 0, tzinfo=datetime.timezone.utc), datetime.datetime(2025, 7, 14, 15, 0, tzinfo=datetime.timezone.utc), datetime.datetime(2025, 7, 14, 16, 0, tzinfo=datetime.timezone.utc), datetime.datetime(2025, 7, 14, 17, 0, tzinfo=datetime.timezone.utc), datetime.datetime(2025, 7, 14, 18, 0, tzinfo=datetime.timezone.utc)]), 'typed_search_attributes': TypedSearchAttributes(search_attributes=[]), 'search_attributes': {}, 'data_converter': DataConverter(payload_converter_class=<class 'temporalio.converter.DefaultPayloadConverter'>, payload_codec=None, failure_converter_class=<class 'temporalio.converter.DefaultFailureConverter'>, payload_converter=<temporalio.converter.DefaultPayloadConverter object at 0x787d51390750>, failure_converter=<temporalio.converter.DefaultFailureConverter object at 0x787d5277b590>), 'raw_entry': schedule_id: \"orchestrator\"\n",
"info {\n",
" spec {\n",
" interval {\n",
" interval {\n",
" seconds: 3600\n",
" }\n",
" }\n",
" }\n",
" workflow_type {\n",
" name: \"orchestrator\"\n",
" }\n",
" recent_actions {\n",
" schedule_time {\n",
" seconds: 1752483600\n",
" }\n",
" actual_time {\n",
" seconds: 1752483600\n",
" nanos: 165083498\n",
" }\n",
" start_workflow_result {\n",
" workflow_id: \"orchestrator-2025-07-14T09:00:00Z\"\n",
" run_id: \"01980829-9700-771a-9c9d-2450eecc9af4\"\n",
" }\n",
" start_workflow_status: WORKFLOW_EXECUTION_STATUS_COMPLETED\n",
" }\n",
" recent_actions {\n",
" schedule_time {\n",
" seconds: 1752487200\n",
" }\n",
" actual_time {\n",
" seconds: 1752487200\n",
" nanos: 125309119\n",
" }\n",
" start_workflow_result {\n",
" workflow_id: \"orchestrator-2025-07-14T10:00:00Z\"\n",
" run_id: \"01980860-8578-759d-97fa-dbdfc784f88a\"\n",
" }\n",
" start_workflow_status: WORKFLOW_EXECUTION_STATUS_COMPLETED\n",
" }\n",
" recent_actions {\n",
" schedule_time {\n",
" seconds: 1752490800\n",
" }\n",
" actual_time {\n",
" seconds: 1752490800\n",
" nanos: 124356906\n",
" }\n",
" start_workflow_result {\n",
" workflow_id: \"orchestrator-2025-07-14T11:00:00Z\"\n",
" run_id: \"01980897-73f7-7e83-a7a6-20eaac38e7d4\"\n",
" }\n",
" start_workflow_status: WORKFLOW_EXECUTION_STATUS_COMPLETED\n",
" }\n",
" recent_actions {\n",
" schedule_time {\n",
" seconds: 1752494400\n",
" }\n",
" actual_time {\n",
" seconds: 1752494400\n",
" nanos: 167329351\n",
" }\n",
" start_workflow_result {\n",
" workflow_id: \"orchestrator-2025-07-14T12:00:00Z\"\n",
" run_id: \"019808ce-62a2-75d6-b11d-c5387cfa258f\"\n",
" }\n",
" start_workflow_status: WORKFLOW_EXECUTION_STATUS_COMPLETED\n",
" }\n",
" recent_actions {\n",
" schedule_time {\n",
" seconds: 1752498000\n",
" }\n",
" actual_time {\n",
" seconds: 1752498000\n",
" nanos: 167575982\n",
" }\n",
" start_workflow_result {\n",
" workflow_id: \"orchestrator-2025-07-14T13:00:00Z\"\n",
" run_id: \"01980905-5122-7807-90ae-3782d0332e79\"\n",
" }\n",
" start_workflow_status: WORKFLOW_EXECUTION_STATUS_RUNNING\n",
" }\n",
" future_action_times {\n",
" seconds: 1752501600\n",
" }\n",
" future_action_times {\n",
" seconds: 1752505200\n",
" }\n",
" future_action_times {\n",
" seconds: 1752508800\n",
" }\n",
" future_action_times {\n",
" seconds: 1752512400\n",
" }\n",
" future_action_times {\n",
" seconds: 1752516000\n",
" }\n",
"}\n",
"}\n",
"{'_client': <temporalio.client.Client object at 0x787d53dd3490>, 'id': 'orchestrator'}\n"
]
}
],
"source": [
"async for schedule in await temporal_client.list_schedules():\n",
" print(vars(schedule))\n",
" id = schedule.id\n",
"\n",
" handle = temporal_client.get_schedule_handle(id)\n",
"\n",
" print(vars(handle))"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "988d1718",
"metadata": {},
"outputs": [],
"source": [
"schedules_config = {\n",
" \"scouter-opcua-orchestrated-pipeline\": schedules_config['scouter-opcua-orchestrated-pipeline'],\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "c12f5e75",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"scouter-opcua-orchestrated-pipeline {'frequency': 5, 'data': {'filters': {'NULL_VALUES_FILTER': {'policy': 'DISCARD'}, 'OUT_OF_BOUNDS_FILTER': {'policy': 'DISCARD'}}, 'frequency': '5s', 'max_retry_policy': 1, 'model_id': '1', 'model_name': 'Demo Model-Demo2', 'model_tags': {'Counter': {'aggr_func': 'avg', 'data_range': [-100, 100]}}, 'retention_time': 3600, 'schedule_name': 'scouter-opcua-orchestrated-pipeline', 'schema': 'sientia_data', 'table_name': 'laborious_data', 'topic': 'raw_scouter-opcua-orchestrated-pipeline', 'trigger_laborious': False, 'workflow_type': 'scouter'}, 'handle': <temporalio.client.ScheduleHandle object at 0x7dfab3b2ab50>}\n",
"scouter-opcua-orchestrated-pipeline\n",
"{'workflow': 'scouter', 'args': [metadata {\n",
" key: \"encoding\"\n",
" value: \"json/plain\"\n",
"}\n",
"data: \"{\\\"filters\\\":{\\\"NULL_VALUES_FILTER\\\":{\\\"policy\\\":\\\"DISCARD\\\"},\\\"OUT_OF_BOUNDS_FILTER\\\":{\\\"policy\\\":\\\"DISCARD\\\"}},\\\"frequency\\\":\\\"5s\\\",\\\"max_retry_policy\\\":1,\\\"model_id\\\":\\\"1\\\",\\\"model_name\\\":\\\"Demo Model-Demo2\\\",\\\"model_tags\\\":{\\\"Counter\\\":{\\\"aggr_func\\\":\\\"avg\\\",\\\"data_range\\\":[-100,100]}},\\\"retention_time\\\":3600,\\\"schedule_name\\\":\\\"scouter-opcua-orchestrated-pipeline\\\",\\\"schema\\\":\\\"sientia_data\\\",\\\"table_name\\\":\\\"laborious_data\\\",\\\"topic\\\":\\\"raw_scouter-opcua-orchestrated-pipeline\\\",\\\"trigger_laborious\\\":false,\\\"workflow_type\\\":\\\"scouter\\\"}\"\n",
"], 'id': 'scouter-opcua-orchestrated-pipeline', 'task_queue': 'scouter-queue', 'execution_timeout': datetime.timedelta(seconds=120), 'run_timeout': None, 'task_timeout': None, 'retry_policy': None, 'memo': None, 'typed_search_attributes': TypedSearchAttributes(search_attributes=[]), 'headers': None, 'untyped_search_attributes': {}, 'static_summary': None, 'static_details': None, 'priority': Priority(priority_key=None)}\n"
]
}
],
"source": [
"from temporalio.client import Client, ScheduleUpdateInput, ScheduleUpdate, ScheduleSpec\n",
"\n",
"\n",
"for id, schedule in schedules_config.items():\n",
" print(id, schedule)\n",
" \n",
" if schedule['frequency'] != 600:\n",
" print(id)\n",
"\n",
" handle = schedule['handle']\n",
" \n",
" async def update_schedule(input: ScheduleUpdateInput) -> ScheduleUpdate:\n",
" schedule_action = input.description.schedule.action\n",
"\n",
" print(schedule_action.__dict__)\n",
" \n",
" if hasattr(schedule_action, 'args'):\n",
" schedule_action.args = [{}]\n",
" \n",
" # Atualiza o intervalo de execução\n",
" input.description.schedule.spec.intervals = [\n",
" ScheduleIntervalSpec(every=timedelta(minutes=10))\n",
" ]\n",
" \n",
" return ScheduleUpdate(schedule=input.description.schedule)\n",
"\n",
" await handle.update(update_schedule)\n",
" \n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "87eb10c8",
"metadata": {},
"outputs": [],
"source": [
"from redis import Redis\n",
"\n",
"redis = Redis(host='localhost', port=6379)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "fe4ad9dc",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Chave: slot:opc_tags:2, Valor: {\n",
"\"slot2\": \"value\"\n",
"}\n",
"Chave: slot:opc_tags:1, Valor: {\n",
"\"slot1\": \"value\"\n",
"}\n"
]
}
],
"source": [
"matching_keys = redis.keys(\"slot:opc_tags:*\")\n",
"\n",
"if matching_keys:\n",
" decoded_keys = [key.decode('utf-8') for key in matching_keys]\n",
" values = redis.mget(decoded_keys)\n",
"\n",
" items = {}\n",
" for i, key in enumerate(decoded_keys):\n",
" value = values[i]\n",
" if value is not None:\n",
" try:\n",
" items[key] = value.decode('utf-8')\n",
" except (UnicodeDecodeError, AttributeError):\n",
" items[key] = value\n",
" else:\n",
" items[key] = None\n",
"\n",
" for key, value in items.items():\n",
" print(f\"Chave: {key}, Valor: {value}\")"
]
},
{
"cell_type": "markdown",
"id": "e8025cbb",
"metadata": {},
"source": [
"## Model Monitoring"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "87a9dc89",
"metadata": {},
"outputs": [],
"source": [
"from sientia.ModelAnalysis import ModelAnalysis\n",
"\n",
"config = {\n",
" \"target\": \"Square\",\n",
" \"prediction\": \"prediction\",\n",
" \"timestamp\": \"timestamp\",\n",
" \"features\": [\"Counter\", \"Rollout\"]\n",
"}\n",
"\n",
"model = ModelAnalysis(config=config)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "2a74ad2f",
"metadata": {},
"outputs": [],
"source": [
"from sientia_do.temporal.activities.postgres import Postgres\n",
"from unittest.mock import AsyncMock\n",
"from pandas import DataFrame\n",
"\n",
"postgres = Postgres(\n",
" host=\"localhost\",\n",
" port=5432,\n",
" dbname=\"sientia\",\n",
" user=\"sientia\",\n",
" password=\"sientia\",\n",
" min_connections=1,\n",
" max_connections=10,\n",
" logger=AsyncMock(),\n",
" notification_handler=AsyncMock(),\n",
" metrics_controller=AsyncMock()\n",
")\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "938cecbd",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/grezewave/Documents/projects/sientia/sientia-dataops-orchestrator_temporal/venv/lib/python3.11/site-packages/sientia_do/observability/sientia_monitoring.py:83: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited\n",
" self.logger.custom_info(message, metadata)\n",
"/home/grezewave/Documents/projects/sientia/sientia-dataops-orchestrator_temporal/venv/lib/python3.11/site-packages/sientia_do/observability/sientia_monitoring.py:59: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited\n",
" self.metrics_controller.start()\n",
"/home/grezewave/Documents/projects/sientia/sientia-dataops-orchestrator_temporal/venv/lib/python3.11/site-packages/sientia_do/observability/sientia_monitoring.py:83: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited\n",
" self.logger.custom_info(message, metadata)\n",
"/home/grezewave/Documents/projects/sientia/sientia-dataops-orchestrator_temporal/venv/lib/python3.11/site-packages/sientia_do/observability/sientia_monitoring.py:95: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited\n",
" self.logger.custom_debug(message, metadata)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>variable</th>\n",
" <th>value</th>\n",
" <th>prediction</th>\n",
" <th>timestamp</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Square</td>\n",
" <td>42.2950</td>\n",
" <td>-3.018465</td>\n",
" <td>2025-11-12 12:44:50+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Rollout</td>\n",
" <td>1.8610</td>\n",
" <td>-3.018465</td>\n",
" <td>2025-11-12 12:44:50+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Counter</td>\n",
" <td>-45.0980</td>\n",
" <td>-3.018465</td>\n",
" <td>2025-11-12 12:44:50+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Rollout</td>\n",
" <td>0.3970</td>\n",
" <td>2.341423</td>\n",
" <td>2025-11-12 12:44:20+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Counter</td>\n",
" <td>-40.0260</td>\n",
" <td>2.341423</td>\n",
" <td>2025-11-12 12:44:20+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Square</td>\n",
" <td>43.3190</td>\n",
" <td>2.341423</td>\n",
" <td>2025-11-12 12:44:20+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Rollout</td>\n",
" <td>-0.2645</td>\n",
" <td>4.696591</td>\n",
" <td>2025-11-12 12:42:15+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Square</td>\n",
" <td>42.1850</td>\n",
" <td>4.696591</td>\n",
" <td>2025-11-12 12:42:15+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Counter</td>\n",
" <td>-37.8385</td>\n",
" <td>4.696591</td>\n",
" <td>2025-11-12 12:42:15+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Square</td>\n",
" <td>2.8880</td>\n",
" <td>-70.845157</td>\n",
" <td>2025-11-11 23:00:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>Rollout</td>\n",
" <td>18.7945</td>\n",
" <td>-70.845157</td>\n",
" <td>2025-11-11 23:00:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>Counter</td>\n",
" <td>-12.6565</td>\n",
" <td>-70.845157</td>\n",
" <td>2025-11-11 23:00:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>Rollout</td>\n",
" <td>17.7415</td>\n",
" <td>-71.894590</td>\n",
" <td>2025-11-11 23:00:18+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>Counter</td>\n",
" <td>-11.1570</td>\n",
" <td>-71.894590</td>\n",
" <td>2025-11-11 23:00:18+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>Square</td>\n",
" <td>2.1610</td>\n",
" <td>-71.894590</td>\n",
" <td>2025-11-11 23:00:18+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>Square</td>\n",
" <td>-2.0490</td>\n",
" <td>-67.033953</td>\n",
" <td>2025-11-11 22:59:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>Rollout</td>\n",
" <td>16.5365</td>\n",
" <td>-67.033953</td>\n",
" <td>2025-11-11 22:59:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>Counter</td>\n",
" <td>-15.2205</td>\n",
" <td>-67.033953</td>\n",
" <td>2025-11-11 22:59:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>Counter</td>\n",
" <td>-11.7930</td>\n",
" <td>-70.514462</td>\n",
" <td>2025-11-11 22:59:18+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>Square</td>\n",
" <td>-4.3350</td>\n",
" <td>-70.514462</td>\n",
" <td>2025-11-11 22:59:18+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>Rollout</td>\n",
" <td>16.3065</td>\n",
" <td>-70.514462</td>\n",
" <td>2025-11-11 22:59:18+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>Square</td>\n",
" <td>0.6840</td>\n",
" <td>-72.523279</td>\n",
" <td>2025-11-11 22:58:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>Counter</td>\n",
" <td>-9.2570</td>\n",
" <td>-72.523279</td>\n",
" <td>2025-11-11 22:58:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>Rollout</td>\n",
" <td>14.9965</td>\n",
" <td>-72.523279</td>\n",
" <td>2025-11-11 22:58:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>Square</td>\n",
" <td>1.1700</td>\n",
" <td>-72.831684</td>\n",
" <td>2025-11-11 22:58:18+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>Counter</td>\n",
" <td>-7.0635</td>\n",
" <td>-72.831684</td>\n",
" <td>2025-11-11 22:58:18+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>Rollout</td>\n",
" <td>10.9875</td>\n",
" <td>-72.831684</td>\n",
" <td>2025-11-11 22:58:18+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>Counter</td>\n",
" <td>-2.0110</td>\n",
" <td>-77.865944</td>\n",
" <td>2025-11-11 22:57:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>Rollout</td>\n",
" <td>10.4545</td>\n",
" <td>-77.865944</td>\n",
" <td>2025-11-11 22:57:48+00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>Square</td>\n",
" <td>-0.2070</td>\n",
" <td>-77.865944</td>\n",
" <td>2025-11-11 22:57:48+00:00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" variable value prediction timestamp\n",
"0 Square 42.2950 -3.018465 2025-11-12 12:44:50+00:00\n",
"1 Rollout 1.8610 -3.018465 2025-11-12 12:44:50+00:00\n",
"2 Counter -45.0980 -3.018465 2025-11-12 12:44:50+00:00\n",
"3 Rollout 0.3970 2.341423 2025-11-12 12:44:20+00:00\n",
"4 Counter -40.0260 2.341423 2025-11-12 12:44:20+00:00\n",
"5 Square 43.3190 2.341423 2025-11-12 12:44:20+00:00\n",
"6 Rollout -0.2645 4.696591 2025-11-12 12:42:15+00:00\n",
"7 Square 42.1850 4.696591 2025-11-12 12:42:15+00:00\n",
"8 Counter -37.8385 4.696591 2025-11-12 12:42:15+00:00\n",
"9 Square 2.8880 -70.845157 2025-11-11 23:00:48+00:00\n",
"10 Rollout 18.7945 -70.845157 2025-11-11 23:00:48+00:00\n",
"11 Counter -12.6565 -70.845157 2025-11-11 23:00:48+00:00\n",
"12 Rollout 17.7415 -71.894590 2025-11-11 23:00:18+00:00\n",
"13 Counter -11.1570 -71.894590 2025-11-11 23:00:18+00:00\n",
"14 Square 2.1610 -71.894590 2025-11-11 23:00:18+00:00\n",
"15 Square -2.0490 -67.033953 2025-11-11 22:59:48+00:00\n",
"16 Rollout 16.5365 -67.033953 2025-11-11 22:59:48+00:00\n",
"17 Counter -15.2205 -67.033953 2025-11-11 22:59:48+00:00\n",
"18 Counter -11.7930 -70.514462 2025-11-11 22:59:18+00:00\n",
"19 Square -4.3350 -70.514462 2025-11-11 22:59:18+00:00\n",
"20 Rollout 16.3065 -70.514462 2025-11-11 22:59:18+00:00\n",
"21 Square 0.6840 -72.523279 2025-11-11 22:58:48+00:00\n",
"22 Counter -9.2570 -72.523279 2025-11-11 22:58:48+00:00\n",
"23 Rollout 14.9965 -72.523279 2025-11-11 22:58:48+00:00\n",
"24 Square 1.1700 -72.831684 2025-11-11 22:58:18+00:00\n",
"25 Counter -7.0635 -72.831684 2025-11-11 22:58:18+00:00\n",
"26 Rollout 10.9875 -72.831684 2025-11-11 22:58:18+00:00\n",
"27 Counter -2.0110 -77.865944 2025-11-11 22:57:48+00:00\n",
"28 Rollout 10.4545 -77.865944 2025-11-11 22:57:48+00:00\n",
"29 Square -0.2070 -77.865944 2025-11-11 22:57:48+00:00"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>variable</th>\n",
" <th>value</th>\n",
" <th>prediction</th>\n",
" <th>timestamp</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Square</td>\n",
" <td>42.2950</td>\n",
" <td>-3.018465</td>\n",
" <td>2025-11-12 12:44:50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Rollout</td>\n",
" <td>1.8610</td>\n",
" <td>-3.018465</td>\n",
" <td>2025-11-12 12:44:50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Counter</td>\n",
" <td>-45.0980</td>\n",
" <td>-3.018465</td>\n",
" <td>2025-11-12 12:44:50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Rollout</td>\n",
" <td>0.3970</td>\n",
" <td>2.341423</td>\n",
" <td>2025-11-12 12:44:20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Counter</td>\n",
" <td>-40.0260</td>\n",
" <td>2.341423</td>\n",
" <td>2025-11-12 12:44:20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Square</td>\n",
" <td>43.3190</td>\n",
" <td>2.341423</td>\n",
" <td>2025-11-12 12:44:20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Rollout</td>\n",
" <td>-0.2645</td>\n",
" <td>4.696591</td>\n",
" <td>2025-11-12 12:42:15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Square</td>\n",
" <td>42.1850</td>\n",
" <td>4.696591</td>\n",
" <td>2025-11-12 12:42:15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Counter</td>\n",
" <td>-37.8385</td>\n",
" <td>4.696591</td>\n",
" <td>2025-11-12 12:42:15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Square</td>\n",
" <td>2.8880</td>\n",
" <td>-70.845157</td>\n",
" <td>2025-11-11 23:00:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>Rollout</td>\n",
" <td>18.7945</td>\n",
" <td>-70.845157</td>\n",
" <td>2025-11-11 23:00:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>Counter</td>\n",
" <td>-12.6565</td>\n",
" <td>-70.845157</td>\n",
" <td>2025-11-11 23:00:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>Rollout</td>\n",
" <td>17.7415</td>\n",
" <td>-71.894590</td>\n",
" <td>2025-11-11 23:00:18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>Counter</td>\n",
" <td>-11.1570</td>\n",
" <td>-71.894590</td>\n",
" <td>2025-11-11 23:00:18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>Square</td>\n",
" <td>2.1610</td>\n",
" <td>-71.894590</td>\n",
" <td>2025-11-11 23:00:18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>Square</td>\n",
" <td>-2.0490</td>\n",
" <td>-67.033953</td>\n",
" <td>2025-11-11 22:59:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>Rollout</td>\n",
" <td>16.5365</td>\n",
" <td>-67.033953</td>\n",
" <td>2025-11-11 22:59:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>Counter</td>\n",
" <td>-15.2205</td>\n",
" <td>-67.033953</td>\n",
" <td>2025-11-11 22:59:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>Counter</td>\n",
" <td>-11.7930</td>\n",
" <td>-70.514462</td>\n",
" <td>2025-11-11 22:59:18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>Square</td>\n",
" <td>-4.3350</td>\n",
" <td>-70.514462</td>\n",
" <td>2025-11-11 22:59:18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>Rollout</td>\n",
" <td>16.3065</td>\n",
" <td>-70.514462</td>\n",
" <td>2025-11-11 22:59:18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>Square</td>\n",
" <td>0.6840</td>\n",
" <td>-72.523279</td>\n",
" <td>2025-11-11 22:58:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>Counter</td>\n",
" <td>-9.2570</td>\n",
" <td>-72.523279</td>\n",
" <td>2025-11-11 22:58:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>Rollout</td>\n",
" <td>14.9965</td>\n",
" <td>-72.523279</td>\n",
" <td>2025-11-11 22:58:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>Square</td>\n",
" <td>1.1700</td>\n",
" <td>-72.831684</td>\n",
" <td>2025-11-11 22:58:18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>Counter</td>\n",
" <td>-7.0635</td>\n",
" <td>-72.831684</td>\n",
" <td>2025-11-11 22:58:18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>Rollout</td>\n",
" <td>10.9875</td>\n",
" <td>-72.831684</td>\n",
" <td>2025-11-11 22:58:18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>Counter</td>\n",
" <td>-2.0110</td>\n",
" <td>-77.865944</td>\n",
" <td>2025-11-11 22:57:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>Rollout</td>\n",
" <td>10.4545</td>\n",
" <td>-77.865944</td>\n",
" <td>2025-11-11 22:57:48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>Square</td>\n",
" <td>-0.2070</td>\n",
" <td>-77.865944</td>\n",
" <td>2025-11-11 22:57:48</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" variable value prediction timestamp\n",
"0 Square 42.2950 -3.018465 2025-11-12 12:44:50\n",
"1 Rollout 1.8610 -3.018465 2025-11-12 12:44:50\n",
"2 Counter -45.0980 -3.018465 2025-11-12 12:44:50\n",
"3 Rollout 0.3970 2.341423 2025-11-12 12:44:20\n",
"4 Counter -40.0260 2.341423 2025-11-12 12:44:20\n",
"5 Square 43.3190 2.341423 2025-11-12 12:44:20\n",
"6 Rollout -0.2645 4.696591 2025-11-12 12:42:15\n",
"7 Square 42.1850 4.696591 2025-11-12 12:42:15\n",
"8 Counter -37.8385 4.696591 2025-11-12 12:42:15\n",
"9 Square 2.8880 -70.845157 2025-11-11 23:00:48\n",
"10 Rollout 18.7945 -70.845157 2025-11-11 23:00:48\n",
"11 Counter -12.6565 -70.845157 2025-11-11 23:00:48\n",
"12 Rollout 17.7415 -71.894590 2025-11-11 23:00:18\n",
"13 Counter -11.1570 -71.894590 2025-11-11 23:00:18\n",
"14 Square 2.1610 -71.894590 2025-11-11 23:00:18\n",
"15 Square -2.0490 -67.033953 2025-11-11 22:59:48\n",
"16 Rollout 16.5365 -67.033953 2025-11-11 22:59:48\n",
"17 Counter -15.2205 -67.033953 2025-11-11 22:59:48\n",
"18 Counter -11.7930 -70.514462 2025-11-11 22:59:18\n",
"19 Square -4.3350 -70.514462 2025-11-11 22:59:18\n",
"20 Rollout 16.3065 -70.514462 2025-11-11 22:59:18\n",
"21 Square 0.6840 -72.523279 2025-11-11 22:58:48\n",
"22 Counter -9.2570 -72.523279 2025-11-11 22:58:48\n",
"23 Rollout 14.9965 -72.523279 2025-11-11 22:58:48\n",
"24 Square 1.1700 -72.831684 2025-11-11 22:58:18\n",
"25 Counter -7.0635 -72.831684 2025-11-11 22:58:18\n",
"26 Rollout 10.9875 -72.831684 2025-11-11 22:58:18\n",
"27 Counter -2.0110 -77.865944 2025-11-11 22:57:48\n",
"28 Rollout 10.4545 -77.865944 2025-11-11 22:57:48\n",
"29 Square -0.2070 -77.865944 2025-11-11 22:57:48"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from pandas import DataFrame, to_datetime\n",
"\n",
"query_data = \"\"\"\n",
"select ld.variable, ld.value, p.prediction, p.\"timestamp\"\n",
"from sientia_data.laborious_data ld\n",
" right join sientia_data.predictions p \n",
" on ld.timestamp = p.timestamp\n",
" and ld.model_id = p.model_id\n",
" where\n",
" ld.model_id = '1'\n",
" order by\n",
" ld.created_at desc limit 30;\n",
"\"\"\"\n",
"\n",
"input_data = {\n",
" \"query\": query_data,\n",
" \"metadata\": {}\n",
"}\n",
"\n",
"\n",
"raw_data = DataFrame(await postgres.load_custom_query(\n",
" input_data))\n",
"\n",
"raw_data['timestamp'] = to_datetime(raw_data['timestamp'])\n",
"raw_data['timestamp'] = raw_data['timestamp'].dt.strftime('%Y-%m-%d %H:%M:%S')\n",
"\n",
"display(raw_data)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "297f648f",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>timestamp</th>\n",
" <th>prediction</th>\n",
" <th>Counter</th>\n",
" <th>Rollout</th>\n",
" <th>Square</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2025-11-11 22:57:48</td>\n",
" <td>-77.865944</td>\n",
" <td>-2.0110</td>\n",
" <td>10.4545</td>\n",
" <td>-0.207</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2025-11-11 22:58:18</td>\n",
" <td>-72.831684</td>\n",
" <td>-7.0635</td>\n",
" <td>10.9875</td>\n",
" <td>1.170</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2025-11-11 22:58:48</td>\n",
" <td>-72.523279</td>\n",
" <td>-9.2570</td>\n",
" <td>14.9965</td>\n",
" <td>0.684</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2025-11-11 22:59:18</td>\n",
" <td>-70.514462</td>\n",
" <td>-11.7930</td>\n",
" <td>16.3065</td>\n",
" <td>-4.335</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2025-11-11 22:59:48</td>\n",
" <td>-67.033953</td>\n",
" <td>-15.2205</td>\n",
" <td>16.5365</td>\n",
" <td>-2.049</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2025-11-11 23:00:18</td>\n",
" <td>-71.894590</td>\n",
" <td>-11.1570</td>\n",
" <td>17.7415</td>\n",
" <td>2.161</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>2025-11-11 23:00:48</td>\n",
" <td>-70.845157</td>\n",
" <td>-12.6565</td>\n",
" <td>18.7945</td>\n",
" <td>2.888</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>2025-11-12 12:42:15</td>\n",
" <td>4.696591</td>\n",
" <td>-37.8385</td>\n",
" <td>-0.2645</td>\n",
" <td>42.185</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>2025-11-12 12:44:20</td>\n",
" <td>2.341423</td>\n",
" <td>-40.0260</td>\n",
" <td>0.3970</td>\n",
" <td>43.319</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>2025-11-12 12:44:50</td>\n",
" <td>-3.018465</td>\n",
" <td>-45.0980</td>\n",
" <td>1.8610</td>\n",
" <td>42.295</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" timestamp prediction Counter Rollout Square\n",
"0 2025-11-11 22:57:48 -77.865944 -2.0110 10.4545 -0.207\n",
"1 2025-11-11 22:58:18 -72.831684 -7.0635 10.9875 1.170\n",
"2 2025-11-11 22:58:48 -72.523279 -9.2570 14.9965 0.684\n",
"3 2025-11-11 22:59:18 -70.514462 -11.7930 16.3065 -4.335\n",
"4 2025-11-11 22:59:48 -67.033953 -15.2205 16.5365 -2.049\n",
"5 2025-11-11 23:00:18 -71.894590 -11.1570 17.7415 2.161\n",
"6 2025-11-11 23:00:48 -70.845157 -12.6565 18.7945 2.888\n",
"7 2025-11-12 12:42:15 4.696591 -37.8385 -0.2645 42.185\n",
"8 2025-11-12 12:44:20 2.341423 -40.0260 0.3970 43.319\n",
"9 2025-11-12 12:44:50 -3.018465 -45.0980 1.8610 42.295"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from pandas import merge, pivot\n",
"\n",
"raw_data.drop_duplicates(subset=[\"timestamp\", \"prediction\", \"variable\"], inplace=True, keep=\"first\")\n",
"data = raw_data.pivot(index=[\"timestamp\", \"prediction\"], columns=\"variable\", values=\"value\")\n",
"\n",
"data.columns.name = None\n",
"data.reset_index(inplace=True)\n",
"display(data)\n",
"\n",
"\n",
"drift_methods = ['kolmogorov_smirnov']#, 'jensen_shannon', 'wasserstein']\n",
"chunk_period = 's'\n",
"target_col = \"Square\"\n",
"timestamp_col = \"timestamp\"\n",
"\n",
"data.to_csv(\"data.csv\", index=False)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "9ab4774a",
"metadata": {},
"outputs": [],
"source": [
"from mlflow.tracking import MlflowClient\n",
"from os import environ\n",
"\n",
"environ['MLFLOW_TRACKING_USERNAME'] = 'aignosi'\n",
"environ['MLFLOW_TRACKING_PASSWORD'] = '1L0FP50j3ncp123'\n",
"environ['MLFLOW_TRACKING_URI'] = 'http://localhost:5080'\n",
"mlflow_client = MlflowClient()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "e8427625",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"run_id = '9e9fa748822c44ab92dd769d6a45c4f4'\n",
"output_dir = './tmp/model'\n",
"\n",
"artifacts = mlflow_client.list_artifacts(run_id)\n",
"paths = [artifact.path for artifact in artifacts]\n",
"\n",
"any(artifact.path == 'retrain_data.csv' for artifact in artifacts)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "cf4ddf41",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>timestamp</th>\n",
" <th>Counter</th>\n",
" <th>Rollout</th>\n",
" <th>Square</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2025-11-10 18:58:39</td>\n",
" <td>13.5970</td>\n",
" <td>-52.4500</td>\n",
" <td>43.381</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2025-11-10 18:58:49</td>\n",
" <td>15.0660</td>\n",
" <td>-50.0240</td>\n",
" <td>45.813</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2025-11-10 18:58:54</td>\n",
" <td>14.2780</td>\n",
" <td>-49.4810</td>\n",
" <td>47.677</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2025-11-10 18:59:04</td>\n",
" <td>14.2080</td>\n",
" <td>-51.8015</td>\n",
" <td>48.995</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2025-11-10 18:59:09</td>\n",
" <td>16.3530</td>\n",
" <td>-52.6850</td>\n",
" <td>47.745</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2025-11-10 18:59:19</td>\n",
" <td>15.5415</td>\n",
" <td>-53.5625</td>\n",
" <td>48.327</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>2025-11-10 18:59:24</td>\n",
" <td>16.8580</td>\n",
" <td>-53.6960</td>\n",
" <td>47.160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>2025-11-10 18:59:34</td>\n",
" <td>14.9745</td>\n",
" <td>-54.7510</td>\n",
" <td>48.480</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>2025-11-10 18:59:39</td>\n",
" <td>12.3020</td>\n",
" <td>-53.4330</td>\n",
" <td>48.631</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>2025-11-10 18:59:49</td>\n",
" <td>12.5640</td>\n",
" <td>-52.9805</td>\n",
" <td>50.130</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" timestamp Counter Rollout Square\n",
"0 2025-11-10 18:58:39 13.5970 -52.4500 43.381\n",
"1 2025-11-10 18:58:49 15.0660 -50.0240 45.813\n",
"2 2025-11-10 18:58:54 14.2780 -49.4810 47.677\n",
"3 2025-11-10 18:59:04 14.2080 -51.8015 48.995\n",
"4 2025-11-10 18:59:09 16.3530 -52.6850 47.745\n",
"5 2025-11-10 18:59:19 15.5415 -53.5625 48.327\n",
"6 2025-11-10 18:59:24 16.8580 -53.6960 47.160\n",
"7 2025-11-10 18:59:34 14.9745 -54.7510 48.480\n",
"8 2025-11-10 18:59:39 12.3020 -53.4330 48.631\n",
"9 2025-11-10 18:59:49 12.5640 -52.9805 50.130"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import mlflow\n",
"from io import StringIO\n",
"from pandas import read_csv\n",
"\n",
"if 'retrain_data.csv' in paths:\n",
" artifact_path = 'retrain_data.csv'\n",
"elif 'train_data.csv' in paths:\n",
" artifact_path = 'train_data.csv'\n",
"else:\n",
" raise RuntimeError(\n",
" f\"Could not find 'train_data.csv' or 'retrain_data.csv' for run_id '{run_id}'.\\n\"\n",
" )\n",
"\n",
"# Carregar diretamente na memória como string\n",
"artifact_content = mlflow.artifacts.load_text(\n",
" f\"runs:/{run_id}/{artifact_path}\"\n",
")\n",
"\n",
"reference_df = read_csv(StringIO(artifact_content))\n",
"\n",
"reference_df.drop(columns=['timestamp.1'], inplace=True)\n",
"\n",
"reference_df['timestamp'] = to_datetime(reference_df['timestamp'])\n",
"reference_df['timestamp'] = reference_df['timestamp'].dt.strftime('%Y-%m-%d %H:%M:%S')\n",
"\n",
"display(reference_df)\n",
"\n",
"reference_df.to_csv(\"reference_df.csv\", index=False)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "d375752b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas._libs.tslibs.timestamps.Timestamp'>\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/grezewave/Documents/projects/sientia/sientia-dataops-orchestrator_temporal/venv/lib/python3.11/site-packages/numpy/core/_methods.py:206: RuntimeWarning: Degrees of freedom <= 0 for slice\n",
" ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,\n",
"/home/grezewave/Documents/projects/sientia/sientia-dataops-orchestrator_temporal/venv/lib/python3.11/site-packages/numpy/core/_methods.py:198: RuntimeWarning: invalid value encountered in scalar divide\n",
" ret = ret.dtype.type(ret / rcount)\n",
"/home/grezewave/Documents/projects/sientia/sientia-dataops-orchestrator_temporal/venv/lib/python3.11/site-packages/numpy/core/_methods.py:206: RuntimeWarning: Degrees of freedom <= 0 for slice\n",
" ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,\n",
"/home/grezewave/Documents/projects/sientia/sientia-dataops-orchestrator_temporal/venv/lib/python3.11/site-packages/numpy/core/_methods.py:198: RuntimeWarning: invalid value encountered in scalar divide\n",
" ret = ret.dtype.type(ret / rcount)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>timestamp</th>\n",
" <th>feature</th>\n",
" <th>metric</th>\n",
" <th>statistic</th>\n",
" <th>p_value</th>\n",
" <th>alert</th>\n",
" <th>chunk_index</th>\n",
" <th>chunk_start_date</th>\n",
" <th>chunk_end_date</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2025-11-10 18:58:00+0000</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>3.000000e-01</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>2025-11-10 18:58</td>\n",
" <td>2025-11-10 18:58:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2025-11-10 18:59:00+0000</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.285714e-01</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2025-11-10 18:59</td>\n",
" <td>2025-11-10 18:59:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2025-11-11 22:57:00+0000</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>2025-11-11 22:57</td>\n",
" <td>2025-11-11 22:57:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2025-11-11 22:58:00+0000</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2025-11-11 22:58</td>\n",
" <td>2025-11-11 22:58:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2025-11-11 22:59:00+0000</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2025-11-11 22:59</td>\n",
" <td>2025-11-11 22:59:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2025-11-11 23:00:00+0000</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>3</td>\n",
" <td>2025-11-11 23:00</td>\n",
" <td>2025-11-11 23:00:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>2025-11-12 12:42:00+0000</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2025-11-12 12:42</td>\n",
" <td>2025-11-12 12:42:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>2025-11-12 12:44:00+0000</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2025-11-12 12:44</td>\n",
" <td>2025-11-12 12:44:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>2025-11-10 18:58:00+0000</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>6.000000e-01</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>2025-11-10 18:58</td>\n",
" <td>2025-11-10 18:58:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>2025-11-10 18:59:00+0000</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>2.571429e-01</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2025-11-10 18:59</td>\n",
" <td>2025-11-10 18:59:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>2025-11-11 22:57:00+0000</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>2025-11-11 22:57</td>\n",
" <td>2025-11-11 22:57:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>2025-11-11 22:58:00+0000</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2025-11-11 22:58</td>\n",
" <td>2025-11-11 22:58:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>2025-11-11 22:59:00+0000</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2025-11-11 22:59</td>\n",
" <td>2025-11-11 22:59:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>2025-11-11 23:00:00+0000</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>3</td>\n",
" <td>2025-11-11 23:00</td>\n",
" <td>2025-11-11 23:00:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>2025-11-12 12:42:00+0000</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2025-11-12 12:42</td>\n",
" <td>2025-11-12 12:42:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>2025-11-12 12:44:00+0000</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2025-11-12 12:44</td>\n",
" <td>2025-11-12 12:44:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>2025-11-10 18:58:00+0000</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>2.015043e-16</td>\n",
" <td>3.748123e-17</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>2025-11-10 18:58</td>\n",
" <td>2025-11-10 18:58:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>2025-11-10 18:59:00+0000</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>2.493220e-16</td>\n",
" <td>3.998584e-17</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2025-11-10 18:59</td>\n",
" <td>2025-11-10 18:59:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>2025-11-11 22:57:00+0000</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.432145e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>2025-11-11 22:57</td>\n",
" <td>2025-11-11 22:57:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>2025-11-11 22:58:00+0000</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.234840e-14</td>\n",
" <td>2.299811e-15</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2025-11-11 22:58</td>\n",
" <td>2025-11-11 22:58:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>2025-11-11 22:59:00+0000</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>7.944109e-15</td>\n",
" <td>0.000000e+00</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2025-11-11 22:59</td>\n",
" <td>2025-11-11 22:59:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>2025-11-11 23:00:00+0000</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>7.524768e-15</td>\n",
" <td>4.193410e-16</td>\n",
" <td>True</td>\n",
" <td>3</td>\n",
" <td>2025-11-11 23:00</td>\n",
" <td>2025-11-11 23:00:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>2025-11-12 12:42:00+0000</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.004859e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2025-11-12 12:42</td>\n",
" <td>2025-11-12 12:42:59.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>2025-11-12 12:44:00+0000</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.004859e-14</td>\n",
" <td>0.000000e+00</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2025-11-12 12:44</td>\n",
" <td>2025-11-12 12:44:59.999999999</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" timestamp feature metric statistic \\\n",
"0 2025-11-10 18:58:00+0000 Counter kolmogorov_smirnov 3.000000e-01 \n",
"1 2025-11-10 18:59:00+0000 Counter kolmogorov_smirnov 1.285714e-01 \n",
"2 2025-11-11 22:57:00+0000 Counter kolmogorov_smirnov 1.000000e+00 \n",
"3 2025-11-11 22:58:00+0000 Counter kolmogorov_smirnov 1.000000e+00 \n",
"4 2025-11-11 22:59:00+0000 Counter kolmogorov_smirnov 1.000000e+00 \n",
"5 2025-11-11 23:00:00+0000 Counter kolmogorov_smirnov 1.000000e+00 \n",
"6 2025-11-12 12:42:00+0000 Counter kolmogorov_smirnov 1.000000e+00 \n",
"7 2025-11-12 12:44:00+0000 Counter kolmogorov_smirnov 1.000000e+00 \n",
"8 2025-11-10 18:58:00+0000 Rollout kolmogorov_smirnov 6.000000e-01 \n",
"9 2025-11-10 18:59:00+0000 Rollout kolmogorov_smirnov 2.571429e-01 \n",
"10 2025-11-11 22:57:00+0000 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"11 2025-11-11 22:58:00+0000 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"12 2025-11-11 22:59:00+0000 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"13 2025-11-11 23:00:00+0000 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"14 2025-11-12 12:42:00+0000 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"15 2025-11-12 12:44:00+0000 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"16 2025-11-10 18:58:00+0000 multivariate multivariate 2.015043e-16 \n",
"17 2025-11-10 18:59:00+0000 multivariate multivariate 2.493220e-16 \n",
"18 2025-11-11 22:57:00+0000 multivariate multivariate 1.432145e-14 \n",
"19 2025-11-11 22:58:00+0000 multivariate multivariate 1.234840e-14 \n",
"20 2025-11-11 22:59:00+0000 multivariate multivariate 7.944109e-15 \n",
"21 2025-11-11 23:00:00+0000 multivariate multivariate 7.524768e-15 \n",
"22 2025-11-12 12:42:00+0000 multivariate multivariate 1.004859e-14 \n",
"23 2025-11-12 12:44:00+0000 multivariate multivariate 1.004859e-14 \n",
"\n",
" p_value alert chunk_index chunk_start_date \\\n",
"0 NaN False 0 2025-11-10 18:58 \n",
"1 NaN False 1 2025-11-10 18:59 \n",
"2 NaN True 0 2025-11-11 22:57 \n",
"3 NaN True 1 2025-11-11 22:58 \n",
"4 NaN True 2 2025-11-11 22:59 \n",
"5 NaN True 3 2025-11-11 23:00 \n",
"6 NaN True 4 2025-11-12 12:42 \n",
"7 NaN True 5 2025-11-12 12:44 \n",
"8 NaN False 0 2025-11-10 18:58 \n",
"9 NaN False 1 2025-11-10 18:59 \n",
"10 NaN True 0 2025-11-11 22:57 \n",
"11 NaN True 1 2025-11-11 22:58 \n",
"12 NaN True 2 2025-11-11 22:59 \n",
"13 NaN True 3 2025-11-11 23:00 \n",
"14 NaN True 4 2025-11-12 12:42 \n",
"15 NaN True 5 2025-11-12 12:44 \n",
"16 3.748123e-17 False 0 2025-11-10 18:58 \n",
"17 3.998584e-17 False 1 2025-11-10 18:59 \n",
"18 NaN True 0 2025-11-11 22:57 \n",
"19 2.299811e-15 True 1 2025-11-11 22:58 \n",
"20 0.000000e+00 True 2 2025-11-11 22:59 \n",
"21 4.193410e-16 True 3 2025-11-11 23:00 \n",
"22 NaN True 4 2025-11-12 12:42 \n",
"23 0.000000e+00 True 5 2025-11-12 12:44 \n",
"\n",
" chunk_end_date \n",
"0 2025-11-10 18:58:59.999999999 \n",
"1 2025-11-10 18:59:59.999999999 \n",
"2 2025-11-11 22:57:59.999999999 \n",
"3 2025-11-11 22:58:59.999999999 \n",
"4 2025-11-11 22:59:59.999999999 \n",
"5 2025-11-11 23:00:59.999999999 \n",
"6 2025-11-12 12:42:59.999999999 \n",
"7 2025-11-12 12:44:59.999999999 \n",
"8 2025-11-10 18:58:59.999999999 \n",
"9 2025-11-10 18:59:59.999999999 \n",
"10 2025-11-11 22:57:59.999999999 \n",
"11 2025-11-11 22:58:59.999999999 \n",
"12 2025-11-11 22:59:59.999999999 \n",
"13 2025-11-11 23:00:59.999999999 \n",
"14 2025-11-12 12:42:59.999999999 \n",
"15 2025-11-12 12:44:59.999999999 \n",
"16 2025-11-10 18:58:59.999999999 \n",
"17 2025-11-10 18:59:59.999999999 \n",
"18 2025-11-11 22:57:59.999999999 \n",
"19 2025-11-11 22:58:59.999999999 \n",
"20 2025-11-11 22:59:59.999999999 \n",
"21 2025-11-11 23:00:59.999999999 \n",
"22 2025-11-12 12:42:59.999999999 \n",
"23 2025-11-12 12:44:59.999999999 "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"\n",
"\n",
"from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ\n",
"\n",
"\n",
"univariate_drift = model.detect_univariate_drift(\n",
" reference_df=reference_df,\n",
" analysis_df=data,\n",
" features=config['features'],\n",
" timestamp_col=timestamp_col,\n",
" methods=drift_methods,\n",
" chunk_period=\"min\"\n",
")\n",
"multivariate_drift = model.detect_multivariate_drift(\n",
" reference_df=reference_df,\n",
" analysis_df=data,\n",
" features=config['features'],\n",
" timestamp_col=timestamp_col,\n",
" chunk_period=\"min\"\n",
")\n",
"\n",
"drift = model.get_drift_metrics_dataframe(\n",
" univariate_drift=univariate_drift,\n",
" multivariate_drift=multivariate_drift\n",
")\n",
"drift.drop_duplicates(subset=[\"timestamp\", \"feature\", \"metric\"], inplace=True, keep=\"first\")\n",
"drift.reset_index(drop=True, inplace=True)\n",
"\n",
"drift['timestamp'] = to_datetime(drift['timestamp'])\n",
"print(type(drift['timestamp'].iloc[0]))\n",
"\n",
"# Add timezone UTC to timestamp\n",
"drift['timestamp'] = drift['timestamp'].dt.tz_localize('UTC')\n",
"drift['timestamp'] = drift['timestamp'].dt.strftime(DATETIME_FORMAT_WITH_TZ)\n",
"\n",
"display(drift)\n",
"drift.to_csv(\"drift.csv\", index=False)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "d30f6475",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>timestamp</th>\n",
" <th>feature</th>\n",
" <th>metric</th>\n",
" <th>statistic</th>\n",
" <th>p_value</th>\n",
" <th>alert</th>\n",
" <th>chunk_index</th>\n",
" <th>chunk_start_date</th>\n",
" <th>chunk_end_date</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>2025-11-11 11:55:18</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>2025-11-11 11:55:18</td>\n",
" <td>2025-11-11 11:55:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>2025-11-11 11:55:48</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2025-11-11 11:55:48</td>\n",
" <td>2025-11-11 11:55:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>2025-11-11 11:56:18</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>2025-11-11 11:56:18</td>\n",
" <td>2025-11-11 11:56:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>2025-11-11 11:56:48</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>3</td>\n",
" <td>2025-11-11 11:56:48</td>\n",
" <td>2025-11-11 11:56:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>2025-11-11 11:57:18</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2025-11-11 11:57:18</td>\n",
" <td>2025-11-11 11:57:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>2025-11-11 11:57:48</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>5</td>\n",
" <td>2025-11-11 11:57:48</td>\n",
" <td>2025-11-11 11:57:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>2025-11-11 11:58:18</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>6</td>\n",
" <td>2025-11-11 11:58:18</td>\n",
" <td>2025-11-11 11:58:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>2025-11-11 11:58:48</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>7</td>\n",
" <td>2025-11-11 11:58:48</td>\n",
" <td>2025-11-11 11:58:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>2025-11-11 11:59:18</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>8</td>\n",
" <td>2025-11-11 11:59:18</td>\n",
" <td>2025-11-11 11:59:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>2025-11-11 11:59:48</td>\n",
" <td>Counter</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>9</td>\n",
" <td>2025-11-11 11:59:48</td>\n",
" <td>2025-11-11 11:59:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>2025-11-11 11:55:18</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>2025-11-11 11:55:18</td>\n",
" <td>2025-11-11 11:55:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>2025-11-11 11:55:48</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>2025-11-11 11:55:48</td>\n",
" <td>2025-11-11 11:55:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>2025-11-11 11:56:18</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>2025-11-11 11:56:18</td>\n",
" <td>2025-11-11 11:56:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>2025-11-11 11:56:48</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>3</td>\n",
" <td>2025-11-11 11:56:48</td>\n",
" <td>2025-11-11 11:56:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>2025-11-11 11:57:18</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>4</td>\n",
" <td>2025-11-11 11:57:18</td>\n",
" <td>2025-11-11 11:57:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>2025-11-11 11:57:48</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>5</td>\n",
" <td>2025-11-11 11:57:48</td>\n",
" <td>2025-11-11 11:57:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>2025-11-11 11:58:18</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>6</td>\n",
" <td>2025-11-11 11:58:18</td>\n",
" <td>2025-11-11 11:58:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>2025-11-11 11:58:48</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>7</td>\n",
" <td>2025-11-11 11:58:48</td>\n",
" <td>2025-11-11 11:58:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
" <td>2025-11-11 11:59:18</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>8</td>\n",
" <td>2025-11-11 11:59:18</td>\n",
" <td>2025-11-11 11:59:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>2025-11-11 11:59:48</td>\n",
" <td>Rollout</td>\n",
" <td>kolmogorov_smirnov</td>\n",
" <td>1.000000e+00</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>9</td>\n",
" <td>2025-11-11 11:59:48</td>\n",
" <td>2025-11-11 11:59:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50</th>\n",
" <td>2025-11-11 11:55:18</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.517720e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>2025-11-11 11:55:18</td>\n",
" <td>2025-11-11 11:55:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51</th>\n",
" <td>2025-11-11 11:55:48</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.588822e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2025-11-11 11:55:48</td>\n",
" <td>2025-11-11 11:55:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>2025-11-11 11:56:18</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.432145e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>2</td>\n",
" <td>2025-11-11 11:56:18</td>\n",
" <td>2025-11-11 11:56:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53</th>\n",
" <td>2025-11-11 11:56:48</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.421085e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>3</td>\n",
" <td>2025-11-11 11:56:48</td>\n",
" <td>2025-11-11 11:56:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>54</th>\n",
" <td>2025-11-11 11:57:18</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.421085e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>4</td>\n",
" <td>2025-11-11 11:57:18</td>\n",
" <td>2025-11-11 11:57:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>55</th>\n",
" <td>2025-11-11 11:57:48</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.776357e-15</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>5</td>\n",
" <td>2025-11-11 11:57:48</td>\n",
" <td>2025-11-11 11:57:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56</th>\n",
" <td>2025-11-11 11:58:18</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>7.324107e-15</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>6</td>\n",
" <td>2025-11-11 11:58:18</td>\n",
" <td>2025-11-11 11:58:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>2025-11-11 11:58:48</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.464821e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>7</td>\n",
" <td>2025-11-11 11:58:48</td>\n",
" <td>2025-11-11 11:58:48.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58</th>\n",
" <td>2025-11-11 11:59:18</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.551137e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>8</td>\n",
" <td>2025-11-11 11:59:18</td>\n",
" <td>2025-11-11 11:59:18.999999999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>59</th>\n",
" <td>2025-11-11 11:59:48</td>\n",
" <td>multivariate</td>\n",
" <td>multivariate</td>\n",
" <td>1.427317e-14</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>9</td>\n",
" <td>2025-11-11 11:59:48</td>\n",
" <td>2025-11-11 11:59:48.999999999</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" timestamp feature metric statistic \\\n",
"10 2025-11-11 11:55:18 Counter kolmogorov_smirnov 1.000000e+00 \n",
"11 2025-11-11 11:55:48 Counter kolmogorov_smirnov 1.000000e+00 \n",
"12 2025-11-11 11:56:18 Counter kolmogorov_smirnov 1.000000e+00 \n",
"13 2025-11-11 11:56:48 Counter kolmogorov_smirnov 1.000000e+00 \n",
"14 2025-11-11 11:57:18 Counter kolmogorov_smirnov 1.000000e+00 \n",
"15 2025-11-11 11:57:48 Counter kolmogorov_smirnov 1.000000e+00 \n",
"16 2025-11-11 11:58:18 Counter kolmogorov_smirnov 1.000000e+00 \n",
"17 2025-11-11 11:58:48 Counter kolmogorov_smirnov 1.000000e+00 \n",
"18 2025-11-11 11:59:18 Counter kolmogorov_smirnov 1.000000e+00 \n",
"19 2025-11-11 11:59:48 Counter kolmogorov_smirnov 1.000000e+00 \n",
"30 2025-11-11 11:55:18 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"31 2025-11-11 11:55:48 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"32 2025-11-11 11:56:18 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"33 2025-11-11 11:56:48 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"34 2025-11-11 11:57:18 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"35 2025-11-11 11:57:48 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"36 2025-11-11 11:58:18 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"37 2025-11-11 11:58:48 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"38 2025-11-11 11:59:18 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"39 2025-11-11 11:59:48 Rollout kolmogorov_smirnov 1.000000e+00 \n",
"50 2025-11-11 11:55:18 multivariate multivariate 1.517720e-14 \n",
"51 2025-11-11 11:55:48 multivariate multivariate 1.588822e-14 \n",
"52 2025-11-11 11:56:18 multivariate multivariate 1.432145e-14 \n",
"53 2025-11-11 11:56:48 multivariate multivariate 1.421085e-14 \n",
"54 2025-11-11 11:57:18 multivariate multivariate 1.421085e-14 \n",
"55 2025-11-11 11:57:48 multivariate multivariate 1.776357e-15 \n",
"56 2025-11-11 11:58:18 multivariate multivariate 7.324107e-15 \n",
"57 2025-11-11 11:58:48 multivariate multivariate 1.464821e-14 \n",
"58 2025-11-11 11:59:18 multivariate multivariate 1.551137e-14 \n",
"59 2025-11-11 11:59:48 multivariate multivariate 1.427317e-14 \n",
"\n",
" p_value alert chunk_index chunk_start_date \\\n",
"10 None False 0 2025-11-11 11:55:18 \n",
"11 None False 1 2025-11-11 11:55:48 \n",
"12 None False 2 2025-11-11 11:56:18 \n",
"13 None False 3 2025-11-11 11:56:48 \n",
"14 None False 4 2025-11-11 11:57:18 \n",
"15 None False 5 2025-11-11 11:57:48 \n",
"16 None False 6 2025-11-11 11:58:18 \n",
"17 None False 7 2025-11-11 11:58:48 \n",
"18 None False 8 2025-11-11 11:59:18 \n",
"19 None False 9 2025-11-11 11:59:48 \n",
"30 None False 0 2025-11-11 11:55:18 \n",
"31 None False 1 2025-11-11 11:55:48 \n",
"32 None False 2 2025-11-11 11:56:18 \n",
"33 None False 3 2025-11-11 11:56:48 \n",
"34 None False 4 2025-11-11 11:57:18 \n",
"35 None False 5 2025-11-11 11:57:48 \n",
"36 None False 6 2025-11-11 11:58:18 \n",
"37 None False 7 2025-11-11 11:58:48 \n",
"38 None False 8 2025-11-11 11:59:18 \n",
"39 None False 9 2025-11-11 11:59:48 \n",
"50 NaN True 0 2025-11-11 11:55:18 \n",
"51 NaN True 1 2025-11-11 11:55:48 \n",
"52 NaN True 2 2025-11-11 11:56:18 \n",
"53 NaN True 3 2025-11-11 11:56:48 \n",
"54 NaN True 4 2025-11-11 11:57:18 \n",
"55 NaN True 5 2025-11-11 11:57:48 \n",
"56 NaN True 6 2025-11-11 11:58:18 \n",
"57 NaN True 7 2025-11-11 11:58:48 \n",
"58 NaN True 8 2025-11-11 11:59:18 \n",
"59 NaN True 9 2025-11-11 11:59:48 \n",
"\n",
" chunk_end_date \n",
"10 2025-11-11 11:55:18.999999999 \n",
"11 2025-11-11 11:55:48.999999999 \n",
"12 2025-11-11 11:56:18.999999999 \n",
"13 2025-11-11 11:56:48.999999999 \n",
"14 2025-11-11 11:57:18.999999999 \n",
"15 2025-11-11 11:57:48.999999999 \n",
"16 2025-11-11 11:58:18.999999999 \n",
"17 2025-11-11 11:58:48.999999999 \n",
"18 2025-11-11 11:59:18.999999999 \n",
"19 2025-11-11 11:59:48.999999999 \n",
"30 2025-11-11 11:55:18.999999999 \n",
"31 2025-11-11 11:55:48.999999999 \n",
"32 2025-11-11 11:56:18.999999999 \n",
"33 2025-11-11 11:56:48.999999999 \n",
"34 2025-11-11 11:57:18.999999999 \n",
"35 2025-11-11 11:57:48.999999999 \n",
"36 2025-11-11 11:58:18.999999999 \n",
"37 2025-11-11 11:58:48.999999999 \n",
"38 2025-11-11 11:59:18.999999999 \n",
"39 2025-11-11 11:59:48.999999999 \n",
"50 2025-11-11 11:55:18.999999999 \n",
"51 2025-11-11 11:55:48.999999999 \n",
"52 2025-11-11 11:56:18.999999999 \n",
"53 2025-11-11 11:56:48.999999999 \n",
"54 2025-11-11 11:57:18.999999999 \n",
"55 2025-11-11 11:57:48.999999999 \n",
"56 2025-11-11 11:58:18.999999999 \n",
"57 2025-11-11 11:58:48.999999999 \n",
"58 2025-11-11 11:59:18.999999999 \n",
"59 2025-11-11 11:59:48.999999999 "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# drop rows of drift with timestamp in reference data but not in analysis data\n",
"drift_filtered = drift[drift['timestamp'].isin(data['timestamp'])]\n",
"display(drift_filtered)\n",
"\n",
"drift_filtered.to_csv(\"drift_filtered.csv\", index=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "70671022",
"metadata": {},
"outputs": [
{
"ename": "ValueError",
"evalue": "Target column 'Square' not found in DataFrames",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mValueError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[36]\u001b[39m\u001b[32m, line 6\u001b[39m\n\u001b[32m 3\u001b[39m \u001b[38;5;66;03m# rename column square to prediction\u001b[39;00m\n\u001b[32m 4\u001b[39m performance_reference.rename(columns={\u001b[33m'\u001b[39m\u001b[33mSquare\u001b[39m\u001b[33m'\u001b[39m: \u001b[33m'\u001b[39m\u001b[33mprediction\u001b[39m\u001b[33m'\u001b[39m}, inplace=\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[32m----> \u001b[39m\u001b[32m6\u001b[39m real_performance = \u001b[43mmodel\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcalculate_performance\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 7\u001b[39m \u001b[43m \u001b[49m\u001b[43mreference_df\u001b[49m\u001b[43m=\u001b[49m\u001b[43mperformance_reference\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 8\u001b[39m \u001b[43m \u001b[49m\u001b[43manalysis_df\u001b[49m\u001b[43m=\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 9\u001b[39m \u001b[43m \u001b[49m\u001b[43mtarget_col\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtarget_col\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 10\u001b[39m \u001b[43m \u001b[49m\u001b[43mtimestamp_col\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtimestamp_col\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 11\u001b[39m \u001b[43m \u001b[49m\u001b[43mchunk_period\u001b[49m\u001b[43m=\u001b[49m\u001b[43mchunk_period\u001b[49m\n\u001b[32m 12\u001b[39m \u001b[43m)\u001b[49m\n\u001b[32m 14\u001b[39m metrics_df = model.get_calculated_metrics_dataframe(real_performance)\n\u001b[32m 15\u001b[39m display(metrics_df)\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/Documents/projects/sientia/sientia-dataops-orchestrator_temporal/venv/lib/python3.11/site-packages/sientia/ModelAnalysis.py:397\u001b[39m, in \u001b[36mModelAnalysis.calculate_performance\u001b[39m\u001b[34m(self, reference_df, analysis_df, target_col, timestamp_col, metrics, chunk_period)\u001b[39m\n\u001b[32m 395\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(DATAFRAMES_EMPTY_ERROR)\n\u001b[32m 396\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m target_col \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m reference_df.columns \u001b[38;5;129;01mor\u001b[39;00m target_col \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m analysis_df.columns:\n\u001b[32m--> \u001b[39m\u001b[32m397\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mTarget column \u001b[39m\u001b[33m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtarget_col\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33m not found in DataFrames\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m 398\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m timestamp_col \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m reference_df.columns \u001b[38;5;129;01mor\u001b[39;00m timestamp_col \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m analysis_df.columns:\n\u001b[32m 399\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mTimestamp column \u001b[39m\u001b[33m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtimestamp_col\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33m not found in DataFrames\u001b[39m\u001b[33m\"\u001b[39m)\n",
"\u001b[31mValueError\u001b[39m: Target column 'Square' not found in DataFrames"
]
}
],
"source": [
"\n",
"real_performance = model.calculate_performance(\n",
" reference_df=data,\n",
" analysis_df=data,\n",
" target_col=target_col,\n",
" timestamp_col=timestamp_col,\n",
" chunk_period=chunk_period\n",
")\n",
"\n",
"metrics_df = model.get_calculated_metrics_dataframe(real_performance)\n",
"display(metrics_df)\n",
"\n",
"metrics_df.to_csv(\"metrics_df.csv\", index=False)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue View Git Blame Copy Permalink