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

SIENTIAPDE-1646

Browse Source 
SIENTIAPDE-1646 Add new scheduling configurations and remove outdated documentation

- Introduced new scheduling configurations for minimal retrain, drift analysis, and simple metrics in `input_sample.json`.
- Removed obsolete documentation files related to drift analysis and E2E test reports to streamline project resources.
- Updated E2E tests for minimal retrain to enhance reporting and error handling during model retraining processes.
This commit is contained in:
vitor-aignosi
2026-05-11 17:02:08 -03:00
parent 16ea436e45
commit 4989cfcb3c
5 changed files with 182 additions and 131 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
laborious/activities/mlflow.py
View File

@@ -322,9 +322,9 @@ class MLFlow(SientiaMonitoring):
"""
Load the production wrapper and call ``wrapper.predict`` on the prepared feature frame.
The activity normalizes ``NaN`` to ``None`` for JSON-friendly columns, rebuilds a
``timestamp`` column in the internal string format, preserves the original index for
alignment, and records ``response_time`` seconds on the output frame. Non-DataFrame
The activity normalizes ``NaN`` to ``None`` for JSON-friendly columns, sets the row index
the same way as ``retrain_model`` (UTC ``DatetimeIndex`` from ``DATETIME_FORMAT_WITH_TZ``),
restores that index on the prediction frame, and records ``response_time``. Non-DataFrame
predictions are coerced to a single ``prediction`` column.
Args:
@@ -346,14 +346,12 @@ class MLFlow(SientiaMonitoring):
self._debug_dataframe('Input data for prediction:', data, metadata)
input_index = data.index
data.replace(np.nan, None, inplace=True)
data['timestamp'] = data.index
data['timestamp'] = to_datetime(
data['timestamp'], format=DATETIME_FORMAT_WITH_TZ
).dt.strftime(DATETIME_FORMAT)
data.index = pd.DatetimeIndex(
to_datetime(data.index, format=DATETIME_FORMAT_WITH_TZ, utc=True)
)
input_index = data.index
try:
wrapper = self.mlflow_repository.get_cached_model(
@@ -493,14 +491,11 @@ class MLFlow(SientiaMonitoring):
data = data.pivot(index='timestamp', columns='variable', values='value')
data.fillna(np.nan, inplace=True)
data.columns.name = None
data.index.name = None
data['timestamp'] = data.index
data['timestamp'] = to_datetime(
data['timestamp'], format=DATETIME_FORMAT_WITH_TZ
).dt.strftime(DATETIME_FORMAT)
data['timestamp'] = to_datetime(data['timestamp'], format=DATETIME_FORMAT)
data.columns.name = None
data.index = pd.DatetimeIndex(
to_datetime(data.index, format=DATETIME_FORMAT_WITH_TZ, utc=True)
)
target = model_config.get('target')
if target is None: