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

SIENTIAPDE-1222

Browse Source 
Enhance MLFlow data handling by adding timestamp column and improving debug logging

- Added a 'timestamp' column to the input data, converting the index to a datetime format for better tracking of predictions.
- Improved debug logging to provide clearer context by including the input data preview in the log output.
This commit is contained in:
vitor-aignosi
2025-09-17 11:15:05 -03:00
parent 295cab9f73
commit b279244160
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
laborious/activities/mlflow.py
View File

@@ -169,11 +169,15 @@ class MLFlow(BaseActivity):
model_name = input_data['model_name'] model_name = input_data['model_name']
model_config = input_data.get('model_config', {}) model_config = input_data.get('model_config', {})
self.debug(data.head(5).to_string(), metadata) self.debug(f"Input data for: \n {data.head(5).to_string()}", metadata)
# Convert numpy.nan to None for model compatibility # Convert numpy.nan to None for model compatibility
data.replace(np.nan, None, inplace=True) 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)
# Request prediction from MLFlow model # Request prediction from MLFlow model
response_data = self.model_monitoring_repository.predict( response_data = self.model_monitoring_repository.predict(
model_name, data, model_config, metadata model_name, data, model_config, metadata