85642bed25
Merge pull request #27 from Aignosi/release/SIENTIAPDE-1645
Bruno Domingues
2026-08-05 13:17:43 -03:00
e3e1c712a8
SIENTIAPDE-1645: Refactor temporary directory cleanup activity by extracting processing and deletion logic into dedicated helper methods. Update train_test_split to use a local numpy.random generator for improved reproducibility. Remove an unnecessary else: pass block.
Bruno Domingues
2026-08-05 12:10:54 -03:00
4133e200f7
SIENTIAPDE-1645: Remove validate.sh script, add jsonschema dependency, and improve test code readability
Bruno Domingues
2026-08-05 11:23:22 -03:00
ebc7e5ce6f
SIENTIAPDE-1645: Overhaul deployment, add Claude AI guidance, and enhance CI/CD.
Bruno Domingues
2026-08-05 10:38:38 -03:00
b6e59cf18e
chore: bump version to 1.3.0 [skip ci]
github-actions[bot]
2026-07-10 14:48:08 +00:00
3457496c0a
Merge pull request #28 from Aignosi/feature/SIENTIAPDE-1945
Bruno Domingues
2026-07-10 11:47:50 -03:00
159607fc72
SIENTIAPDE-1945: Adopt shared Docker image and Kubernetes deployment strategy. Removed the local Dockerfile, .dockerignore, and values.yaml, as image building and Kubernetes deployment are now handled by external sientia-module components. Updated README accordingly.
Bruno Domingues
2026-07-08 20:22:32 -03:00
1c06a8e584
ci(sonar): Update project key
Bruno Domingues
2026-07-01 21:07:47 -03:00
2c63414770
SIENTIAPDE-1645: Expose detailed model training information via a new Prometheus gauge. This gauge, sientia_training_info, records metadata such as dataset sizes, feature count, and evaluation metrics (MSE, MAE, R2) along with the training run's timestamp.
vitor-aignosi
2026-06-18 09:56:30 -03:00
bc65ebb955
SIENTIAPDE-1645: Use absolute time (time.time()) for training start timestamps instead of monotonic time.
vitor-aignosi
2026-06-17 17:26:34 -03:00
214923b93e
SIENTIAPDE-1645: Update pod_id label retrieval in training activities to use HOSTNAME environment variable with localhost fallback.
vitor-aignosi
2026-06-17 16:12:51 -03:00
fe8a9384ba
SIENTIAPDE-1645: Rename Prometheus 'sientia_app_up' metric to 'app_up' and update test assertion.
vitor-aignosi
2026-06-17 12:26:25 -03:00
ea98032057
SIENTIAPDE-1645: Upgrade sqlalchemy to version 2.0.50 in requirements.txt
vitor-aignosi
2026-06-17 11:20:23 -03:00
76f926a8ab
SIENTIAPDE-1645: Add comprehensive model training observability metrics and Grafana dashboard.
vitor-aignosi
2026-06-17 10:34:56 -03:00
445fe643fe
chore: update .gitignore and requirements for development
vitor-aignosi
2026-05-26 09:38:24 -03:00
526edcb50e
feat: update training workflow and repository management
vitor-aignosi
2026-04-09 12:09:52 -03:00
0ae03b246f
feat: update environment configuration and remove deprecated model serving
vitor-aignosi
2026-04-07 16:58:50 -03:00
c5cd382350
feat: enhance configuration and scheduling for cleanup processes
vitor-aignosi
2026-04-07 12:57:29 -03:00
09ee92f100
feat: enhance configuration and error handling in project setup
vitor-aignosi
2026-04-07 10:25:17 -03:00
6b1df7c3a7
feat: enhance training and experiment tracking functionality
vitor-aignosi
2026-04-06 15:05:57 -03:00
1352d1ac8f
feat: enhance training model functionality and reporting
vitor-aignosi
2026-04-06 11:40:08 -03:00
a8b926649a
feat: enhance training reporting and directory management
vitor-aignosi
2026-04-06 10:38:24 -03:00
18412958d2
refactor: remove MinIO repository references and streamline cleanup process
vitor-aignosi
2026-04-06 09:30:38 -03:00
d2bb588739
Merge branch 'main' into release/SIENTIAPDE-1645
vitor-aignosi
2026-04-06 08:34:15 -03:00
bf2b6b3888
feat: improve error handling and resource cleanup in training workflow
vitor-aignosi
2026-04-06 08:26:42 -03:00
dfe05a063a
chore: bump version to 1.2.0 [skip ci]
github-actions[bot]
2026-03-30 18:27:46 +00:00
f43fe6a399
Merge pull request #26 from Aignosi/feature/SIENTIAPDE-1717
Bruno Domingues
2026-03-30 15:27:20 -03:00
14f91b40aa
SIENTIAPDE-1717: Updated documentation to reflect the removal of MinIO data download and cleanup operations from Model Manager workflows.
Bruno Domingues
2026-03-30 14:54:44 -03:00
cce350bfb1
SIENTIAPDE-1717: Remove FILE_DELETE_ERROR from ExperimentStatus enum and related tests.
Bruno Domingues
2026-03-30 14:33:19 -03:00
f5eb8d1e5b
SIENTIAPDE-1717: Remove list_bucket_objects method from StorageRepository and its associated test.
Bruno Domingues
2026-03-30 14:18:14 -03:00
7a0961f29d
SIENTIAPDE-1717: Remove MinIO cleanup functionality and associated components. This change streamlines the cleanup workflow to focus solely on local temporary directories, removes the ModelTrainingError exception, and updates related configurations, documentation, and tests.
Bruno Domingues
2026-03-30 14:14:10 -03:00
342a02d6f7
feat: enhance training workflow with model metadata loading and refactor data handling
vitor-aignosi
2026-03-24 14:39:28 -03:00
63a94dae0a
chore: bump version to 1.1.3 [skip ci]
github-actions[bot]
2026-03-12 17:33:24 +00:00
fb54ee4e9a
Merge pull request #25 from Aignosi/fix/SIENTIAPDE-1672
Bruno Domingues
2026-03-12 14:33:02 -03:00
1d096a6dc0
SIENTIAPDE-1672: Streamline deploy workflow by removing dedicated versioning job, passing branch name to reusable deploy, and enabling VPN.
Bruno Domingues
2026-03-12 13:17:07 -03:00
cf5111e520
feat: integrate PluginStore and MinIO repository into model manager activities
vitor-aignosi
2026-03-11 17:35:05 -03:00
9d71c0cf80
chore: bump version to 1.1.2 [skip ci]
github-actions[bot]
2026-02-20 00:20:15 +00:00
0a0adac86c
Merge pull request #24 from Aignosi/fix/SIENTIAPDE-1579
Bruno Domingues
2026-02-19 21:19:53 -03:00
41c4490cad
SIENTIAPDE-1579: Fix SientiaMlException propagation in ModelServing.search_runs_by_name to correctly raise the exception with its message, resolving a TypeError. Enhance training test script to support scenario-specific CSV files for different test cases. Update search_runs_by_name return type hint and apply minor code formatting.
Bruno Domingues
2026-02-19 21:13:41 -03:00
f952647cf6
SIENTIAPDE-1579: Update MLflow to 2.18.0 and add setuptools version constraint.
Bruno Domingues
2026-02-19 17:56:08 -03:00
b0629cb34a
chore: bump version to 1.1.1 [skip ci]
github-actions[bot]
2026-02-19 12:34:59 +00:00
8609245e77
Merge pull request #23 from Aignosi/fix/SIENTIAPDE-1579
Lucas Kou Kinoshita
2026-02-19 09:34:34 -03:00
14f3fbadbe
SIENTIAPDE-1579: Switched from replace logic to validation + mapping
Kou Kinoshita
2026-02-18 18:57:41 -03:00
b6eb346a0b
SIENTIAPDE-1579: Added test case scenario to test filter, also updated old scenarios
Kou Kinoshita
2026-02-18 14:24:17 -03:00
54a47a1d96
SIENTIAPDE-1579: Added extra test files and support filters implementation
Kou Kinoshita
2026-02-18 14:16:21 -03:00
8b7bd81328
SIENTIAPDE-1579: Fixed data preprocessor
Kou Kinoshita
2026-02-18 11:14:27 -03:00
a4d94dd2ff
SIENTIAPDE-1579: Added date format and convert methods
Kou Kinoshita
2026-02-13 18:41:46 -03:00
9e3585afce
SIENTIAPDE-1579: Added local and validation flags to test script
Kou Kinoshita
2026-02-13 17:51:17 -03:00
f0cdace820
chore: bump version to 1.1.0 [skip ci]
github-actions[bot]
2025-12-19 19:43:10 +00:00
68ed97583a
Merge pull request #22 from Aignosi/feature/SIENTIAPDE-1430
Bruno Domingues
2025-12-19 16:42:51 -03:00
df6bf1daba
SIENTIAPDE-1430: Refactor static threshold calculation logic and enhance test coverage
Bruno Domingues
2025-12-19 16:19:10 -03:00
06571011f2
SIENTIAPDE-1430: Introduce static_threshold parameter for static window removal. This parameter allows customizing the threshold (1-1000) used when rem_static_win is enabled, defaulting to 1 if null. Updates include parameter definition, business rule validation, repository logic for passing the threshold, documentation in README.md and PIPELINE_PARAMS_CHANGELOG.md, and new unit and integration tests.
Bruno Domingues
2025-12-19 15:44:18 -03:00
7cbb7022e5
SIENTIAPDE-1430: Refactor DataPreprocessor date filtering, make rce_train radius optional, and introduce constants for model names.
Bruno Domingues
2025-12-19 12:28:07 -03:00
9a77257920
SIENTIAPDE-1430: Update README to document new features, expanded validation, and enhanced testing. * Documents support for Polynomial Regression, per-variable lag configuration, date range filtering, and NaN treatment options. * Includes details on RCE drift metrics and comprehensive business validation rules for training parameters. * Describes new JSON-based integration test scenarios with batch execution and updated 100% code coverage. * Refines architecture overview and example workflow parameters.
Bruno Domingues
2025-12-19 11:54:08 -03:00
44dca9b66b
SIENTIAPDE-1430: Add option to run all training test scenarios with summary reporting. - Introduce --all argument to run_training_test.py to execute all available scenarios sequentially. - Refactor single scenario execution into a run_single_scenario function for better modularity and error handling. - Implement a print_summary function to report results for multiple scenario runs.
Bruno Domingues
2025-12-18 21:46:51 -03:00
Eduardo Rios
gitea_admin