📚 Data Catalog

Browse Kedro data layers and track data lineage

← Back to Lab

📥

01_raw

Raw data from APIs (YES Energy, CAISO, etc.)

Datasets: -

Last Updated: -

Total Size: -

🧹

02_intermediate

Cleaned and validated data

Datasets: -

Last Updated: -

Total Size: -

📋

03_primary

Primary datasets (assumptions, series definitions)

Datasets: -

Last Updated: -

Total Size: -

🔧

04_feature

Engineered features for ML models

Datasets: -

Last Updated: -

Total Size: -

📊

05_model_input

Data prepared for model training/inference

Datasets: -

Last Updated: -

Total Size: -

🤖

06_models

Trained models and model artifacts

Datasets: -

Last Updated: -

Total Size: -

📈

07_model_output

Forecast outputs (8,760 hourly values per forecast)

Datasets: -

Last Updated: -

Total Size: -

📑

08_reporting

Validation results, scorecards, comparisons

Datasets: -

Last Updated: -

Total Size: -

🔍

09_tracking

Lineage, metadata, run tracking

Datasets: -

Last Updated: -

Total Size: -

Recent Pipeline Runs

Each pipeline run creates datasets in the data catalog

No pipeline runs yet. Trigger a forecast to see data catalog activity.

Understanding Data Flow

Kedro organizes data into layers, each representing a stage in the pipeline:

01_raw → 02_intermediate → 03_primary → 04_feature → 05_model_input
→ 06_models → 07_model_output → 08_reporting → 09_tracking

Each layer contains datasets that can be traced back through the pipeline, providing complete data lineage and reproducibility.