Instructions to use jobet1995/power_forecasting_project with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use jobet1995/power_forecasting_project with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://jobet1995/power_forecasting_project") - Notebooks
- Google Colab
- Kaggle
Download final_model_metadata.json from jobet1995/power_forecasting_project: direct link, hf CLI and curl.
- Browser
- Download file 430 Bytes
-
https://huggingface.co/jobet1995/power_forecasting_project/resolve/main/final_model_metadata.json
- Command line
-
hf download hf://jobet1995/power_forecasting_project/final_model_metadata.json
-
curl -L -o final_model_metadata.json https://huggingface.co/jobet1995/power_forecasting_project/resolve/main/final_model_metadata.json
430 Bytes
| {"input_features": ["voltage_V", "current_A", "power_factor", "active_power_kW", "apparent_power_kVA", "reactive_power_kVAR", "hour", "minute", "dayofweek", "is_weekend", "voltage_roll_mean_10", "current_roll_std_10", "power_factor_roll_min_10", "lag1_active_power", "lag2_active_power", "delta_active_power", "volt_amp_mult", "real_over_apparent", "power_ratio", "pca1", "pca2", "pca3"], "input_shape": [13], "output_shape": [1]} |