Time Series Forecasting
Joblib
Keras
PyTorch
generic
demand-forecasting
supply-chain
gru
lstm
lightgbm
xgboost
random-forest
mixture-of-experts
Instructions to use AbdullahImran/Saudi-Supply-Demand-Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use AbdullahImran/Saudi-Supply-Demand-Models with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://AbdullahImran/Saudi-Supply-Demand-Models") - Notebooks
- Google Colab
- Kaggle
| { | |
| "seq_len": 8, | |
| "feature_cols": [ | |
| "lag_1", | |
| "lag_2", | |
| "lag_3", | |
| "lag_4", | |
| "rolling_3_mean", | |
| "rolling_4_mean", | |
| "rolling_8_mean", | |
| "mean_stock", | |
| "mean_discount", | |
| "holiday_flag", | |
| "avg_precip", | |
| "avg_temp", | |
| "avg_hum", | |
| "avg_wind", | |
| "wti_price_usd_per_barrel", | |
| "rolling_std_4", | |
| "rolling_cv_4", | |
| "covid_flag" | |
| ], | |
| "static_col": "combined_weight", | |
| "target_col": "target_next_week", | |
| "sku_embedding_rows_minus_one": 865, | |
| "device": "cuda", | |
| "torchscript": false, | |
| "onnx": false, | |
| "moe_weights": "/content/gdrive/MyDrive/saudi_supply_demand/deep_learning_models/moe_entropy_final.pth", | |
| "lgbm_resid": "/content/gdrive/MyDrive/saudi_supply_demand/deep_learning_models/lgbm_resid.txt", | |
| "feat_scaler": "/content/gdrive/MyDrive/saudi_supply_demand/deep_learning_models/feat_scaler_moe_plus.pkl", | |
| "sku_stats": "/content/gdrive/MyDrive/saudi_supply_demand/deep_learning_models/sku_stats_moe_plus.pkl" | |
| } |