steffen/entrix_case_challange
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

intermediate backup

Browse Source
This commit is contained in:
Steffen Illium
2025-05-03 20:46:14 +02:00
parent 2b0a5728d4
commit 6542caf48f
38 changed files with 4513 additions and 1067 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
forecasting_config.yaml
View File

@ -2,6 +2,13 @@
project_name: "TimeSeriesForecasting" # Name for the project/run
random_seed: 42 # Optional: Global random seed for reproducibility
log_level: INFO # Or DEBUG
# --- Execution Control ---
run_cross_validation: true # Run the main cross-validation loop?
run_classic_training: true # Run a single classic train/val/test split?
run_ensemble_evaluation: true # Run ensemble evaluation (requires run_cross_validation=true)?
# --- End Execution Control ---
# --- Data Loading Configuration ---
data:
@ -20,7 +27,7 @@ data:
# --- Feature Engineering & Preprocessing Configuration ---
features:
sequence_length: 72 # REQUIRED: Lookback window size (e.g., 72 hours = 3 days)
forecast_horizon: 24 # REQUIRED: Number of steps ahead to predict (e.g., 24 hours)
forecast_horizon: [ 1, 6, 12, 24] # REQUIRED: List of steps ahead to predict (e.g., 1 hour, 6 hours, 12 hours, 24 hours, 48 hours, 72 hours, 168 hours)
lags: [24, 48, 72, 168] # List of lag features to create (e.g., 1 day, 2 days, 3 days, 1 week)
rolling_window_sizes: [24, 72, 168] # List of window sizes for rolling stats (mean, std)
use_time_features: true # Create calendar features (hour, dayofweek, month, etc.)?
@ -62,7 +69,7 @@ training:
scheduler_step_size: null # Optional: Step size for StepLR scheduler (epochs). Set null/None to disable. Must be > 0 if set.
scheduler_gamma: null # Optional: Gamma factor for StepLR scheduler. Set null/None to disable. Must be 0 < gamma < 1 if set.
gradient_clip_val: 1.0 # Optional: Value for gradient clipping. Set null/None to disable. Must be >= 0.0 if set.
num_workers: 0 # Number of workers for DataLoader (>= 0). 0 means data loading happens in the main process.
num_workers: 4 # Number of workers for DataLoader (>= 0). 0 means data loading happens in the main process.
precision: 32 # Training precision (16, 32, 64, 'bf16')
# --- Cross-Validation Configuration (Rolling Window) ---
@ -80,9 +87,11 @@ evaluation:
# --- Optuna Hyperparameter Optimization Configuration ---
optuna:
enabled: false # Enable Optuna HPO? If true, requires optuna.py script.
n_trials: 20 # Number of trials to run (must be > 0)
storage: null # Optional: Optuna storage URL (e.g., "sqlite:///output/hpo_results/study.db"). If null, uses in-memory.
direction: "minimize" # Optimization direction ('minimize' or 'maximize')
metric_to_optimize: "val_mae_orig_scale" # Metric logged by LightningModule to optimize
pruning: true # Enable Optuna trial pruning?
enabled: true # Set to true to actually run HPO via optuna_run.py
study_name: "lstm_price_forecast_hpo_v1" # Specific name for this study
n_trials: 200 # Number of trials to run
storage: "sqlite:///output/hpo_results/study_v1.db" # Path to database file
direction: "minimize" # 'minimize' or 'maximize'
metric_to_optimize: "val_MeanAbsoluteError" # Metric logged in validation_step
pruning: true # Enable pruning