Command-Line Interface

The LoS Estimator can be run directly from the command line using the module entry point or by calling the provided analysis script.

Basic Usage

Run with default configuration:

python -m los_estimator

Run with a custom configuration file:

python -m los_estimator --config_file path/to/config.toml

Run with base config and selective overrides:

python -m los_estimator --config_file los_estimator/default_config.toml --overwrite_config_file los_estimator/overwrite_config.toml

Arguments

--config_file PATH

Path to a complete configuration file (TOML format). If not provided, the default configuration at los_estimator/default_config.toml is used.

--overwrite_config_file PATH

Path to a partial configuration file that overrides specific settings in the base configuration. Useful for testing different model parameters without creating a full new config file.

Configuration Files

Configuration is managed via TOML files. The package includes:

  • default_config.toml: Default settings for model fitting, data paths, and visualization.

  • overwrite_config.toml: Sample overrides for common adjustments.

Key Configuration Sections

data_config

  • icu_file: Path to ICU occupancy data CSV.

  • los_file: Path to hospital LOS data CSV.

  • start_day and end_day: Time range for analysis.

model_config

  • kernel_width: Width of distribution kernel in days (default: 120).

  • train_width: Width of training window in days (default: 102).

  • test_width: Width of test window in days (default: 21).

  • step: Step size for sliding windows (default: 7).

  • distributions: List of distributions to fit (e.g., ["lognorm", "gaussian", "linear"]).

  • error_fun: Error function for optimization ("mse", "mae", etc.).

debug_config

  • one_window: Fit only the first window (bool).

  • less_windows: Reduce windows to ~3 for quick testing (bool).

  • less_distros: Test only linear and compartmental (bool).

  • only_linear: Fit only linear models (bool).

visualization_config

  • show_figures: Display plots interactively (bool).

  • save_figures: Save plots to disk (bool).

  • figsize: Figure dimensions as [width, height].

animation_config

  • show_figures: Display animations interactively (bool).

  • save_figures: Save animations as GIFs (bool).

Example: Quick Test Run

For rapid prototyping, enable debug flags in your config or override:

# overwrite_config.toml
[debug_config]
less_windows = true
less_distros = true

Then run:

python -m los_estimator --overwrite_config_file overwrite_config.toml

This limits fitting to ~3 windows and 2 distributions, completing in seconds.

Alternative: Using run_analysis.py

A convenience script is provided:

python run_analysis.py

This script applies the same analysis pipeline using configurations from the package. Edit run_analysis.py directly to adjust settings programmatically if preferred.

Output Structure

See Output Format for complete documentation of all output artifacts.