CLI Reference¶
mmm-eval provides a command-line interface (CLI) for running MMM evaluations. This guide covers all available options and usage patterns.
Basic Usage¶
Command Structure¶
mmm-eval [OPTIONS] --input-data-path PATH --framework FRAMEWORK --config-path PATH --output-path PATH
Required Arguments¶
- --input-data-path: Path to your input data file (CSV or Parquet)
- --framework: MMM framework to use (- pymc-marketingor- meridian)
- --config-path: Path to your configuration file (JSON)
- --output-path: Directory where results will be saved
Example Commands¶
# Basic evaluation
mmm-eval --input-data-path data.csv --framework pymc-marketing --config-path config.json --output-path results/
# Run specific tests only
mmm-eval --input-data-path data.csv --framework meridian --config-path config.json --output-path results/ --test-names holdout_accuracy in_sample_accuracy cross_validation
Command Options¶
Input Options¶
- --input-data-path: Path to input data file (required)
- --config-path: Path to configuration file (required)
- --framework: MMM framework to use (required)
- Options: pymc-marketing,meridian
Output Options¶
- --output-path: Directory for output files (required)
- --test-names: Specific tests to run (optional)
- Options: holdout_accuracy,in_sample_accuracy,cross_validation,refresh_stability,perturbation,placebo
- Default: All tests
Advanced Options¶
- --random-seed: Random seed for reproducibility (optional)
- --verbose: Enable verbose output (optional)
- --help: Show help message
Examples¶
Basic Evaluation¶
mmm-eval \
  --input-data-path data.csv \
  --framework pymc-marketing \
  --config-path config.json \
  --output-path results/
Run Specific Tests¶
mmm-eval \
  --input-data-path data.csv \
  --framework pymc-marketing \
  --config-path config.json \
  --output-path results/ \
  --test-names holdout_accuracy in_sample_accuracy cross_validation
With Custom Random Seed¶
mmm-eval \
  --input-data-path data.csv \
  --framework pymc-marketing \
  --config-path config.json \
  --output-path results/ \
  --random-seed 42
Verbose Output¶
mmm-eval \
  --input-data-path data.csv \
  --framework pymc-marketing \
  --config-path config.json \
  --output-path results/ \
  --verbose
Error Handling¶
Common Errors¶
- File not found: Ensure all file paths are correct
- Invalid configuration: Check your config file format
- Framework not supported: Verify framework name
- Data format issues: Check data requirements
Getting Help¶
Next Steps¶
- Learn about Data Requirements for input format
- Check Configuration for setup
- Explore Examples for use cases