meridian-result-visualization
Loads a fitted Meridian model and generates standard visualization reports: Model Results Summary. Use when the user wants to load a saved model and view results (model performance, fit, health). Don't use for running budget optimization (use meridian-budget-optimization) or building/fitting the model (use meridian-model-building).
- License 许可
- Apache-2.0
- 所属仓库
- google/meridian
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 312
01 前言 Front Matter
- name
- meridian-result-visualization
- description
- Loads a fitted Meridian model and generates standard visualization reports: Model Results Summary. Use when the user wants to load a saved model and view results (model performance, fit, health). Don't use for running budget optimization (use meridian-budget-optimization) or building/fitting the model (use meridian-model-building).
02 资源文件 3
- 参考文档references/health_check.md482 B
- 参考文档references/load_model.md461 B
- 参考文档references/results_summary.md391 B
03 SKILL.md 正文
Meridian Result Visualization
A skill for loading a fitted Meridian model and generating standard visualization reports.
Core Workflow
Interactivity Checkpoint Rule
Throughout this workflow, you will encounter CRITICAL INTERACTIVE CHECKPOINTs. At each checkpoint, you MUST:
- Present the current proposed configurations, report paths, script path, or status to the user for approval.
- Ask the user if they are ready to proceed using the available
user-interaction tool (e.g.,
ask_question), structured as a multiple-choice question. Do NOT use raw chat text. - Wait for their response before proceeding.
- MANDATORY: You MUST pause at every checkpoint regardless of the initial prompt instructions (even if the user request contains phrases like "run autonomously", "execute directly", "fix autonomously", etc.). The initial request does NOT bypass these interactive checkpoints.
- Note: If the user replies to a checkpoint with a generic approval (e.g., "proceed", "do what you think is best"), proceed with the proposed defaults.
1. Initial Setup
- Prompt the user for the path to the serialized model file
(
meridian_model.binpbby default). - Prompt the user for output paths for:
- Model Results Summary report (
results_summary.htmlby default).
- Model Results Summary report (
- Prompt the user for the desired path for the generated Python script.
- Prompt the user for any optional configuration for the reports (e.g., date ranges for results summary).
- CRITICAL INTERACTIVE CHECKPOINT: Present the gathered paths and configurations to the user and obtain confirmation before loading the model.
2. Add Model Loading Code
- Use
meridian_serde.load_meridian()to load the model. - See load_model.md for code template.
- CRITICAL INTERACTIVE CHECKPOINT: Present the model load path configuration and proposed Python code snippet to the user, and obtain approval before continuing to specify health checks.
3. Add Post-Modeling Health Checks Code (Optional)
- Use
reviewer.ModelReviewerto run health checks and save to HTML. - Small / Test Models: If a model has fewer than 2 MCMC draws (e.g. test or
mock models where R-hat computation requires >= 2 samples), catch
ValueErroror skip R-hat calculation gracefully so health check reports generate cleanly. - See health_check.md for code template.
- CRITICAL INTERACTIVE CHECKPOINT: Present the proposed health check report path and code snippet to the user, and obtain approval before continuing to results summary configuration.
4. Add Model Results Summary Code
- Use
summarizer.Summarizerto generate the HTML results summary, applying any user-specified configuration (e.g., date ranges).- Date Range Auto-Clipping: If applying a user-specified date range falls outside the model's time coordinates, clip or adjust the date range to match the model's actual coordinates.
- Tip for errors: If you encounter errors regarding
sample_prior, bypass or fix the requirement (for example, by settingsample_prior=Falseor passing the required parameters) to ensure successful generation.
- See results_summary.md for code template.
- CRITICAL INTERACTIVE CHECKPOINT: Present the proposed date ranges, output path configuration, and code snippet for the results summary to the user, and obtain approval before proceeding to script generation and execution.
5. Pre-execution Checkpoint
- CRITICAL INTERACTIVE CHECKPOINT: Present the final report path and script path to the user, and ask for final confirmation to execute the results generation script now.
6. Execution & Script Setup
- Write the accumulated Python script to the user-specified path. If your file-writing tool can ask the user to review the written file, don't request that review: the pre-execution checkpoint already asks for approval, and an extra prompt pauses the workflow.
- Execute the script with the Python interpreter of the environment where
google-meridianis installed: the one the user named; elsepython3if a virtual environment is already active (VIRTUAL_ENVorCONDA_PREFIXis set); else the project directory's virtual environment (.venv/orvenv/, e.g.,.venv/bin/python3) if there is one; elsepython3. Ifimport meridianfails, ask the user which environment to use instead of searching the machine or installing packages unprompted. - CRITICAL: Do NOT delete the generated reports, the script, or the output directory at the end of the task. These are the deliverables requested by the user and must be preserved.
04 同仓库更多 Skills
meridian-scenario-planner
Generates Scenario Planner data from a fitted Meridian model and exports it for Looker Studio dashboard creation via Colab handoff. Use when the user wants to generate scenario planning data, budget grids, or Looker Studio dashboards from a saved model. Don't use for visualizing model results (use meridian-result-visualization) or running standard budget optimization (use meridian-budget-optimization).
meridian-model-building
Guides users through building a Meridian Marketing Mix Modeling (MMM) model. Use when a user wants to load data, map columns, configure ModelSpec, run Exploratory Data Analysis (EDA), fit a model, and save the model. Don't use for visualizing results or creating a scenario planner.
meridian-doc-consultant
Assists users with questions about Meridian Marketing Mix Modeling and Meridian GeoX geo-experiment concepts, parameters, and best practices by finding and consulting the relevant documentation on developers.google.com/meridian. Use when the user asks for explanations or guidance on Meridian MMM or GeoX topics. Don't use for writing code or running models directly.
meridian-budget-optimization
Loads a fitted Meridian model and runs budget optimization scenarios. Use when the user wants to load a saved model and find the optimal budget allocation or target ROI spending. Don't use for visualizing model performance (use meridian-result-visualization) or building/fitting the model (use meridian-model-building).