This refined prompt is designed to elicit a highly structured, professional, and reusable Jupyter Notebook template. You can copy and paste the block below directly into your AI assistant.

Prompt: Professional Data Science Jupyter Notebook Template Generator

🎭 Role

Act as a Senior Data Scientist and Lead Machine Learning Engineer with expertise in MLOps, reproducible research, and clean code principles. You are a mentor for junior data scientists and advocate for "notebooks that are as clean as production code."

🌐 Context

Data science projects often spiral into "spaghetti code" notebooks that are difficult to debug, share, or productionalize. I need a master template that enforces structure, reproducibility, and clarity to ensure that my notebooks remain professional and audit-ready from the first cell to the last.

🛠️ Task Instruction

Generate a comprehensive, production-ready Jupyter Notebook skeleton using Markdown and Python code cells. The template must follow this structured workflow:

1. Metadata Header: A professional Markdown block containing the project title, author, date, version, and a clear executive objective.
2. Navigation: A Table of Contents section using HTML anchor links for easy navigation.
3. Environment & Reproducibility: A dedicated setup cell that includes:
   • Essential library imports.
   • Configuration settings (e.g., plot style, display options).
   • Global random seed setting for reproducibility.
   • A warning suppression block.
4. Data Ingestion & Cleaning: A section for loading data with logging and initial sanity checks.
5. Exploratory Data Analysis (EDA): A structured approach to EDA including summary statistics and visual insight generation.
6. Modeling Pipeline: A modular section that explicitly separates data preprocessing, train/test splitting, model training, and evaluation.
7. Results & Business Impact: A final section focused on quantitative metrics and clear, non-technical business recommendations.

⚖️ Constraints & Tone

• Tone: Professional, technical, and pedagogical.
• Documentation: Every major code block must include docstrings or inline comments explaining the why behind the logic.
• Style: Use consistent formatting. Avoid cluttering the notebook with excessive or redundant code.
• Best Practices: Incorporate standard library conventions (e.g., using pathlib for file paths, defining functions for repetitive tasks).

🧩 VariablesPlaceholders

Please use the following placeholders in your response so I can easily customize them:

• [PROJECT_TITLE]
• [AUTHOR_NAME]
• [PROJECT_OBJECTIVE]
• [DATA_SOURCE_PATH]

📝 Output Format

• Use Markdown headers for section organization.
• Provide the code in structured blocks.
• Include brief "Pro-Tips" in bullet points after each major section explaining why that structure is beneficial for production workflows.

Instructions for you: Once you paste this, the AI will provide a highly professional template. You can then fill in the [BRACKETS] as needed for your specific project.