Python PyTorch integration .cursorrules prompt file
100
Eric Ma
Visit
About .cursorrules prompt file
What you can build
- Data Analysis Automation App: Develop a command line application using Typer that automates data cleaning and analysis processes, utilizing the Python data science stack for quick insights and visualizations.
- Python Docstring Generator: Create a tool that generates Sphinx-style docstrings for Python functions, improving code documentation efficiency by leveraging LLMs to understand and describe code functionality.
- Predictive Modeling Service: Build a web service that offers parameterized callable models for predictive analytics, allowing users to easily configure and apply models to their datasets.
- Command Line AI Assistant: Design a command line interface using Typer that interacts with LLMs to provide conversational assistance for coding problems and data science queries.
- Interactive Data Science Notebook: Develop a web application that allows users to interactively write Python scripts with real-time feedback and suggestions from LLMs to improve code quality and efficiency.
- Intelligent Code Review App: Create an application that uses LLMs to automatically review Python code, providing suggestions and corrections for both style adherence and functional optimization.
- Automated Testing Framework: Implement a tool that integrates with pytest to automatically generate test cases for Python code, guided by LLM analysis to ensure comprehensive coverage.
- Data Pipeline Builder: Develop a command line app that assists users in building robust data pipelines using Python's data science libraries, with guidance on best practices and optimizations via LLMs.
- Parameter Optimization Service: Offer a platform that uses LLMs to suggest optimal hyperparameters for machine learning models, enhancing performance and efficiency in predictive tasks.
- Efficient Code Refactoring Tool: Create a refactoring tool that applies functional programming principles, with LLM-driven suggestions for transforming object-oriented code into a more functional style where applicable.
Benefits
- Emphasizes use of sphinx-style docstrings for clear and maintainable documentation.
- Encourages functional programming over object-oriented, except for specific submodule requiring PyTorch-like design.
- Utilizes Typer for CLI application development and pytest for thorough testing.
Synopsis
Data scientists and ML engineers can utilize this prompt to develop a Python library that interfaces with LLMs, leveraging PyTorch objects, Typer CLIs, and pytest for robust testing.
Overview of .cursorrules prompt
The .cursorrules file designates guidelines for a Python developer who excels in both Python data science tools and prompt engineering for large language models (LLMs). It specifies that docstrings should utilize sphinx-style formatting. Functionally, the code should favor functional programming techniques over object-oriented design, except in cases involving the Bots submodule, which resembles PyTorch's parameterized callable objects. The codebase leverages Typer for building command line applications and employs pytest for testing purposes.