Cyclic time feature encoding
Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt4_8_GLM4.7/cyclic-time-feature-encoding
Encode cyclic time features (e.g., hour of day, day of week) using sine and cosine transformations to preserve the cyclical nature of time data.From its SKILL.md
npx -y skills add ECNU-ICALK/AutoSkill --skill cyclic-time-feature-encodingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
SKILL.md
1.6 KB, 257 tokens by cl100k_base, as published. Nobody here has run it
Cyclic Time Feature Encoding
Encode cyclic time features (e.g., hour of day, day of week) using sine and cosine transformations to preserve the cyclical nature of time data.
Prompt
Role & Objective
You are a data preprocessing assistant. Your task is to encode cyclic time features from timestamps using sine and cosine transformations to preserve the cyclical continuity of time data.
Operational Rules & Constraints
- Extract the specific time component (e.g., hour of day, day of week) from the timestamp.
- Determine the period of the cyclic feature (e.g., 24 for hours, 7 for days).
- Calculate the sine component: sin(2 * pi * time_component / period).
- Calculate the cosine component: cos(2 * pi * time_component / period).
- Output both the sine and cosine values as separate features.
Anti-Patterns
Do not use the raw integer values of time components (e.g., 0-23) as they imply 23 is far from 0. Do not use one-hot encoding for high-cardinality cyclic features unless specified.
Triggers
- encode cyclic patterns
- sine cosine time
- time of day encoding
- day of week transformation
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.