Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

K线OHLC数据的PCA与伪PCA降维实现 · ecnu-icalk | DecimalAI

databy ecnu-icalk

K线OHLC数据的PCA与伪PCA降维实现

ecnu-icalk/K线OHLC数据的PCA与伪PCA降维实现

Source ecnu-icalk/autoskill ↗License Not recorded

针对金融K线OHLC数据进行降维分析，包括数据预处理（变化率计算、标准化）、标准PCA降维以及基于随机化SVD的伪PCA降维的Python实现步骤。

SkillScore100Maintained

Automatic

Data Analyst pack

Last verified 8/18/2026

What it changes

Passed 22 of 22 test cases with the skill, and 15 of 22 without it.

Without skill68%

With skill100%

Checks it passed that the model alone missed

The pseudo-PCA algorithm uses TruncatedSVD
The code incorporates both PCA and TruncatedSVD
The code calls pct_change on the price DataFrame

and 6 more in the full report

7 fixed15 passed either way0 still failing0 broke

Pass-rate lift: +32 pp
Tokens: +4%
Agent turns: 0%
Response time: -19%

Model gemini-3.6-flashMeasured 8/18/2026v122 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/ecnu-icalk-k-ohlc-pca-pca-6fc6f9/SKILL.md https://app.decimal.ai/s/ecnu-icalk-k-ohlc-pca-pca/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ecnu-icalk-k-ohlc-pca-pca, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/ecnu-icalk-k-ohlc-pca-pca-6fc6f9/ and pins it in .decimal/skills.lock

decimalai skills add ecnu-icalk-k-ohlc-pca-pca

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ecnu-icalk-k-ohlc-pca-pca-6fc6f9/SKILL.md https://app.decimal.ai/s/ecnu-icalk-k-ohlc-pca-pca/SKILL.md

Raw file: /s/ecnu-icalk-k-ohlc-pca-pca/SKILL.md ↗ · machine-readable summary at /s/ecnu-icalk-k-ohlc-pca-pca.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

我有一批股票的K线（OHLC）数据，想用 Python 进行特征降维处理。请给我一套完整的处理流程和代码，要求既包含标准的 PCA 方法，也包含适合大数据的伪 PCA 实现，最后能把降维结果画图展示出来。

What was checked, without and with the skill
Checked	Without skill	With skill
The code uses pct_change on OHLC data before normalization	Passed	Passed
The code applies dropna to remove NaN values generated by price change calculation	Passed	Passed
The code uses StandardScaler for feature normalization	Passed	Passed
The code uses TruncatedSVD for the pseudo-PCA implementation	Missed	Passed

case-01 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md42 linessingle file

K线OHLC数据的PCA与伪PCA降维实现

针对金融K线OHLC数据进行降维分析，包括数据预处理（变化率计算、标准化）、标准PCA降维以及基于随机化SVD的伪PCA降维的Python实现步骤。

Prompt

Role & Objective

你是一名专注于金融数据分析的数据科学家。你的任务是对K线（OHLC）时间序列数据进行降维处理，并提供详细的Python实现代码。

Communication & Style Preferences

使用中文进行回答。
提供清晰的步骤说明和可执行的Python代码。
代码应包含必要的注释，使用pandas、sklearn和matplotlib等常用库。

Operational Rules & Constraints

数据预处理：
- 对于OHLC数据，必须先计算价格变化率（通常使用pct_change()），以处理数据的非平稳性。
- 计算变化率后，必须删除产生的NaN值（dropna）。
数据归一化：
- 在进行PCA或SVD之前，必须使用StandardScaler对数据进行标准化处理（均值为0，方差为1）。
标准PCA降维：
- 使用sklearn.decomposition.PCA进行降维。
- 根据用户需求设置n_components参数（如降为1维或3维）。
- 提供拟合（fit）和转换（transform）的代码。
伪PCA降维：
- 针对不规则数据结构或大数据集，使用sklearn.decomposition.TruncatedSVD（随机化SVD）作为伪PCA的实现方法。
- 说明该方法通过计算顶部奇异向量来估计主成分。
结果展示：
- 提供使用matplotlib对降维结果进行可视化的代码（如散点图）。

Anti-Patterns

不要跳过数据归一化步骤直接对原始价格进行PCA。
不要忽略计算变化率这一处理金融时间序列的常见步骤。
不要提供无法直接运行的代码片段。

Triggers

K线OHLC如何编写python程序PCA降维
OHLC数据降维
伪PCA实现

Track record

Benchmark

22 / 22

test cases passed, vs 15 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ecnu-icalk / autoskill

SkillBank/ConvSkill/chinese_gpt3.5_8/k%E7%BA%BFohlc%E6%95%B0%E6%8D%AE%E7%9A%84pca%E4%B8%8E%E4%BC%AApca%E9%99%8D%E7%BB%B4%E5%AE%9E%E7%8E%B0/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

K线OHLC数据的PCA与伪PCA降维实现

Prompt

Role & Objective

Communication & Style Preferences

Operational Rules & Constraints

Anti-Patterns

Triggers

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills