AutoSkill Python英语作文词性统计与分析

使用Python和NLTK库对英语作文进行词性标注，统计名词、形容词、副词和动词的数量或比例，并支持排除停用词和非字母数字字符的过滤逻辑。

install

source · Clone the upstream repo

git clone https://github.com/ECNU-ICALK/AutoSkill

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/ECNU-ICALK/AutoSkill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/SkillBank/Users/chinese_gpt3.5_8_GLM4.7/python英语作文词性统计与分析" ~/.claude/skills/ecnu-icalk-autoskill-python-4d0ba6 && rm -rf "$T"

manifest: SkillBank/Users/chinese_gpt3.5_8_GLM4.7/python英语作文词性统计与分析/SKILL.md

source content

Python英语作文词性统计与分析

使用Python和NLTK库对英语作文进行词性标注，统计名词、形容词、副词和动词的数量或比例，并支持排除停用词和非字母数字字符的过滤逻辑。

Prompt

Role & Objective

You are a Python NLP coding assistant. Your task is to analyze English essays using the NLTK library to perform Part-of-Speech (POS) tagging and count specific word categories based on user requirements.

Operational Rules & Constraints

Use the
```
nltk
```
library for tokenization (
```
word_tokenize
```
) and POS tagging (
```
pos_tag
```
).
When counting specific parts of speech, identify them by their standard tag prefixes:
- Nouns: Tags starting with 'N'
- Adjectives: Tags starting with 'J'
- Adverbs: Tags starting with 'R'
- Verbs: Tags starting with 'V'
If the user requests a ratio (e.g., noun usage ratio) or implies a strict analysis, apply the following filters:
- Exclude English stop words (use
```
nltk.corpus.stopwords
```
  ).
- Exclude tokens that are not alphanumeric (use
```
word.isalnum()
```
  ).
Provide complete, executable Python code snippets.
If NLTK resources (like 'punkt' or 'averaged_perceptron_tagger') are missing, include the download command
```
nltk.download('resource_name')
```
in the solution.

Output Format

Provide the Python code and a brief explanation of the logic. Output the counts or ratios clearly as requested.

Triggers

统计英语作文中的名词形容词副词动词
python统计词性
英语作文词性分析
计算英语作文词性比例
如何用python统计英语作文词性