Extracting Keywords Skill for Claude

cd /home/claude
uv venv yake-venv --system-site-packages
uv pip install yake --python yake-venv/bin/python --no-deps
uv pip install jellyfish segtok regex --python yake-venv/bin/python

import yake

# Read text
with open('document.txt', 'r') as f:
    text = f.read()

# Extract with English stopwords (default)
kw_extractor = yake.KeywordExtractor(
    lan="en",           # Language code
    n=3,                # Max n-gram size (1-3 word phrases)
    dedupLim=0.9,       # Deduplication threshold (0-1)
    top=20              # Number of keywords to return
)

keywords = kw_extractor.extract_keywords(text)

# Display results (lower score = more important)
for kw, score in keywords:
    print(f"{score:.4f}  {kw}")

# Copy life sciences stopwords to YAKE package
cp assets/stopwords_ls.txt /home/claude/yake-venv/lib/python3.12/site-packages/yake/core/StopwordsList/stopwords_ls.txt

# Use with lan="ls"
kw_extractor = yake.KeywordExtractor(lan="ls", n=3, top=20)

# Load stopwords from file
with open('assets/stopwords_ls.txt', 'r') as f:
    custom_stops = set(line.strip().lower() for line in f)

# Pass to extractor
kw_extractor = yake.KeywordExtractor(
    stopwords=custom_stops,
    n=3,
    top=20
)

# Load AI/ML stopwords
with open('/mnt/skills/user/extracting-keywords/assets/stopwords_ai.txt', 'r') as f:
    ai_stops = set(line.strip().lower() for line in f)

# Extract with AI stopwords
kw_extractor = yake.KeywordExtractor(
    stopwords=ai_stops,
    n=3,
    top=20
)
keywords = kw_extractor.extract_keywords(text)

import yake

# Load domain stopwords
with open('/mnt/skills/user/extracting-keywords/assets/stopwords_ai.txt', 'r') as f:
    stops = set(line.strip().lower() for line in f)

# Extract with n=2 (captures focused phrases)
kw_n2 = yake.KeywordExtractor(stopwords=stops, n=2, dedupLim=0.9, top=50)
results_n2 = kw_n2.extract_keywords(text)

# Extract with n=3 (captures broader context)
kw_n3 = yake.KeywordExtractor(stopwords=stops, n=3, dedupLim=0.9, top=50)
results_n3 = kw_n3.extract_keywords(text)

# Consolidate: union with score averaging for overlaps
combined = {}
for kw, score in results_n2:
    combined[kw] = score
for kw, score in results_n3:
    if kw in combined:
        combined[kw] = (combined[kw] + score) / 2
    else:
        combined[kw] = score

# Sort by score (lower = more important)
consolidated = sorted(combined.items(), key=lambda x: x[1])

# Display top 30
for kw, score in consolidated[:30]:
    print(f"{score:.4f}  {kw}")

import yake

# Read document
with open('/mnt/user-data/uploads/article.txt', 'r') as f:
    text = f.read()

# Extract keywords
kw_extractor = yake.KeywordExtractor(lan="en", n=3, top=30)
keywords = kw_extractor.extract_keywords(text)

# Format results
results = []
for kw, score in keywords:
    results.append(f"{score:.4f}  {kw}")

print("\n".join(results))

import yake

# Load life sciences stopwords
with open('assets/stopwords_ls.txt', 'r') as f:
    ls_stops = set(line.strip().lower() for line in f)

# Extract with English stopwords
kw_en = yake.KeywordExtractor(lan="en", n=3, top=20)
keywords_en = kw_en.extract_keywords(text)

# Extract with life sciences stopwords
kw_ls = yake.KeywordExtractor(stopwords=ls_stops, n=3, top=20)
keywords_ls = kw_ls.extract_keywords(text)

# Compare results
print("English stopwords:")
for kw, score in keywords_en:
    print(f"  {score:.4f}  {kw}")

print("\nLife sciences stopwords:")
for kw, score in keywords_ls:
    print(f"  {score:.4f}  {kw}")

import yake
import os

# Initialize extractor
kw_extractor = yake.KeywordExtractor(lan="en", n=3, top=15)

# Process multiple files
results = {}
for filename in os.listdir('/mnt/user-data/uploads'):
    if filename.endswith('.txt'):
        with open(f'/mnt/user-data/uploads/{filename}', 'r') as f:
            text = f.read()
        
        keywords = kw_extractor.extract_keywords(text)
        results[filename] = keywords

# Output results
for filename, keywords in results.items():
    print(f"\n{filename}:")
    for kw, score in keywords[:10]:  # Top 10
        print(f"  {score:.4f}  {kw}")

import yake

# French document
with open('/mnt/user-data/uploads/article_fr.txt', 'r') as f:
    french_text = f.read()

# Extract with French stopwords
kw_fr = yake.KeywordExtractor(lan="fr", n=3, top=20)
keywords_fr = kw_fr.extract_keywords(french_text)

print("Mots-clés (French):")
for kw, score in keywords_fr:
    print(f"  {score:.4f}  {kw}")

# German document
with open('/mnt/user-data/uploads/artikel_de.txt', 'r') as f:
    german_text = f.read()

# Extract with German stopwords
kw_de = yake.KeywordExtractor(lan="de", n=3, top=20)
keywords_de = kw_de.extract_keywords(german_text)

print("\nSchlüsselwörter (German):")
for kw, score in keywords_de:
    print(f"  {score:.4f}  {kw}")

for kw, score in keywords:
    print(f"{kw}: {score:.4f}")

import csv

with open('/mnt/user-data/outputs/keywords.csv', 'w', newline='') as f:
    writer = csv.writer(f)
    writer.writerow(['Keyword', 'Score'])
    writer.writerows(keywords)

import json

output = [{"keyword": kw, "score": score} for kw, score in keywords]
with open('/mnt/user-data/outputs/keywords.json', 'w') as f:
    json.dump(output, f, indent=2)

/home/claude/yake-venv/bin/python -c "import yake; print(yake.__version__)"

with open('assets/stopwords_ls.txt', 'r') as f:
    stops = set(line.strip().lower() for line in f)

# Add domain-specific terms
stops.update(['term1', 'term2', 'term3'])

kw_extractor = yake.KeywordExtractor(stopwords=stops, n=3, top=20)