A comprehensive tool for analyzing writing style and document characteristics, providing detailed metrics and ML-ready outputs.
-
Comprehensive Analysis: Extracts and analyzes multiple aspects of writing style
- Lexical features (word usage, vocabulary richness)
- Syntactic patterns (sentence structure, complexity)
- Structural elements (paragraph organization, text density)
- Readability metrics (Flesch Reading Ease, Gunning Fog)
-
Multiple Output Formats:
- Detailed JSON reports
- ML-ready CSV format
- Human-readable summaries
-
Advanced Metrics:
- Style consistency scoring
- Document complexity analysis
- Writing pattern detection
- Vocabulary usage assessment
-
Performance:
- Efficient PDF text extraction
- Parallel processing for large documents
- Optimized feature calculations
-
Developer-Friendly:
- Modular architecture
- Extensive logging
- Clear documentation
- Type-safe implementation
- Python 3.8 or higher
- pip (Python package installer)
- Virtual environment (recommended)
- Clone the repository:
git clone https://github.com/yourusername/stylometrics-analyzer.git
cd stylometrics-analyzer- Create and activate a virtual environment:
# Windows
python -m venv venv
.\venv\Scripts\activate
# Linux/Mac
python -m venv venv
source venv/bin/activate- Install dependencies:
# Install required packages
pip install -r requirements.txt
# Install NLTK data
python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords'); nltk.download('averaged_perceptron_tagger')"
# Install spaCy model
python -m spacy download en_core_web_sm
# Install the package in development mode
pip install -e .python -m src.main "<path_to_pdf>"
or
stilo "<path_to_pdf>"
# Creates:
# - results/analysis_TIMESTAMP.json
# - results/analysis_TIMESTAMP.csvThis will create both JSON and CSV files in the results directory with a timestamp.
- JSON output only:
python -m src.main "<path_to_pdf>" --format json
or
stilo "<path_to_pdf>" --format json
# Creates: ./results/analysis_TIMESTAMP.json- CSV output only:
python -m src.main "<path_to_pdf>" --format csv
or
stilo "<path_to_pdf>" --format csv
# Creates: ./results/analysis_TIMESTAMP.csv-
JSON (default when format specified):
- Complete analysis with all metrics
- Formatted for readability (pretty-printed)
- Includes all features and analysis results
-
CSV (optimized for ML):
- Flattened data structure
- Key metrics and features only
- Ready for machine learning or spreadsheet analysis
When no format is specified, both JSON and CSV files are generated automatically.
stylometrics-analyzer/
├── src/ # Source code
│ ├── main.py # Entry point
│ ├── features/ # Feature extractors
│ ├── models/ # Analysis models
│ └── utils/ # Utility functions
├── results/ # Output directory
├── tests/ # Test files
└── docs/ # Documentation
See METRICS_GUIDE.md for detailed explanation of:
- Style metrics (complexity, consistency)
- Writing patterns
- Lexical features
- Syntactic features
- Readability scores
-
If you get import errors:
pip install -e . -
If NLTK data is missing:
python -c "import nltk; nltk.download('all')" -
If spaCy model is missing:
python -m spacy download en_core_web_sm