pystylometry 1.1.0__py3-none-any.whl → 1.3.0__py3-none-any.whl

pystylometry/stylistic/vocabulary_overlap.py

@@ -10,15 +10,275 @@ Related GitHub Issue:
 
 References:
     Jaccard, P. (1912). The distribution of the flora in the alpine zone.
-    Salton, G., & McGill, M. J. (1983). Introduction to Modern Information Retrieval.
+        New Phytologist, 11(2), 37-50.
+    Sørensen, T. (1948). A method of establishing groups of equal amplitude in
+        plant sociology based on similarity of species. Kongelige Danske
+        Videnskabernes Selskab, 5(4), 1-34.
+    Salton, G., & McGill, M. J. (1983). Introduction to Modern Information
+        Retrieval. McGraw-Hill.
+    Kullback, S., & Leibler, R. A. (1951). On Information and Sufficiency.
+        Annals of Mathematical Statistics, 22(1), 79-86.
+    Manning, C. D., & Schütze, H. (1999). Foundations of Statistical NLP.
+        MIT Press.
 """
 
+from __future__ import annotations
+
+import math
+import re
+from collections import Counter
+
 from .._types import VocabularyOverlapResult
 
 
-def compute_vocabulary_overlap(text1: str, text2: str) -> VocabularyOverlapResult:
+def _tokenize(text: str) -> list[str]:
+    """Tokenize text into lowercase words.
+
+    Uses a simple regex-based tokenizer that extracts word characters.
+    Converts to lowercase for case-insensitive comparison.
+
+    Args:
+        text: Input text to tokenize
+
+    Returns:
+        List of lowercase word tokens
+    """
+    # Match word characters, convert to lowercase
+    tokens = re.findall(r"\b[a-zA-Z]+\b", text.lower())
+    return tokens
+
+
+def _compute_jaccard(set1: set[str], set2: set[str]) -> float:
+    """Compute Jaccard similarity coefficient.
+
+    The Jaccard index measures similarity as the size of the intersection
+    divided by the size of the union of two sets.
+
+    J(A, B) = |A ∩ B| / |A ∪ B|
+
+    Args:
+        set1: First vocabulary set
+        set2: Second vocabulary set
+
+    Returns:
+        Jaccard similarity coefficient (0.0 to 1.0)
+
+    References:
+        Jaccard, P. (1912). The distribution of the flora in the alpine zone.
+    """
+    if not set1 and not set2:
+        return 1.0  # Both empty = identical
+
+    intersection = len(set1 & set2)
+    union = len(set1 | set2)
+
+    return intersection / union if union > 0 else 0.0
+
+
+def _compute_dice(set1: set[str], set2: set[str]) -> float:
+    """Compute Sørensen-Dice coefficient.
+
+    The Dice coefficient is similar to Jaccard but weights the intersection
+    more heavily. Also known as the Sørensen-Dice index.
+
+    D(A, B) = 2|A ∩ B| / (|A| + |B|)
+
+    Args:
+        set1: First vocabulary set
+        set2: Second vocabulary set
+
+    Returns:
+        Dice coefficient (0.0 to 1.0)
+
+    References:
+        Sørensen, T. (1948). A method of establishing groups of equal amplitude
+            in plant sociology based on similarity of species.
     """
-    Compute vocabulary overlap and similarity between two texts.
+    if not set1 and not set2:
+        return 1.0  # Both empty = identical
+
+    intersection = len(set1 & set2)
+    total_size = len(set1) + len(set2)
+
+    return (2 * intersection) / total_size if total_size > 0 else 0.0
+
+
+def _compute_overlap_coefficient(set1: set[str], set2: set[str]) -> float:
+    """Compute overlap coefficient.
+
+    The overlap coefficient measures the overlap relative to the smaller set.
+    Useful when comparing texts of very different lengths.
+
+    O(A, B) = |A ∩ B| / min(|A|, |B|)
+
+    Args:
+        set1: First vocabulary set
+        set2: Second vocabulary set
+
+    Returns:
+        Overlap coefficient (0.0 to 1.0)
+    """
+    if not set1 or not set2:
+        return 0.0 if set1 or set2 else 1.0
+
+    intersection = len(set1 & set2)
+    min_size = min(len(set1), len(set2))
+
+    return intersection / min_size if min_size > 0 else 0.0
+
+
+def _compute_cosine_similarity(freq1: Counter[str], freq2: Counter[str], vocab: set[str]) -> float:
+    """Compute cosine similarity between term frequency vectors.
+
+    Treats each text as a vector in vocabulary space where each dimension
+    is the frequency of a word. Computes the cosine of the angle between vectors.
+
+    cos(θ) = (A · B) / (||A|| × ||B||)
+
+    Args:
+        freq1: Word frequencies for text 1
+        freq2: Word frequencies for text 2
+        vocab: Combined vocabulary (union of both texts)
+
+    Returns:
+        Cosine similarity (-1.0 to 1.0, though word frequencies yield 0.0 to 1.0)
+
+    References:
+        Salton, G., & McGill, M. J. (1983). Introduction to Modern Information
+            Retrieval.
+    """
+    if not vocab:
+        return 1.0  # Both empty = identical
+
+    # Compute dot product and magnitudes
+    dot_product = 0.0
+    magnitude1 = 0.0
+    magnitude2 = 0.0
+
+    for word in vocab:
+        f1 = freq1.get(word, 0)
+        f2 = freq2.get(word, 0)
+        dot_product += f1 * f2
+        magnitude1 += f1 * f1
+        magnitude2 += f2 * f2
+
+    magnitude1 = math.sqrt(magnitude1)
+    magnitude2 = math.sqrt(magnitude2)
+
+    if magnitude1 == 0 or magnitude2 == 0:
+        return 0.0
+
+    return dot_product / (magnitude1 * magnitude2)
+
+
+def _compute_kl_divergence(
+    freq1: Counter[str], freq2: Counter[str], vocab: set[str], smoothing: float = 1e-10
+) -> float:
+    """Compute Kullback-Leibler divergence from text1 to text2.
+
+    KL divergence measures how one probability distribution diverges from
+    another. It is asymmetric: D_KL(P || Q) ≠ D_KL(Q || P).
+
+    D_KL(P || Q) = Σ P(x) log(P(x) / Q(x))
+
+    A small smoothing value is added to avoid division by zero when Q(x) = 0.
+
+    Args:
+        freq1: Word frequencies for text 1 (P distribution)
+        freq2: Word frequencies for text 2 (Q distribution)
+        vocab: Combined vocabulary (union of both texts)
+        smoothing: Small value added to probabilities to avoid log(0)
+
+    Returns:
+        KL divergence (non-negative, unbounded above)
+
+    Note:
+        Returns 0.0 for identical distributions. Higher values indicate
+        greater difference between distributions.
+
+    References:
+        Kullback, S., & Leibler, R. A. (1951). On Information and Sufficiency.
+    """
+    if not vocab:
+        return 0.0  # Both empty = identical
+
+    # Convert frequencies to probabilities
+    total1 = sum(freq1.values())
+    total2 = sum(freq2.values())
+
+    if total1 == 0 or total2 == 0:
+        return 0.0
+
+    kl_div = 0.0
+    for word in vocab:
+        p = (freq1.get(word, 0) / total1) + smoothing
+        q = (freq2.get(word, 0) / total2) + smoothing
+        kl_div += p * math.log(p / q)
+
+    return max(0.0, kl_div)  # Ensure non-negative due to smoothing artifacts
+
+
+def _compute_tfidf_distinctive_words(
+    freq1: Counter[str],
+    freq2: Counter[str],
+    unique_to_1: set[str],
+    unique_to_2: set[str],
+    top_n: int = 20,
+) -> tuple[list[tuple[str, float]], list[tuple[str, float]]]:
+    """Compute distinctive words for each text using TF-IDF-like scoring.
+
+    Words unique to each text are scored by their frequency, providing
+    a measure of how "distinctive" they are for that text.
+
+    For texts with shared vocabulary, the scoring considers relative
+    frequency differences.
+
+    Args:
+        freq1: Word frequencies for text 1
+        freq2: Word frequencies for text 2
+        unique_to_1: Words appearing only in text 1
+        unique_to_2: Words appearing only in text 2
+        top_n: Number of top distinctive words to return
+
+    Returns:
+        Tuple of (text1_distinctive, text2_distinctive) lists,
+        each containing (word, score) tuples sorted by score descending
+    """
+    # For unique words, score by frequency
+    text1_scores: list[tuple[str, float]] = []
+    for word in unique_to_1:
+        score = float(freq1[word])
+        text1_scores.append((word, score))
+
+    text2_scores: list[tuple[str, float]] = []
+    for word in unique_to_2:
+        score = float(freq2[word])
+        text2_scores.append((word, score))
+
+    # Sort by score descending
+    text1_scores.sort(key=lambda x: x[1], reverse=True)
+    text2_scores.sort(key=lambda x: x[1], reverse=True)
+
+    return text1_scores[:top_n], text2_scores[:top_n]
+
+
+def compute_vocabulary_overlap(
+    text1: str,
+    text2: str,
+    top_distinctive: int = 20,
+) -> VocabularyOverlapResult:
+    """Compute vocabulary overlap and similarity between two texts.
+
+    This function computes multiple similarity metrics based on vocabulary
+    comparison, useful for authorship verification, plagiarism detection,
+    and measuring stylistic consistency across texts.
+
+    Metrics computed:
+        - Jaccard similarity: intersection / union (set-based)
+        - Sørensen-Dice coefficient: 2 * intersection / (size1 + size2)
+        - Overlap coefficient: intersection / min(size1, size2)
+        - Cosine similarity: dot product of frequency vectors
+        - KL divergence: distributional difference (asymmetric)
 
     Related GitHub Issue:
         #21 - Vocabulary Overlap and Similarity Metrics
@@ -27,21 +287,102 @@ def compute_vocabulary_overlap(text1: str, text2: str) -> VocabularyOverlapResul
     Args:
         text1: First text to compare
         text2: Second text to compare
+        top_distinctive: Number of most distinctive words to return per text
 
     Returns:
-        VocabularyOverlapResult with Jaccard, Dice, cosine similarities,
-        shared vocabulary statistics, and distinctive words for each text.
+        VocabularyOverlapResult with similarity scores, vocabulary statistics,
+        shared vocabulary, and distinctive words for each text.
 
     Example:
-        >>> result = compute_vocabulary_overlap(text1, text2)
+        >>> result = compute_vocabulary_overlap(
+        ...     "The quick brown fox jumps over the lazy dog",
+        ...     "The fast brown fox leaps over the sleepy dog"
+        ... )
         >>> print(f"Jaccard similarity: {result.jaccard_similarity:.3f}")
-        Jaccard similarity: 0.456
+        Jaccard similarity: 0.583
         >>> print(f"Shared words: {result.shared_vocab_size}")
-        Shared words: 234
+        Shared words: 7
+        >>> print(f"Text1 distinctive: {result.text1_distinctive_words}")
+        [('quick', 1.0), ('jumps', 1.0), ('lazy', 1.0)]
+
+    References:
+        Jaccard, P. (1912). The distribution of the flora in the alpine zone.
+            New Phytologist, 11(2), 37-50.
+        Sørensen, T. (1948). A method of establishing groups of equal amplitude
+            in plant sociology based on similarity of species.
+        Salton, G., & McGill, M. J. (1983). Introduction to Modern Information
+            Retrieval. McGraw-Hill.
+        Kullback, S., & Leibler, R. A. (1951). On Information and Sufficiency.
+            Annals of Mathematical Statistics, 22(1), 79-86.
+        Manning, C. D., & Schütze, H. (1999). Foundations of Statistical NLP.
+            MIT Press.
     """
-    # TODO: Implement vocabulary overlap analysis
-    # GitHub Issue #21: https://github.com/craigtrim/pystylometry/issues/21
-    raise NotImplementedError(
-        "Vocabulary overlap not yet implemented. "
-        "See GitHub Issue #21: https://github.com/craigtrim/pystylometry/issues/21"
+    # Tokenize texts
+    tokens1 = _tokenize(text1)
+    tokens2 = _tokenize(text2)
+
+    # Build frequency counters and vocabulary sets
+    freq1: Counter[str] = Counter(tokens1)
+    freq2: Counter[str] = Counter(tokens2)
+
+    vocab1 = set(freq1.keys())
+    vocab2 = set(freq2.keys())
+
+    # Compute set operations
+    shared = vocab1 & vocab2
+    union = vocab1 | vocab2
+    unique_to_1 = vocab1 - vocab2
+    unique_to_2 = vocab2 - vocab1
+
+    # Compute similarity metrics
+    jaccard = _compute_jaccard(vocab1, vocab2)
+    dice = _compute_dice(vocab1, vocab2)
+    overlap = _compute_overlap_coefficient(vocab1, vocab2)
+    cosine = _compute_cosine_similarity(freq1, freq2, union)
+    kl_div = _compute_kl_divergence(freq1, freq2, union)
+
+    # Compute coverage ratios
+    text1_coverage = len(shared) / len(vocab1) if vocab1 else 0.0
+    text2_coverage = len(shared) / len(vocab2) if vocab2 else 0.0
+
+    # Get distinctive words
+    text1_distinctive, text2_distinctive = _compute_tfidf_distinctive_words(
+        freq1, freq2, unique_to_1, unique_to_2, top_distinctive
+    )
+
+    # Build shared words list (sorted by combined frequency)
+    shared_with_freq = [(word, freq1[word] + freq2[word]) for word in shared]
+    shared_with_freq.sort(key=lambda x: x[1], reverse=True)
+    shared_words = [word for word, _ in shared_with_freq]
+
+    return VocabularyOverlapResult(
+        # Similarity scores
+        jaccard_similarity=jaccard,
+        dice_coefficient=dice,
+        overlap_coefficient=overlap,
+        cosine_similarity=cosine,
+        kl_divergence=kl_div,
+        # Vocabulary sizes
+        text1_vocab_size=len(vocab1),
+        text2_vocab_size=len(vocab2),
+        shared_vocab_size=len(shared),
+        union_vocab_size=len(union),
+        text1_unique_count=len(unique_to_1),
+        text2_unique_count=len(unique_to_2),
+        # Shared and distinctive vocabulary
+        shared_words=shared_words,
+        text1_distinctive_words=text1_distinctive,
+        text2_distinctive_words=text2_distinctive,
+        # Coverage ratios
+        text1_coverage=text1_coverage,
+        text2_coverage=text2_coverage,
+        # Metadata
+        metadata={
+            "text1_token_count": len(tokens1),
+            "text2_token_count": len(tokens2),
+            "text1_frequencies": dict(freq1),
+            "text2_frequencies": dict(freq2),
+            "unique_to_text1": sorted(unique_to_1),
+            "unique_to_text2": sorted(unique_to_2),
+        },
     )

pystylometry/syntactic/README.md

@@ -0,0 +1,20 @@
+# syntactic
+
+![4 public functions](https://img.shields.io/badge/functions-4-blue)
+![Requires spaCy](https://img.shields.io/badge/requires-spaCy-orange)
+
+Sentence structure, part-of-speech, and parse tree analysis.
+
+## Catalogue
+
+| File | Function | What It Measures |
+|------|----------|-----------------|
+| `pos_ratios.py` | `compute_pos_ratios` | Noun/verb/adjective/adverb ratios |
+| `sentence_stats.py` | `compute_sentence_stats` | Sentence length, word length distributions |
+| `sentence_types.py` | `compute_sentence_types` | Declarative, interrogative, imperative, exclamatory classification |
+| `advanced_syntactic.py` | `compute_advanced_syntactic` | Parse tree depth, clausal density, passive voice, T-units, dependency distance, subordination/coordination ratios |
+
+## See Also
+
+- [`stylistic/`](../stylistic/) for higher-level style features built on syntactic foundations
+- [`ngrams/`](../ngrams/) for POS n-gram sequences via `compute_extended_ngrams(text, pos=True)`

pystylometry/viz/README.md

@@ -0,0 +1,27 @@
+# viz
+
+![6 public functions](https://img.shields.io/badge/functions-6-blue)
+![Optional: matplotlib](https://img.shields.io/badge/optional-matplotlib-yellow)
+
+Visualization for drift detection results. Two output modes: static PNG (matplotlib) and interactive HTML (React JSX).
+
+## Catalogue
+
+| File | Functions | Output |
+|------|-----------|--------|
+| `drift.py` | `plot_drift_timeline`, `plot_drift_scatter`, `plot_drift_report` | PNG via matplotlib/seaborn |
+| `jsx/report.py` | `export_drift_report_jsx` | Interactive HTML dashboard |
+| `jsx/timeline.py` | `export_drift_timeline_jsx` | Interactive HTML timeline |
+| `jsx/viewer.py` | `export_drift_viewer` | Standalone HTML viewer with file upload |
+| `jsx/_base.py` | _(internal)_ | React/JSX rendering base |
+
+## Install
+
+```
+pip install pystylometry[viz]   # For PNG output (matplotlib + seaborn)
+# JSX/HTML output requires no additional dependencies
+```
+
+## See Also
+
+- [`consistency/`](../consistency/) produces the `KilgarriffDriftResult` consumed by all viz functions

pystylometry-1.3.0.dist-info/METADATA

@@ -0,0 +1,136 @@
+Metadata-Version: 2.4
+Name: pystylometry
+Version: 1.3.0
+Summary: Comprehensive Python package for stylometric analysis
+License: MIT
+Keywords: stylometry,nlp,text-analysis,authorship,readability,lexical-diversity,readability-metrics
+Author: Craig Trim
+Author-email: craigtrim@gmail.com
+Requires-Python: >=3.9,<4.0
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Typing :: Typed
+Requires-Dist: stylometry-ttr (>=1.0.3,<2.0.0)
+Project-URL: Homepage, https://github.com/craigtrim/pystylometry
+Project-URL: Issues, https://github.com/craigtrim/pystylometry/issues
+Project-URL: Repository, https://github.com/craigtrim/pystylometry
+Description-Content-Type: text/markdown
+
+# pystylometry
+
+[![PyPI version](https://badge.fury.io/py/pystylometry.svg)](https://badge.fury.io/py/pystylometry)
+[![Downloads](https://pepy.tech/badge/pystylometry)](https://pepy.tech/project/pystylometry)
+[![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+[![Tests](https://img.shields.io/badge/tests-1022%20passed-brightgreen)]()
+
+Stylometric analysis and authorship attribution for Python. 50+ metrics across 11 modules, from vocabulary diversity to AI-generation detection.
+
+## Install
+
+```bash
+pip install pystylometry              # Core (lexical metrics)
+pip install pystylometry[all]         # Everything
+```
+
+<details>
+<summary>Individual extras</summary>
+
+```bash
+pip install pystylometry[readability]   # Readability formulas (pronouncing, spaCy)
+pip install pystylometry[syntactic]     # POS/parse analysis (spaCy)
+pip install pystylometry[authorship]    # Attribution methods
+pip install pystylometry[ngrams]        # N-gram entropy
+pip install pystylometry[viz]           # Matplotlib visualizations
+```
+</details>
+
+## Usage
+
+```python
+from pystylometry.lexical import compute_mtld, compute_yule
+from pystylometry.readability import compute_flesch
+
+result = compute_mtld(text)
+print(result.mtld_average)       # 72.4
+
+result = compute_flesch(text)
+print(result.reading_ease)       # 65.2
+print(result.grade_level)        # 8.1
+```
+
+Every function returns a typed dataclass with the score, components, and metadata -- never a bare float.
+
+### Unified API
+
+```python
+from pystylometry import analyze
+
+results = analyze(text, lexical=True, readability=True, syntactic=True)
+```
+
+### Style Drift Detection
+
+Detect authorship changes, spliced content, and AI-generated text within a single document.
+
+```python
+from pystylometry.consistency import compute_kilgarriff_drift
+
+result = compute_kilgarriff_drift(document)
+print(result.pattern)             # "sudden_spike"
+print(result.pattern_confidence)  # 0.71
+print(result.max_location)        # Window 23 -- the splice point
+```
+
+### CLI
+
+```bash
+pystylometry-drift manuscript.txt --window-size=500 --stride=250
+pystylometry-viewer report.html
+```
+
+## Modules
+
+| Module | Metrics | Description |
+|--------|---------|-------------|
+| [**lexical**](pystylometry/lexical/) | TTR, MTLD, Yule's K/I, Hapax, MATTR, VocD-D, HD-D, MSTTR, function words, word frequency | Vocabulary diversity and richness |
+| [**readability**](pystylometry/readability/) | Flesch, Flesch-Kincaid, SMOG, Gunning Fog, Coleman-Liau, ARI, Dale-Chall, Fry, FORCAST, Linsear Write, Powers-Sumner-Kearl | Grade-level and difficulty scoring |
+| [**syntactic**](pystylometry/syntactic/) | POS ratios, sentence types, parse tree depth, clausal density, passive voice, T-units, dependency distance | Sentence and parse structure (requires spaCy) |
+| [**authorship**](pystylometry/authorship/) | Burrows' Delta, Cosine Delta, Zeta, Kilgarriff chi-squared, MinMax, John's Delta, NCD | Author attribution and text comparison |
+| [**stylistic**](pystylometry/stylistic/) | Contractions, hedges, intensifiers, modals, punctuation, vocabulary overlap (Jaccard/Dice/Cosine/KL), cohesion, genre/register | Style markers and text similarity |
+| [**character**](pystylometry/character/) | Letter frequencies, digit/uppercase ratios, special characters, whitespace | Character-level fingerprinting |
+| [**ngrams**](pystylometry/ngrams/) | Word/character/POS n-grams, Shannon entropy, skipgrams | N-gram profiles and entropy |
+| [**dialect**](pystylometry/dialect/) | British/American classification, spelling/grammar/vocabulary markers, markedness | Regional dialect detection |
+| [**consistency**](pystylometry/consistency/) | Sliding-window chi-squared drift, pattern classification | Intra-document style analysis |
+| [**prosody**](pystylometry/prosody/) | Syllable stress, rhythm regularity | Prose rhythm (requires spaCy) |
+| [**viz**](pystylometry/viz/) | Timeline, scatter, report (PNG + interactive HTML) | Drift detection visualization |
+
+## Development
+
+```bash
+git clone https://github.com/craigtrim/pystylometry && cd pystylometry
+pip install -e ".[dev,all]"
+make test       # 1022 tests
+make lint       # ruff + mypy
+make all        # lint + test + build
+```
+
+## License
+
+MIT
+
+## Author
+
+Craig Trim -- craigtrim@gmail.com
+

{pystylometry-1.1.0.dist-info → pystylometry-1.3.0.dist-info}/RECORD

@@ -1,22 +1,29 @@
-pystylometry/__init__.py,sha256=UQGe2EJUdMh1rE1zmIGNqrMgbipAhPDDU5Cvp_w--64,8594
+pystylometry/README.md,sha256=WFOtCAF3qtDTgGG3a_jTjNSwVgpQEXI1PKqbVBfyo1M,2366
+pystylometry/__init__.py,sha256=Z6zkHlX05SUeObDca9dL1Gkfq4UPBWbU2M4sp4fVj78,9220
 pystylometry/_normalize.py,sha256=7tdfgAKg5CI2d4eoDypmFqOVByoxpwgUUZD6vyBH86A,8679
-pystylometry/_types.py,sha256=OOKJ0Y_2OtaiQn_Y0EVHTOkPrNlWDhdu5Jl-4quuNZw,74257
+pystylometry/_types.py,sha256=HddTq-8kGeXyTXFkUd26HmOlOhCOdIgEVULHp168ais,76563
 pystylometry/_utils.py,sha256=CXTx4KDJ_6iiHcc2OXqOYs-izhLf_ZEmJFKdHyd7q34,5282
-pystylometry/authorship/__init__.py,sha256=QJMZ9xx5mf3u9X-HAdZsgqzZGhi4G6Pgj7wjNYGholE,1343
-pystylometry/authorship/additional_methods.py,sha256=ZCYwM_OEq3fCZGkCL0wsOUBiMSvrF1paVON4xueJDW4,2583
+pystylometry/authorship/README.md,sha256=zNXCpLj7nczPnYykJnCUw3y-kxfC9mWZmngi3nfw6us,1016
+pystylometry/authorship/__init__.py,sha256=D7m38hWi_62o1ZDSrghLCfob9YsykTht4K37wiVgHfg,1530
+pystylometry/authorship/additional_methods.py,sha256=jvEg6TMI55jhkDt1jpC-08iXTzz6TaNmKOkJy5qNF0c,11487
 pystylometry/authorship/burrows_delta.py,sha256=6XC8I7EcBTLbn9BNKZsOtL0otL4vKFX10aHBlU4Bki4,5677
-pystylometry/authorship/kilgarriff.py,sha256=Hqv5Ww7s_Tn4KSpcDAE_dTVESv4X3pglkQt0bYjQGW0,13097
+pystylometry/authorship/compression.py,sha256=qqUHDd7wWOB6Q2E97-cczBEWhKDTF3ynJUhbRqGq_RA,6296
+pystylometry/authorship/kilgarriff.py,sha256=oz4JbLnFEuPXZYLmhfkuapg516A554FvXvVNIVu7uKk,13379
 pystylometry/authorship/zeta.py,sha256=oOi9Y6ZPq15ILLVl6So9O9ERvzig26en6_dpQJWeoOc,4338
+pystylometry/character/README.md,sha256=poQwhbI8MabVD_626CWjEL87IOX5YDGS0ZJTH1hNwEE,607
 pystylometry/character/__init__.py,sha256=CiiKJmZ10UJE8qAecavpOKyw-vGonsOew_mFH34ZOC0,371
 pystylometry/character/character_metrics.py,sha256=OCIGP_ivtwtzcifcxcbmp2R5SIKh2tKyvKcHAv64S8g,14029
 pystylometry/cli.py,sha256=z0yx2O_E05tHT9_BHgSaQ2zq5_fBERXfhbYHcuQ2y-A,15477
+pystylometry/consistency/README.md,sha256=HG_Rd6WRBnIz3M7J11dVDv1S2ARkMABFYrTn-VV8xRY,1058
 pystylometry/consistency/__init__.py,sha256=l7nzpS7M4yHDBbM2LGAtW0XGT2n7YjSey_1xKf45224,2181
 pystylometry/consistency/_thresholds.py,sha256=5fZwdJ_cnDy0ED7CCYs6V_zP6kIAR1p0h0NYkbZ0HRg,6381
 pystylometry/consistency/drift.py,sha256=ZqK7YJXic8ceIfQLkH9ZtXFJCFyOuto5Mktz4qLG9ps,20682
+pystylometry/dialect/README.md,sha256=Bz0oGFRaWXjfZQqlMgvQ75rA9U0E67am2mJ9nWcSBhQ,1089
 pystylometry/dialect/__init__.py,sha256=6S4OKymniuDXPm3ZMqWyy9179RlWoLJoDzkCP4P7Jss,2486
 pystylometry/dialect/_data/dialect_markers.json,sha256=DthluOA6q0rG_8IrCrFIYWh_EMvINqYv7W664sEjNN4,51799
 pystylometry/dialect/_loader.py,sha256=M2ATp-5754v_yX9EWvBP0r5qgNf8xlL8XadVsVb_Hco,12989
 pystylometry/dialect/detector.py,sha256=9x0ZuIfTIjsmdNSx0Ezy5AC0SAFtC4kVw11iOSBd9gQ,20147
+pystylometry/lexical/README.md,sha256=cFQ7KRZV4ubsQwIlOH3YHTbhhNl5X91Sr3zcn-3x0HI,1185
 pystylometry/lexical/__init__.py,sha256=HTncnGVZgpktZqpf-r4_HI_9Jq42WkZZKXn8nho3y3s,751
 pystylometry/lexical/advanced_diversity.py,sha256=rL1hlNqTnaEFcA2v4oBJlojHZMTqdvvm4jYXTFGVpYE,25664
 pystylometry/lexical/function_words.py,sha256=eel9bq_qWgWlvG0NtDiouilMt9kaFqz2rh3add2UC4U,17832
@@ -25,11 +32,14 @@ pystylometry/lexical/mtld.py,sha256=XpeCF8sOXZhWbaazHGuqm08mrOf_DYfkfGGAltWnyy4,
 pystylometry/lexical/ttr.py,sha256=iEsXkoSPyZEyiiFwKatKA8KhLRukD7RDRvyRkRQOTsk,5848
 pystylometry/lexical/word_frequency_sophistication.py,sha256=OHOS0fBvd1Bz8zsJk-pJbWLTgImmBd-aewQnp_kq8BY,38828
 pystylometry/lexical/yule.py,sha256=NXggha8jmQCu4i-qKZpISwyJBqNpuPHyVR86BLDLgio,5192
+pystylometry/ngrams/README.md,sha256=50wyaWcLGbosLzTPR1cXdE_xAVU8jVY7fd3ReEk9KnY,802
 pystylometry/ngrams/__init__.py,sha256=eyITmSG4QP1NtVSagPsvc4j6W_E8TdB9wvBvXQHUnwo,379
 pystylometry/ngrams/entropy.py,sha256=i2RzYXrcTTIv6QaUCNQjAahL5LFOctG3ZE1OJ_tY4II,7246
-pystylometry/ngrams/extended_ngrams.py,sha256=OsBHTaaK73ZOhpS_yG2aWip1yWY2Fitdte0qx3wIshc,9475
+pystylometry/ngrams/extended_ngrams.py,sha256=288nrXbY6-PIJiQ3NaspnuRZ7qWakantnNKvtb5LhWI,18316
+pystylometry/prosody/README.md,sha256=YNTU0sTnXbCJ9GBPDDfTqHELr4YoF59_bg99ejPiqEE,608
 pystylometry/prosody/__init__.py,sha256=9tiD-U4sqEtUV8n9X339oF_C5tBNingjL-shGBXOrnY,265
-pystylometry/prosody/rhythm_prosody.py,sha256=V9OoxV5d4AZRZAb2HDY7-iEK1ijE7gtHhvFRD2DJvdA,1960
+pystylometry/prosody/rhythm_prosody.py,sha256=fifKW0FiRwC6xPX1NX0Yr4Il3APNfQiBEXB-uXXgZo8,28697
+pystylometry/readability/README.md,sha256=jj5I5525WRJceMJR8lECiZb-7y1nFzSK00GSotqupFs,1173
 pystylometry/readability/__init__.py,sha256=bJenjlGpNx7FF5AfOb6VA-wODdIa7Hc9iqoba1DLlh0,637
 pystylometry/readability/additional_formulas.py,sha256=nlVegnn_RRh6TP0BoLWlLBNnAgtFqLqyDsxFN_fUrAg,44993
 pystylometry/readability/ari.py,sha256=_wPl0FjEReLRHN0v4JQbRaU_kbikIxkr9mLO6hmNVyI,6833
@@ -39,17 +49,20 @@ pystylometry/readability/flesch.py,sha256=7kMeqpYnm-oqQGsDw7yJBhFecXB5ZRU9C8P4UK
 pystylometry/readability/gunning_fog.py,sha256=ntV90NUfqSm_84H1jBa2Fhr5DhlkderHLq8_z3khb48,8375
 pystylometry/readability/smog.py,sha256=8hdQQHUR9UBP-02AyZK3TbNhyyE1LQuZmlnVrs5Yvrk,5742
 pystylometry/readability/syllables.py,sha256=U_tO1fmdOh2xyIJVkFooGMhmZs1hqlFPBa9wBjEwLw8,4272
+pystylometry/stylistic/README.md,sha256=1GBo3AQ8f4ATap723is6pJtgUM9jmLy-hDOTcVWuI48,1020
 pystylometry/stylistic/__init__.py,sha256=nMykFZUCUKj-ZTk5H0OSKn24w6CSVEVIWieNG2B2hhc,581
-pystylometry/stylistic/cohesion_coherence.py,sha256=M_Pqfj0ZfCLDZBKFQCPx7rX9k6mxWFOjIsm1gsLdFyg,1618
-pystylometry/stylistic/genre_register.py,sha256=R32csC0M3eRcnACJNqMsyN-1ucMwdK8Twm5Tsa0Dd4k,1664
-pystylometry/stylistic/markers.py,sha256=s0ybwUZ6_wE064NXL9kQeTLKVeSHScFgZip7zkKYi2U,5134
-pystylometry/stylistic/vocabulary_overlap.py,sha256=TD8Rn32htB6MPHjc9xkr0LepJ6Q9k7f6uJvZt9_5aXA,1717
+pystylometry/stylistic/cohesion_coherence.py,sha256=9al3AYH2KQ62aluQJQr0pQHcNf1Aec6G8Oa9zux_uZk,23286
+pystylometry/stylistic/genre_register.py,sha256=4s-TxEBnFB-iog2yIO1RT6D66AQ3ChOjakRmOZzL8LM,41279
+pystylometry/stylistic/markers.py,sha256=AsuBsq5ZNTGHEp12AEL0mHj9XCJBKf3bwt7JW4H_xKs,24204
+pystylometry/stylistic/vocabulary_overlap.py,sha256=6ujoiE7TqrCiGEBrBuDeU6sdKSQYAG6IbrYVR3o9lMY,12931
+pystylometry/syntactic/README.md,sha256=0eQGqQz9MIE024_Oge4pq9LNdi-GmuTuAlz-DrK2jDI,982
 pystylometry/syntactic/__init__.py,sha256=B9qe0R7w9t5x2s2dXygSuvciuEHrScgD3CkxvPWKMPE,391
 pystylometry/syntactic/advanced_syntactic.py,sha256=ygbm7y1hrNJCaIxRCfZsafvt6BInh2iCTY1eWk2PdaE,19195
 pystylometry/syntactic/pos_ratios.py,sha256=lcvtx6tshVG6MpTWivyWnqFsjFXIHK3LCqyg2AL2AjY,7444
 pystylometry/syntactic/sentence_stats.py,sha256=SJg6TYCiT3gs2bXHYuEMSRgzFnxqOCH5q6WyhjXKgH4,4947
 pystylometry/syntactic/sentence_types.py,sha256=xEQPieGqTInCz9BinvItBX5Z_ofQ-BbFwTFNgY0jWx0,18730
 pystylometry/tokenizer.py,sha256=03FEF4kKp72v-ypbtMg8u0WyVJGk3YJx6Nw3SGzyAnA,18166
+pystylometry/viz/README.md,sha256=mizuBpUzWgJqjC2u9C-Lu4sVDCcTQOgGsarRSkeWPf4,1031
 pystylometry/viz/__init__.py,sha256=3kHMAcJJi8oPhTqUZIRdyf311cdyPOHWaJIUv-w0V04,2219
 pystylometry/viz/drift.py,sha256=r98gQ4s_IlrEuaouxDMyue3cTjGqj10i4IeKC01IuCo,18956
 pystylometry/viz/jsx/__init__.py,sha256=ZCgbpMPhG5PiJ92IkJRrZwrb7RodZB9MyauO0MGgbRM,1107
@@ -57,7 +70,7 @@ pystylometry/viz/jsx/_base.py,sha256=nd7kEc13fUcRMom3A5jqjGyTy-djIeydq2k3oPHZIHY
 pystylometry/viz/jsx/report.py,sha256=DbbHnnNAEi5tmVg4PmiHb17vkBBXujyE4x1CfVBiOBw,25857
 pystylometry/viz/jsx/timeline.py,sha256=hor-xnBa6oVkSqN0AEZUCQFBOB-iTfHSFZHiEfeakPA,30716
 pystylometry/viz/jsx/viewer.py,sha256=3LO49d_2bRf_P-P-2oSKpKx4N8Ugo4oCLb3DtvyNxXI,43716
-pystylometry-1.1.0.dist-info/METADATA,sha256=QEXVX6buqxGwilLuOIvjFT2ZxoPNazUWX1iyhaM8vI8,8348
-pystylometry-1.1.0.dist-info/WHEEL,sha256=3ny-bZhpXrU6vSQ1UPG34FoxZBp3lVcvK0LkgUz6VLk,88
-pystylometry-1.1.0.dist-info/entry_points.txt,sha256=iHOaFXlyiwcQM1LlID2gWGmN4DBLdTSpKGjttU8tgm8,113
-pystylometry-1.1.0.dist-info/RECORD,,
+pystylometry-1.3.0.dist-info/METADATA,sha256=wsQ5QTEH7i6hpePEnlfDgJFKVHJi1m-HpMcHuznQt3c,5706
+pystylometry-1.3.0.dist-info/WHEEL,sha256=3ny-bZhpXrU6vSQ1UPG34FoxZBp3lVcvK0LkgUz6VLk,88
+pystylometry-1.3.0.dist-info/entry_points.txt,sha256=iHOaFXlyiwcQM1LlID2gWGmN4DBLdTSpKGjttU8tgm8,113
+pystylometry-1.3.0.dist-info/RECORD,,