tmplot 0.1.0__tar.gz → 0.1.2__tar.gz

{tmplot-0.1.0/src/tmplot.egg-info → tmplot-0.1.2}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.1
 Name: tmplot
-Version: 0.1.0
+Version: 0.1.2
 Summary: Visualization of Topic Modeling Results
-Author-email: Maksim Terpilowski <maximtrp@gmail.com>
+Author-email: Maksim Terpilovskii <maximtrp@gmail.com>
 License: MIT License
         
         Copyright (c) 2021 Maksim Terpilowski
@@ -34,20 +34,36 @@ Classifier: Programming Language :: Python :: 3.8
 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: Topic :: Scientific/Engineering :: Information Analysis
 Classifier: Topic :: Text Processing :: General
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: seaborn
+Requires-Dist: pandas
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: altair
+Requires-Dist: ipywidgets
+Requires-Dist: tqdm
 Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: coverage; extra == "test"
 Provides-Extra: models
-License-File: LICENSE
+Requires-Dist: tomotopy>=0.8.0; extra == "models"
+Requires-Dist: gensim; extra == "models"
+Requires-Dist: bitermplus; extra == "models"
 
 # tmplot
 
+[![Codacy coverage](https://img.shields.io/codacy/coverage/5939b1cf99bc4f9d91de11c0d3ff9e50)](https://app.codacy.com/gh/maximtrp/tmplot/coverage)
+[![Codacy grade](https://img.shields.io/codacy/grade/5939b1cf99bc4f9d91de11c0d3ff9e50)](https://app.codacy.com/gh/maximtrp/tmplot)
 [![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/maximtrp/tmplot/python-package.yml?label=tests)](https://github.com/maximtrp/tmplot/actions/workflows/python-package.yml)
 [![Documentation Status](https://readthedocs.org/projects/tmplot/badge/?version=latest)](https://tmplot.readthedocs.io/en/latest/?badge=latest)
-[![Downloads](https://pepy.tech/badge/tmplot)](https://pepy.tech/project/tmplot)
-![PyPI](https://img.shields.io/pypi/v/tmplot)
+[![Downloads](https://static.pepy.tech/badge/tmplot)](https://pepy.tech/project/tmplot)
+[![PyPI](https://img.shields.io/pypi/v/tmplot)](https://pypi.org/project/tmplot)
 [![Issues](https://img.shields.io/github/issues/maximtrp/tmplot.svg)](https://github.com/maximtrp/tmplot/issues)
 
 **tmplot** is a Python package for analysis and visualization of topic modeling results. It provides the interactive report interface that borrows much from LDAvis/pyLDAvis and builds upon it offering a number of metrics for calculating topic distances and a number of algorithms for calculating scatter coordinates of topics. It can be used to select closest and stable topics across multiple models.

{tmplot-0.1.0 → tmplot-0.1.2}/README.md

@@ -1,9 +1,11 @@
 # tmplot
 
+[![Codacy coverage](https://img.shields.io/codacy/coverage/5939b1cf99bc4f9d91de11c0d3ff9e50)](https://app.codacy.com/gh/maximtrp/tmplot/coverage)
+[![Codacy grade](https://img.shields.io/codacy/grade/5939b1cf99bc4f9d91de11c0d3ff9e50)](https://app.codacy.com/gh/maximtrp/tmplot)
 [![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/maximtrp/tmplot/python-package.yml?label=tests)](https://github.com/maximtrp/tmplot/actions/workflows/python-package.yml)
 [![Documentation Status](https://readthedocs.org/projects/tmplot/badge/?version=latest)](https://tmplot.readthedocs.io/en/latest/?badge=latest)
-[![Downloads](https://pepy.tech/badge/tmplot)](https://pepy.tech/project/tmplot)
-![PyPI](https://img.shields.io/pypi/v/tmplot)
+[![Downloads](https://static.pepy.tech/badge/tmplot)](https://pepy.tech/project/tmplot)
+[![PyPI](https://img.shields.io/pypi/v/tmplot)](https://pypi.org/project/tmplot)
 [![Issues](https://img.shields.io/github/issues/maximtrp/tmplot.svg)](https://github.com/maximtrp/tmplot/issues)
 
 **tmplot** is a Python package for analysis and visualization of topic modeling results. It provides the interactive report interface that borrows much from LDAvis/pyLDAvis and builds upon it offering a number of metrics for calculating topic distances and a number of algorithms for calculating scatter coordinates of topics. It can be used to select closest and stable topics across multiple models.

{tmplot-0.1.0 → tmplot-0.1.2}/pyproject.toml

@@ -4,13 +4,13 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tmplot"
-version = "0.1.0"
+dynamic = ["version"]
 description = "Visualization of Topic Modeling Results"
 readme = "README.md"
 requires-python = ">=3.8"
 license.file = "LICENSE"
 authors = [
-  { name = "Maksim Terpilowski", email = "maximtrp@gmail.com" },
+  { name = "Maksim Terpilovskii", email = "maximtrp@gmail.com" },
 ]
 keywords = [
     "data science",
@@ -23,6 +23,7 @@ classifiers = [
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
     "Topic :: Scientific/Engineering :: Information Analysis",
     "Topic :: Text Processing :: General",
 ]
@@ -41,9 +42,12 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-test = ["pytest"]
+test = ["pytest", "coverage"]
 models = ["tomotopy>=0.8.0", "gensim", "bitermplus"]
 
+[tool.setuptools.dynamic]
+version = {attr = "tmplot.__version__"}
+
 [tool.pytest.ini_options]
 log_cli = true
 log_cli_level = "INFO"

{tmplot-0.1.0 → tmplot-0.1.2}/src/tmplot/__init__.py

@@ -5,4 +5,4 @@ from ._stability import *  # noqa: F401, F403
 from ._vis import *  # noqa: F401, F403
 from ._metrics import *  # noqa: F401, F403
 
-__version__ = '0.1.0'
+__version__ = '0.1.2'

{tmplot-0.1.0 → tmplot-0.1.2}/src/tmplot/_distance.py

@@ -152,7 +152,7 @@ def get_topics_scatter(
         method_kws.setdefault('init', 'pca')
         method_kws.setdefault('learning_rate', 'auto')
         method_kws.setdefault(
-            'perplexity', min(50, max(topic_dists.shape[0] // 2, 5)))
+            'perplexity', min(50, max(topic_dists.shape[0] // 2, 1)))
         transformer = TSNE(**method_kws)
 
     elif method == 'sem':
@@ -161,6 +161,7 @@ def get_topics_scatter(
 
     elif method == 'mds':
         method_kws.setdefault('dissimilarity', 'precomputed')
+        method_kws.setdefault('normalized_stress', 'auto')
         transformer = MDS(**method_kws)
 
     elif method == 'lle':

{tmplot-0.1.0 → tmplot-0.1.2}/src/tmplot/_helpers.py

@@ -10,6 +10,7 @@ from typing import Union, Optional, Sequence, List
 from functools import partial
 from math import log
 from numpy import ndarray, zeros, argsort, array, arange, vstack
+from numpy import log as nplog
 from pandas import concat, Series, DataFrame
 
 tomotopy_installed = find_spec('tomotopy')
@@ -96,26 +97,26 @@ def _is_tomotopy(model: object) -> bool:
             tomotopyLDA, tomotopyLLDA, tomotopyCT, tomotopyDMR, tomotopyHDP,
             tomotopyPT, tomotopySLDA, tomotopyGDMR]
         return any(map(partial(isinstance, model), tomotopy_models))
-    else:
-        __warn_package_installation("tomotopy")
-        return False
+
+    __warn_package_installation("tomotopy")
+    return False
 
 
 def _is_gensim(model: object) -> bool:
     if gensim_installed:
         gensim_models = [gensimLDA, gensimLDAMC]
         return any(map(partial(isinstance, model), gensim_models))
-    else:
-        __warn_package_installation("gensim")
-        return False
+
+    __warn_package_installation("gensim")
+    return False
 
 
 def _is_btmplus(model: object) -> bool:
     if bitermplus_installed:
         return isinstance(model, BTM)
-    else:
-        __warn_package_installation("bitermplus")
-        return False
+
+    __warn_package_installation("bitermplus")
+    return False
 
 
 def get_theta(
@@ -225,7 +226,7 @@ def get_top_docs(
     if all([model is None, theta is None]):
         raise ValueError("Please pass a model or a theta matrix to function")
 
-    if model and not theta:
+    if model and theta is not None:
         theta = get_theta(model, corpus=corpus).values
 
     def _select_docs(docs, theta, topic_id: int):
@@ -258,13 +259,13 @@ def calc_topics_marg_probs(
     Union[pandas.DataFrame, numpy.ndarray]
         Marginal topics probabilities.
     """
-    if topic_id:
+    if topic_id is not None:
         if isinstance(theta, ndarray):
             return theta[topic_id, :].sum()
-        elif isinstance(theta, DataFrame):
+        if isinstance(theta, DataFrame):
             return theta.iloc[topic_id, :].sum()
-    else:
-        return theta.sum(axis=1)
+
+    return theta.sum(axis=1)
 
 
 def calc_terms_marg_probs(
@@ -284,13 +285,13 @@ def calc_terms_marg_probs(
     Union[numpy.ndarray, pandas.Series]
         Marginal terms probabilities.
     """
-    if word_id:
+    if word_id is not None:
         if isinstance(phi, ndarray):
             return phi[word_id, :].sum()
-        elif isinstance(phi, DataFrame):
+        if isinstance(phi, DataFrame):
             return phi.iloc[word_id, :].sum()
-    else:
-        return phi.sum(axis=1)
+
+    return phi.sum(axis=1)
 
 
 def get_salient_terms(
@@ -323,12 +324,12 @@ def get_salient_terms(
     def _p_tw(phi, w, t):
         return phi[w, t] * p_t[t] / p_w[w]
 
-    saliency = array([
-        terms_freqs[w] * sum([
+    saliency = array((
+        terms_freqs[w] * sum((
             _p_tw(phi, w, t) * log(_p_tw(phi, w, t) / p_t[t])
-            for t in range(phi.shape[1])])
+            for t in range(phi.shape[1])))
         for w in range(phi.shape[0])
-    ])
+    ))
     # saliency(term w) = frequency(w)
     # * [sum_t p(t | w) * log(p(t | w)/p(t))] for topics t
     # p(t | w) = p(w | t) * p(t) / p(w)
@@ -367,7 +368,7 @@ def calc_terms_probs_ratio(
     pandas.DataFrame
         Words conditional and marginal probabilities.
     """
-    p_cond_name = 'Conditional term probability, p(w|t)'
+    p_cond_name = 'Conditional term probability, p(w | t)'
     p_cond = phi.iloc[:, topic]\
         .rename(p_cond_name)\
         if isinstance(phi, DataFrame)\
@@ -424,7 +425,8 @@ def get_relevant_terms(
     phi_topic = phi.iloc[:, topic]\
         if isinstance(phi, DataFrame)\
         else phi[:, topic]
-    # relevance = lambda * p(w | t) + (1 - lambda) * p(w | t)/p(w)
-    relevance = lambda_ * phi_topic\
-        + (1 - lambda_) * phi_topic / phi.sum(axis=1)
+
+    # relevance = lambda * log(p(w | t)) + (1 - lambda) * log(p(w | t) / p(w))
+    relevance = lambda_ * nplog(phi_topic)\
+        + (1 - lambda_) * nplog(phi_topic / phi.sum(axis=1))
     return relevance.sort_values(ascending=False)

{tmplot-0.1.0 → tmplot-0.1.2}/src/tmplot/_metrics.py

@@ -1,8 +1,7 @@
-__all__ = [
-    'entropy']
 """Metrics module"""
 from math import log
 import numpy as np
+__all__ = ['entropy']
 
 
 def entropy(phi: np.ndarray, max_probs: bool = False):

{tmplot-0.1.0 → tmplot-0.1.2}/src/tmplot/_stability.py

@@ -2,7 +2,7 @@ __all__ = ['get_closest_topics', 'get_stable_topics']
 from typing import List, Tuple, Any
 import numpy as np
 import tqdm
-from ._distance import _dist_klb, _dist_sklb, _dist_jsd, _dist_jef, _dist_hel,\
+from ._distance import _dist_klb, _dist_sklb, _dist_jsd, _dist_jef, _dist_hel, \
     _dist_bhat, _dist_jac, _dist_tv
 from ._helpers import get_phi
 
@@ -50,12 +50,13 @@ def get_closest_topics(
     Returns
     -------
     closest_topics : np.ndarray
-        Closest topics indices in one two-dimensional array.
+        Closest topics indices in one two-dimensional array (topics ✕ models).
         Columns correspond to the compared models (their indices),
         rows are the closest topics pairs.
     dist : np.ndarray
-        Kullback-Leibler (if ``method`` is set to ``klb``) or Jaccard index
-        values corresponding to the matrix of the closest topics.
+        Closest topics distances (e.g., Kullback-Leibler or Jaccard index
+        values). Shape of this array corresponds to the shape of the first
+        returned argument.
 
     Example
     -------
@@ -75,7 +76,6 @@ def get_closest_topics(
     model_ref_phi = get_phi(model_ref)
 
     # Number of topics
-    print(type(model_ref_phi))
     topics_num = model_ref_phi.shape[1]
 
     # Array with the closest topics ids
@@ -105,7 +105,7 @@ def get_closest_topics(
         for t_ref in range(topics_num):
             for t in range(topics_num):
                 all_vs_all_dists[t_ref, t] = dist_func(
-                    model_ref_phi.iloc[t_ref, :], get_phi(model).iloc[t, :])
+                    model_ref_phi.iloc[:, t_ref], get_phi(model).iloc[:, t])
 
         # Creating two arrays for the closest topics ids and distance values
         if method == "jac":

{tmplot-0.1.0 → tmplot-0.1.2/src/tmplot.egg-info}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.1
 Name: tmplot
-Version: 0.1.0
+Version: 0.1.2
 Summary: Visualization of Topic Modeling Results
-Author-email: Maksim Terpilowski <maximtrp@gmail.com>
+Author-email: Maksim Terpilovskii <maximtrp@gmail.com>
 License: MIT License
         
         Copyright (c) 2021 Maksim Terpilowski
@@ -34,20 +34,36 @@ Classifier: Programming Language :: Python :: 3.8
 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: Topic :: Scientific/Engineering :: Information Analysis
 Classifier: Topic :: Text Processing :: General
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: seaborn
+Requires-Dist: pandas
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: altair
+Requires-Dist: ipywidgets
+Requires-Dist: tqdm
 Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: coverage; extra == "test"
 Provides-Extra: models
-License-File: LICENSE
+Requires-Dist: tomotopy>=0.8.0; extra == "models"
+Requires-Dist: gensim; extra == "models"
+Requires-Dist: bitermplus; extra == "models"
 
 # tmplot
 
+[![Codacy coverage](https://img.shields.io/codacy/coverage/5939b1cf99bc4f9d91de11c0d3ff9e50)](https://app.codacy.com/gh/maximtrp/tmplot/coverage)
+[![Codacy grade](https://img.shields.io/codacy/grade/5939b1cf99bc4f9d91de11c0d3ff9e50)](https://app.codacy.com/gh/maximtrp/tmplot)
 [![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/maximtrp/tmplot/python-package.yml?label=tests)](https://github.com/maximtrp/tmplot/actions/workflows/python-package.yml)
 [![Documentation Status](https://readthedocs.org/projects/tmplot/badge/?version=latest)](https://tmplot.readthedocs.io/en/latest/?badge=latest)
-[![Downloads](https://pepy.tech/badge/tmplot)](https://pepy.tech/project/tmplot)
-![PyPI](https://img.shields.io/pypi/v/tmplot)
+[![Downloads](https://static.pepy.tech/badge/tmplot)](https://pepy.tech/project/tmplot)
+[![PyPI](https://img.shields.io/pypi/v/tmplot)](https://pypi.org/project/tmplot)
 [![Issues](https://img.shields.io/github/issues/maximtrp/tmplot.svg)](https://github.com/maximtrp/tmplot/issues)
 
 **tmplot** is a Python package for analysis and visualization of topic modeling results. It provides the interactive report interface that borrows much from LDAvis/pyLDAvis and builds upon it offering a number of metrics for calculating topic distances and a number of algorithms for calculating scatter coordinates of topics. It can be used to select closest and stable topics across multiple models.

{tmplot-0.1.0 → tmplot-0.1.2}/src/tmplot.egg-info/requires.txt

@@ -14,3 +14,4 @@ bitermplus
 
 [test]
 pytest
+coverage