tmplot 0.1.2__tar.gz → 0.1.3__tar.gz

{tmplot-0.1.2/src/tmplot.egg-info → tmplot-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tmplot
-Version: 0.1.2
+Version: 0.1.3
 Summary: Visualization of Topic Modeling Results
 Author-email: Maksim Terpilovskii <maximtrp@gmail.com>
 License: MIT License
@@ -96,6 +96,12 @@ Requires-Dist: bitermplus; extra == "models"
   - LocallyLinearEmbedding
   - Isomap
 
+## Donate
+
+If you find this package useful, please consider donating any amount of money. This will help me spend more time on supporting open-source software.
+
+<a href="https://www.buymeacoffee.com/maximtrp" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
+
 ## Installation
 
 The package can be installed from PyPi:

{tmplot-0.1.2 → tmplot-0.1.3}/README.md

@@ -38,6 +38,12 @@
   - LocallyLinearEmbedding
   - Isomap
 
+## Donate
+
+If you find this package useful, please consider donating any amount of money. This will help me spend more time on supporting open-source software.
+
+<a href="https://www.buymeacoffee.com/maximtrp" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
+
 ## Installation
 
 The package can be installed from PyPi:

{tmplot-0.1.2 → tmplot-0.1.3}/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__ = '0.1.2'
+__version__ = '0.1.3'

{tmplot-0.1.2 → tmplot-0.1.3}/src/tmplot/_helpers.py

@@ -1,9 +1,14 @@
 __all__ = [
-    'get_phi', 'get_theta',
-    'get_relevant_terms', 'get_salient_terms',
-    'get_docs', 'get_top_docs',
-    'calc_terms_marg_probs', 'calc_topics_marg_probs',
-    'calc_terms_probs_ratio']
+    "get_phi",
+    "get_theta",
+    "get_relevant_terms",
+    "get_salient_terms",
+    "get_docs",
+    "get_top_docs",
+    "calc_terms_marg_probs",
+    "calc_topics_marg_probs",
+    "calc_terms_probs_ratio",
+]
 from warnings import warn
 from importlib.util import find_spec
 from typing import Union, Optional, Sequence, List
@@ -13,7 +18,7 @@ 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')
+tomotopy_installed = find_spec("tomotopy")
 if tomotopy_installed:
     from tomotopy import (
         LDAModel as tomotopyLDA,
@@ -23,14 +28,15 @@ if tomotopy_installed:
         HDPModel as tomotopyHDP,
         PTModel as tomotopyPT,
         SLDAModel as tomotopySLDA,
-        GDMRModel as tomotopyGDMR)
+        GDMRModel as tomotopyGDMR,
+    )
 
-gensim_installed = find_spec('gensim')
+gensim_installed = find_spec("gensim")
 if gensim_installed:
     from gensim.models.ldamodel import LdaModel as gensimLDA
     from gensim.models.ldamulticore import LdaMulticore as gensimLDAMC
 
-bitermplus_installed = find_spec('bitermplus')
+bitermplus_installed = find_spec("bitermplus")
 if bitermplus_installed:
     from bitermplus._btm import BTM
 
@@ -38,12 +44,11 @@ if bitermplus_installed:
 def __warn_package_installation(package_name: str):
     warn(
         f'Please install "{package_name}" package to analyze its models.\n'
-        f'Run `pip install {package_name}` in the console.')
+        f"Run `pip install {package_name}` in the console."
+    )
 
 
-def get_phi(
-        model: object,
-        vocabulary: Optional[Sequence] = None) -> DataFrame:
+def get_phi(model: object, vocabulary: Optional[Sequence] = None) -> DataFrame:
     """Get words vs topics matrix (phi).
 
     Returns ``phi`` matrix of shape W x T, where W is the number of words,
@@ -65,7 +70,6 @@ def get_phi(
     phi = None
 
     if _is_tomotopy(model):
-
         # Topics vs words distributions
         twd = list(map(model.get_topic_word_dist, range(model.k)))
 
@@ -76,7 +80,6 @@ def get_phi(
         phi.index = list(model.used_vocabs)
 
     elif _is_gensim(model):
-
         phi = DataFrame(model.get_topics().T)
         if vocabulary:
             phi.index = vocabulary
@@ -85,8 +88,8 @@ def get_phi(
         phi = model.df_words_topics_
 
     if isinstance(phi, DataFrame):
-        phi.index.name = 'words'
-        phi.columns.name = 'topics'
+        phi.index.name = "words"
+        phi.columns.name = "topics"
 
     return phi
 
@@ -94,8 +97,15 @@ def get_phi(
 def _is_tomotopy(model: object) -> bool:
     if tomotopy_installed:
         tomotopy_models = [
-            tomotopyLDA, tomotopyLLDA, tomotopyCT, tomotopyDMR, tomotopyHDP,
-            tomotopyPT, tomotopySLDA, tomotopyGDMR]
+            tomotopyLDA,
+            tomotopyLLDA,
+            tomotopyCT,
+            tomotopyDMR,
+            tomotopyHDP,
+            tomotopyPT,
+            tomotopySLDA,
+            tomotopyGDMR,
+        ]
         return any(map(partial(isinstance, model), tomotopy_models))
 
     __warn_package_installation("tomotopy")
@@ -119,9 +129,7 @@ def _is_btmplus(model: object) -> bool:
     return False
 
 
-def get_theta(
-        model: object,
-        corpus: Optional[List] = None) -> DataFrame:
+def get_theta(model: object, corpus: Optional[List] = None) -> Optional[DataFrame]:
     """Get topics vs documents (theta) matrix.
 
     Returns theta matrix of shape T x D, where T is the number of topics,
@@ -132,7 +140,7 @@ def get_theta(
     model : object
         Topic model instance.
     corpus : Optional[List], optional
-        Corpus.
+        Corpus (must be specified for a `gensim` model).
 
     Returns
     -------
@@ -147,8 +155,7 @@ def get_theta(
 
     elif _is_gensim(model):
         if corpus is None:
-            raise ValueError(
-                '`corpus` must be supplied for a gensim model')
+            raise ValueError("`corpus` must be supplied for a gensim model")
         tdd = list(map(model.get_document_topics, corpus))
         theta = DataFrame(zeros((len(tdd), model.num_topics)))
         for doc_id, doc_topic in enumerate(tdd):
@@ -160,14 +167,13 @@ def get_theta(
         theta = DataFrame(model.matrix_topics_docs_)
 
     if isinstance(theta, DataFrame):
-        theta.index.name = 'topics'
-        theta.columns.name = 'docs'
+        theta.index.name = "topics"
+        theta.columns.name = "docs"
 
     return theta
 
 
-def get_docs(
-        model: object) -> List[str]:
+def get_docs(model: object) -> Optional[List[str]]:
     """Retrieve documents from topic model object.
 
     Parameters
@@ -183,19 +189,19 @@ def get_docs(
     if _is_tomotopy(model):
         docs_raw = map(lambda x: x.words, model.docs)
         return list(
-            map(
-                lambda doc: " ".join(map(lambda x: model.vocabs[x], doc)),
-                docs_raw))
+            map(lambda doc: " ".join(map(lambda x: model.vocabs[x], doc)), docs_raw)
+        )
     return None
 
 
 def get_top_docs(
-        docs: Sequence[str],
-        model: object = None,
-        theta: ndarray = None,
-        corpus: Optional[List] = None,
-        docs_num: int = 5,
-        topics: Sequence[int] = None) -> DataFrame:
+    docs: Sequence[str],
+    model: object = None,
+    theta: Optional[ndarray] = None,
+    corpus: Optional[List] = None,
+    docs_num: int = 5,
+    topics: Optional[Sequence[int]] = None,
+) -> DataFrame:
     """Get top documents for all (or a selected) topic.
 
     Parameters
@@ -231,20 +237,19 @@ def get_top_docs(
 
     def _select_docs(docs, theta, topic_id: int):
         probs = theta[topic_id, :]
-        idx = argsort(probs)[:-docs_num-1:-1]
+        idx = argsort(probs)[: -docs_num - 1 : -1]
         result = Series(list(map(lambda x: docs[x], idx)))
-        result.name = f'topic{topic_id}'
+        result.name = f"topic{topic_id}"
         return result
 
     topics_num = theta.shape[0]
     topics_idx = arange(topics_num) if topics is None else topics
-    return concat(
-        map(lambda x: _select_docs(docs, theta, x), topics_idx), axis=1)
+    return concat(map(lambda x: _select_docs(docs, theta, x), topics_idx), axis=1)
 
 
 def calc_topics_marg_probs(
-        theta: Union[DataFrame, ndarray],
-        topic_id: int = None) -> Union[DataFrame, ndarray]:
+    theta: Union[DataFrame, ndarray], topic_id: Optional[int] = None
+) -> Union[DataFrame, ndarray]:
     """Calculate marginal topics probabilities.
 
     Parameters
@@ -269,8 +274,8 @@ def calc_topics_marg_probs(
 
 
 def calc_terms_marg_probs(
-        phi: Union[ndarray, DataFrame],
-        word_id: Optional[int] = None) -> Union[ndarray, Series]:
+    phi: Union[ndarray, DataFrame], word_id: Optional[int] = None
+) -> Union[ndarray, Series]:
     """Calculate marginal terms probabilities.
 
     Parameters
@@ -294,10 +299,7 @@ def calc_terms_marg_probs(
     return phi.sum(axis=1)
 
 
-def get_salient_terms(
-        terms_freqs: ndarray,
-        phi: ndarray,
-        theta: ndarray) -> ndarray:
+def get_salient_terms(terms_freqs: ndarray, phi: ndarray, theta: ndarray) -> ndarray:
     """Get salient terms.
 
     Calculated as:
@@ -324,12 +326,18 @@ 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((
-            _p_tw(phi, w, t) * log(_p_tw(phi, w, t) / p_t[t])
-            for t in range(phi.shape[1])))
-        for w in range(phi.shape[0])
-    ))
+    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 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)
@@ -337,10 +345,8 @@ def get_salient_terms(
 
 
 def calc_terms_probs_ratio(
-        phi: DataFrame,
-        topic: int,
-        terms_num: int = 30,
-        lambda_: float = 0.6) -> DataFrame:
+    phi: DataFrame, topic: int, terms_num: int = 30, lambda_: float = 0.6
+) -> DataFrame:
     """Get terms conditional and marginal probabilities.
 
     Parameters
@@ -368,35 +374,38 @@ def calc_terms_probs_ratio(
     pandas.DataFrame
         Words conditional and marginal probabilities.
     """
-    p_cond_name = 'Conditional term probability, p(w | t)'
-    p_cond = phi.iloc[:, topic]\
-        .rename(p_cond_name)\
-        if isinstance(phi, DataFrame)\
+    p_cond_name = "Conditional term probability, p(w | t)"
+    p_cond = (
+        phi.iloc[:, topic].rename(p_cond_name)
+        if isinstance(phi, DataFrame)
         else Series(phi[:, topic], name=p_cond_name)
+    )
 
-    p_marg_name = 'Marginal term probability, p(w)'
-    p_marg = phi.sum(axis=1)\
-        .rename(p_marg_name)\
-        if isinstance(phi, DataFrame)\
+    p_marg_name = "Marginal term probability, p(w)"
+    p_marg = (
+        phi.sum(axis=1).rename(p_marg_name)
+        if isinstance(phi, DataFrame)
         else Series(phi[:, topic], name=p_marg_name)
+    )
 
     terms_probs = concat((p_marg, p_cond), axis=1)
     relevant_idx = get_relevant_terms(phi, topic, lambda_).index
     terms_probs_slice = terms_probs.loc[relevant_idx].head(terms_num)
 
-    return terms_probs_slice\
-        .reset_index(drop=False)\
+    return (
+        terms_probs_slice.reset_index(drop=False)
         .melt(
             id_vars=[terms_probs_slice.index.name],
-            var_name='Type',
-            value_name='Probability')\
-        .rename(columns={terms_probs_slice.index.name: 'Terms'})
+            var_name="Type",
+            value_name="Probability",
+        )
+        .rename(columns={terms_probs_slice.index.name: "Terms"})
+    )
 
 
 def get_relevant_terms(
-        phi: Union[ndarray, DataFrame],
-        topic: int,
-        lambda_: float = 0.6) -> Series:
+    phi: Union[ndarray, DataFrame], topic: int, lambda_: float = 0.6
+) -> Series:
     """Select relevant terms.
 
     Parameters
@@ -422,11 +431,10 @@ def get_relevant_terms(
     pandas.Series
         Terms sorted by relevance (descendingly).
     """
-    phi_topic = phi.iloc[:, topic]\
-        if isinstance(phi, DataFrame)\
-        else phi[:, topic]
+    phi_topic = phi.iloc[:, topic] if isinstance(phi, DataFrame) else phi[:, topic]
 
     # 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))
+    relevance = lambda_ * nplog(phi_topic) + (1 - lambda_) * nplog(
+        phi_topic / phi.sum(axis=1)
+    )
     return relevance.sort_values(ascending=False)

tmplot-0.1.3/src/tmplot/_report.py

@@ -0,0 +1,334 @@
+__all__ = ["prepare_coords", "report"]
+import warnings
+from typing import Dict, Optional, Sequence, List
+from copy import deepcopy
+from IPython.display import display
+from ipywidgets import widgets as wdg
+from pandas import DataFrame
+from ._distance import get_topics_dist, get_topics_scatter
+from ._vis import plot_scatter_topics, plot_terms, plot_docs
+from ._helpers import calc_terms_probs_ratio, get_phi, get_theta, get_top_docs
+
+warnings.filterwarnings("ignore", category=DeprecationWarning)
+warnings.filterwarnings("ignore", category=FutureWarning)
+
+
+def prepare_coords(
+    model: object,
+    labels: Optional[Sequence] = None,
+    corpus: Optional[List] = None,
+    dist_kws: Optional[Dict] = None,
+    scatter_kws: Optional[Dict] = None,
+) -> DataFrame:
+    """Prepare coordinates for topics scatter plot.
+
+    Parameters
+    ----------
+    model : object
+        Topic model instance.
+    labels : Optional[Sequence]
+        Topics labels.
+    corpus : Optional[List], optional
+        Corpus (must be specified for a `gensim` model).
+    dist_kws : dict, optional
+        Keyword arguments passed to :py:meth:`tmplot.get_topics_dist()`.
+    scatter_kws : dict, optional
+        Keyword arguments passed to :py:meth:`tmplot.get_topics_scatter()`.
+    """
+    if not dist_kws:
+        dist_kws = {}
+    if not scatter_kws:
+        scatter_kws = {}
+
+    phi = get_phi(model)
+    theta = get_theta(model, corpus=corpus)
+    topics_dists = get_topics_dist(phi, **dist_kws)
+    topics_coords = get_topics_scatter(topics_dists, theta, **scatter_kws)
+    topics_coords["label"] = labels or theta.index
+    return topics_coords
+
+
+def report(
+    model: object,
+    docs: Sequence[str],
+    *,
+    topics_labels: Optional[Sequence[str]] = None,
+    corpus: Optional[List] = None,
+    layout: Optional[wdg.Layout] = None,
+    show_headers: bool = True,
+    show_docs: bool = True,
+    show_words: bool = True,
+    show_topics: bool = True,
+    topics_kws: Optional[dict] = None,
+    height: int = 500,
+    width: int = 300,
+    coords_kws: Optional[dict] = None,
+    words_kws: Optional[dict] = None,
+    docs_kws: Optional[dict] = None,
+    top_docs_kws: Optional[dict] = None,
+) -> wdg.VBox:
+    """Interactive report interface.
+
+    Parameters
+    ----------
+    model : object
+        Topic model instance.
+    docs : Sequence[str]
+        Documents.
+    topics_labels : Optional[Sequence[str]], optional
+        Topics labels.
+    corpus : Optional[List[str]], optional
+        Gensim corpus (must be specified if you are using a `gensim` model).
+    layout : wdg.Layout, optional
+        Interface layout instance.
+    show_headers : bool, optional
+        Show headers.
+    show_docs : bool, optional
+        Show documents widget.
+    show_words : bool, optional
+        Show words widget.
+    show_topics : bool, optional
+        Show topics scatter plot widget.
+    topics_kws : dict, optional
+        Keyword arguments passed to :py:meth:`tmplot.plot_scatter_topics()`.
+    coords_kws : dict, optional
+        Keyword arguments passed to :py:meth:`tmplot.prepare_coords()`.
+    words_kws : dict, optional
+        Keyword arguments passed to :py:meth:`tmplot.plot_terms()`.
+    docs_kws : dict, optional
+        Keyword arguments passed to :py:meth:`tmplot.plot_docs()`.
+    top_docs_kws : dict, optional
+        Keyword arguments passed to :py:meth:`tmplot.get_top_docs()`.
+
+    Returns
+    -------
+    ipywidgets.widgets.widget_box.VBox
+        Report interface as a VBox instance.
+    """
+
+    _topics_kws = (
+        {"chart_kws": {"height": height, "width": width}}
+        if not topics_kws
+        else deepcopy(topics_kws)
+    )
+    _coords_kws = {"corpus": corpus} if not coords_kws else deepcopy(coords_kws)
+    _words_kws = (
+        {"chart_kws": {"height": height, "width": width}}
+        if not words_kws
+        else deepcopy(words_kws)
+    )
+    _top_docs_kws = {} if not docs_kws else deepcopy(top_docs_kws)
+    _docs_kws = {} if not docs_kws else deepcopy(docs_kws)
+
+    # Headers init
+    topics_header = (
+        wdg.HTML("<b>Intertopic distance plot</b>")
+        if show_headers and show_topics
+        else None
+    )
+    words_header = (
+        wdg.HTML("<b>Relevant words (terms)</b>")
+        if show_headers and show_words
+        else None
+    )
+    docs_header = (
+        wdg.HTML("<b>Top documents in a topic</b>")
+        if show_headers and show_docs
+        else None
+    )
+
+    # Layout init
+    grid_cols = " ".join(["1fr"] * sum([show_docs, show_words, show_topics]))
+    layout = (
+        wdg.Layout(
+            grid_template_columns=grid_cols,
+            # justify_items='center'
+        )
+        if not layout
+        else layout
+    )
+
+    # Children widgets list init
+    children = []
+
+    if "topics_coords" not in _topics_kws:
+        topics_coords = prepare_coords(model, **_coords_kws)
+        _topics_kws.update(
+            {
+                "topics_coords": topics_coords,
+                "label_col": "label",
+                "size_col": "size",
+                "topic": 0,
+            }
+        )
+
+    if "terms_probs" not in _words_kws:
+        phi = get_phi(model)
+        terms_probs = calc_terms_probs_ratio(phi, topic=0)
+        _words_kws.update({"terms_probs": terms_probs})
+
+    if "docs" not in _docs_kws:
+        theta = get_theta(model, corpus=corpus).values
+        _top_docs_kws.update(
+            {"docs": docs, "theta": theta, "topics": [0], "docs_num": 2}
+        )
+        top_docs = get_top_docs(**_top_docs_kws)
+        top_docs.columns = [""]
+        _docs_kws.update({"docs": top_docs})
+
+    # Topic selection
+    def _on_select_topic(sel):
+        topic = sel['new']
+
+        if show_words:
+            words_plot_output.clear_output(wait=False)
+            with words_plot_output:
+                terms_probs = calc_terms_probs_ratio(
+                    phi, topic=topic, lambda_=lambda_slider.value)
+                _words_kws.update({'terms_probs': terms_probs})
+                display(plot_terms(**_words_kws))
+
+        if show_topics:
+            topics_plot_output.clear_output(wait=False)
+            with topics_plot_output:
+                _topics_kws.update({'topic': topic})
+                display(plot_scatter_topics(**_topics_kws))
+
+        if show_docs:
+            docs_plot_output.clear_output(wait=False)
+            with docs_plot_output:
+                _top_docs_kws.update({'topics': [sel['new']]})
+                top_docs = get_top_docs(**_top_docs_kws)
+                top_docs.columns = ['']
+                _docs_kws.update({'docs': top_docs})
+                display(plot_docs(**_docs_kws))
+
+    topics_ids = list(range(len(_topics_kws["topics_coords"])))
+    topics_labels = topics_labels or topics_ids
+    select_topic = wdg.Dropdown(options=list(zip(topics_labels, topics_ids)), value=0)
+    select_topic.observe(_on_select_topic, names="value")
+    select_topic_header = wdg.HTML("<b>Select a topic</b>:")
+    select_topic_widget = wdg.HBox([select_topic_header, select_topic])
+    select_topic_wrapper = wdg.VBox(
+        [select_topic_widget], layout={"align_items": "center"}
+    )
+
+    # Topics scatter
+    def _on_select_topics_method(names):
+        topics_plot_output.clear_output(wait=False)
+        with topics_plot_output:
+            _coords_kws.update({"scatter_kws": {"method": names["new"]}})
+            topics_coords = prepare_coords(model, **_coords_kws)
+            _topics_kws.update(
+                {"topics_coords": topics_coords, "topic": select_topic.value}
+            )
+            display(plot_scatter_topics(**_topics_kws))
+
+    if show_topics:
+        topics_plot_children = [topics_header] if show_headers else []
+        options_methods = [
+            ("TSNE", "tsne"),
+            ("Spectral Embedding", "sem"),
+            ("MDS", "mds"),
+            ("Locally Linear Embedding (Standard)", "lle"),
+            ("Locally Linear Embedding (LTSA)", "ltsa"),
+            ("Isomap", "isomap"),
+        ]
+        topics_method_header = wdg.HTML("Select a method:")
+        topics_method = wdg.Dropdown(
+            options=options_methods,
+            value="tsne",
+            layout=wdg.Layout(width=f"{width/1.25}px"),
+        )
+        topics_method_widget = wdg.HBox([topics_method_header, topics_method])
+        topics_method.observe(_on_select_topics_method, names="value")
+        topics_plot_output = wdg.Output()
+        topics_plot = plot_scatter_topics(**_topics_kws)
+        topics_plot_output.append_display_data(topics_plot)
+        topics_plot_children.extend([topics_method_widget, topics_plot_output])
+        topics_widget = wdg.VBox(topics_plot_children, layout={"align_items": "center"})
+        children.append(topics_widget)
+
+    # Words
+    if show_words:
+
+        def _on_select_lambda(sel):
+            topic = select_topic.value
+            lambda_ = lambda_slider.value
+            words_plot_output.clear_output(wait=False)
+            with words_plot_output:
+                terms_probs = calc_terms_probs_ratio(phi, topic=topic, lambda_=lambda_)
+                _words_kws.update({"terms_probs": terms_probs})
+                display(plot_terms(**_words_kws))
+
+        lambda_slider = wdg.FloatSlider(
+            value=0.6,
+            min=0.0,
+            max=1.0,
+            step=0.01,
+            description="",
+            continuous_update=False,
+            orientation="horizontal",
+            readout=True,
+            readout_format=".2f",
+            layout=wdg.Layout(width=f"{width/1.25}px"),
+        )
+        lambda_slider.observe(_on_select_lambda, names="value")
+        lambda_slider_header = wdg.HTML("Lambda value:")
+        lambda_slider_widget = wdg.HBox([lambda_slider_header, lambda_slider])
+        words_plot = plot_terms(**_words_kws)
+        words_plot_output = wdg.Output()
+        words_plot_output.append_display_data(words_plot)
+        words_plot_children = (
+            [words_header, lambda_slider_widget]
+            if show_headers
+            else [lambda_slider_widget]
+        )
+        words_plot_children.append(words_plot_output)
+        words_widget = wdg.VBox(words_plot_children, layout={"align_items": "center"})
+        children.append(words_widget)
+
+    # Docs
+    if show_docs:
+
+        def _on_select_docs_num(_):
+            docs_num = docs_num_slider.value
+            docs_plot_output.clear_output(wait=False)
+            with docs_plot_output:
+                _top_docs_kws.update({"docs_num": docs_num})
+                top_docs = get_top_docs(**_top_docs_kws)
+                top_docs.columns = [""]
+                _docs_kws.update({"docs": top_docs})
+                display(plot_docs(**_docs_kws))
+
+        docs_num_slider = wdg.IntSlider(
+            value=2,
+            min=1,
+            max=100,
+            continuous_update=False,
+            orientation="horizontal",
+            readout=True,
+            readout_format="d",
+            layout=wdg.Layout(width=f"{width/1.25}px"),
+        )
+        docs_num_slider.observe(_on_select_docs_num, names="value")
+        docs_num_slider_header = wdg.HTML("Documents number:")
+        docs_num_slider_widget = wdg.HBox([docs_num_slider_header, docs_num_slider])
+
+        docs_plot = plot_docs(**_docs_kws)
+        docs_plot_output = wdg.Output()
+        docs_plot_output.append_display_data(docs_plot)
+        docs_plot_children = (
+            [docs_header, docs_num_slider_widget]
+            if show_headers
+            else [docs_num_slider_widget]
+        )
+        docs_plot_children.append(docs_plot_output)
+        docs_widget = wdg.VBox(docs_plot_children, layout={"align_items": "center"})
+        children.append(docs_widget)
+
+    grid_box = wdg.GridBox(children, layout=layout)
+    hr_line = wdg.HTML('<hr style="border: 0; border-bottom: 1px solid #aaa">')
+    app = wdg.VBox([select_topic_wrapper, hr_line, grid_box])
+
+    return app

{tmplot-0.1.2 → tmplot-0.1.3/src/tmplot.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tmplot
-Version: 0.1.2
+Version: 0.1.3
 Summary: Visualization of Topic Modeling Results
 Author-email: Maksim Terpilovskii <maximtrp@gmail.com>
 License: MIT License
@@ -96,6 +96,12 @@ Requires-Dist: bitermplus; extra == "models"
   - LocallyLinearEmbedding
   - Isomap
 
+## Donate
+
+If you find this package useful, please consider donating any amount of money. This will help me spend more time on supporting open-source software.
+
+<a href="https://www.buymeacoffee.com/maximtrp" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
+
 ## Installation
 
 The package can be installed from PyPi:

tmplot-0.1.2/src/tmplot/_report.py

@@ -1,309 +0,0 @@
-__all__ = ['prepare_coords', 'report']
-import warnings
-from typing import Optional, Sequence, List
-from copy import deepcopy
-from ipywidgets import widgets as wdg
-from pandas import DataFrame
-from ._distance import get_topics_dist, get_topics_scatter
-from ._vis import plot_scatter_topics, plot_terms, plot_docs
-from ._helpers import (
-    calc_terms_probs_ratio,
-    get_phi, get_theta,
-    get_top_docs)
-
-warnings.filterwarnings("ignore", category=DeprecationWarning)
-warnings.filterwarnings("ignore", category=FutureWarning)
-
-
-def prepare_coords(
-        model: object,
-        labels: Optional[Sequence] = None,
-        dist_kws: dict = None,
-        scatter_kws: dict = None) -> DataFrame:
-    """Prepare coordinates for topics scatter plot.
-
-    Parameters
-    ----------
-    model : object
-        Topic model instance.
-    labels : Optional[Sequence]
-        Topics labels.
-    dist_kws : dict, optional
-        Keyword arguments passed to :py:meth:`tmplot.get_topics_dist()`.
-    scatter_kws : dict, optional
-        Keyword arguments passed to :py:meth:`tmplot.get_topics_scatter()`.
-    """
-    if not dist_kws:
-        dist_kws = {}
-    if not scatter_kws:
-        scatter_kws = {}
-
-    phi = get_phi(model)
-    theta = get_theta(model)
-    topics_dists = get_topics_dist(phi, **dist_kws)
-    topics_coords = get_topics_scatter(topics_dists, theta, **scatter_kws)
-    topics_coords['label'] = labels or theta.index
-    return topics_coords
-
-
-def report(
-        model: object,
-        docs: Sequence[str],
-        *,
-        topics_labels: Optional[Sequence[str]] = None,
-        corpus: Optional[List] = None,
-        layout: wdg.Layout = None,
-        show_headers: bool = True,
-        show_docs: bool = True,
-        show_words: bool = True,
-        show_topics: bool = True,
-        topics_kws: dict = None,
-        height: int = 500,
-        width: int = 300,
-        coords_kws: dict = None,
-        words_kws: dict = None,
-        docs_kws: dict = None,
-        top_docs_kws: dict = None) -> wdg.VBox:
-    """Interactive report interface.
-
-    Parameters
-    ----------
-    model : object
-        Topic model instance.
-    docs : Sequence[str]
-        Documents.
-    topics_labels : Optional[Sequence[str]], optional
-        Topics labels.
-    corpus : Optional[List[str]], optional
-        Gensim corpus.
-    layout : wdg.Layout, optional
-        Interface layout instance.
-    show_headers : bool, optional
-        Show headers.
-    show_docs : bool, optional
-        Show documents widget.
-    show_words : bool, optional
-        Show words widget.
-    show_topics : bool, optional
-        Show topics scatter plot widget.
-    topics_kws : dict, optional
-        Keyword arguments passed to :py:meth:`tmplot.plot_scatter_topics()`.
-    coords_kws : dict, optional
-        Keyword arguments passed to :py:meth:`tmplot.prepare_coords()`.
-    words_kws : dict, optional
-        Keyword arguments passed to :py:meth:`tmplot.plot_terms()`.
-    docs_kws : dict, optional
-        Keyword arguments passed to :py:meth:`tmplot.plot_docs()`.
-    top_docs_kws : dict, optional
-        Keyword arguments passed to :py:meth:`tmplot.get_top_docs()`.
-
-    Returns
-    -------
-    ipywidgets.widgets.widget_box.VBox
-        Report interface as a VBox instance.
-    """
-    from IPython.display import display
-
-    _topics_kws = {
-        'chart_kws': {'height': height, 'width': width}}\
-        if not topics_kws else deepcopy(topics_kws)
-    _coords_kws = {} if not coords_kws else deepcopy(coords_kws)
-    _words_kws = {
-        'chart_kws': {'height': height, 'width': width}}\
-        if not words_kws else deepcopy(words_kws)
-    _top_docs_kws = {} if not docs_kws else deepcopy(top_docs_kws)
-    _docs_kws = {} if not docs_kws else deepcopy(docs_kws)
-
-    # Headers init
-    topics_header = wdg.HTML('<b>Intertopic distance plot</b>')\
-        if show_headers and show_topics else None
-    words_header = wdg.HTML('<b>Relevant words (terms)</b>')\
-        if show_headers and show_words else None
-    docs_header = wdg.HTML('<b>Top documents in a topic</b>')\
-        if show_headers and show_docs else None
-
-    # Layout init
-    grid_cols = " ".join(['1fr'] * sum([show_docs, show_words, show_topics]))
-    layout = wdg.Layout(
-            grid_template_columns=grid_cols,
-            # justify_items='center'
-        )\
-        if not layout else layout
-
-    # Children widgets list init
-    children = []
-
-    if 'topics_coords' not in _topics_kws:
-        topics_coords = prepare_coords(model, **_coords_kws)
-        _topics_kws.update({
-            'topics_coords': topics_coords,
-            'label_col': 'label',
-            'size_col': 'size',
-            'topic': 0
-        })
-
-    if 'terms_probs' not in _words_kws:
-        phi = get_phi(model)
-        terms_probs = calc_terms_probs_ratio(phi, topic=0)
-        _words_kws.update({'terms_probs': terms_probs})
-
-    if 'docs' not in _docs_kws:
-        theta = get_theta(model, corpus=corpus).values
-        _top_docs_kws.update({
-            'docs': docs, 'theta': theta,
-            'topics': [0], 'docs_num': 2})
-        top_docs = get_top_docs(**_top_docs_kws)
-        top_docs.columns = ['']
-        _docs_kws.update({'docs': top_docs})
-
-    # Topic selection
-    def _on_select_topic(sel):
-        topic = sel['new']
-        topics_plot_output.clear_output(wait=False)
-        words_plot_output.clear_output(wait=False)
-        docs_plot_output.clear_output(wait=False)
-        with words_plot_output:
-            terms_probs = calc_terms_probs_ratio(
-                phi, topic=topic, lambda_=lambda_slider.value)
-            _words_kws.update({'terms_probs': terms_probs})
-            display(plot_terms(**_words_kws))
-        with topics_plot_output:
-            _topics_kws.update({'topic': topic})
-            display(plot_scatter_topics(**_topics_kws))
-        with docs_plot_output:
-            _top_docs_kws.update({'topics': [sel['new']]})
-            top_docs = get_top_docs(**_top_docs_kws)
-            top_docs.columns = ['']
-            _docs_kws.update({'docs': top_docs})
-            display(plot_docs(**_docs_kws))
-
-    topics_ids = list(range(len(_topics_kws['topics_coords'])))
-    topics_labels = topics_labels or topics_ids
-    select_topic = wdg.Dropdown(
-        options=list(zip(topics_labels, topics_ids)), value=0)
-    select_topic.observe(_on_select_topic, names='value')
-    select_topic_header = wdg.HTML('<b>Select a topic</b>:')
-    select_topic_widget = wdg.HBox([select_topic_header, select_topic])
-    select_topic_wrapper = wdg.VBox(
-        [select_topic_widget], layout={'align_items': 'center'})
-
-    # Topics scatter
-    def _on_select_topics_method(names):
-        topics_plot_output.clear_output(wait=False)
-        with topics_plot_output:
-            _coords_kws.update({'scatter_kws': {'method': names['new']}})
-            topics_coords = prepare_coords(model, **_coords_kws)
-            _topics_kws.update({
-                'topics_coords': topics_coords,
-                'topic': select_topic.value
-            })
-            display(plot_scatter_topics(**_topics_kws))
-
-    if show_topics:
-        topics_plot_children = [topics_header] if show_headers else []
-        options_methods = [
-            ('TSNE', 'tsne'),
-            ('Spectral Embedding', 'sem'),
-            ('MDS', 'mds'),
-            ('Locally Linear Embedding (Standard)', 'lle'),
-            ('Locally Linear Embedding (LTSA)', 'ltsa'),
-            ('Isomap', 'isomap')
-        ]
-        topics_method_header = wdg.HTML('Select a method:')
-        topics_method = wdg.Dropdown(
-            options=options_methods,
-            value='tsne',
-            layout=wdg.Layout(width=f'{width/1.25}px')
-        )
-        topics_method_widget = wdg.HBox([topics_method_header, topics_method])
-        topics_method.observe(_on_select_topics_method, names='value')
-        topics_plot_output = wdg.Output()
-        topics_plot = plot_scatter_topics(**_topics_kws)
-        topics_plot_output.append_display_data(topics_plot)
-        topics_plot_children.extend([topics_method_widget, topics_plot_output])
-        topics_widget = wdg.VBox(
-            topics_plot_children,
-            layout={'align_items': 'center'})
-        children.append(topics_widget)
-
-    # Words
-    if show_words:
-        def _on_select_lambda(sel):
-            topic = select_topic.value
-            lambda_ = lambda_slider.value
-            words_plot_output.clear_output(wait=False)
-            with words_plot_output:
-                terms_probs = calc_terms_probs_ratio(
-                    phi, topic=topic, lambda_=lambda_)
-                _words_kws.update({'terms_probs': terms_probs})
-                display(plot_terms(**_words_kws))
-
-        lambda_slider = wdg.FloatSlider(
-            value=0.6,
-            min=0.0,
-            max=1.0,
-            step=0.01,
-            description='',
-            continuous_update=False,
-            orientation='horizontal',
-            readout=True,
-            readout_format='.2f',
-            layout=wdg.Layout(width=f'{width/1.25}px')
-        )
-        lambda_slider.observe(_on_select_lambda, names='value')
-        lambda_slider_header = wdg.HTML('Lambda value:')
-        lambda_slider_widget = wdg.HBox([lambda_slider_header, lambda_slider])
-        words_plot = plot_terms(**_words_kws)
-        words_plot_output = wdg.Output()
-        words_plot_output.append_display_data(words_plot)
-        words_plot_children = [words_header, lambda_slider_widget]\
-            if show_headers else [lambda_slider_widget]
-        words_plot_children.append(words_plot_output)
-        words_widget = wdg.VBox(
-            words_plot_children,
-            layout={'align_items': 'center'})
-        children.append(words_widget)
-
-    # Docs
-    if show_docs:
-        def _on_select_docs_num(_):
-            docs_num = docs_num_slider.value
-            docs_plot_output.clear_output(wait=False)
-            with docs_plot_output:
-                _top_docs_kws.update({'docs_num': docs_num})
-                top_docs = get_top_docs(**_top_docs_kws)
-                top_docs.columns = ['']
-                _docs_kws.update({'docs': top_docs})
-                display(plot_docs(**_docs_kws))
-
-        docs_num_slider = wdg.IntSlider(
-            value=2,
-            min=1,
-            max=100,
-            continuous_update=False,
-            orientation='horizontal',
-            readout=True,
-            readout_format='d',
-            layout=wdg.Layout(width=f'{width/1.25}px')
-        )
-        docs_num_slider.observe(_on_select_docs_num, names='value')
-        docs_num_slider_header = wdg.HTML('Documents number:')
-        docs_num_slider_widget = wdg.HBox(
-            [docs_num_slider_header, docs_num_slider])
-
-        docs_plot = plot_docs(**_docs_kws)
-        docs_plot_output = wdg.Output()
-        docs_plot_output.append_display_data(docs_plot)
-        docs_plot_children = [docs_header, docs_num_slider_widget]\
-            if show_headers else [docs_num_slider_widget]
-        docs_plot_children.append(docs_plot_output)
-        docs_widget = wdg.VBox(
-            docs_plot_children,
-            layout={'align_items': 'center'})
-        children.append(docs_widget)
-
-    grid_box = wdg.GridBox(children, layout=layout)
-    hr_line = wdg.HTML('<hr style="border: 0; border-bottom: 1px solid #aaa">')
-    app = wdg.VBox([select_topic_wrapper, hr_line, grid_box])
-
-    return app