PrivacyScanData/target/visualize/visualize_3_2.py

def wordcloud(
    s: TextSeries,
    font_path: str = None,
    width: int = 400,
    height: int = 200,
    max_words=200,
    mask=None,
    contour_width=0,
    contour_color="PAPAYAWHIP",
    min_font_size=4,
    background_color="PAPAYAWHIP",
    max_font_size=None,
    relative_scaling="auto",
    colormap=None,
    return_figure=False,
):
    """
    Plot wordcloud image using WordCloud from word_cloud package.

    Most of the arguments are very similar if not equal to the mother
    function. In constrast, all words are taken into account when computing
    the wordcloud, inclusive stopwords. They can be easily removed with
    preprocessing.remove_stopwords.

    Words are computed using generate_from_frequencies.

    To reduce blur in the wordcloud image, `width` and `height` should be at
    least 400.

    Parameters
    ----------
    s : :class:`texthero._types.TextSeries`

    font_path : str, optional, default=None
        Font path to the font that will be used (OTF or TTF). Defaults to
        DroidSansMono path on a Linux machine. If you are on another OS or
        don't have this font, you need to adjust this path.

    width : int, optional, default=400
        Width of the canvas.

    height : int, optional, default=200
        Height of the canvas.

    max_words : int, optional, default=200
        The maximum number of words.

    mask : nd-array or None, optional, default=None
        When set, gives a binary mask on where to draw words. When set, width
        and height will be ignored and the shape of mask will be used instead.
        All white (#FF or #FFFFFF) entries will be considerd "masked out"
        while other entries will be free to draw on.

    contour_width: float, optional, default=0
        If mask is not None and contour_width > 0, draw the mask contour.

    contour_color: str, optional, default="PAPAYAWHIP"
        Mask contour color.

    min_font_size : int, optional, default=4
        Smallest font size to use. Will stop when there is no more room in
        this size.

    background_color : str, optional, default="PAPAYAWHIP"
        Background color for the word cloud image.

    max_font_size : int or None, optional, default=None
        Maximum font size for the largest word. If None, height of the image
        is used.

    relative_scaling : float, optional, default="auto"
        Importance of relative word frequencies for font-size.  With
        relative_scaling=0, only word-ranks are considered.  With
        relative_scaling=1, a word that is twice as frequent will have twice
        the size.  If you want to consider the word frequencies and not only
        their rank, relative_scaling around .5 often looks good.
        If 'auto' it will be set to 0.5 unless repeat is true, in which
        case it will be set to 0.

    colormap : string or matplotlib colormap, optional, default="viridis"
        Matplotlib colormap to randomly draw colors from for each word.

    """
    text = s.str.cat(sep=" ")

    if colormap is None:

        # Custom palette.
        # TODO move it under tools.
        corn = (255.0 / 256, 242.0 / 256, 117.0 / 256)
        mango_tango = (255.0 / 256, 140.0 / 256, 66.0 / 256)
        crayola = (63.0 / 256, 136.0 / 256, 197.0 / 256)
        crimson = (215.0 / 256, 38.0 / 256, 61.0 / 256)
        oxford_blue = (2.0 / 256, 24.0 / 256, 43.0 / 256)

        texthero_cm = lsg.from_list(
            "texthero", [corn, mango_tango, crayola, crimson, oxford_blue]
        )

        colormap = texthero_cm

    words = s.str.cat(sep=" ").split()

    wordcloud = WordCloud(
        font_path=font_path,
        width=width,
        height=height,
        max_words=max_words,
        mask=mask,
        contour_width=contour_width,
        contour_color=contour_color,
        min_font_size=min_font_size,
        background_color=background_color,
        max_font_size=max_font_size,
        relative_scaling=relative_scaling,
        colormap=colormap,
        # stopwords=[],  # TODO. Will use generate from frequencies.
        # normalize_plurals=False,  # TODO.
    ).generate_from_frequencies(dict(Counter(words)))

    # fig = px.imshow(wordcloud)
    # fig.show()

    fig, ax = plt.subplots(figsize=(20, 10))
    ax.imshow(wordcloud, interpolation="bilinear")
    ax.axis("off")

    if return_figure:
        return fig