Method plot

nltk/probability.py:247–309

Plot samples from the frequency distribution displaying the most frequent sample first. If an integer parameter is supplied, stop after this many samples have been plotted. For a cumulative plot, specify cumulative=True. Additional ``**kwargs`` are passed t

(
        self, *args, title="", cumulative=False, percents=False, show=False, **kwargs
    )

        return self.most_common(1)[0][0]

    def plot(
        self, *args, title="", cumulative=False, percents=False, show=False, **kwargs
    ):
        """
        Plot samples from the frequency distribution
        displaying the most frequent sample first.  If an integer
        parameter is supplied, stop after this many samples have been
        plotted.  For a cumulative plot, specify cumulative=True. Additional
        ``**kwargs`` are passed to matplotlib's plot function.
        (Requires Matplotlib to be installed.)

        :param title: The title for the graph.
        :type title: str
        :param cumulative: Whether the plot is cumulative. (default = False)
        :type cumulative: bool
        :param percents: Whether the plot uses percents instead of counts. (default = False)
        :type percents: bool
        :param show: Whether to show the plot, or only return the ax.
        :type show: bool
        """
        try:
            import matplotlib.pyplot as plt
        except ImportError as e:
            raise ValueError(
                "The plot function requires matplotlib to be installed."
                "See https://matplotlib.org/"
            ) from e

        if len(args) == 0:
            args = [len(self)]
        samples = [item for item, _ in self.most_common(*args)]

        if cumulative:
            freqs = list(self._cumulative_frequencies(samples))
            ylabel = "Cumulative "
        else:
            freqs = [self[sample] for sample in samples]
            ylabel = ""

        if percents:
            freqs = [f / self.N() * 100 for f in freqs]
            ylabel += "Percents"
        else:
            ylabel += "Counts"

        ax = plt.gca()
        ax.grid(True, color="silver")

        if "linewidth" not in kwargs:
            kwargs["linewidth"] = 2
        if title:
            ax.set_title(title)

        ax.plot(freqs, **kwargs)
        ax.set_xticks(range(len(samples)))
        ax.set_xticklabels([str(s) for s in samples], rotation=90)
        ax.set_xlabel("Samples")
        ax.set_ylabel(ylabel)