使用 matplotlib 从绘图中获取数据

Question

我在 python 中使用 matplotlib 来构建散点图。

假设我有以下 2 个数据列表。

X=[1,2,3,4,5]

Y=[6,7,8,9,10]

然后我使用 X 作为 X 轴值和 Y 作为 Y 轴值来制作散点图。 所以我会有一张有 5 个散射点的图片，对吧？

现在的问题是：是否可以将这 5 个点与实际数据建立联系。 例如，当我点击这 5 个点之一时，它可以告诉我我使用什么原始数据来说明这一点？

提前致谢

Answer 1

使用Joe Kington 的 DataCursor的稍微修改版本：

import matplotlib.pyplot as plt
import matplotlib.mlab as mlab
import matplotlib.cbook as cbook
import numpy as np

def fmt(x, y):
    return 'x: {x:0.2f}\ny: {y:0.2f}'.format(x = x, y = y)

class DataCursor(object):
    # https://stackoverflow.com/a/4674445/190597
    """A simple data cursor widget that displays the x,y location of a
    matplotlib artist when it is selected."""
    def __init__(self, artists, x = [], y = [], tolerance = 5, offsets = (-20, 20),
                 formatter = fmt, display_all = False):
        """Create the data cursor and connect it to the relevant figure.
        "artists" is the matplotlib artist or sequence of artists that will be 
            selected. 
        "tolerance" is the radius (in points) that the mouse click must be
            within to select the artist.
        "offsets" is a tuple of (x,y) offsets in points from the selected
            point to the displayed annotation box
        "formatter" is a callback function which takes 2 numeric arguments and
            returns a string
        "display_all" controls whether more than one annotation box will
            be shown if there are multiple axes.  Only one will be shown
            per-axis, regardless. 
        """
        self._points = np.column_stack((x,y))
        self.formatter = formatter
        self.offsets = offsets
        self.display_all = display_all
        if not cbook.iterable(artists):
            artists = [artists]
        self.artists = artists
        self.axes = tuple(set(art.axes for art in self.artists))
        self.figures = tuple(set(ax.figure for ax in self.axes))

        self.annotations = {}
        for ax in self.axes:
            self.annotations[ax] = self.annotate(ax)

        for artist in self.artists:
            artist.set_picker(tolerance)
        for fig in self.figures:
            fig.canvas.mpl_connect('pick_event', self)

    def annotate(self, ax):
        """Draws and hides the annotation box for the given axis "ax"."""
        annotation = ax.annotate(self.formatter, xy = (0, 0), ha = 'right',
                xytext = self.offsets, textcoords = 'offset points', va = 'bottom',
                bbox = dict(boxstyle = 'round,pad=0.5', fc = 'yellow', alpha = 0.5),
                arrowprops = dict(arrowstyle = '->', connectionstyle = 'arc3,rad=0')
                )
        annotation.set_visible(False)
        return annotation

    def snap(self, x, y):
        """Return the value in self._points closest to (x, y).
        """
        idx = np.nanargmin(((self._points - (x,y))**2).sum(axis = -1))
        return self._points[idx]
    def __call__(self, event):
        """Intended to be called through "mpl_connect"."""
        # Rather than trying to interpolate, just display the clicked coords
        # This will only be called if it's within "tolerance", anyway.
        x, y = event.mouseevent.xdata, event.mouseevent.ydata
        annotation = self.annotations[event.artist.axes]
        if x is not None:
            if not self.display_all:
                # Hide any other annotation boxes...
                for ann in self.annotations.values():
                    ann.set_visible(False)
            # Update the annotation in the current axis..
            x, y = self.snap(x, y)
            annotation.xy = x, y
            annotation.set_text(self.formatter(x, y))
            annotation.set_visible(True)
            event.canvas.draw()

x=[1,2,3,4,5]
y=[6,7,8,9,10]

fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
scat = ax.scatter(x, y)
DataCursor(scat, x, y)
plt.show()

产量

您可以单击任何点，气球将显示基础数据值。

---

我对 DataCursor 的轻微修改是添加了snap方法，它确保显示的数据点来自原始数据集，而不是鼠标实际单击的位置。

---

如果您安装了 scipy，您可能更喜欢这个版本的 Cursor，它使气球跟随鼠标（无需单击）：

import datetime as DT
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import numpy as np
import scipy.spatial as spatial

def fmt(x, y, is_date):
    if is_date:
        x = mdates.num2date(x).strftime("%Y-%m-%d")
        return 'x: {x}\ny: {y}'.format(x=x, y=y)
    else:
        return 'x: {x:0.2f}\ny: {y:0.2f}'.format(x=x, y=y)


class FollowDotCursor(object):
    """Display the x,y location of the nearest data point."""
    def __init__(self, ax, x, y, tolerance=5, formatter=fmt, offsets=(-20, 20)):
        try:
            x = np.asarray(x, dtype='float')
            self.is_date = False
        except (TypeError, ValueError):
            x = np.asarray(mdates.date2num(x), dtype='float')
            self.is_date = True
        y = np.asarray(y, dtype='float')
        self._points = np.column_stack((x, y))
        self.offsets = offsets
        self.scale = x.ptp()
        self.scale = y.ptp() / self.scale if self.scale else 1
        self.tree = spatial.cKDTree(self.scaled(self._points))
        self.formatter = formatter
        self.tolerance = tolerance
        self.ax = ax
        self.fig = ax.figure
        self.ax.xaxis.set_label_position('top')
        self.dot = ax.scatter(
            [x.min()], [y.min()], s=130, color='green', alpha=0.7)
        self.annotation = self.setup_annotation()
        plt.connect('motion_notify_event', self)

    def scaled(self, points):
        points = np.asarray(points)
        return points * (self.scale, 1)

    def __call__(self, event):
        ax = self.ax
        # event.inaxes is always the current axis. If you use twinx, ax could be
        # a different axis.
        if event.inaxes == ax:
            x, y = event.xdata, event.ydata
        elif event.inaxes is None:
            return
        else:
            inv = ax.transData.inverted()
            x, y = inv.transform([(event.x, event.y)]).ravel()
        annotation = self.annotation
        x, y = self.snap(x, y)
        annotation.xy = x, y
        annotation.set_text(self.formatter(x, y, self.is_date))
        self.dot.set_offsets((x, y))
        bbox = ax.viewLim
        event.canvas.draw()

    def setup_annotation(self):
        """Draw and hide the annotation box."""
        annotation = self.ax.annotate(
            '', xy=(0, 0), ha = 'right',
            xytext = self.offsets, textcoords = 'offset points', va = 'bottom',
            bbox = dict(
                boxstyle='round,pad=0.5', fc='yellow', alpha=0.75),
            arrowprops = dict(
                arrowstyle='->', connectionstyle='arc3,rad=0'))
        return annotation

    def snap(self, x, y):
        """Return the value in self.tree closest to x, y."""
        dist, idx = self.tree.query(self.scaled((x, y)), k=1, p=1)
        try:
            return self._points[idx]
        except IndexError:
            # IndexError: index out of bounds
            return self._points[0]

x = [DT.date.today()+DT.timedelta(days=i) for i in [10,20,30,40,50]]
y = [6,7,8,9,10]

fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
ax.scatter(x, y)
cursor = FollowDotCursor(ax, x, y)
fig.autofmt_xdate()
plt.show()

Answer 2

现在可以在几行中使用 mpld3 来做到这一点：

https://mpld3.github.io/examples/html_tooltips.html