使用matplotlib从图获取数据 [英] Get data from plot with matplotlib

问题描述

我正在python中使用matplotlib构建散点图.

I'm using matplotlib in python to build a scatter plot.

假设我有以下2个数据列表.

suppose I have the following 2 data lists.

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

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

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

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

然后我将X用作X轴值，将Y用作Y轴值来绘制散点图.因此，我将获得一张带有5个散射点的图片，对吗?

then I use X as the X-axis value and Y as the Y-axis value to make a scatter plot. So I will have a picture with 5 scattering points on it, right?

现在的问题是:是否可以用实际数据为这5个点建立连接.例如，当我单击这5个点之一时，它可以告诉我使用什么原始数据来表示这一点?

Now the question: is it possible to build connection for these 5 points with the actual data. For example, when I click on one of these 5 points, it can tell me what original data I have used to make this point?

预先感谢

推荐答案

使用 Joe Kington的DataCursor 的稍作修改的版本:

Using a slightly modified version of Joe Kington's DataCursor:

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()

收益

您可以单击任何点，气球将显示基础数据值.

You can click on any of the points and the balloon will show the underlying data values.

我对DataCursor的略微修改是添加了snap方法，该方法可以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.

My slight modification to the DataCursor was to add the snap method, which ensures that the data point displayed came from the original data set, rather than the location where the mouse actually clicked.

如果安装了scipy，则可能更喜欢此版本的Cursor，它使气球跟随鼠标移动(无需单击):

If you have scipy installed, you might prefer this version of the Cursor, which makes the balloon follow the mouse (without clicking):

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()

这篇关于使用matplotlib从图获取数据的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！