如何在散点图中包围不同的数据集？

Question

如何在散点图中包围不同的数据集？

我正在寻找的是这样的：

此外，我如何用（阴影）颜色填充圆圈？

Answer 1

您可以通过凸包scipy.spatial.ConvexHull获得包含所有点的路径。

import matplotlib.pyplot as plt
import numpy as np; np.random.seed(1)
from scipy.spatial import ConvexHull

x1, y1 = np.random.normal(loc=5, scale=2, size=(2,15))
x2, y2 = np.random.normal(loc=8, scale=2.5, size=(2,13))

plt.scatter(x1, y1)
plt.scatter(x2, y2)

def encircle(x,y, ax=None, **kw):
    if not ax: ax=plt.gca()
    p = np.c_[x,y]
    hull = ConvexHull(p)
    poly = plt.Polygon(p[hull.vertices,:], **kw)
    ax.add_patch(poly)

encircle(x1, y1, ec="k", fc="gold", alpha=0.2)
encircle(x2, y2, ec="orange", fc="none")

plt.show()

另一个选择是围绕点云的平均值绘制一个圆圈。

import matplotlib.pyplot as plt
import numpy as np; np.random.seed(1)
from scipy.spatial import ConvexHull

x1, y1 = np.random.normal(loc=5, scale=2, size=(2,15))
x2, y2 = np.random.normal(loc=8, scale=2.5, size=(2,13))

plt.scatter(x1, y1)
plt.scatter(x2, y2)


def encircle2(x,y, ax=None, **kw):
    if not ax: ax=plt.gca()
    p = np.c_[x,y]
    mean = np.mean(p, axis=0)
    d = p-mean
    r = np.max(np.sqrt(d[:,0]**2+d[:,1]**2 ))
    circ = plt.Circle(mean, radius=1.05*r,**kw)
    ax.add_patch(circ)

encircle2(x1, y1, ec="k", fc="gold", alpha=0.2)
encircle2(x2, y2, ec="orange", fc="none")

plt.gca().relim()
plt.gca().autoscale_view()
plt.show()