Matplotlib patch not getting applied properly

Question

enter image description here

I expected something like above to be applied to my scatter plot.but instead i received this

enter image description here

code is as below

# Data
import matplotlib.patches as patches
df1=pd.DataFrame({'x_pos': x, 'y_pos': y })
print(df1)
 
# Plot
fig1 = plt.figure(figsize=(20,10))
ax1 = fig1.add_subplot(111)
ax1.plot( 'x_pos', 'y_pos', data=df1, linestyle='none', marker='o')
 
# Annotation
ax1.add_patch(
patches.Circle(
(35, 40), 
3, 
alpha=0.3, facecolor="green", edgecolor="black", linewidth=1, linestyle='solid'
)
)
# Show the graph
plt.show()

Dataframe

 x_pos y_pos
0 38 62506
3 33 64991
4 32 50825
5 44 57568
7 38 59365
.. ... ...
301 44 55140
302 38 58062
303 48 59728
307 39 48513
310 43 45046

what am I doing wrong here ?

• JohanC: You are creating a circle with center (35, 40), while the data points are far away, having x-values around 40 and y-values around 60,000. Also note that when there is a large difference in aspect ratio between the x and y direction, the circle will be squeezed to a thin ellipse.
• Sithija Piyuman Thewa Hettige: how can i fix the issue ? @JohanC
• JohanC: Maybe use another center? Maybe draw an ellipse with a larger y radius? What do you want to show?
• Sithija Piyuman Thewa Hettige: i want to highlight the middle section of the graph with a patch

Answer 1

You could use the mean of the x and the y positions as the center for an ellipse. And the standard deviation in x and in y for its radius in both directions. Note that for an ellipse, the parameters are the width and height, so the double of the radius.

from matplotlib import pyplot as plt
from matplotlib import patches
import pandas as pd
import numpy as np
df1 = pd.DataFrame({'x_pos': np.random.randint(32, 49, 100),
 'y_pos': np.random.randint(45000, 63000, 100)})
fig1 = plt.figure(figsize=(20, 10))
ax1 = fig1.add_subplot(111)
ax1.plot('x_pos', 'y_pos', data=df1, linestyle='none', marker='o')
ax1.add_patch(
 patches.Ellipse(
 (df1['x_pos'].mean(), df1['y_pos'].mean()),
 df1['x_pos'].std() * 2, df1['y_pos'].std() * 2,
 alpha=0.3, facecolor="green", edgecolor="black", linewidth=1, linestyle='solid'))
plt.show()

adding an ellipse near the center of a set of points

See also this tutorial example or this post about drawing a confidence ellipse.

Here is how the code could look like to draw confidence ellipses for 1,2 and 3 standard deviations (using rotated data to test the ellipse rotation):

from matplotlib import pyplot as plt
from matplotlib import patches
import pandas as pd
import numpy as np
x = np.random.randint(32, 49, 100)
y = np.random.randint(45000, 50000, 100) + x * 500
df1 = pd.DataFrame({'x_pos': x, 'y_pos': y})
lamda, v = np.linalg.eig(np.cov(df1['x_pos'], df1['y_pos']))
lamda = np.sqrt(lamda)
fig1 = plt.figure(figsize=(20, 10))
ax1 = fig1.add_subplot(111)
ax1.plot('x_pos', 'y_pos', data=df1, linestyle='none', marker='o')
for num_std in range(1, 4):
 ax1.add_patch(
 patches.Ellipse(
 xy=(df1['x_pos'].mean(), df1['y_pos'].mean()),
 angle=np.rad2deg(np.arctan2(*v[:, 0][::-1])),
 width=lamda[0] * num_std * 2, height=lamda[1] * num_std * 2,
 alpha=0.1, facecolor="green", edgecolor="black", linewidth=1, linestyle='solid'))
plt.show()

drawing confidence ellipses