Different output results for same code in Perceptron project on VS Code and Codecademy

Link to project: https://www.codecademy.com/paths/machine-learning/tracks/perceptrons-and-neural-nets-skill-path/modules/perceptrons-skill-path/projects/perceptron-logic-gates

I wrote my code for this project in VS Code using Python 3.8.5 and found that the same code copied into Codecademy produced a different result. I am curious as to why the output would be different.

Namely, the output to question 9 is what changes.

In VS Code, the output to the following print function is [-2. 2. 0.].

print(classifier.decision_function([[0, 0], [1, 1], [0.5, 0.5]]))

In Codecademy, the output is [-4. 1. -1.5].

Why are these outputs different for the same code?

Here is my code.

from sklearn.linear_model import Perceptron
import matplotlib.pyplot as plt
import numpy as np
from itertools import product

data = [[0,0],[0,1],[1,0],[1,1]]
labels = [0,0,0,1]

classifier = Perceptron(max_iter = 40)
classifier.fit(data, labels)
print(classifier.score(data, labels))

print(classifier.decision_function([[0, 0], [1, 1], [0.5, 0.5]]))

x_values = np.linspace(0,1,100)
y_values = np.linspace(0,1,100)
point_grid = list(product(x_values, y_values))
distances = classifier.decision_function(point_grid)
abs_distances = [abs(point) for point in distances]

distances_matrix = np.reshape(abs_distances, (100, 100))

heatmap = plt.pcolormesh(x_values, y_values, distances_matrix)
plt.colorbar(heatmap)

plt.scatter([point[0] for point in data], [point[1] for point in data], c= labels)
plt.show()

It’s not something I’ve used before but I think the versions will be quite a bit different between the two (probably both Python itself and the installed packages). You could check what’s being used on CC and install the same to see if you can replicate the results difference.
Apologies if that doesn’t help.