import numpy as np
from sklearn.linear_model import SGDClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
# Provided dataset
X = np.array([
[5.2, 2.7], [5.8, 2.7], [5.0, 2.0], [6.4, 2.9], [5.0, 3.5], [6.9, 3.1], [5.8, 2.7], [6.0, 2.2],
[4.7, 3.2], [6.3, 2.3], [6.7, 2.5], [6.3, 2.7], [6.7, 3.1], [4.9, 2.4], [5.8, 4.0], [6.4, 3.2],
[5.9, 3.2], [5.1, 3.5], [5.4, 3.9], [6.1, 2.9], [4.8, 3.4], [5.5, 3.5], [5.0, 3.2], [5.0, 3.4],
[7.0, 3.2], [5.7, 4.4], [4.8, 3.1], [5.0, 3.5], [6.2, 2.8], [6.3, 2.5], [7.9, 3.8], [5.6, 2.9],
[7.7, 2.8], [5.9, 3.0], [7.2, 3.0], [7.7, 3.8], [4.9, 2.5], [6.3, 3.3], [6.1, 3.0], [5.1, 3.4],
[6.3, 2.9], [5.6, 2.8], [5.8, 2.7], [6.3, 2.5], [4.8, 3.0], [5.0, 3.0], [6.8, 2.8], [6.5, 3.0],
[4.9, 3.0], [7.2, 3.6], [5.5, 2.6], [4.8, 3.4], [5.4, 3.0], [7.3, 2.9], [6.7, 3.3], [6.0, 2.2],
[5.1, 3.8], [4.9, 3.1], [6.7, 3.3], [4.4, 3.2], [6.5, 3.2], [6.0, 2.9], [5.5, 4.2], [5.2, 4.1],
[6.4, 2.8], [5.5, 2.4], [5.6, 3.0], [5.1, 3.3], [4.8, 3.0], [5.6, 2.5], [6.1, 2.8], [7.7, 2.6],
[5.9, 3.0], [6.6, 3.0], [4.4, 3.0], [6.0, 3.4], [6.9, 3.1], [6.7, 3.0], [6.9, 3.1], [5.1, 3.7],
[6.7, 3.0], [6.7, 3.1], [6.3, 3.3], [6.8, 3.0], [5.1, 2.5], [4.9, 3.1], [4.6, 3.2], [5.4, 3.4],
[6.4, 2.8], [6.2, 3.4], [4.6, 3.1], [6.0, 3.0], [4.6, 3.4], [5.0, 2.3], [7.6, 3.0], [5.7, 2.8],
[6.2, 2.9], [4.3, 3.0], [6.5, 3.0], [4.9, 3.1], [6.8, 3.2], [6.2, 2.2], [6.3, 2.8], [5.0, 3.4],
[6.9, 3.2], [5.1, 3.8], [5.3, 3.7], [5.7, 2.5], [6.1, 3.0], [6.6, 2.9], [5.7, 2.8], [4.7, 3.2],
[6.4, 2.7], [5.5, 2.3], [5.7, 3.0], [7.7, 3.0], [7.4, 2.8], [6.4, 3.2], [5.5, 2.4], [5.5, 2.5],
[5.1, 3.8], [7.1, 3.0], [6.5, 3.0], [5.8, 2.8], [5.8, 2.7], [5.1, 3.5], [5.0, 3.3], [4.5, 2.3],
[6.7, 3.1], [5.4, 3.9], [7.2, 3.2], [6.1, 2.8], [6.4, 3.1], [6.5, 2.8], [6.0, 2.7], [4.6, 3.6],
[5.6, 3.0], [6.1, 2.6], [5.7, 2.9], [6.3, 3.4], [5.2, 3.4], [5.6, 2.7], [5.4, 3.7], [5.8, 2.6],
[5.4, 3.4], [5.0, 3.6], [5.7, 3.8], [5.2, 3.5], [4.4, 2.9]
])
y = np.array([
1, 2, 1, 1, 0, 2, 2, 1, 0, 1, 2, 2, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0,
1, 0, 0, 0, 2, 2, 2, 1, 2, 2, 2, 2, 2, 1, 2, 0, 2, 2, 1, 1, 0, 0, 1, 2,
0, 2, 1, 0, 1, 2, 2, 2, 0, 0, 2, 0, 2, 1, 0, 0, 2, 1, 1, 0, 0, 1, 1, 2,
1, 1, 0, 1, 1, 1, 2, 0, 2, 1, 2, 2, 1, 0, 0, 0, 2, 2, 0, 2, 0, 1, 2, 1,
1, 0, 2, 0, 2, 1, 2, 1, 0, 2, 0, 0, 2, 1, 1, 1, 0, 2, 1, 1, 2, 2, 2, 1,
1, 0, 2, 2, 2, 1, 0, 0, 0, 2, 0, 2, 1, 2, 1, 1, 0, 1, 2, 1, 2, 0, 1, 0,
1, 0, 0, 0, 0, 0
])
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
# Train with L1 penalty
clf_l1 = SGDClassifier(loss='perceptron', penalty='l1', alpha=0.0001, max_iter=1000, tol=1e-3,
random_state=42)
clf_l1.fit(X_train, y_train)
y_pred_l1 = clf_l1.predict(X_test)
accuracy_l1 = accuracy_score(y_test, y_pred_l1)
# Train with L2 penalty
clf_l2 = SGDClassifier(loss='perceptron', penalty='l2', alpha=0.0001, max_iter=1000, tol=1e-3,
random_state=42)
clf_l2.fit(X_train, y_train)
y_pred_l2 = clf_l2.predict(X_test)
accuracy_l2 = accuracy_score(y_test, y_pred_l2)
print(f"Accuracy with L1 penalty: {accuracy_l1}")
print(f"Accuracy with L2 penalty: {accuracy_l2}")
