Scribd
Upload
3 views

ml-5_31

The document outlines a series of Python scripts using the SVM classifier from the sklearn library to analyze the Iris dataset. It demonstrates training and testing the SVM model, calculating hinge loss and accuracy, and visualizing decision boundaries for different regularization parameters. The results indicate perfect accuracy on the test set and provide visual insights into the model's performance with varying regularization values.

Uploaded by

smkk0304
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

ml-5_31

The document outlines a series of Python scripts using the SVM classifier from the sklearn library to analyze the Iris dataset. It demonstrates training and testing the SVM model, calculating hinge loss and accuracy, and visualizing decision boundaries for different regularization parameters. The results indicate perfect accuracy on the test set and provide visual insights into the model's performance with varying regularization values.

Uploaded by

smkk0304
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

Ml- EXP 5

[ ]: import numpy as np
from sklearn import datasets
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.metrics import hinge_loss

iris = datasets.load_iris()
X = iris.data
y = iris.target
X = X[y != 2]
y = y[y != 2]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,␣
↪random_state=42)

svm = SVC(kernel='linear', C=1, random_state=42)


svm.fit(X_train, y_train)
y_pred = svm.predict(X_test)
decision_values = svm.decision_function(X_test)
hinge_loss_value = hinge_loss(y_test, decision_values)
print(f'Hinge Loss on Test Set: {hinge_loss_value}')
new_data_points = np.array([[5.1, 3.5, 1.4, 0.2],
[6.7, 3.1, 4.7, 1.5]])
new_predictions = svm.predict(new_data_points)
print(f'Predictions for new data points: {new_predictions}')

Hinge Loss on Test Set: 0.0


Predictions for new data points: [0 1]

[ ]: import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
data = datasets.load_iris()
X = data.data
y = data.target
X = X[y != 2]
y = y[y != 2]

1
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,␣
↪random_state=42)
svm = SVC(kernel='linear', C=1.0)
svm.fit(X_train, y_train)
y_pred = svm.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy:.4f}')
plt.figure(figsize=(8, 6))
X_train_2d = X_train[:, :2]
X_test_2d = X_test[:, :2]
svm_2d = SVC(kernel='linear', C=1.0)
svm_2d.fit(X_train_2d, y_train)
xx, yy = np.meshgrid(np.linspace(X_train_2d[:, 0].min() - 1, X_train_2d[:, 0]. ↪max() + 1,
100),
np.linspace(X_train_2d[:, 1].min() - 1, X_train_2d[:, 1].
↪max() + 1, 100))

Z = svm_2d.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, alpha=0.75)
plt.scatter(X_train_2d[:, 0], X_train_2d[:, 1], c=y_train, edgecolors='k',␣ ↪marker='o',
s=100, label='Train Data')
plt.scatter(X_test_2d[:, 0], X_test_2d[:, 1], c=y_test, edgecolors='r',␣ ↪marker='^',
s=100, label='Test Data')
plt.title('SVM Decision Boundary (2D)')
plt.xlabel('Feature 1 (Sepal Length)')
plt.ylabel('Feature 2 (Sepal Width)')
plt.legend()
plt.show()

Accuracy: 1.0000
2

[ ]: import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt

data = datasets.load_iris()
X = data.data
y = data.target

X = X[y != 2]
y = y[y != 2]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,␣


↪random_state=42)

def plot_svm_decision_boundary(C_values):
plt.figure(figsize=(12, 8))

3
accuracies = []

for C in C_values:
svm = SVC(kernel='linear', C=C)
svm.fit(X_train[:, :2], y_train)

y_pred = svm.predict(X_test[:, :2])


accuracy = accuracy_score(y_test, y_pred)
accuracies.append(accuracy)

xx, yy = np.meshgrid(np.linspace(X_train[:, 0].min() - 1, X_train[:, 0]. ↪max() + 1, 100),


np.linspace(X_train[:, 1].min() - 1, X_train[:, 1].
↪max() + 1, 100))

Z = svm.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)

plt.subplot(2, 3, C_values.index(C) + 1)
plt.contourf(xx, yy, Z, alpha=0.75)
plt.scatter(X_train[:, 0], X_train[:, 1], c=y_train, edgecolors='k',␣ ↪marker='o',
s=100, label='Train Data')
plt.scatter(X_test[:, 0], X_test[:, 1], c=y_test, edgecolors='r',␣ ↪marker='^',
s=100, label='Test Data')
plt.title(f'SVM Decision Boundary for C={C}')
plt.xlabel('Feature 1 (Sepal Length)')
plt.ylabel('Feature 2 (Sepal Width)')
plt.legend()

plt.figure(figsize=(8, 6))
plt.plot(C_values, accuracies, marker='o', linestyle='-', color='b') plt.xscale('log')
plt.xlabel('Regularization Parameter (C)')
plt.ylabel('Test Accuracy')
plt.title('Effect of Regularization (C) on SVM Accuracy')
plt.grid(True)
plt.show()

C_values = [0.01, 0.1, 1, 10, 100]

plot_svm_decision_boundary(C_values)

5
6

You might also like