7.

Develop a program to demonstrate the working of Linear Regression and Polynomial

Regression. Use Boston Housing Dataset for Linear Regression and Auto MPG Dataset
(for vehicle fuel efficiency prediction) for Polynomial Regression.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures, StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.metrics import mean_squared_error, r2_score
def linear_regression_california():
housing = fetch_california_housing(as_frame=True)
X = housing.data[["AveRooms"]]
y = housing.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
plt.scatter(X_test, y_test, color="blue", label="Actual")
plt.plot(X_test, y_pred, color="red", label="Predicted")
plt.xlabel("Average number of rooms (AveRooms)")
plt.ylabel("Median value of homes ($100,000)")
plt.title("Linear Regression - California Housing Dataset")
plt.legend()
plt.show()
print("Linear Regression - California Housing Dataset")
print("Mean Squared Error:", mean_squared_error(y_test, y_pred))
print("R^2 Score:", r2_score(y_test, y_pred))
def polynomial_regression_auto_mpg():
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data"
column_names = ["mpg", "cylinders", "displacement", "horsepower", "weight",
"acceleration", "model_year", "origin"]
data = pd.read_csv(url, sep='\s+', names=column_names, na_values="?")
data = data.dropna()
X = data["displacement"].values.reshape(-1, 1)
y = data["mpg"].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
poly_model = make_pipeline(PolynomialFeatures(degree=2), StandardScaler(),
LinearRegression())
poly_model.fit(X_train, y_train)
y_pred = poly_model.predict(X_test)
plt.scatter(X_test, y_test, color="blue", label="Actual")
plt.scatter(X_test, y_pred, color="red", label="Predicted")
plt.xlabel("Displacement")
plt.ylabel("Miles per gallon (mpg)")
plt.title("Polynomial Regression - Auto MPG Dataset")
plt.legend()
plt.show()
print("Polynomial Regression - Auto MPG Dataset")
print("Mean Squared Error:", mean_squared_error(y_test, y_pred))
print("R^2 Score:", r2_score(y_test, y_pred))
if __name__ == "__main__":
print("Demonstrating Linear Regression and Polynomial Regression\n")
linear_regression_california()
polynomial_regression_auto_mpg()

OUTPUT:
Demonstrating Linear Regression and Polynomial Regression
Linear Regression - California Housing Dataset
Mean Squared Error: 1.2923314440807299
R^2 Score: 0.013795337532284901
Polynomial Regression - Auto MPG Dataset
Mean Squared Error: 0.743149055720586
R^2 Score: 0.7505650609469626
8. Develop a program to demonstrate the working of the decision tree algorithm. Use
Breast Cancer Data set for building the decision tree and apply this knowledge to
classify a new sample.
# Importing necessary libraries
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn import treedata = load_breast_cancer()
X = data.data
y = data.targetX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42)
clf = DecisionTreeClassifier(random_state=42)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)accuracy = accuracy_score(y_test, y_pred)
print(f"Model Accuracy: {accuracy * 100:.2f}%")
new_sample = np.array([X_test[0]])
prediction = clf.predict(new_sample)prediction_class = "Benign" if prediction == 1 else
"Malignant"
print(f"Predicted Class for the new sample: {prediction_class}")plt.figure(figsize=(12,8))
tree.plot_tree(clf,filled=True,feature_names=data.feature_names,class_names=data.target_na
mes)
plt.title("Decision Tree - Breast Cancer Dataset")
plt.show()
OUTPUT:
9. Develop a program to implement the Naive Bayesian classifier considering Olivetti
Face Data set for training. Compute the accuracy of the classifier, considering a few test
data sets.
import numpy as np
from sklearn.datasets import fetch_olivetti_faces
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import matplotlib.pyplot as pltdata = fetch_olivetti_faces(shuffle=True, random_state=42)
X = data.data
y = data.targetX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,
random_state=42)gnb = GaussianNB()
gnb.fit(X_train, y_train)
y_pred = gnb.predict(X_test)accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy * 100:.2f}%')print("\nClassification Report:")
print(classification_report(y_test, y_pred, zero_division=1))print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))cross_val_accuracy = cross_val_score(gnb, X, y,
cv=5, scoring='accuracy')
print(f'\nCross-validation accuracy: {cross_val_accuracy.mean() * 100:.2f}%')fig, axes =
plt.subplots(3, 5, figsize=(12, 8))
for ax, image, label, prediction in zip(axes.ravel(), X_test, y_test, y_pred):
ax.imshow(image.reshape(64, 64), cmap=plt.cm.gray)
ax.set_title(f"True: {label}, Pred: {prediction}")
ax.axis('off')plt.show()
Output:
Accuracy: 80.83%
Classification Report:
precision recall f1-score support
0 0.67 1.00 0.80 2
1 1.00 1.00 1.00 2
2 0.33 0.67 0.44 3
3 1.00 0.00 0.00 5
4 1.00 0.50 0.67 4
5 1.00 1.00 1.00 2
7 1.00 0.75 0.86 4
8 1.00 0.67 0.80 3
9 1.00 0.75 0.86 4
10 1.00 1.00 1.00 3
11 1.00 1.00 1.00 1
12 0.40 1.00 0.57 4
13 1.00 0.80 0.89 5
14 1.00 0.40 0.57 5
15 0.67 1.00 0.80 2
16 1.00 0.67 0.80 3
17 1.00 1.00 1.00 3
18 1.00 1.00 1.00 3
19 0.67 1.00 0.80 2
20 1.00 1.00 1.00 3
21 1.00 0.67 0.80 3
22 1.00 0.60 0.75 5
23 1.00 0.75 0.86 4
24 1.00 1.00 1.00 3
25 1.00 0.75 0.86 4
26 1.00 1.00 1.00 2
27 1.00 1.00 1.00 5
28 0.50 1.00 0.67 2
29 1.00 1.00 1.00 2
30 1.00 1.00 1.00 2
31 1.00 0.75 0.86 4
32 1.00 1.00 1.00 2
34 0.25 1.00 0.40 1
35 1.00 1.00 1.00 5
36 1.00 1.00 1.00 3
37 1.00 1.00 1.00 1
38 1.00 0.75 0.86 4
39 0.50 1.00 0.67 5accuracy 0.81 120
macro avg 0.89 0.85 0.83 120
weighted avg 0.91 0.81 0.81 120Confusion Matrix:
[[2 0 0 ... 0 0 0]
[0 2 0 ... 0 0 0]
[0 0 2 ... 0 0 1]
...
[0 0 0 ... 1 0 0]
[0 0 0 ... 0 3 0]
[0 0 0 ... 0 0 5]]
Cross-validation accuracy: 87.25%

10. Develop a program to implement k-means clustering using Wisconsin Breast Cancer data
set and visualize the clustering result.

PROGRAM:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_breast_cancer
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.metrics import confusion_matrix, classification_report
data = load_breast_cancer()
X = data.data
y = data.target
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
kmeans = KMeans(n_clusters=2, random_state=42)
y_kmeans = kmeans.fit_predict(X_scaled)
print("Confusion Matrix:")
print(confusion_matrix(y, y_kmeans))
print("\nClassification Report:")
print(classification_report(y, y_kmeans))
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_scaled)
df = pd.DataFrame(X_pca, columns=['PC1', 'PC2'])
df['Cluster'] = y_kmeans
df['True Label'] = y
plt.figure(figsize=(8, 6))
sns.scatterplot(data=df, x='PC1', y='PC2', hue='Cluster', palette='Set1', s=100,
edgecolor='black', alpha=0.7)
plt.title('K-Means Clustering of Breast Cancer Dataset')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title="Cluster")
plt.show()
plt.figure(figsize=(8, 6))
sns.scatterplot(data=df, x='PC1', y='PC2', hue='True Label', palette='coolwarm', s=100,
edgecolor='black', alpha=0.7)
plt.title('True Labels of Breast Cancer Dataset')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title="True Label")
plt.show()
plt.figure(figsize=(8, 6))
sns.scatterplot(data=df, x='PC1', y='PC2', hue='Cluster', palette='Set1', s=100,
edgecolor='black', alpha=0.7)
centers = pca.transform(kmeans.cluster_centers_)
plt.scatter(centers[:, 0], centers[:, 1], s=200, c='red', marker='X', label='Centroids')
plt.title('K-Means Clustering with Centroids')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title="Cluster")
plt.show()
Output:
Confusion Matrix:
[[175 37]
[ 13 344]]

Classification Report:
precision recall f1-score support

0 0.93 0.83 0.88 212

1 0.90 0.96 0.93 357

accuracy 0.91 569

macro avg 0.92 0.89 0.90 569
weighted avg 0.91 0.91 0.91 569