7.

Write a program to implement Hierarchical clustering

import numpy as np

import matplotlib.pyplot as plt

from sklearn.datasets import load_iris

from sklearn.cluster import AgglomerativeClustering

from sklearn.preprocessing import StandardScaler

from scipy.cluster.hierarchy import dendrogram, linkage

# Step 1: Load the Iris dataset

data = load_iris()

X = data.data # Features

# Step 2: Standardize the features

scaler = StandardScaler()

X_scaled = scaler.fit_transform(X)

# Step 3: Apply Agglomerative Hierarchical Clustering

agg_clust = AgglomerativeClustering(n_clusters=3, affinity='euclidean', linkage='ward')

labels = agg_clust.fit_predict(X_scaled)

# Step 4: Visualize the results using a dendrogram

linked = linkage(X_scaled, method='ward')

plt.figure(figsize=(10, 7))

dendrogram(linked, labels=data.target_names[labels])

plt.title('Hierarchical Clustering Dendrogram (Iris Dataset)')

plt.ylabel('Distance')

plt.show()

# Step 5: Output the cluster labels

print("Cluster Labels: ", labels)

Output :
8. Write a program to implement Support Vector Machine algorithm
import numpy as np

import matplotlib.pyplot as plt

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

from sklearn.svm import SVC

from sklearn.metrics import accuracy_score, classification_report

# Step 1: Load the Iris dataset

data = load_iris()

X = data.data # Features

y = data.target # Target (class labels)

# Step 2: 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)

model = SVC(kernel='linear') # Using a linear kernel

model.fit(X_train, y_train)

# Step 4: Make predictions on the test set

y_pred = model.predict(X_test)

# Step 5: Evaluate the model

accuracy = accuracy_score(y_test, y_pred)

class_report = classification_report(y_test, y_pred, target_names=data.target_names)

# Step 6: Print the evaluation results

print("Accuracy: ", accuracy)

print("\nClassification Report:\n", class_report)

# Step 7: Visualize the decision boundary (Only using the first two features for simplicity)

plt.figure(figsize=(8, 6))

# Plot the data points

plt.scatter(X_test[:, 0], X_test[:, 1], c=y_pred, cmap='coolwarm', edgecolors='k', marker='o', s=100,

# Plot decision boundary

h = 0.02 # Step size in the mesh

x_min, x_max = X_test[:, 0].min() - 1, X_test[:, 0].max() + 1

y_min, y_max = X_test[:, 1].min() - 1, X_test[:, 1].max() + 1

Z = model.predict(np.c_[xx.ravel(), yy.ravel()])

Z = Z.reshape(xx.shape)

plt.contourf(xx, yy, Z, alpha=0.3)

plt.xlabel("Feature 1")

plt.ylabel("Feature 2")

plt.title("SVM Classifier (Iris Dataset)")

plt.colorbar()

plt.show()

Output:
9. Write a program to implement clustering using random forest algorithm using
an appropriate dataset.
import numpy as np

import matplotlib.pyplot as plt

from sklearn.datasets import load_iris

from sklearn.ensemble import RandomForestClassifier

from sklearn.model_selection import train_test_split

from sklearn.metrics import accuracy_score

# Step 1: Load the Iris dataset

data = load_iris()

X = data.data # Features

y = data.target # Target (class labels)

# Step 2: 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)

# Step 3: Create and train the Random Forest classifier

rf_model = RandomForestClassifier(n_estimators=100, random_state=42)

rf_model.fit(X_train, y_train)
# Step 4: Make predictions on the test set

y_pred = rf_model.predict(X_test)

# Step 5: Evaluate the model

accuracy = accuracy_score(y_test, y_pred)

print("Accuracy: ", accuracy)

# Step 6: Visualize the clusters (use the first two features for simplicity)

plt.figure(figsize=(8, 6))

plt.scatter(X_test[:, 0], X_test[:, 1], c=y_pred, cmap='viridis', marker='o', edgecolor='k', s=100,

plt.title('Random Forest Classifier "Clustering" (Iris Dataset)')

plt.xlabel('Feature 1')

plt.ylabel('Feature 2')

plt.colorbar(label='Predicted Cluster')

plt.show()

# Step 7: Output the predicted labels (cluster-like grouping)

print("Predicted Cluster Labels: ", y_pred)

OUTPUT:

10. Write a program to implement Forecasting using ARIMA Model

import matplotlib.pyplot as plt

from statsmodels.tsa.arima.model import ARIMA

from sklearn.model_selection import train_test_split

from statsmodels.graphics.tsaplots import plot_acf, plot_pacf

# Step 1: Load the dataset (Airline Passengers dataset)

url = 'https://raw.githubusercontent.com/jbrownlee/Datasets/master/airline-passengers.csv'

data = pd.read_csv(url, header=0, parse_dates=[0], index_col=0, squeeze=True)

# Step 2: Visualize the dataset

plt.figure(figsize=(10,6))

plt.plot(data)

plt.title('Monthly Number of Airline Passengers')

plt.xlabel('Date')

plt.ylabel('Number of Passengers')

plt.show()

# Step 3: Split the data into training and testing sets

train_size = int(len(data) * 0.8)

train, test = data[0:train_size], data[train_size:]

# Step 4: Visualize ACF and PACF plots for choosing p, d, q values

plot_acf(train, lags=40)

plot_pacf(train, lags=40)

plt.show()
# Step 5: Fit the ARIMA model

# ARIMA(p, d, q) where p is the number of lag observations included in the model (AR), d is the number
of times the raw observations are differenced,

# and q is the size of the moving average window.

model = ARIMA(train, order=(5, 1, 0)) # (p=5, d=1, q=0) - Adjust these parameters based on your ACF
and PACF plots

model_fit = model.fit()

# Step 6: Make predictions on the test set

forecast = model_fit.forecast(steps=len(test))

# Step 7: Visualize the actual vs predicted values

plt.figure(figsize=(10,6))

plt.plot(train, label='Train')

plt.plot(test, label='Test')

plt.plot(test.index, forecast, label='Forecast', color='red')

plt.title('ARIMA Model Forecasting')

plt.xlabel('Date')

plt.ylabel('Number of Passengers')

plt.legend()

plt.show()

# Step 8: Evaluate the model

# Calculate Mean Squared Error (MSE) or other evaluation metrics

from sklearn.metrics import mean_squared_error

mse = mean_squared_error(test, forecast)

print(f'Mean Squared Error: {mse}')