Ass6
Set A
1. Write a python program to implement k-means algorithm to build prediction model
(Use Credit Card Dataset CC GENERAL.csv Download from kaggle.com)
import numpy as nm
import matplotlib.pyplot as mtp
import pandas as pd
# Load the dataset
df = pd.read_csv('CC GENERAL.csv')
# Display the first few rows of the dataset
print(df.head())
# Check for missing values and drop rows with NaN values
df.dropna(inplace=True)
# Selecting relevant features for clustering (you can choose which features to use)
features = df.drop(columns=['CUST_ID']).values # Using .values to get numpy array
# K-Means Clustering Implementation
def kmeans(X, k, max_iters=100):
# Randomly initialize the centroids
centroids = X[nm.random.choice(X.shape[0], k, replace=False)]
for _ in range(max_iters):
# Calculate distances from data points to centroids
distances = nm.linalg.norm(X[:, nm.newaxis] - centroids, axis=2)
# Assign clusters based on closest centroid
labels = nm.argmin(distances, axis=1)
# Calculate new centroids
new_centroids = nm.array([X[labels == i].mean(axis=0) for i in range(k)])
# If centroids do not change, break
if nm.all(centroids == new_centroids):
break
centroids = new_centroids
return labels, centroids
# Specify the number of clusters
k = 4 # You can adjust this based on your analysis
# Run K-Means
labels, centroids = kmeans(features, k)
# Add cluster labels to the dataframe
df['Cluster'] = labels
# Display the first few rows with cluster labels
print(df.head())
# Optional: Plotting clusters (use only 2 features for visualization)
mtp.scatter(features[:, 0], features[:, 1], c=labels, cmap='viridis', marker='o',
edgecolor='k')
mtp.scatter(centroids[:, 0], centroids[:, 1], c='red', s=200, alpha=0.75,
marker='X') # Plot centroids
mtp.title('K-Means Clustering of Credit Card Data')
mtp.xlabel('Feature 1')
mtp.ylabel('Feature 2')
mtp.show()
2. Write a python program to implement hierarchical Agglomerative clustering
algorithm.
(Download Customer.csv dataset from github.com).
url---> https://gist.github.com/akuks/2e9b08cebef0181b583a1dff4a97f8a1
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import AgglomerativeClustering
from sklearn.preprocessing import StandardScaler
# Load the dataset directly from the URL
url = 'Customer.csv' # Replace with the actual URL
df = pd.read_csv(url)
# Display the first few rows of the dataset
print(df.head())
# Check for missing values
print(df.isnull().sum())
# Drop rows with missing values (if any)
df.dropna(inplace=True)
# Convert DOB to age - specify the date format
df['DOB'] = pd.to_datetime(df['DOB'], format='%d/%m/%y %H:%M', dayfirst=True) #
Adjust the format for day first
df['Age'] = (pd.Timestamp.now() - df['DOB']).dt.days // 365 # Calculate age in
years
# Select relevant features for clustering
features = df[['Age', 'Gender']]
# One-hot encode the categorical 'Gender' feature
features_encoded = pd.get_dummies(features, columns=['Gender'], drop_first=True)
# Check the resulting DataFrame after encoding
print("Encoded Features:\n", features_encoded.head())
print("Columns after Encoding:", features_encoded.columns.tolist())
# Standardize the features
scaler = StandardScaler()
features_scaled = scaler.fit_transform(features_encoded)
# Perform Hierarchical Agglomerative Clustering
model = AgglomerativeClustering(n_clusters=4) # Adjust the number of clusters as
needed
labels = model.fit_predict(features_scaled)
# Add cluster labels to the original dataframe
df['Cluster'] = labels
# Display the first few rows with cluster labels
print(df.head())
# Check the unique labels
print("Unique Cluster Labels:", df['Cluster'].unique())
# Optional: Plotting the clusters (use only Age and one gender column for
visualization)
gender_column = features_encoded.columns[1] # Assuming the first column is 'Age'
plt.figure(figsize=(10, 6))
plt.scatter(df['Age'], features_encoded[gender_column], c=labels, cmap='viridis',
marker='o', edgecolor='k')
plt.title('Hierarchical Agglomerative Clustering of Customers')
plt.xlabel('Age')
plt.ylabel(gender_column) # Update the y-label to match the gender column
plt.colorbar(label='Cluster')
plt.grid(True) # Add grid for better readability
plt.show()
# Optional: Dendrogram for visualizing hierarchical clustering
plt.figure(figsize=(10, 6))
from scipy.cluster.hierarchy import dendrogram, linkage
linked = linkage(features_scaled, 'ward')
dendrogram(linked,
orientation='top',
distance_sort='descending',
show_leaf_counts=True)
plt.title('Dendrogram for Hierarchical Clustering')
plt.xlabel('Sample Index')
plt.ylabel('Distance')
plt.grid(True) # Add grid for better readability
plt.show()
Set B
1. Write a python program to implement k-means algorithms on a synthetic dataset.
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Step 1: Generate a synthetic dataset
from sklearn.datasets import make_blobs
# Generate synthetic data with 3 clusters
n_samples = 300
n_features = 2
n_clusters = 3
random_state = 42
X, y = make_blobs(n_samples=n_samples, centers=n_clusters, n_features=n_features,
random_state=random_state)
# Convert to a DataFrame for easier manipulation
data = pd.DataFrame(X, columns=['Feature_1', 'Feature_2'])
# Step 2: Visualize the synthetic dataset
plt.figure(figsize=(10, 6))
plt.scatter(data['Feature_1'], data['Feature_2'], s=30)
plt.title('Synthetic Dataset')
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.grid()
plt.show()
# Step 3: Implement K-Means algorithm
def k_means(X, n_clusters, n_iterations=100):
# Step 3.1: Randomly initialize the centroids
centroids = X.sample(n_clusters).to_numpy()
for _ in range(n_iterations):
# Step 3.2: Assign clusters based on closest centroid
distances = np.linalg.norm(X.to_numpy()[:, np.newaxis] - centroids, axis=2)
labels = np.argmin(distances, axis=1)
# Step 3.3: Update centroids based on mean of assigned points
new_centroids = np.array([X.to_numpy()[labels == k].mean(axis=0) for k in
range(n_clusters)])
# Step 3.4: Check for convergence
if np.all(centroids == new_centroids):
break
centroids = new_centroids
return labels, centroids
# Step 4: Run K-Means algorithm
labels, centroids = k_means(data, n_clusters)
# Step 5: Visualize the clustering results
plt.figure(figsize=(10, 6))
plt.scatter(data['Feature_1'], data['Feature_2'], c=labels, s=30, cmap='viridis',
marker='o', edgecolor='k')
plt.scatter(centroids[:, 0], centroids[:, 1], c='red', s=200, alpha=0.75,
marker='X') # Centroids
plt.title('K-Means Clustering Results')
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.grid()
plt.show()
2. Write a python program to implement hierarchical clustering algorithm. (Download
Wholesale customers data dataset from github.com).
url----> https://github.com/TrainingByPackt/Data-Science-with-Python/blob/master/
Chapter01/Data/Wholesale%20customers%20data.csv
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import dendrogram, linkage, fcluster
# Step 1: Load the dataset
# Replace 'path_to_your_dataset' with the actual path to your dataset
url = 'wholesale-customer.csv'
df = pd.read_csv(url)
# Step 2: Preprocessing the data
# Dropping non-numeric columns (Channel and Region)
data = df.drop(['Channel', 'Region'], axis=1)
# Step 3: Perform Hierarchical Clustering
# Linkage matrix
Z = linkage(data, method='ward')
# Step 4: Plotting the Dendrogram
plt.figure(figsize=(12, 8))
dendrogram(Z, truncate_mode='level', p=3)
plt.title('Dendrogram for Hierarchical Clustering')
plt.xlabel('Customers')
plt.ylabel('Distance')
plt.grid()
plt.show()
# Step 5: Form clusters
# Define the number of clusters (e.g., 3)
n_clusters = 3
clusters = fcluster(Z, n_clusters, criterion='maxclust')
# Step 6: Add cluster labels to the original DataFrame
df['Cluster'] = clusters
# Step 7: Visualize the clusters
# For visualization, let's plot the first two features (Fresh and Milk)
plt.figure(figsize=(10, 6))
plt.scatter(df['Fresh'], df['Milk'], c=df['Cluster'], cmap='viridis', s=100)
plt.title('Hierarchical Clustering of Wholesale Customers')
plt.xlabel('Fresh Products')
plt.ylabel('Milk Products')
plt.grid()
plt.colorbar(label='Cluster')
plt.show()
Set C
1. Write a python program to implement Agglomerative clustering on a synthetic
dataset.
(use inbuilt Iris data set).
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.cluster import AgglomerativeClustering
from sklearn.decomposition import PCA
# Step 1: Load the Iris dataset
iris = load_iris()
X = iris.data # Features
y = iris.target # True labels (for comparison)
# Step 2: Perform Agglomerative Clustering
# Choose the number of clusters (e.g., 3)
n_clusters = 3
agg_clustering = AgglomerativeClustering(n_clusters=n_clusters)
clusters = agg_clustering.fit_predict(X)
# Step 3: Reduce dimensions for visualization (using PCA)
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X)
# Step 4: Plot the clusters
plt.figure(figsize=(10, 6))
plt.scatter(X_pca[:, 0], X_pca[:, 1], c=clusters, cmap='viridis', marker='o',
edgecolor='k', s=100)
plt.title('Agglomerative Clustering on Iris Dataset')
plt.xlabel('PCA Component 1')
plt.ylabel('PCA Component 2')
plt.grid()
plt.colorbar(label='Cluster Label')
plt.show()
# Optional: Compare with true labels
plt.figure(figsize=(10, 6))
plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='viridis', marker='o',
edgecolor='k', s=100)
plt.title('True Labels of Iris Dataset')
plt.xlabel('PCA Component 1')
plt.ylabel('PCA Component 2')
plt.grid()
plt.colorbar(label='True Label')
plt.show()
