Scribd Logo
Upload

Welcome to Scribd!

  • 5 views

    INTRO TO ML ASS

    Uploaded by

    gayukalai67

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    INTRO TO ML ASS

    Uploaded by

    gayukalai67
    5 views3 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    5 views3 pages

    INTRO TO ML ASS

    Uploaded by

    gayukalai67

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 3

    INTRODUCTION TO MACHINE LEARNING

    NAME:GAYATHRI.K
    REG NO:212223230061

    Assignment: K-Means Clustering

    1. Introduction to Clustering:

    Clustering is a form of unsupervised learning where data is grouped based on similarities.


    Unlike supervised learning, there are no predefined labels in clustering. Instead, the algorithm
    identifies patterns or groupings within the data.

    K-Means clustering is a popular clustering algorithm that divides a dataset into kkk distinct
    non-overlapping clusters. Each cluster is defined by its centroid, and data points are assigned to
    the cluster with the closest centroid.

    2. Applications of K-Means Clustering:

    1. Market Segmentation: Group customers based on purchasing behavior.


    2. Image Compression: Reduce the number of colors in images by grouping similar
    colors.
    3. Document Clustering: Group similar documents or articles for better organization.
    4. Anomaly Detection: Identify outliers in datasets for fraud detection or security.

    3. K-Means Algorithm Steps:

    1. Initialize kkk centroids randomly or using a specific method.


    2. Assign each data point to the nearest centroid based on a distance metric (e.g.,
    Euclidean distance).
    3. Update the centroids by calculating the mean of the points assigned to each cluster.
    4. Repeat steps 2 and 3 until:
    ○ Centroids no longer change, or
    ○ A predefined number of iterations is reached.
    4. Advantages and Disadvantages:

    Advantages:

    ● Simple and easy to implement.


    ● Efficient with large datasets.
    ● Works well when clusters are distinct and well-separated.

    Disadvantages:

    ● Sensitive to the initial placement of centroids.


    ● Struggles with clusters of varying sizes and densities.
    ● Requires the number of clusters (kkk) to be specified beforehand.

    5. Python Implementation:

    The dataset consists of 2D points:

    Points: (2,3),(3,3),(6,7),(8,8),(3,5),(7,6)\text{Points: } (2, 3), (3, 3), (6, 7), (8, 8), (3, 5), (7,
    6)Points: (2,3),(3,3),(6,7),(8,8),(3,5),(7,6)

    Code:
    import numpy as np

    # Example dataset
    data = np.array([[2, 3], [3, 3], [6, 7], [8, 8], [3, 5], [7, 6]])
    k = 2 # Number of clusters

    # Initialize centroids randomly


    centroids = data[np.random.choice(data.shape[0], k, replace=False)]

    # K-Means algorithm
    for _ in range(100): # Max iterations
    clusters = [[] for _ in range(k)]
    for point in data:
    # Assign points to the nearest centroid
    idx = np.argmin([np.linalg.norm(point - c) for c in centroids])
    clusters[idx].append(point)

    # Update centroids
    new_centroids = [np.mean(cluster, axis=0) if cluster else centroids[i]
    for i, cluster in enumerate(clusters)]
    if np.allclose(new_centroids, centroids): # Check for convergence
    break
    centroids = new_centroids

    # Display results
    for i, cluster in enumerate(clusters):
    print(f"Cluster {i+1}: {cluster}")
    print(f"Final Centroids: {centroids}")

    7. Conclusion:

    The K-Means algorithm is a powerful clustering technique for grouping similar data. Its simplicity
    and scalability make it a popular choice for many practical applications. However, understanding
    its limitations and choosing kkk wisely are critical for optimal performance.

    You might also like