Scribd Logo
Upload

Welcome to Scribd!

  • 44 views

    21BEC505 Exp2

    Uploaded by

    jay
    The document describes an experiment applying k-means clustering to unlabeled datasets. It shows how k-means clustering was used to group 2D points into a varying number of clusters (task 1) and to cluster customers based on annual income and spending score from a CSV file (task 2). Exercises include clustering other datasets, identifying performance metrics for clustering, and generating a synthetic 7-cluster dataset to analyze elbow method and visualize clusters. The conclusion discusses clustering algorithms like k-means and DBSCAN as well as approaches for choosing the optimal number of clusters.

    Copyright:

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

    21BEC505 Exp2

    Uploaded by

    jay
    44 views7 pages
    The document describes an experiment applying k-means clustering to unlabeled datasets. It shows how k-means clustering was used to group 2D points into a varying number of clusters (task 1) and to cluster customers based on annual income and spending score from a CSV file (task 2). Exercises include clustering other datasets, identifying performance metrics for clustering, and generating a synthetic 7-cluster dataset to analyze elbow method and visualize clusters. The conclusion discusses clustering algorithms like k-means and DBSCAN as well as approaches for choosing the optimal number of clusters.

    Original Title

    21BEC505_exp2

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes an experiment applying k-means clustering to unlabeled datasets. It shows how k-means clustering was used to group 2D points into a varying number of clusters (task 1) and to cluster customers based on annual income and spending score from a CSV file (task 2). Exercises include clustering other datasets, identifying performance metrics for clustering, and generating a synthetic 7-cluster dataset to analyze elbow method and visualize clusters. The conclusion discusses clustering algorithms like k-means and DBSCAN as well as approaches for choosing the optimal number of clusters.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    44 views7 pages

    21BEC505 Exp2

    Uploaded by

    jay
    The document describes an experiment applying k-means clustering to unlabeled datasets. It shows how k-means clustering was used to group 2D points into a varying number of clusters (task 1) and to cluster customers based on annual income and spending score from a CSV file (task 2). Exercises include clustering other datasets, identifying performance metrics for clustering, and generating a synthetic 7-cluster dataset to analyze elbow method and visualize clusters. The conclusion discusses clustering algorithms like k-means and DBSCAN as well as approaches for choosing the optimal number of clusters.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 7

    Machine Learning 21BEC505

    Experiment-2
    Objective: Application on k-means algorithm for clustering of unsupervised data
    Task #1
    Code:
    import numpy as np
    import matplotlib.pyplot as plt
    from sklearn.cluster import KMeans

    # Define the 2D dataset


    data = np.array([[1.0, 1.0],
    [1.5, 2.0],
    [3.0, 4.0],
    [5.0, 7.0],
    [3.5, 5.0],
    [4.5, 5.0],
    [3.5, 4.5]])

    # Define the range of k values to try


    k_values = range(1, 5)

    # Iterate over different k values and perform k-means clustering


    for k in k_values:
    kmeans = KMeans(n_clusters=k).fit(data)
    labels = kmeans.labels_
    centroids = kmeans.cluster_centers_

    # Visualize the clustering result


    plt.figure()
    plt.scatter(data[:,0], data[:,1], c=labels, cmap='plasma',label=f'Cluster {k+1}')
    plt.scatter(centroids[:,0], centroids[:,1], marker='*', s=200, color='black',label='Centroids')
    plt.title('k = {}'.format(k))
    plt.show()
    Machine Learning 21BEC505

    Output:

    Task #2
    Code:
    import numpy as np
    import matplotlib.pyplot as plt
    import pandas as pd

    dataset = pd.read_csv(r 'E:\Jay\NIRMA\Sem6\ML\Exp2\Mall_Customers.csv')


    X = dataset.iloc[:, [3, 4]].values

    # Using the elbow method to find the optimal number of clusters


    from sklearn.cluster import KMeans
    wcss = []
    for i in range(1, 11):
    kmeans = KMeans(n_clusters = i, init = 'k-means++', random_state = 42)
    Machine Learning 21BEC505

    kmeans.fit(X)
    wcss.append(kmeans.inertia_)
    plt.plot(range(1, 11), wcss)
    plt.title('The Elbow Method')
    plt.xlabel('Number of clusters')
    plt.ylabel('WCSS')
    plt.show()

    # Fitting K-Means to the dataset


    kmeans = KMeans(n_clusters = 5, init = 'k-means++', random_state = 42)
    y_kmeans = kmeans.fit_predict(X)

    # Visualising the clusters


    plt.scatter(X[y_kmeans == 0, 0], X[y_kmeans == 0, 1], s = 100, c = 'red', label ='Cluster 1')
    plt.scatter(X[y_kmeans == 1, 0], X[y_kmeans == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')
    plt.scatter(X[y_kmeans == 2, 0], X[y_kmeans == 2, 1], s = 100, c = 'green', label = 'Cluster 3')
    plt.scatter(X[y_kmeans == 3, 0], X[y_kmeans == 3, 1], s = 100, c = 'cyan', label = 'Cluster 4')
    plt.scatter(X[y_kmeans == 4, 0], X[y_kmeans == 4, 1], s = 100, c = 'magenta', label = 'Cluster 5')
    plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s = 300, c = 'yellow', label = 'Centroids')
    plt.title('Clusters of customers')
    plt.xlabel('Annual Income (k$)')
    plt.ylabel('Spending Score (1-100)')
    plt.legend()
    plt.show()

    Output:
    Machine Learning 21BEC505

    Exercise:
    1. Take different features from the 'Mall_Customers.csv’ and repeat the task-2. OR perform
    clustering on any other such dataset.
    import pandas as pd
    from sklearn.cluster import KMeans
    import matplotlib.pyplot as plt

    data = pd.read_csv("Social_Network_Ads.csv")
    #X = df[['Age', 'EstimatedSalary']]
    X = data.iloc[:, [2, 3]].values

    # Using the elbow method to find the optimal number of clusters


    wcss = []
    for i in range(1, 11):
    kmeans = KMeans(n_clusters=i, init='k-means++', random_state=42)
    kmeans.fit(X)
    wcss.append(kmeans.inertia_)
    plt.plot(range(1, 11), wcss)
    plt.title('Elbow Method')
    plt.xlabel('Number of clusters')
    plt.ylabel('WCSS')
    plt.show()

    # Apply the k-means algorithm with k=4


    kmeans = KMeans(n_clusters=4, init='k-means++', random_state=42)
    y_kmeans = kmeans.fit_predict(X)

    # Visualize the clusters


    plt.scatter(X[y_kmeans == 0, 0], X[y_kmeans == 0, 1], s=100, c='red', label='Cluster 1')
    plt.scatter(X[y_kmeans == 1, 0], X[y_kmeans == 1, 1], s=100, c='blue', label='Cluster 2')
    plt.scatter(X[y_kmeans == 2, 0], X[y_kmeans == 2, 1], s=100, c='green', label='Cluster 3')
    plt.scatter(X[y_kmeans == 3, 0], X[y_kmeans == 3, 1], s=100, c='orange', label='Cluster 4')
    plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=300, c='yellow', label='Centroids')
    plt.title('Clusters of customers')
    plt.xlabel('Age')
    plt.ylabel('Estimated Salary')
    Machine Learning 21BEC505

    plt.legend()
    plt.show()

    Output:

    2. Which is the performance parameter for clustering?


    The performance parameter for clustering depends on the evaluation metrics used for the specific clustering algorithm
    and problem. There are several metrics that can be used to evaluate the performance of a clustering algorithm,
    including:

     Inertia or Within-Cluster-Sum-of-Squares (WCSS): Measures the sum of squared distances of all points to
    their respective cluster center. This metric is commonly used with k-means clustering.
     Silhouette Score: Measures the similarity of data points within their own cluster compared to other clusters.
    This metric provides a score between -1 and 1, where a higher score indicates better-defined clusters.
     Calinski-Harabasz Index: Measures the ratio of between-cluster variance to within-cluster variance. A
    higher index indicates better-defined clusters.
     Davies-Bouldin Index: Measures the average similarity between each cluster and its most similar cluster. A
    lower index indicates better-defined clusters.
     Adjusted Rand Index (ARI): Measures the similarity between the true and predicted cluster assignments.
    This metric provides a score between -1 and 1, where a score of 1 indicates a perfect match between true and
    predicted cluster assignments.
    The choice of performance parameter depends on the problem and the specific clustering algorithm used. Some
    clustering algorithms, such as k-means, optimize the WCSS metric directly, while others may use different evaluation
    metrics to optimize their objective function.

    3. Create your own dataset using the function make_blobs function from from the sklearn.datasets
    module and specifies the number of clusters (using parameter ‘centers’) as 7. Use elbow method to
    verify the clusters and visualize it.
    Code:
    from sklearn.datasets import make_blobs
    from sklearn.cluster import KMeans
    import matplotlib.pyplot as plt
    Machine Learning 21BEC505

    # Generate dataset
    X, y = make_blobs(n_samples=1000, centers=7, random_state=42)

    # Find optimal number of clusters using elbow method


    inertias = []
    k_range = range(1, 11)
    for k in k_range:
    kmeans = KMeans(n_clusters=k, random_state=42)
    kmeans.fit(X)
    inertias.append(kmeans.inertia_)

    # Plot elbow curve


    plt.plot(k_range, inertias)
    plt.xlabel('Number of clusters')
    plt.ylabel('Inertia')
    plt.title('Elbow Method')
    plt.show()

    kmeans = KMeans(n_clusters=7, random_state=42)


    labels = kmeans.fit_predict(X)

    # Plot cluster graph


    plt.scatter(X[:, 0], X[:, 1], c=labels)
    plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], marker='*', color='r', s=100)
    plt.title('Cluster Graph')
    plt.xlabel('A')
    plt.ylabel('B')
    plt.show()
    Machine Learning 21BEC505

    Output:

    Conclusion:
    In this experiment, we talked about clustering, a method of unsupervised machine learning used to group similar data
    points together, in this experiment. K-means, hierarchical clustering, and DBSCAN were among the various clustering
    algorithms we looked into. We also looked at various approaches, such as the elbow method and Within-Cluster-Sum-
    of-Squares (WCSS), and talked about how crucial it is to choose the right number of clusters for a given problem. After
    that, we applied these ideas to three distinct datasets: Ads on social media and shoppers in a mall. We pre-processed the
    data for each dataset and used one or more clustering algorithms to group data points that are similar. Various evaluation
    metrics, such as inertia and silhouette score, were utilized in our evaluation of each clustering algorithm's performance.
    In general, clustering is an effective method for uncovering hidden data structures and patterns. Depending on the
    problem at hand and the data, a clustering algorithm and performance metric should be selected. When it comes to
    applying clustering to real-world issues, we are able to make well-informed choices if we comprehend the advantages
    and disadvantages of various clustering algorithms and evaluation metrics.

    You might also like