Scribd Logo
Upload

Welcome to Scribd!

  • 1 views

    ML Assignment 1 - Nageswar

    Uploaded by

    upendrakomurumallu

    Copyright:

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

    ML Assignment 1 - Nageswar

    Uploaded by

    upendrakomurumallu
    1 views7 pages

    Original Title

    ML Assignment 1_Nageswar

    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
    1 views7 pages

    ML Assignment 1 - Nageswar

    Uploaded by

    upendrakomurumallu

    Copyright:

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

    Name Nageswar.

    MSC DS.

    Subject ML

    Assignment 1:

    1. illustrate the K means clustering with a suitably identified choice of k for mall-data and
    drawing inerfaces related to the resulting clusters

    Answer:

    import pandas as pd

    import matplotlib.pyplot as plt

    from sklearn.cluster import KMeans

    # Load the dataset

    data = pd.read_csv('Mall_Customers.csv')

    # Selecting the features for clustering

    X = data[['Annual Income (k$)', 'Spending Score (1-100)']]

    # Applying K-means

    kmeans = KMeans(n_clusters=5, random_state=42)

    data['Cluster'] = kmeans.fit_predict(X)

    # Plotting the clusters

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

    for cluster in range(5):

    plt.scatter(X[data['Cluster'] == cluster]['Annual Income (k$)'],

    X[data['Cluster'] == cluster]['Spending Score (1-100)'],

    label=f'Cluster {cluster}')

    plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=300, c='red',


    label='Centroids')
    plt.xlabel('Annual Income (k$)')

    plt.ylabel('Spending Score (1-100)')

    plt.legend()

    plt.title('Customer Segments')

    plt.show()
    2. Illustrate and create decision tree for any data set and compare its performance.

    Answer:

    import pandas as pd

    from sklearn.datasets import load_iris

    from sklearn.model_selection import train_test_split

    from sklearn.tree import DecisionTreeClassifier

    from sklearn.metrics import accuracy_score, classification_report

    # Load the Iris dataset

    iris = load_iris()

    X, y = iris.data, iris.target

    # Split data into training and test sets

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # Create a decision tree classifier

    clf = DecisionTreeClassifier(random_state=42)

    clf.fit(X_train, y_train)

    # Make predictions

    y_pred = clf.predict(X_test)

    # Evaluate performance

    accuracy = accuracy_score(y_test, y_pred)

    report = classification_report(y_test, y_pred)

    print(f"Accuracy: {accuracy:.2f}")

    print("Classification Report:\n", report)


    3. Using SVM for any data, performing hyper-parameter turning and compare the result.

    Answer:

    import pandas as pd

    import numpy as np

    from sklearn.datasets import load_breast_cancer

    from sklearn.model_selection import train_test_split, GridSearchCV

    from sklearn.svm import SVC

    from sklearn.metrics import classification_report, confusion_matrix

    # Load the breast cancer dataset

    cancer = load_breast_cancer()
    # Extract features and target

    df_feat = pd.DataFrame(cancer['data'], columns=cancer['feature_names'])

    df_target = pd.DataFrame(cancer['target'], columns=['Cancer'])

    # Split data into train and test sets

    X_train, X_test, y_train, y_test = train_test_split(df_feat, np.ravel(df_target), test_size=0.30,


    random_state=101)

    # Create an SVM classifier

    svc = SVC()

    # Define hyperparameter grid

    param_grid = {'C': [0.1, 1, 10], 'gamma': [0.1, 0.01, 0.001]}

    # Perform grid search

    grid = GridSearchCV(svc, param_grid, verbose=2)

    grid.fit(X_train, y_train)

    # Get best hyperparameters

    best_C = grid.best_params_['C']

    best_gamma = grid.best_params_['gamma']

    # Train SVM with best hyperparameters

    best_svc = SVC(C=best_C, gamma=best_gamma)

    best_svc.fit(X_train, y_train)

    # Evaluate performance

    y_pred = best_svc.predict(X_test)

    print("Classification Report:\n", classification_report(y_test, y_pred))


    print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

    You might also like