Scribd Logo
Upload

Welcome to Scribd!

  • 29 views

    Exp 6

    Uploaded by

    jay
    The document describes an experiment implementing a support vector machine (SVM) classifier in Python. It loads and prepares a social network advertising dataset, then trains and tests linear, polynomial, and radial basis function SVM models on the data. It evaluates the models using accuracy scores and confusion matrices. It also visualizes the SVM classifiers and trained and test data to understand the models. The objective is to classify the data using SVMs and analyze how changing hyperparameters affects accuracy.

    Copyright:

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

    Exp 6

    Uploaded by

    jay
    29 views6 pages
    The document describes an experiment implementing a support vector machine (SVM) classifier in Python. It loads and prepares a social network advertising dataset, then trains and tests linear, polynomial, and radial basis function SVM models on the data. It evaluates the models using accuracy scores and confusion matrices. It also visualizes the SVM classifiers and trained and test data to understand the models. The objective is to classify the data using SVMs and analyze how changing hyperparameters affects accuracy.

    Original Title

    Exp6

    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 implementing a support vector machine (SVM) classifier in Python. It loads and prepares a social network advertising dataset, then trains and tests linear, polynomial, and radial basis function SVM models on the data. It evaluates the models using accuracy scores and confusion matrices. It also visualizes the SVM classifiers and trained and test data to understand the models. The objective is to classify the data using SVMs and analyze how changing hyperparameters affects accuracy.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    29 views6 pages

    Exp 6

    Uploaded by

    jay
    The document describes an experiment implementing a support vector machine (SVM) classifier in Python. It loads and prepares a social network advertising dataset, then trains and tests linear, polynomial, and radial basis function SVM models on the data. It evaluates the models using accuracy scores and confusion matrices. It also visualizes the SVM classifiers and trained and test data to understand the models. The objective is to classify the data using SVMs and analyze how changing hyperparameters affects accuracy.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 6

    Machine Learning 21BEC505

    Experiment-6
    Objective: Implementation of Support Vector Machine (SVMs)
    Task #1
    Code:
    import numpy as np
    import matplotlib.pyplot as plt
    import pandas as pd
    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import StandardScaler
    from sklearn.svm import SVC
    from sklearn.metrics import confusion_matrix,accuracy_score
    from matplotlib.colors import ListedColormap

    dataset = pd.read_csv(r"E:\Jay\NIRMA\Sem6\ML\Exp6\Social_Network_Ads.csv")

    X = dataset.iloc[:,[2,3]].values
    y = dataset.iloc[:,4].values

    X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=1/3,random_state=0)
    sc = StandardScaler()
    X_train = sc.fit_transform(X_train)
    X_test = sc.fit_transform(X_test)
    classifier = SVC(kernel='linear',random_state=0)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))

    x_set, y_set = X_train, y_train


    x1, x2 = np.meshgrid(np.arange(start = x_set[:, 0].min() - 1, stop = x_set[:, 0].max() + 1, step=0.01),
    np.arange(start = x_set[:, 1].min() - 1, stop = x_set[:, 1].max() + 1, step = 0.01))
    plt.contourf(x1, x2, classifier.predict(np.array([x1.ravel(), x2.ravel()]).T).reshape(x1.shape),
    alpha = 0.75, cmap = ListedColormap(('red', 'green')))
    plt.xlim(x1.min(), x1.max())
    plt.ylim(x2.min(), x2.max())
    for i, j in enumerate(np.unique(y_set)):
    plt.scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],c = ListedColormap(('red', 'green'))(i), label = j)
    plt.legend()
    plt.show()

    x_set, y_set = X_test, y_test


    x1, x2 = np.meshgrid(np.arange(start = x_set[:, 0].min() - 1, stop = x_set[:, 0].max() + 1, step=0.01),
    np.arange(start = x_set[:, 1].min() - 1, stop = x_set[:, 1].max() + 1, step = 0.01))
    plt.contourf(x1, x2, classifier.predict(np.array([x1.ravel(), x2.ravel()]).T).reshape(x1.shape),
    alpha = 0.75, cmap = ListedColormap(('red', 'green')))
    plt.xlim(x1.min(), x1.max())
    plt.ylim(x2.min(), x2.max())
    for i, j in enumerate(np.unique(y_set)):
    plt.scatter(x_set[y_set == j, 0], x_set[y_set == j, 1], c = ListedColormap(('red', 'green'))(i), label = j)
    Machine Learning 21BEC505

    plt.legend()
    plt.show()

    classifier = SVC(kernel='poly',random_state=0)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))
    classifier = SVC(kernel='rbf',random_state=0)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))
    classifier = SVC(C=0.1,kernel='rbf',random_state=0)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))
    classifier = SVC(C=1,kernel='rbf',random_state=0)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))
    classifier = SVC(C=10,kernel='rbf',random_state=0)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)

    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))
    classifier = SVC(C=100,kernel='rbf',random_state=0)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))
    classifier = SVC(C=10,kernel='rbf',random_state=0,gamma=0.1)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))
    classifier = SVC(C=10,kernel='rbf',random_state=0,gamma=1)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))
    classifier = SVC(C=10,kernel='rbf',random_state=0,gamma=10)
    classifier.fit(X_train,y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))
    classifier = SVC(C=10,kernel='rbf',random_state=0,gamma=100)
    classifier.fit(X_train,y_train)
    Machine Learning 21BEC505

    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test,y_pred)
    print(accuracy_score(y_test,y_pred))

    Output:
    Machine Learning 21BEC505

    Exercise:

    1. Use SVM as a classifier and predict the traffic.

    Code:

    import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt
    from sklearn.svm import SVC
    from sklearn.preprocessing import StandardScaler
    from sklearn.model_selection import train_test_split
    from sklearn.metrics import confusion_matrix
    from matplotlib.colors import ListedColormap
    data=pd.read_csv(r"E:\Jay\NIRMA\Sem6\ML\Exp6\dodgers.data",header=None)
    print('Raw Data: \n', data.head())
    data.columns = ['date_time', 'Cars']
    data['date_time'] = pd.to_datetime(data['date_time'],
    infer_datetime_format=True, errors='coerce')
    Date = data.date_time.dt.date
    Time = data.date_time.dt.time
    data = data.reindex(['Date', 'Time', *data.columns], axis=1).assign(Date = Date, Time = Time)
    del data['date_time']
    print('\n Parsed Data: \n', data.head())
    data['Date'] = [str(d)[:10].replace("-", "") for d in data['Date']]
    data['Time'] = [str(t)[:9].replace(":", "") for t in data['Time']]
    data = data[data['Cars'] != -1]
    traffic_map = {"light": 0, "medium": 1, "heavy": 2}
    data['Traffic'] = data['Cars'].apply(lambda x: "heavy" if x >= 27 else "medium" if x >= 9 else "light")
    data['Traffic'] = data['Traffic'].map(traffic_map)
    X = data.iloc[:, [0, 1]].values
    y = data.iloc[:, 3].values
    column = data.columns.values[:2]
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.10, random_state=101)
    sc = StandardScaler()
    X_train = sc.fit_transform(X_train)
    X_test = sc.transform(X_test)
    classifier = SVC(kernel='linear', random_state=26)
    classifier.fit(X_train, y_train)
    y_pred = classifier.predict(X_test)
    cm = confusion_matrix(y_test, y_pred)
    print(cm)
    # Visulaize output (trained set)
    X_set, y_set = X_train, y_train
    X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() -1, stop = X_set[:,0].max() +1, step = 1),
    np.arange(start = X_set[:, 1].min() -1, stop = X_set[:, 1].max() +1, step = 0.5))
    plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(),
    X2.ravel()]).T).reshape(X1.shape), alpha = 0.68, cmap = ListedColormap(('red', 'green', 'blue')) )
    plt.xlim(X1.min(), X1.max())
    plt.ylim(X2.min(), X2.max())
    for i,j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], color =
    ListedColormap(('red','green', 'blue'))(i), label=next(key for key, value in traffic_map.items() if value == j))
    Machine Learning 21BEC505

    plt.title('SVM (Training Set)')


    plt.xlabel(column[0])
    plt.ylabel(column[1])
    plt.legend()
    plt.show()
    from sklearn.metrics import accuracy_score
    # Visualize test results (prediction)
    X_set, y_set = X_test, y_test
    X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() -1, stop = X_set[:, 0].max() +1, step = 1),
    np.arange(start = X_set[:, 1].min() -1, stop = X_set[:, 1].max() +1, step = 0.5))
    plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape), alpha = 0.68,
    cmap = ListedColormap(('red', 'green', 'blue')) )
    plt.xlim(X1.min(), X1.max())
    plt.ylim(X2.min(), X2.max())
    for i,j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], color =
    ListedColormap(('red','green', 'blue'))(i), label=next(key for key, value in traffic_map.items() if value == j))
    plt.title('SVM (Test Set)')
    plt.xlabel(column[0])
    plt.ylabel(column[1])
    plt.legend()
    plt.show()
    accuracy = accuracy_score(y_test, y_pred)
    print("Accuracy:", accuracy)

    Output:
    Machine Learning 21BEC505

    Conclusion:
    From this experiment, I understood about Support Vector Machine and furthermore about how to execute
    SVM Classifier in python. Support vectors are used in SVM to find the hyperplane, and we can use this
    hyperplane to predict the data point's label. By altering parameters like gamma, C, and the kernel, I was also
    able to improve the model's accuracy. For the given dataset, we have implemented a Support Vector Machine
    Classifier. Our model has an initial accuracy of 83 percent. The model's accuracy was then increased to 91.79
    percent by adjusting kernel, C, and gamma parameters.

    You might also like