Python load_data_set Examples

Example #1

File: module3_cancer-data-visualisation.py Project: vaborges/machine-learning-classification

def main():
    """
    Main function of the script.
    """
    feature_data, classification_data = wdbc.load_data_set()
    plot_classification_frequency(classification_data)
    plot_feature_correlation(feature_data)
    plot_feature_distribution(feature_data, classification_data)

Example #2

File: module3_cancer-data-visualisation.py Project: UIKit0/machine-learning-classification

def main():
    """
    Main function of the script.
    """
    feature_data, classification_data = wdbc.load_data_set()
    plot_classification_frequency(classification_data)
    plot_feature_correlation(feature_data)
    plot_feature_distribution(feature_data, classification_data)

Example #3

File: module5_naive-bayes.py Project: rajeshrajan71/machine-learning-classification

def main():
    """
    Main function of the script.
    """

    feature_data, classification_data = wdbc.load_data_set()

    # scikit-learn functions require classification in terms of numerical
    # values (i.e. 0, 1, 2) instead of strings (e.g. 'benign', 'malignant')
    label_encoder = preprocessing.LabelEncoder()
    label_encoder.fit(classification_data)
    classification_data_numerical = label_encoder.transform(classification_data)

    test_naive_bayes(feature_data, classification_data_numerical)

Example #4

File: module5_naive-bayes.py Project: vaborges/machine-learning-classification

def main():
    """
    Main function of the script.
    """

    feature_data, classification_data = wdbc.load_data_set()

    # scikit-learn functions require classification in terms of numerical
    # values (i.e. 0, 1, 2) instead of strings (e.g. 'benign', 'malignant')
    label_encoder = preprocessing.LabelEncoder()
    label_encoder.fit(classification_data)
    classification_data_numerical = label_encoder.transform(
        classification_data)

    test_naive_bayes(feature_data, classification_data_numerical)

Example #5

File: module6_cross-validation-and-grid-search.py Project: UIKit0/machine-learning-classification

def main():
    """
    Main function of the script.
    """

    feature_data, classification_data = wdbc.load_data_set()

    # scikit-learn functions require classification in terms of numerical
    # values (i.e. 0, 1, 2) instead of strings (e.g. 'benign', 'malignant')
    label_encoder = preprocessing.LabelEncoder()
    label_encoder.fit(classification_data)
    classification_data_numerical = label_encoder.transform(classification_data)

    plot_accuracy_vs_folds(feature_data, classification_data_numerical)
    optimise_knn_parameters(feature_data, classification_data_numerical)

Example #6

File: module6_cross-validation-and-grid-search.py Project: vaborges/machine-learning-classification

def main():
    """
    Main function of the script.
    """

    feature_data, classification_data = wdbc.load_data_set()

    # scikit-learn functions require classification in terms of numerical
    # values (i.e. 0, 1, 2) instead of strings (e.g. 'benign', 'malignant')
    label_encoder = preprocessing.LabelEncoder()
    label_encoder.fit(classification_data)
    classification_data_numerical = label_encoder.transform(
        classification_data)

    plot_accuracy_vs_folds(feature_data, classification_data_numerical)
    optimise_knn_parameters(feature_data, classification_data_numerical)

Example #7

File: module4_knn-classifiers-and-validation.py Project: UIKit0/machine-learning-classification

def main():
    """
    Main function of the script.
    """
    feature_data, classification_data = wdbc.load_data_set()

    # scikit-learn functions require classification in terms of numerical
    # values (i.e. 0, 1, 2) instead of strings (e.g. 'benign', 'malignant')
    label_encoder = preprocessing.LabelEncoder()
    label_encoder.fit(classification_data)
    classification_data_numerical = label_encoder.transform(classification_data)

    test_nearest_neighbors(feature_data, classification_data_numerical)
    optimise_nearest_neighbours(feature_data, classification_data_numerical)
    validation_metrics(feature_data, classification_data_numerical)
    plot_accuracies(feature_data, classification_data_numerical)
    plot_decision_boundaries(feature_data, classification_data_numerical)

Example #8

File: module4_knn-classifiers-and-validation.py Project: vaborges/machine-learning-classification

def main():
    """
    Main function of the script.
    """
    feature_data, classification_data = wdbc.load_data_set()

    # scikit-learn functions require classification in terms of numerical
    # values (i.e. 0, 1, 2) instead of strings (e.g. 'benign', 'malignant')
    label_encoder = preprocessing.LabelEncoder()
    label_encoder.fit(classification_data)
    classification_data_numerical = label_encoder.transform(
        classification_data)

    test_nearest_neighbors(feature_data, classification_data_numerical)
    optimise_nearest_neighbours(feature_data, classification_data_numerical)
    validation_metrics(feature_data, classification_data_numerical)
    plot_accuracies(feature_data, classification_data_numerical)
    plot_decision_boundaries(feature_data, classification_data_numerical)