Python run_fft_preprocessor Examples

Example #1

def run_trainer():
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    # path
    data_path = settings_dict['path'][
        'processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    model_path = settings_dict['path'][
        'model_path'] + '/' + create_cnn_model_name(settings_dict)
    print data_path
    print model_path

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    if not os.path.exists(model_path):
        os.makedirs(model_path)
    shutil.copy2('SETTINGS.json', model_path + '/SETTINGS.json')

    # params
    model_params = settings_dict['model']
    validation_params = settings_dict['validation']

    subjects = [
        'Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2'
    ]
    for subject in subjects:
        print '***********************', subject, '***************************'
        train(subject, data_path, model_path, model_params, validation_params)

Example #2

File: train.py Project: IraKorshunova/kaggle-seizure-prediction

def run_trainer():
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    # path
    data_path = settings_dict['path']['processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    model_path = settings_dict['path']['model_path'] + '/' + create_cnn_model_name(settings_dict)
    print data_path
    print model_path

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    if not os.path.exists(model_path):
        os.makedirs(model_path)
    shutil.copy2('SETTINGS.json', model_path + '/SETTINGS.json')

    # params
    model_params = settings_dict['model']
    validation_params = settings_dict['validation']

    subjects = ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']
    for subject in subjects:
        print '***********************', subject, '***************************'
        train(subject, data_path, model_path, model_params, validation_params)

Example #3

File: log_reg.py Project: zhmz90/kaggle-seizure-prediction

def run_trainer():
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    reg_list = [10000000, 100, 10, 1.0, 0.1, 0.01]
    for reg_C in reg_list:
        print reg_C
        data_path = settings_dict['path']['processed_data_path'] + '/' + create_fft_data_name(settings_dict)
        submission_path = settings_dict['path']['submission_path'] + '/logreg_' + str(
            reg_C) + '_' + create_fft_data_name(settings_dict)

        if not os.path.exists(data_path):
            fft.run_fft_preprocessor()

        if not os.path.exists(submission_path):
            os.makedirs(submission_path)

        subjects = ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']
        for subject in subjects:
            print subject
            model, data_scaler, = train(subject, data_path, reg_C)
            predict(subject, model, data_scaler, data_path, submission_path)

        merge_csv_files(submission_path, subjects, 'submission')
        merge_csv_files(submission_path, subjects, 'submission_softmax')
        merge_csv_files(submission_path, subjects, 'submission_minmax')
        merge_csv_files(submission_path, subjects, 'submission_median')

Example #4

File: lda.py Project: IraKorshunova/kaggle-seizure-prediction

def run_trainer():
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    data_path = settings_dict['path']['processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    submission_path = settings_dict['path']['submission_path'] + '/LDA_' + create_fft_data_name(settings_dict)
    print data_path

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    if not os.path.exists(submission_path):
        os.makedirs(submission_path)

    test_labels_path = '/mnt/sda4/CODING/python/kaggle_data/test_labels.csv'
    test_labels = load_test_labels(test_labels_path)

    subjects = ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']
    coef_list = []
    for subject in subjects:
        print '***********************', subject, '***************************'
        model, data_scaler, coefs  = train(subject, data_path)
        predict(subject, model, data_scaler, data_path, submission_path, test_labels[subject]['preictal'])
        coef_list.append(coefs)

    merge_csv_files(submission_path, subjects, 'submission')
    merge_csv_files(submission_path, subjects, 'submission_softmax')
    merge_csv_files(submission_path, subjects, 'submission_minmax')
    merge_csv_files(submission_path, subjects, 'submission_median')

Example #5

File: lda.py Project: zhmz90/kaggle-seizure-prediction

def run_trainer():
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    data_path = settings_dict['path'][
        'processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    submission_path = settings_dict['path'][
        'submission_path'] + '/LDA_' + create_fft_data_name(settings_dict)
    print data_path

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    if not os.path.exists(submission_path):
        os.makedirs(submission_path)

    test_labels_path = '/mnt/sda4/CODING/python/kaggle_data/test_labels.csv'
    test_labels = load_test_labels(test_labels_path)

    subjects = [
        'Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2'
    ]
    coef_list = []
    for subject in subjects:
        print '***********************', subject, '***************************'
        model, data_scaler, coefs = train(subject, data_path)
        predict(subject, model, data_scaler, data_path, submission_path,
                test_labels[subject]['preictal'])
        coef_list.append(coefs)

    merge_csv_files(submission_path, subjects, 'submission')
    merge_csv_files(submission_path, subjects, 'submission_softmax')
    merge_csv_files(submission_path, subjects, 'submission_minmax')
    merge_csv_files(submission_path, subjects, 'submission_median')

Example #6

def run_trainer():
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    # path
    data_path = settings_dict['path'][
        'processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    print data_path

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    subjects = [
        'Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2'
    ]
    for reg_C in [10000000, 100, 10, 1.0, 0.1, 0.01]:
        print reg_C
        all_valid_probs = []
        all_valid_y = []
        for subject in subjects:
            p, y = cross_validate(subject, data_path, reg_C=reg_C)
            all_valid_probs.extend(p)
            all_valid_y.extend(y)

        fpr, tpr, _ = roc_curve(all_valid_y, all_valid_probs, pos_label=1)
        print auc(fpr, tpr)
        print log_loss(all_valid_y, all_valid_probs)

Example #7

File: predict.py Project: IraKorshunova/kaggle-seizure-prediction

def run_predictor():
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    model_path = settings_dict['path']['model_path'] + '/' + create_cnn_model_name(settings_dict)
    data_path = settings_dict['path']['processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    submission_path = model_path + '/submission'
    print submission_path

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    if not os.path.exists(submission_path):
        os.makedirs(submission_path)
    shutil.copy2('SETTINGS.json', submission_path + '/SETTINGS.json')

    subjects = ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']
    #subjects = ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4']
    for subject in subjects:
        print '***********************', subject, '***************************'
        predict(subject, data_path, model_path, submission_path)

    merge_csv_data(submission_path, subjects, submission_name='submission', scale='minmax')
    merge_csv_data(submission_path, subjects, submission_name='submission', scale='softmax')
    merge_csv_data(submission_path, subjects, submission_name='submission', scale='median')
    merge_csv_data(submission_path, subjects, submission_name='submission')

Example #8

File: predict.py Project: Keesiu/meta-kaggle

def run_predictor():
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    model_path = settings_dict['path'][
        'model_path'] + '/' + create_cnn_model_name(settings_dict)
    data_path = settings_dict['path'][
        'processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    submission_path = model_path + '/submission'
    print(submission_path)

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    if not os.path.exists(submission_path):
        os.makedirs(submission_path)
    shutil.copy2('SETTINGS.json', submission_path + '/SETTINGS.json')

    subjects = [
        'Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2'
    ]
    #subjects = ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4']
    for subject in subjects:
        print('***********************', subject,
              '***************************')
        predict(subject, data_path, model_path, submission_path)

    merge_csv_data(submission_path,
                   subjects,
                   submission_name='submission',
                   scale='minmax')
    merge_csv_data(submission_path,
                   subjects,
                   submission_name='submission',
                   scale='softmax')
    merge_csv_data(submission_path,
                   subjects,
                   submission_name='submission',
                   scale='median')
    merge_csv_data(submission_path, subjects, submission_name='submission')

Example #9

File: log_reg_cv.py Project: IraKorshunova/kaggle-seizure-prediction

def run_trainer():
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    # path
    data_path = settings_dict['path']['processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    print data_path

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    subjects = ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']
    for reg_C in [10000000, 100, 10, 1.0, 0.1, 0.01]:
        print reg_C
        all_valid_probs = []
        all_valid_y = []
        for subject in subjects:
            p, y = cross_validate(subject, data_path, reg_C=reg_C)
            all_valid_probs.extend(p)
            all_valid_y.extend(y)

        fpr, tpr, _ = roc_curve(all_valid_y, all_valid_probs, pos_label=1)
        print auc(fpr, tpr)
        print log_loss(all_valid_y, all_valid_probs)

Example #10

        sn.append(sn_t)
        sp.append(sp_t)

    return t_list, sn, sp


if __name__ == '__main__':
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    data_path = settings_dict['path']['processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    submission_path = settings_dict['path']['submission_path'] + '/LDA_' + create_fft_data_name(settings_dict)
    print(data_path)

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    if not os.path.exists(submission_path):
        os.makedirs(submission_path)

    test_labels_path = '/mnt/sda4/CODING/python/kaggle_data/test_labels.csv'
    test_labels = load_test_labels(test_labels_path)

    subjects = ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']
    t, sn, sp = [], [], []
    for subject in subjects:
        print('***********************', subject, '***************************')
        t_i, sn_i, sp_i = curve_per_subject(subject, data_path, test_labels[subject]['preictal'])
        t.append(t_i)
        sn.append(sn_i)
        sp.append(sp_i)

Example #11

File: lda_snsp_curves.py Project: IraKorshunova/kaggle-seizure-prediction

        sn.append(sn_t)
        sp.append(sp_t)

    return t_list, sn, sp


if __name__ == '__main__':
    with open('SETTINGS.json') as f:
        settings_dict = json.load(f)

    data_path = settings_dict['path']['processed_data_path'] + '/' + create_fft_data_name(settings_dict)
    submission_path = settings_dict['path']['submission_path'] + '/LDA_' + create_fft_data_name(settings_dict)
    print data_path

    if not os.path.exists(data_path):
        fft.run_fft_preprocessor()

    if not os.path.exists(submission_path):
        os.makedirs(submission_path)

    test_labels_path = '/mnt/sda4/CODING/python/kaggle_data/test_labels.csv'
    test_labels = load_test_labels(test_labels_path)

    subjects = ['Dog_1', 'Dog_2', 'Dog_3', 'Dog_4', 'Dog_5', 'Patient_1', 'Patient_2']
    t, sn, sp = [], [], []
    for subject in subjects:
        print '***********************', subject, '***************************'
        t_i, sn_i, sp_i = curve_per_subject(subject, data_path, test_labels[subject]['preictal'])
        t.append(t_i)
        sn.append(sn_i)
        sp.append(sp_i)