svm.py 文件源码

def load_csv(training_fn, features_fn):
    '''
    Transform tabular data set into NumPy arrays.
    '''
    df = pd.read_csv(training_fn, sep='\t')

    features = json.load(open(features_fn))['features']
    data = df[features].as_matrix()
    print('Data:', data.shape)

    labels = df[['label']].as_matrix().reshape(-1)
    lb = preprocessing.LabelBinarizer()
    lb.fit(labels)
    print('Labels:', labels.shape)

    return features, data, labels