Function get_normalized_data

ann_class2/util.py:117–145

()

def get_normalized_data():
    print("Reading in and transforming data...")

    if not os.path.exists('../large_files/train.csv'):
        print('Looking for ../large_files/train.csv')
        print('You have not downloaded the data and/or not placed the files in the correct location.')
        print('Please get the data from: https://www.kaggle.com/c/digit-recognizer')
        print('Place train.csv in the folder large_files adjacent to the class folder')
        exit()

    df = pd.read_csv('../large_files/train.csv')
    data = df.values.astype(np.float32)
    np.random.shuffle(data)
    X = data[:, 1:]
    Y = data[:, 0]

    Xtrain = X[:-1000]
    Ytrain = Y[:-1000]
    Xtest  = X[-1000:]
    Ytest  = Y[-1000:]

    # normalize the data
    mu = Xtrain.mean(axis=0)
    std = Xtrain.std(axis=0)
    np.place(std, std == 0, 1)
    Xtrain = (Xtrain - mu) / std
    Xtest = (Xtest - mu) / std
    
    return Xtrain, Xtest, Ytrain, Ytest


def plot_cumulative_variance(pca):