CO2_1d_regression.py 文件源码

def load_co2_data(prop=0.8):
    from sklearn.datasets import fetch_mldata
    from sklearn import cross_validation
    data = fetch_mldata('mauna-loa-atmospheric-co2').data
    X = data[:, [1]]
    y = data[:, 0]
    y = y[:, None]
    X = X.astype(np.float64)
    ntrain = y.shape[0]
    train_inds = npr.choice(range(ntrain), int(prop*ntrain), replace=False)
    valid_inds = np.setdiff1d(range(ntrain), train_inds)
    X_train, y_train = X[train_inds].copy(), y[train_inds].copy()
    X_valid, y_valid = X[valid_inds].copy(), y[valid_inds].copy()
    return X_train, y_train, X_valid, y_valid

############################ Training & Visualizing ############################