utils.py 文件源码

def make_xy_data(csv, drop_nan_columns=None):
    data = pd.read_csv(csv, index_col=0)
    n = len(data)

    if drop_nan_columns:
        data = data.dropna(subset=drop_nan_columns)

    print "[Warning] dropped %s samples because of NaN values" % (n-len(data))

    y = np.divide(data[['prix']].astype(float).values.T,
                  data[['surface_m2']].astype(float).values.T
                  )[0]

    x = data.drop(['prix'], axis=1)

    return x, y