p1b3_locally_connected_v2.py 文件源码

def impute_and_scale(df, scaling=None):
    """Impute missing values with mean and scale data included in pandas dataframe.

    Parameters
    ----------
    df : pandas dataframe
        dataframe to impute and scale
    scaling : 'maxabs' [-1,1], 'minmax' [0,1], 'std', or None, optional (default 'std')
        type of scaling to apply
    """

    df = df.dropna(axis=1, how='all')

    imputer = Imputer(strategy='mean', axis=0)
    mat = imputer.fit_transform(df)
    # print(mat.shape)

    if scaling is None:
        return pd.DataFrame(mat, columns=df.columns)

    # Scaling data
    if scaling == 'maxabs':
        # Normalizing -1 to 1
        scaler = MaxAbsScaler()
    elif scaling == 'minmax':
        # Scaling to [0,1]
        scaler = MinMaxScaler()
    else:
        # Standard normalization
        scaler = StandardScaler()

    mat = scaler.fit_transform(mat)

    # print(mat.shape)
    df = pd.DataFrame(mat, columns=df.columns)

    return df