pipelinecomponents.py 文件源码

def data_handlemissing(dataframe, pipeline):
    try:
        if pipeline['options']['type'] == "dropcolumns":
            thresh = pipeline['options']['thresh']
            if thresh == -1:
                dataframe.dropna(axis=1, how="all", inplace=True)
            elif thresh == 0:
                dataframe.dropna(axis=1, how="any", inplace=True)
            elif thresh > 0:
                dataframe.dropna(axis=1, thresh=thresh, inplace=True)
        elif pipeline['options']['type'] == "droprows":
            thresh = pipeline['options']['thresh']
            if thresh == -1:
                dataframe.dropna(axis=0, how="all", inplace=True)
            elif thresh == 0:
                dataframe.dropna(axis=0, how="any", inplace=True)
            elif thresh > 0:
                dataframe.dropna(axis=0, thresh=thresh)
        elif pipeline['options']['type'] == "fillmissing":
            strategy = pipeline['options']['strategy']
            imp = Imputer(missing_values='NaN', strategy=strategy, axis=0)
            array = imp.fit_transform(dataframe.values)
            dataframe = pandas.DataFrame(array, columns = dataframe.columns)

        return dataframe
    except Exception as e:
        raise Exception("data_handlemissing: " + str(e))