mdf = dd.read_parquet(self.local_location + self.megafile, engine='pyarrow')
            inx = df.index.unique()
            start1 = '2016-01-01'
            end1 = pd.to_datetime(inx.values.min()).strftime('%Y-%m-%d')
            start2 = pd.to_datetime(inx.values.max()).strftime('%Y-%m-%d')
            end2 = '2029-01-01'
            mdf1 = mdf[start1:end1]
            mdf2 = mdf[start2:end2]
            if len(mdf1) > 0:
                df_usage1 = 1 + mdf1.memory_usage(deep=True).sum().compute() // 100000001

                if len(mdf2) > 0:
                    df_usage2 = 1 + mdf1.memory_usage(deep=True).sum().compute() // 100000001
                    mdf1 = mdf1.append(mdf2, npartitions=df_usage2)
            else:
                if len(mdf2) > 0:
                    df_usage2 = 1 + mdf2.memory_usage(deep=True).sum().compute() // 100000001
                    mdf1 = dd.from_pandas(df).append(mdf2, npartitions=df_usage2)

mdf1 = mdf1.append(df, npartitions=df_usage1)

{ValueError}Exactly one of npartitions and chunksize must be specified.