The file Ecoli$\_$GCF$\_003018035\mathrm{.}1\_$ASM$301803$v$1\_$genomic.fna cotains the genome of bacteria E$.$Coli, which has $5,901,472$ nucleotides denoted by four characters: A$,$ T$,$ C$,$ G$.$ Split data into a train set $(80\%)$ and a test set $(20\%),$ and do the following:

Build an RNN model similar to the project of character$-$level language modeling in Chapter $15$ of the MLPS book. Use the train set to train the model, and use the test dataset to test the prediction of the trained model.