This had been bugging me all day in the back of my head... turns out shuffle is enabled by default. Both in sklearn and in tf.keras (also original keras).
On a separate note, I think there may be a source file missing in your notebook. I kept getting an error when trying to load "GSE87571_series_matrix.csv". Might just be me.
Interesting write up. I'd be interested to see how it performs with k-folds validation as well as shuffling. Kind of worried its learning order or samples.
But hey Rudis is probably right. Everything should be free and no one should get paid for work. lets not even try to fix or attempt a different economic model. We're all so happy with the current one...