Roots of that chaos.
Well, usually we are always in a hurry while working on something exciting. In one of those days you promised yourself that it’s easy to remember which dataset is which. Nonetheless, time flies, you know! The deadline has crept up on you.
It is absolutely essential that the right data in production must be used. Garbage in — garbage out, remember? What do you do now?
So… which dataset is the one?
First you go over all your notebooks, compare metrics or other calculations, you spend some time, then a little more… Whew! You are almost 100% sure that user_activity_april_2020_cleaned_df_improved.csv dataset is the one you’re looking for.

#pandas #data-science #python #machine-learning