Hi,
A little question : The hint in Q12 says to use df.info() to know if there’s any missing values.
Doing that indeed it is said that there’s no pb.
But when I do data.head(), I see some missing values marked with ‘?’. How can we explain the result of data.info() so ?
Thank you
Geoffrey
Hi,
The ‘?’ are in the categorical columns, and i assume that it is treated the same as all other categories in these columns. So for the regression there is no missing data.
oh ok thx a lot ! I still need to familiarize with all these stuffs haha but I think i get a little bit what you mean. Thank you Thomas !
Geoffrey
It is indeed a tricky one that we will correct in the next MOOC version. Here to simplify the exercise, we consider ? as a category as mentioned by @ThomasLoock
We could have used a different strategy and considered them as missing values as well but we would need to handle them specifically in the pipeline.