I have a dataframe in a csv
file that I would like to perform different unsupervised machine learning algorithms on.
The file itself has some cells that are not filled - they are just empty:
As shown in the picture above, some of the cells are empty. So the question follows - will these empty cells effect the outlier detection process which I would like to use?
Or should I instead work on a code that fills these empty cells with 0's
I have been told that that filling the empty cells has to be done so we don't have data sparsity, even though my csv files is thousands of rows long
Any advice regarding this is more than welcome.