We deleted the duplicate rows from android data. We did not do it with ios data. They also did not do it in the solution they provided.
In the beginning ios data has 7197 rows. I deleted the non English app names.
my ios_english data has 7197 rows, at the solution they provided they have 6183.
I used this code to detect more than 3 non english characters:
for character in string:
if ord(character) > 127:
And I used the code below to get the data with English app names:
for app in ios:
name = app
I do not know why we have different answers