Is there any way to pre-process this kind of data in python?

Question

I am trying to load dataset but having problem

UnicodeDecodeError: 'utf-8' codec can't decode byte 0x95 in position 1079: invalid start byte

I already try

 DL = pd.read_csv('eg1.csv',encoding = 'UTF-8')
 DL

I think there should be some way to solve this error can anybody help me.

I am attaching the dataset file.

the main problem causing is this data "10mM NH4OAï½ƒ aq. pH7.0 / 2-propanol"

user_11920375 · Answer

Please use the following codec package in the read_csv() command:

file = pd.read_csv('data-preprocess.csv',encoding = 'unicode_escape')