For Incremental Learning ML Model do we have to perform any kind of label encoding?

Please guide me on Online / Incremental Learning ML model, I am using Creme tool for my hands-on, where as my dataset has some categorical features, I did tried to do encoding but still getting error as TypeError: unsupported operand type(s) for -: 'str' and 'float'. Please do let if we need any kind of label encoding or we should not do any encoding, I did tried passing the raw data itself, it also failed. For example : Restaurants dataset has some features like genre_name which is categorical, and also has Date datatype.

I did tried with Categorical data for Label / Class, and there it works without any encoding transformation. However with features having issue. Please guide.

from creme import datasets
from creme import preprocessing
from creme import linear_model
from creme import metrics
from creme import optim

X_y = datasets.Restaurants()

model = preprocessing.StandardScaler()

model |= linear_model.LogisticRegression(optimizer=optim.SGD(.1))

for x, y in X_y:
  y_pred = model.predict_one(x)  
  metric = metric.update(y, y_pred)  
  model = model.fit_one(x, y)  

For this as well getting same error as TypeError: unsupported operand type(s) for -: 'str' and 'float'.