I have a huge df

events_id      score

10234829        34
10234829        0
10234829        98
10234829        24
10234829        78
...
38749228        2
38749228        76
38749228        54
38749228        23
38749228        108
38749228        38 

1 - I would like to apply a RobustScaler() or MinMaxScaler() (or other scaler) on score column but i would like to apply a specific scaler instance for each event_id (which are differents series).

2- How I could insert that in this kind of basic pipeline

model = make_pipeline(StandardScaler(), LogisticRegression())
model.fit(X, y)

...

thanks for help

Seb

0 Answers