JuniorTheoryCommon

What happens when this program runs?

Python

from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler

pipe = Pipeline([("scaler", StandardScaler()), ("model", LogisticRegression())])
pipe.set_params(C=0.1)
print(pipe.named_steps["model"].C)

set_params raises ValueError: the step's parameter is named model__C

Expecting the pipeline to route C to the model: it looks the name up among its own parameters and raises ValueError; a step's parameter is set as model__C=0.1.
Expecting an unknown name to be skipped silently: scikit-learn checks every name passed to set_params and refuses one the pipeline does not have.

How would you set C of the model step to 0.1 correctly?
Why does a pipeline need the step name inside a parameter's name?

Back to questions Open topic in roadmap →Answer it yourself — Quiz

Back to questions

JuniorTheoryCommon

What happens when this program runs?

Python

from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler

pipe = Pipeline([("scaler", StandardScaler()), ("model", LogisticRegression())])
pipe.set_params(C=0.1)
print(pipe.named_steps["model"].C)

set_params raises ValueError: the step's parameter is named model__C

Expecting the pipeline to route C to the model: it looks the name up among its own parameters and raises ValueError; a step's parameter is set as model__C=0.1.
Expecting an unknown name to be skipped silently: scikit-learn checks every name passed to set_params and refuses one the pipeline does not have.

How would you set C of the model step to 0.1 correctly?
Why does a pipeline need the step name inside a parameter's name?

Back to questions Open topic in roadmap →Answer it yourself — Quiz