Given an sklearn tranformer t, is there a way to determine whether t changes columns/column order of any given input dataset X, without applying it to the data?
For example with t = sklearn.preprocessing.StandardScaler there is a 1-to-1 mapping between the columns of X and t.transform(X), namely X[:, i] -> t.transform(X)[:, i], whereas this is obviously not the case for sklearn.decomposition.PCA.
A corollary of that would be: Can we know, how the columns of the input will change by applying t, e.g. which columns an already fitted sklearn.feature_selection.SelectKBest chooses.
I am not looking for solutions to specific transformers, but a solution applicable to all or at least a wide selection of transformers.
Feel free to implement your own Pipeline class or wrapper if necessary.
Not all your "transformers" would have the .get_feature_names_out method. Its implementation is discussed in the sklearn github. In the same link, you can see there is, to quote @thomasjpfan, a _OneToOneFeatureMixin class used by transformers with a simple one-to-one correspondence between input and output features
Restricted to sklearn, we can check whether the transformer or estimator is a subclass of _OneToOneFeatureMixin , for example:
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
from sklearn.feature_selection import SelectKBest
from sklearn.base import _OneToOneFeatureMixin
tf = {'pca':PCA(),'standardscaler':StandardScaler(),'kbest':SelectKBest()}
[i+":"+str(issubclass(type(tf[i]),_OneToOneFeatureMixin)) for i in tf.keys()]
['pca:False', 'standardscaler:True', 'kbest:False']
These would the source code for _OneToOneFeatureMixin
I found a partial answer. Both StandardScaler and SelectKBest have .get_feature_names_out methods. I did not find the time to investigate further.
from numpy.random import RandomState
import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.feature_selection import SelectKBest
from sklearn.linear_model import LassoCV
rng = RandomState()
# Make some data
slopes = np.array([-1., 1., .1])
X = pd.DataFrame(
data = np.linspace(-1,1,500)[:, np.newaxis] + rng.random((500, 3)),
columns=["foo", "bar", "baz"]
)
y = pd.Series(data=np.linspace(-1,1, 500) + rng.rand((500)))
# Test Transformers
scaler = StandardScaler().fit(X)
selector = SelectKBest(k=2).fit(X, y)
print(scaler.get_feature_names_out())
print(selector.get_feature_names_out())