Using FunctionTransformer to select columnsΒΆ

Shows how to use a function transformer in a pipeline. If you know your dataset’s first principle component is irrelevant for a classification task, you can use the FunctionTransformer to select all but the first column of the PCA transformed data.

  • ../../_images/sphx_glr_plot_function_transformer_001.png
  • ../../_images/sphx_glr_plot_function_transformer_002.png
import matplotlib.pyplot as plt
import numpy as np

from sklearn.model_selection import train_test_split
from sklearn.decomposition import PCA
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import FunctionTransformer

def _generate_vector(shift=0.5, noise=15):
    return np.arange(1000) + (np.random.rand(1000) - shift) * noise

def generate_dataset():
    This dataset is two lines with a slope ~ 1, where one has
    a y offset of ~100
    return np.vstack((
            _generate_vector() + 100,
    )), np.hstack((np.zeros(1000), np.ones(1000)))

def all_but_first_column(X):
    return X[:, 1:]

def drop_first_component(X, y):
    Create a pipeline with PCA and the column selector and use it to
    transform the dataset.
    pipeline = make_pipeline(
        PCA(), FunctionTransformer(all_but_first_column),
    X_train, X_test, y_train, y_test = train_test_split(X, y), y_train)
    return pipeline.transform(X_test), y_test

if __name__ == '__main__':
    X, y = generate_dataset()
    lw = 0
    plt.scatter(X[:, 0], X[:, 1], c=y, lw=lw)
    X_transformed, y_transformed = drop_first_component(*generate_dataset())
        X_transformed[:, 0],

Total running time of the script: (0 minutes 0.144 seconds)

Download Python source code:
Download IPython notebook: plot_function_transformer.ipynb