Example: Pipelining
Pipelining: chaining a PCA and a logistic regression
The PCA does an unsupervised dimensionality reduction, while the logistic regression does the prediction.
We use a GridSearchCV to set the dimensionality of the PCA
print(__doc__)
# Code source: Gaël Varoquaux
# Modified for documentation by Jaques Grobler
# License: BSD 3 clause
import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model, decomposition, datasets
from sklearn.pipeline import Pipeline
from sklearn.model_selection import GridSearchCV
logistic = linear_model.LogisticRegression()
pca = decomposition.PCA()
pipe = Pipeline(steps=[('pca', pca), ('logistic', logistic)])
digits = datasets.load_digits()
X_digits = digits.data
y_digits = digits.target
Plot the PCA spectrum
pca.fit(X_digits) plt.figure
