scikit-learn/examples/plot_digits_pipe.py

64 lines
1.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/usr/bin/python
# -*- coding: utf-8 -*-
"""
=========================================================
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(1, figsize=(4, 3))
plt.clf()
plt.axes([.2, .2, .7, .7])
plt.plot(pca.explained_variance_, linewidth=2)
plt.axis('tight')
plt.xlabel('n_components')
plt.ylabel('explained_variance_')
# Prediction
n_components = [20, 40, 64]
Cs = np.logspace(-4, 4, 3)
# Parameters of pipelines can be set using __ separated parameter names:
estimator = GridSearchCV(pipe,
dict(pca__n_components=n_components,
logistic__C=Cs))
estimator.fit(X_digits, y_digits)
plt.axvline(estimator.best_estimator_.named_steps['pca'].n_components,
linestyle=':', label='n_components chosen')
plt.legend(prop=dict(size=12))
plt.show()