1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68
|
#!/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: Gael Varoqueux
# Modified for Documentation merge by Jaques Grobler
# License: BSD
import numpy as np
import pylab as pl
from sklearn import linear_model, decomposition, datasets, cross_validation
logistic = linear_model.LogisticRegression()
pca = decomposition.PCA()
from sklearn.pipeline import Pipeline
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)
pl.figure(1, figsize=(4, 3))
pl.clf()
pl.axes([.2, .2, .7, .7])
pl.plot(pca.explained_variance_, linewidth=2)
pl.axis('tight')
pl.xlabel('n_components')
pl.ylabel('explained_variance_')
###############################################################################
# Prediction
from sklearn.grid_search import GridSearchCV
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)
pl.axvline(estimator.best_estimator_.named_steps['pca'].n_components,
linestyle=':', label='n_components chosen')
pl.legend(prop=dict(size=12))
pl.show()
|