Python机器学习---特征积聚与单因素特征选择

This example compares 2 dimensionality reduction strategies:

• univariate feature selection with Anova

• feature agglomeration with Ward hierarchical clustering

Both methods are compared in a regression problem using a BayesianRidge as supervised estimator

# Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>
# License: BSD 3 clause

import shutil
import tempfile

import numpy as np
import matplotlib.pyplot as plt
from scipy import linalg, ndimage
from joblib import Memory

from sklearn.feature_extraction.image import grid_to_graph
from sklearn import feature_selection
from sklearn.cluster import FeatureAgglomeration
from sklearn.linear_model import BayesianRidge
from sklearn.pipeline import Pipeline
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import KFold

# #############################################################################
# Generate data
n_samples = 200
size = 40  # image size
roi_size = 15
snr = 5.0
np.random.seed(0)
mask = np.ones([size, size], dtype=bool)

coef = np.zeros((size, size))
coef[0:roi_size, 0:roi_size] = -1.0
coef[-roi_size:, -roi_size:] = 1.0

X = np.random.randn(n_samples, size ** 2)
for x in X:  # smooth data
    x[:] = ndimage.gaussian_filter(x.reshape(size, size), sigma=1.0).ravel()
X -= X.mean(axis=0)
X /= X.std(axis=0)

y = np.dot(X, coef.ravel())
noise = np.random.randn(y.shape[0])
noise_coef = (linalg.norm(y, 2) / np.exp(snr / 20.0)) / linalg.norm(noise, 2)
y += noise_coef * noise  # add noise

# ############################################################################