Use SelectFromModel meta-transformer along with Lasso to select the best couple of features from the Boston dataset.
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 | # Author: Manoj Kumar <mks542@nyu.edu># License: BSD 3 clauseprint(__doc__)import matplotlib.pyplot as pltimport numpy as npfrom sklearn.datasets import load_bostonfrom sklearn.feature_selection import SelectFromModelfrom sklearn.linear_model import LassoCV# Load the boston dataset.boston = load_boston()X, y = boston['data'], boston['target']# We use the base estimator LassoCV since the L1 norm promotes sparsity of features.clf = LassoCV()# Set a minimum threshold of 0.25sfm = SelectFromModel(clf, threshold=0.25)sfm.fit(X, y)n_features = sfm.transform(X).shape[1]# Reset the threshold till the number of features equals two.# Note that the attribute can be set directly instead of repeatedly# fitting the metatransformer.while n_features > 2: sfm.threshold += 0.1 X_transform = sfm.transform(X) n_features = X_transform.shape[1]# Plot the selected two features from X.plt.title( "Features selected from Boston using SelectFromModel with " "threshold %0.3f." % sfm.threshold)feature1 = X_transform[:, 0]feature2 = X_transform[:, 1]plt.plot(feature1, feature2, 'r.')plt.xlabel("Feature number 1")plt.ylabel("Feature number 2")plt.ylim([np.min(feature2), np.max(feature2)])plt.show() |
Total running time of the script: (0 minutes 0.106 seconds)
Download Python source code:
plot_select_from_model_boston.py
Download IPython notebook:
plot_select_from_model_boston.ipynb
Please login to continue.