An example showing how different online solvers perform on the hand-written digits dataset.
Out:
1 2 3 4 5 6 | training SGDtraining ASGDtraining Perceptrontraining Passive-Aggressive Itraining Passive-Aggressive IItraining SAG |
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 | # Author: Rob Zinkov <rob at zinkov dot com># License: BSD 3 clauseimport numpy as npimport matplotlib.pyplot as pltfrom sklearn import datasetsfrom sklearn.model_selection import train_test_splitfrom sklearn.linear_model import SGDClassifier, Perceptronfrom sklearn.linear_model import PassiveAggressiveClassifierfrom sklearn.linear_model import LogisticRegressionheldout = [0.95, 0.90, 0.75, 0.50, 0.01]rounds = 20digits = datasets.load_digits()X, y = digits.data, digits.targetclassifiers = [ ("SGD", SGDClassifier()), ("ASGD", SGDClassifier(average=True)), ("Perceptron", Perceptron()), ("Passive-Aggressive I", PassiveAggressiveClassifier(loss='hinge', C=1.0)), ("Passive-Aggressive II", PassiveAggressiveClassifier(loss='squared_hinge', C=1.0)), ("SAG", LogisticRegression(solver='sag', tol=1e-1, C=1.e4 / X.shape[0]))]xx = 1. - np.array(heldout)for name, clf in classifiers: print("training %s" % name) rng = np.random.RandomState(42) yy = [] for i in heldout: yy_ = [] for r in range(rounds): X_train, X_test, y_train, y_test = \ train_test_split(X, y, test_size=i, random_state=rng) clf.fit(X_train, y_train) y_pred = clf.predict(X_test) yy_.append(1 - np.mean(y_pred == y_test)) yy.append(np.mean(yy_)) plt.plot(xx, yy, label=name)plt.legend(loc="upper right")plt.xlabel("Proportion train")plt.ylabel("Test Error Rate")plt.show() |
Total running time of the script: (0 minutes 13.767 seconds)
Download Python source code:
plot_sgd_comparison.py
Download IPython notebook:
plot_sgd_comparison.ipynb
Please login to continue.