np.random.seed(0)
n_samples_1 = 1000
n_samples_2 = 100
X = np.r_[1.5*np.random.randn(n_samples_1, 2),
0.5*np.random.randn(n_samples_2, 2) + [2, 2]]
y = np.array([0]*(n_samples_1) + [1]*(n_samples_2), dtype=np.float64)
idx = np.arange(y.shape[0])
np.random.shuffle(idx)
X = X[idx]
y = y[idx]
mean = X.mean(axis=0)
std = X.std(axis=0)
X = (X - mean) / std
# fit the model and get the separating hyperplane
clf = SGDClassifier(n_iter=100, alpha=0.01)
clf.fit(X, y)
w = clf.coef_.ravel()
a = -w[0] / w[1]
xx = np.linspace(-5, 5)
yy = a * xx - clf.intercept_ / w[1]
# get the separating hyperplane using weighted classes
wclf = SGDClassifier(n_iter=100, alpha=0.01)
wclf.fit(X, y, class_weight={1: 10})
ww = wclf.coef_.ravel()
wa = -ww[0] / ww[1]
wyy = wa * xx - wclf.intercept_ / ww[1]
}
liblinear_res = benchmark(LinearSVC(**liblinear_parameters))
liblinear_err, liblinear_train_time, liblinear_test_time = liblinear_res
######################################################################
## Train GNB model
gnb_err, gnb_train_time, gnb_test_time = benchmark(GNB())
######################################################################
## Train SGD model
sgd_parameters = {
'alpha': 0.001,
'n_iter': 2,
}
sgd_err, sgd_train_time, sgd_test_time = benchmark(
SGDClassifier(**sgd_parameters))
######################################################################
## Print classification performance
print("")
print("Classification performance:")
print("===========================")
print("")
def print_row(clf_type, train_time, test_time, err):
print("%s %s %s %s" %
(clf_type.ljust(12), ("%.4fs" % train_time).center(10),
("%.4fs" % test_time).center(10), ("%.4f" % err).center(10)))
# shuffle
idx = np.arange(X.shape[0])
np.random.seed(13)
np.random.shuffle(idx)
X = X[idx]
y = y[idx]
# standardize
mean = X.mean(axis=0)
std = X.std(axis=0)
X = (X - mean) / std
h = .02 # step size in the mesh
clf = SGDClassifier(alpha=0.001, n_iter=100).fit(X, y)
# create a mesh to plot in
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
pl.set_cmap(pl.cm.Paired)
# Plot the decision boundary. For that, we will asign a color to each
# point in the mesh [x_min, m_max]x[y_min, y_max].
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
pl.set_cmap(pl.cm.Paired)
'eps': 1e-3,
}
liblinear_res = benchmark(LinearSVC(**liblinear_parameters))
liblinear_err, liblinear_train_time, liblinear_test_time = liblinear_res
######################################################################
## Train GNB model
gnb_err, gnb_train_time, gnb_test_time = benchmark(GNB())
######################################################################
## Train SGD model
sgd_parameters = {
'alpha': 0.001,
'n_iter': 2,
}
sgd_err, sgd_train_time, sgd_test_time = benchmark(SGDClassifier(
**sgd_parameters))
######################################################################
## Print classification performance
print("")
print("Classification performance:")
print("===========================")
print("")
def print_row(clf_type, train_time, test_time, err):
print("%s %s %s %s" % (clf_type.ljust(12),
("%.4fs" % train_time).center(10),
("%.4fs" % test_time).center(10),
("%.4f" % err).center(10)))
separable dataset using a linear Support Vector Machines classifier
trained using SGD.
"""
print __doc__
import numpy as np
import pylab as pl
from scikits.learn.linear_model import SGDClassifier
# we create 40 separable points
np.random.seed(0)
X = np.r_[np.random.randn(20, 2) - [2,2], np.random.randn(20, 2) + [2, 2]]
Y = [0]*20 + [1]*20
# fit the model
clf = SGDClassifier(loss="hinge", alpha = 0.01, n_iter=50,
fit_intercept=True)
clf.fit(X, Y)
# plot the line, the points, and the nearest vectors to the plane
xx = np.linspace(-5, 5, 10)
yy = np.linspace(-5, 5, 10)
X1, X2 = np.meshgrid(xx, yy)
Z = np.empty(X1.shape)
for (i,j), val in np.ndenumerate(X1):
x1 = val
x2 = X2[i,j]
p = clf.decision_function([x1, x2])
Z[i,j] = p[0]
levels = [-1.0, 0.0, 1.0]
linestyles = ['dashed','solid', 'dashed']
colors = 'k'
