def fit(self):
print "fit the model"
train = np.array(self.model.data)
X = train[:, :2]
y = train[:, 2]
C = float(self.complexity.get())
gamma = float(self.gamma.get())
coef0 = float(self.coef0.get())
degree = int(self.degree.get())
kernel_map = {0: "linear", 1: "rbf", 2: "poly"}
if len(np.unique(y)) == 1:
clf = svm.OneClassSVM(kernel=kernel_map[self.kernel.get()],
gamma=gamma,
coef0=coef0,
degree=degree)
clf.fit(X)
else:
clf = svm.SVC(kernel=kernel_map[self.kernel.get()],
C=C,
gamma=gamma,
coef0=coef0,
degree=degree)
clf.fit(X, y)
if hasattr(clf, 'score'):
print "Accuracy:", clf.score(X, y) * 100
X1, X2, Z = self.decision_surface(clf)
self.model.clf = clf
self.model.set_surface((X1, X2, Z))
self.model.surface_type = self.surface_type.get()
self.fitted = True
self.model.changed("surface")
def test_oneclass():
"""
Test OneClassSVM
"""
clf = svm.OneClassSVM()
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(pred, [1, -1, -1])
assert_array_almost_equal(clf.intercept_, [-1.3514943])
assert_array_almost_equal(clf.dual_coef_, [[ 0.75061969, 0.74938031, 0.74996915, 0.75003085]])
assert_raises(NotImplementedError, lambda: clf.coef_)
def test_oneclass():
"""
Test OneClassSVM
"""
clf = svm.OneClassSVM()
clf.fit(X)
pred = clf.predict(T)
assert_array_almost_equal(pred, [1, -1, -1])
assert_array_almost_equal(clf.intercept_, [-1.351], decimal=3)
assert_array_almost_equal(clf.dual_coef_, [[0.750, 0.749, 0.749, 0.750]],
decimal=3)
assert_raises(NotImplementedError, lambda: clf.coef_)
def train(data, label):
mocsvm_model = []
maxdata = scipy.zeros((len(scipy.unique(label)), data.shape[1]))
mindata = scipy.zeros((len(scipy.unique(label)), data.shape[1]))
cnt = 0
for i in scipy.unique(label):
# for every class learn a one class svm model
# Learn an approximate value for gamma
tempdata = data[(label == i), :]
tempdata, maxdata[cnt, :], mindata[cnt, :] = MLUtility.normalizedata(
tempdata.copy())
dist = scipy.zeros((tempdata.shape[0], tempdata.shape[0]))
for j in range(tempdata.shape[0]):
for k in range(tempdata.shape[0]):
dist[j, k] = sum((tempdata[j, :] - tempdata[k, :])**2)
g = dist.max().max()
model = svm.OneClassSVM(nu=0.1, kernel='rbf', gamma=g * 8, C=10)
model.fit(tempdata)
# append it to the list of models
mocsvm_model.append(model)
cnt = cnt + 1
return mocsvm_model, maxdata, mindata
X.append([data[0], data[1]])
X = np.array(X, dtype='float64')
print X
x1_max = X[:][:, 0].max()
x1_min = X[:][:, 0].min()
x2_max = X[:][:, 1].max()
x2_min = X[:][:, 1].min()
x_size = len(X)
xx, yy = np.meshgrid(np.linspace(x1_min, x1_max, x_size),
np.linspace(x2_min, x2_max, x_size))
# fit the model
clf = svm.OneClassSVM(nu=0.1, kernel="linear", gamma=0.1)
clf.fit(X)
# plot the line, the points, and the nearest vectors to the plane
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
y_pred = clf.predict(X)
pl.set_cmap(pl.cm.Paired)
pl.contourf(xx, yy, Z)
pl.scatter(X[y_pred > 0, 0], X[y_pred > 0, 1], c='white', label='inliers')
pl.scatter(X[y_pred <= 0, 0], X[y_pred <= 0, 1], c='black', label='outliers')
pl.axis('tight')
pl.legend()
pl.show()
# The grid in x,y coordinates
X, Y = np.meshgrid(xx, yy[::-1])
#basemap = False
for i, species in enumerate([bv, mm]):
print "_" * 80
print "Modeling distribution of species '%s'" % species.name
print
# Standardize features
mean = species.train_cover.mean(axis=0)
std = species.train_cover.std(axis=0)
train_cover_std = (species.train_cover - mean) / std
# Fit OneClassSVM
print "fit OneClassSVM ... ",
clf = svm.OneClassSVM(nu=0.1, kernel="rbf", gamma=0.5)
clf.fit(train_cover_std)
print "done. "
# Plot map of South America
pl.subplot(1, 2, i + 1)
if basemap:
print "plot coastlines using basemap"
m = Basemap(projection='cyl', llcrnrlat=ymin,
urcrnrlat=ymax, llcrnrlon=xmin,
urcrnrlon=xmax, resolution='c')
m.drawcoastlines()
m.drawcountries()
#m.drawrivers()
else:
print "plot coastlines from coverage"