def test_classifier_results():
"""tests if classifier results match target"""
alpha = .1
n_features = 20
n_samples = 10
tol = .01
max_iter = 200
rng = np.random.RandomState(0)
X = rng.normal(size=(n_samples, n_features))
w = rng.normal(size=n_features)
y = np.dot(X, w)
y = np.sign(y)
clf1 = LogisticRegression(solver='sag',
C=1. / alpha / n_samples,
max_iter=max_iter,
tol=tol,
random_state=77)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
pred1 = clf1.predict(X)
pred2 = clf2.predict(X)
assert_almost_equal(pred1, y, decimal=12)
assert_almost_equal(pred2, y, decimal=12)
def test_sample_weight():
"""Tests sample_weight parameter of VotingClassifier"""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = SVC(probability=True, random_state=123)
eclf1 = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('svc', clf3)],
voting='soft').fit(X, y, sample_weight=np.ones((len(y),)))
eclf2 = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('svc', clf3)],
voting='soft').fit(X, y)
assert_array_equal(eclf1.predict(X), eclf2.predict(X))
assert_array_almost_equal(eclf1.predict_proba(X), eclf2.predict_proba(X))
sample_weight = np.random.RandomState(123).uniform(size=(len(y),))
eclf3 = VotingClassifier(estimators=[('lr', clf1)], voting='soft')
eclf3.fit(X, y, sample_weight)
clf1.fit(X, y, sample_weight)
assert_array_equal(eclf3.predict(X), clf1.predict(X))
assert_array_almost_equal(eclf3.predict_proba(X), clf1.predict_proba(X))
# check that an error is raised and indicative if sample_weight is not
# supported.
clf4 = KNeighborsClassifier()
eclf3 = VotingClassifier(estimators=[
('lr', clf1), ('svc', clf3), ('knn', clf4)],
voting='soft')
msg = ('Underlying estimator KNeighborsClassifier does not support '
'sample weights.')
with pytest.raises(ValueError, match=msg):
eclf3.fit(X, y, sample_weight)
# check that _parallel_fit_estimator will raise the right error
# it should raise the original error if this is not linked to sample_weight
class ClassifierErrorFit(BaseEstimator, ClassifierMixin):
def fit(self, X, y, sample_weight):
raise TypeError('Error unrelated to sample_weight.')
clf = ClassifierErrorFit()
with pytest.raises(TypeError, match='Error unrelated to sample_weight'):
clf.fit(X, y, sample_weight=sample_weight)
iris = datasets.load_iris()
X = iris.data[:, :2] # we only take the first two features.
Y = iris.target
logreg = LogisticRegression(C=1e5)
# Create an instance of Logistic Regression Classifier and fit the data.
logreg.fit(X, Y)
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]x[y_min, y_max].
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
h = .02 # step size in the mesh
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z = logreg.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure(1, figsize=(4, 3))
plt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired)
# Plot also the training points
plt.scatter(X[:, 0], X[:, 1], c=Y, edgecolors='k', cmap=plt.cm.Paired)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.xticks(())
plt.yticks(())
# Small number of epochs for fast runtime
for this_max_iter in model_params['iters']:
print('[model=%s, solver=%s] Number of epochs: %s' %
(model_params['name'], solver, this_max_iter))
lr = LogisticRegression(
solver=solver,
multi_class=model,
penalty='l1',
max_iter=this_max_iter,
random_state=42,
)
t1 = timeit.default_timer()
lr.fit(X_train, y_train)
train_time = timeit.default_timer() - t1
y_pred = lr.predict(X_test)
accuracy = np.sum(y_pred == y_test) / y_test.shape[0]
density = np.mean(lr.coef_ != 0, axis=1) * 100
accuracies.append(accuracy)
densities.append(density)
times.append(train_time)
models[model]['times'] = times
models[model]['densities'] = densities
models[model]['accuracies'] = accuracies
print('Test accuracy for model %s: %.4f' % (model, accuracies[-1]))
print('%% non-zero coefficients for model %s, '
'per class:\n %s' % (model, densities[-1]))
print('Run time (%i epochs) for model %s:'
'%.2f' % (model_params['iters'][-1], model, times[-1]))
fig = plt.figure()
random_state=42,
multi_class=multi_class).fit(X, y)
# print the training scores
print("training score : %.3f (%s)" % (clf.score(X, y), multi_class))
# create a mesh to plot in
h = .02 # step size in the mesh
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))
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_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)
plt.figure()
plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)
plt.title("Decision surface of LogisticRegression (%s)" % multi_class)
plt.axis('tight')
# Plot also the training points
colors = "bry"
for i, color in zip(clf.classes_, colors):
idx = np.where(y == i)
plt.scatter(X[idx, 0],
X[idx, 1],
c=color,
cmap=plt.cm.Paired,