def make_prediction(dataset=None, binary=False):
"""Make some classification predictions on a toy dataset using a SVC
If binary is True restrict to a binary classification problem instead of a
multiclass classification problem
"""
if dataset is None:
# import some data to play with
dataset = datasets.load_iris()
X = dataset.data
y = dataset.target
if binary:
# restrict to a binary classification task
X, y = X[y < 2], y[y < 2]
n_samples, n_features = X.shape
p = np.arange(n_samples)
rng = check_random_state(37)
rng.shuffle(p)
X, y = X[p], y[p]
half = int(n_samples / 2)
# add noisy features to make the problem harder and avoid perfect results
rng = np.random.RandomState(0)
X = np.c_[X, rng.randn(n_samples, 200 * n_features)]
# run classifier, get class probabilities and label predictions
clf = svm.SVC(kernel='linear', probability=True, random_state=0)
probas_pred = clf.fit(X[:half], y[:half]).predict_proba(X[half:])
if binary:
# only interested in probabilities of the positive case
# XXX: do we really want a special API for the binary case?
probas_pred = probas_pred[:, 1]
y_pred = clf.predict(X[half:])
y_true = y[half:]
return y_true, y_pred, probas_pred
###############################################################################
# Tests
评论列表
文章目录
