def test_scaler():
"""Test scaling of dataset along all axis
"""
# First test with 1D data
X = np.random.randn(5)
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
X = np.random.randn(4, 5)
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 5*[0.0])
assert_array_almost_equal(X_scaled.std(axis=0), 5*[1.0])
# Check that X has not been copied
assert X_scaled is X
X_scaled = scaler.fit(X).transform(X, copy=True)
assert_array_almost_equal(X_scaled.mean(axis=0), 5*[0.0])
assert_array_almost_equal(X_scaled.std(axis=0), 5*[1.0])
# Check that X has not been copied
assert X_scaled is not X
X_scaled = scale(X, axis=1, with_std=False)
assert_array_almost_equal(X_scaled.mean(axis=1), 4*[0.0])
X_scaled = scale(X, axis=1, with_std=True)
assert_array_almost_equal(X_scaled.std(axis=1), 4*[1.0])
def test_scaler():
"""Test scaling of dataset along all axis"""
# First test with 1D data
X = np.random.randn(5)
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
X = np.random.randn(4, 5)
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), 5 * [1.0])
# Check that X has not been copied
assert X_scaled is X
X_scaled = scaler.fit(X).transform(X, copy=True)
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), 5 * [1.0])
# Check that X has not been copied
assert X_scaled is not X
X_scaled = scale(X, axis=1, with_std=False)
assert_array_almost_equal(X_scaled.mean(axis=1), 4 * [0.0])
X_scaled = scale(X, axis=1, with_std=True)
assert_array_almost_equal(X_scaled.std(axis=1), 4 * [1.0])
# Check that the data hasn't been modified
assert X_scaled is not X
def test_scaler():
"""Test scaling of dataset along all axis"""
# First test with 1D data
X = np.random.randn(5)
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
# Test with 1D list
X = [0., 1., 2, 0.4, 1.]
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
X_scaled = scale(X)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
# Test with 2D data
X = np.random.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=True)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert X_scaled is not X
X_scaled = scale(X, axis=1, with_std=False)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(X_scaled.mean(axis=1), 4 * [0.0])
X_scaled = scale(X, axis=1, with_std=True)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(X_scaled.mean(axis=1), 4 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=1), 4 * [1.0])
# Check that the data hasn't been modified
assert X_scaled is not X
X_scaled = scaler.fit(X).transform(X, copy=False)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert X_scaled is X
X = np.random.randn(4, 5)
X[:, 0] = 1.0 # first feature is a constant, non zero feature
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=True)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert X_scaled is not X
def test_auto_weight(self):
"""Test class weights for imbalanced data"""
# compute reference metrics on iris dataset that is quite balanced by
# default
X, y = iris.data, iris.target
X = preprocessing.scale(X)
idx = np.arange(X.shape[0])
np.random.seed(13)
np.random.shuffle(idx)
X = X[idx]
y = y[idx]
clf = self.factory(alpha=0.0001, n_iter=1000).fit(X, y)
assert_approx_equal(metrics.f1_score(y, clf.predict(X)), 0.96, 2)
# make the same prediction using automated class_weight
clf_auto = self.factory(alpha=0.0001,
n_iter=1000).fit(X, y, class_weight="auto")
assert_approx_equal(metrics.f1_score(y, clf_auto.predict(X)), 0.96, 2)
# Make sure that in the balanced case it does not change anything
# to use "auto"
assert_array_almost_equal(clf.coef_, clf_auto.coef_, 6)
# build an very very imbalanced dataset out of iris data
X_0 = X[y == 0, :]
y_0 = y[y == 0]
X_imbalanced = np.vstack([X] + [X_0] * 10)
y_imbalanced = np.concatenate([y] + [y_0] * 10)
# fit a model on the imbalanced data without class weight info
clf = self.factory(n_iter=1000)
clf.fit(X_imbalanced, y_imbalanced)
y_pred = clf.predict(X)
assert metrics.f1_score(y, y_pred) < 0.96
# fit a model with auto class_weight enabled
clf = self.factory(n_iter=1000)
clf.fit(X_imbalanced, y_imbalanced, class_weight="auto")
y_pred = clf.predict(X)
assert metrics.f1_score(y, y_pred) > 0.96
def test_auto_weight(self):
"""Test class weights for imbalanced data"""
# compute reference metrics on iris dataset that is quite balanced by
# default
X, y = iris.data, iris.target
X = preprocessing.scale(X)
idx = np.arange(X.shape[0])
np.random.seed(13)
np.random.shuffle(idx)
X = X[idx]
y = y[idx]
clf = self.factory(alpha=0.0001, n_iter=1000).fit(X, y)
assert_approx_equal(metrics.f1_score(y, clf.predict(X)), 0.96, 2)
# make the same prediction using automated class_weight
clf_auto = self.factory(alpha=0.0001,
n_iter=1000).fit(X, y, class_weight="auto")
assert_approx_equal(metrics.f1_score(y, clf_auto.predict(X)), 0.96, 2)
# Make sure that in the balanced case it does not change anything
# to use "auto"
assert_array_almost_equal(clf.coef_, clf_auto.coef_, 6)
# build an very very imbalanced dataset out of iris data
X_0 = X[y == 0, :]
y_0 = y[y == 0]
X_imbalanced = np.vstack([X] + [X_0] * 10)
y_imbalanced = np.concatenate([y] + [y_0] * 10)
# fit a model on the imbalanced data without class weight info
clf = self.factory(n_iter=1000)
clf.fit(X_imbalanced, y_imbalanced)
y_pred = clf.predict(X)
assert metrics.f1_score(y, y_pred) < 0.96
# fit a model with auto class_weight enabled
clf = self.factory(n_iter=1000)
clf.fit(X_imbalanced, y_imbalanced, class_weight="auto")
y_pred = clf.predict(X)
assert metrics.f1_score(y, y_pred) > 0.96
def test_scaler_without_centering():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
scaler = Scaler(with_mean=False)
X_scaled = scaler.fit(X).transform(X, copy=True)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(X_scaled.mean(axis=0),
[0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert X_scaled is not X
X_scaled = scale(X, with_mean=False)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(X_scaled.mean(axis=0),
[0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert X_scaled is not X
def test_scaler_without_centering():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
scaler = Scaler(with_mean=False)
X_scaled = scaler.fit(X).transform(X, copy=True)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(
X_scaled.mean(axis=0), [0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert X_scaled is not X
X_scaled = scale(X, with_mean=False)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(
X_scaled.mean(axis=0), [0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert X_scaled is not X
the Pearson correlation as an additional measure of the clustering quality. """ print __doc__ from time import time import numpy as np from scikits.learn.cluster import KMeans from scikits.learn.datasets import load_digits from scikits.learn.pca import PCA from scikits.learn.preprocessing import scale np.random.seed(42) digits = load_digits() data = scale(digits.data) n_samples, n_features = data.shape n_digits = len(np.unique(digits.target)) print "n_digits: %d" % n_digits print "n_features: %d" % n_features print "n_samples: %d" % n_samples print print "Raw k-means with k-means++ init..." t0 = time() km = KMeans(init='k-means++', k=n_digits, n_init=10).fit(data) print "done in %0.3fs" % (time() - t0) print "inertia: %f" % km.inertia_ print
