def test_project_data_pca(self):
x1 = ml.feature_normalize(self.ex7data1['X'])[0]
ex1 = ml.project_data_pca(x1, ml.pca(x1)[0], 1)
self.assertEqual(round(ex1[0][0], 3), 1.496)
X = utils.getData()
X[All] = machine_learning.norm(X[All])
print "Done."
print "Hierarchial clustering..."
hierarchy = machine_learning.recursiveCluster(X[dAll], size=500)
Y = machine_learning.flatten(hierarchy, min=40)
X = X[Y >= 0] # Eliminating outliers
Y = Y[Y >= 0]
y_values = np.unique(Y)
for i in range(0, len(y_values)):
Y[Y == y_values[i]] = i
print "Done."
print "Visualizing..."
machine_learning.pca(X[dAll], Y)
machine_learning.hist(X[["time"]], Y)
print "Done."
print "Shifting and randomizing..."
shift = 10
X, Y = utils.shiftLabels(X, Y, shift)
X, Y = utils.randomize(X, Y)
print 'Done.'
print "Choosing best parameters for classifier..."
clf, clf_acc, test_acc = machine_learning.best_classifier(X[All], Y)
print "Done."
print "Classifier accuracy: ", clf_acc
print "Test data accuracy: ", test_acc
print "Classifier model: ", clf
def test_pca(self):
x1 = ml.feature_normalize(self.ex7data1['X'])[0]
ex1 = ml.pca(x1)
self.assertEqual(ex1[0].all(), np.array([[-0.707107,-0.707107],
[-0.707107, 0.707107]]).all())