def test_cluster(self):
data = self.dat['Dat']
assignments, centers = uncurl.poisson_cluster(data, 3)
self.assertEqual(assignments.shape[0], data.shape[1])
self.assertEqual(centers.shape[0], data.shape[0])
# just checking that the values are valid
self.assertFalse(np.isnan(centers).any())
def test_cluster(self):
data = self.data
assignments, centers = uncurl.poisson_cluster(data, 2)
self.assertEqual(assignments.shape[0], data.shape[1])
self.assertEqual(centers.shape[0], data.shape[0])
# just checking that the values are valid
self.assertFalse(np.isnan(centers).any())
self.assertTrue(purity(assignments, self.labs) > 0.8)
def test_simulation(self):
"""
Basically this is to test that the Poisson EM can correctly separate
clusters in simulated data.
"""
centers = np.array([[1, 10, 20], [1, 11, 1], [50, 1, 100]])
centers = centers.astype(float)
data, labs = generate_poisson_data(centers, 500)
data = data.astype(float)
assignments, c_centers = uncurl.poisson_cluster(data, 3)
distances = np.zeros((3, 3))
for i in range(3):
for j in range(3):
distances[i, j] = uncurl.poisson_dist(centers[:, i],
c_centers[:, j])
self.assertTrue(purity(assignments, labs) > 0.8)
from scipy.io import loadmat
import numpy as np
import matplotlib.pyplot as plt
import uncurl
from uncurl.lineage import fourier_series
if __name__ == '__main__':
dat = loadmat('data/BranchedSynDat.mat')
data = dat['Dat'].astype(float)
# Poisson clustering
assignments, centers = uncurl.poisson_cluster(data, 3)
# State estimation
#means, weights = uncurl.poisson_estimate_state(data, 3, max_iters=5)
means, weights = np.load('means_weights.npy')
# dimensionality reduction
X = uncurl.dim_reduce(means, weights, 2)
proj = np.dot(X.T, weights)
cluster_curves, cluster_fitted_vals, cluster_edges, cluster_assignments = uncurl.lineage(
means, weights, curve_function='poly')
# dimensionality reduction with true data
true_weights = dat['X']
true_means = dat['M']
X = uncurl.dim_reduce(true_means, true_weights, 2)
proj_true = np.dot(X.T, true_weights)
true_curves, true_fitted, true_edges, true_assignments = uncurl.lineage(
true_means, true_weights)
# plotting dimensionality reduction, fitted curves
plt.clf()
plt.cla()
plt.title('Dimensionality reduction plot')
from scipy.io import loadmat
import numpy as np
import matplotlib.pyplot as plt
import uncurl
from uncurl.evaluation import purity
if __name__ == '__main__':
dat = loadmat('data/SCDE_test.mat')
data = dat['dat'].toarray()
centers, assignments = uncurl.kmeans_pp(data, 2)
lls = uncurl.poisson_ll(data, centers)
# Poisson clustering
assignments_poisson, centers = uncurl.poisson_cluster(data,
2,
init=centers)
# NB clustering
assignments_nb, P, R = uncurl.nb_cluster(data, 2)
# ZIP clustering
assignments_zip, M, L = uncurl.zip_cluster(data, 2)
true_labs = dat['Lab'][0]
print 'poisson purity:', purity(assignments_poisson, true_labs)
print 'NB purity:', purity(assignments_nb, true_labs)
print 'ZIP purity:', purity(assignments_zip, true_labs)
# State estimation
means, weights, ll = uncurl.poisson_estimate_state(data, 2, disp=False)
w_classes = weights.argmax(0)
print 'W argmax purity:', purity(w_classes, true_labs)
# dimensionality reduction
X = uncurl.dim_reduce(means, weights, 2)
proj = np.dot(X, weights)