diff --git a/scikits/learn/pyem/Changelog b/scikits/learn/pyem/Changelog
index bca9b599c979fd02c0f62c122f685903db518098..0545abf1076ea2761da1634e940a051de37f58b5 100644
--- a/scikits/learn/pyem/Changelog
+++ b/scikits/learn/pyem/Changelog
@@ -1,3 +1,11 @@
+pyem (0.5.6) Thu, 16 Nov 2006 21:02:02 +0900
+
+ * correct examples
+ * correct exceptions msg strings in gauss_mix, which
+ were buggy
+ * add examples from website to the package, so that above errors
+ do not appear again
+
pyem (0.5.6) Thu, 16 Nov 2006 14:18:19 +0900
* bump to 0.5.6
diff --git a/scikits/learn/pyem/__init__.py b/scikits/learn/pyem/__init__.py
index 371e315a96885b4ac4aa451ce1a2f49ae269b92d..ae6d83c73b75d8371cdca32ed5409a668def7372 100644
--- a/scikits/learn/pyem/__init__.py
+++ b/scikits/learn/pyem/__init__.py
@@ -1,11 +1,12 @@
#! /usr/bin/env python
-# Last Change: Fri Oct 20 11:00 AM 2006 J
+# Last Change: Thu Nov 16 09:00 PM 2006 J
from info import __doc__
from gauss_mix import GmParamError, GM
from gmm_em import GmmParamError, GMM, EM
from online_em import OnGMM as _OnGMM
+import examples as _examples
__all__ = filter(lambda s:not s.startswith('_'),dir())
diff --git a/scikits/learn/pyem/basic_example1.py b/scikits/learn/pyem/basic_example1.py
new file mode 100644
index 0000000000000000000000000000000000000000..a47e0b935645231a9763aad17c2835e4d4eda33c
--- /dev/null
+++ b/scikits/learn/pyem/basic_example1.py
@@ -0,0 +1,48 @@
+import numpy as N
+import pylab as P
+from scipy.sandbox.pyem import GM
+
+#------------------------------
+# Hyper parameters:
+# - K: number of clusters
+# - d: dimension
+k = 3
+d = 2
+
+#-------------------------------------------------------
+# Values for weights, mean and (diagonal) variances
+# - the weights are an array of rank 1
+# - mean is expected to be rank 2 with one row for one component
+# - variances are also expteced to be rank 2. For diagonal, one row
+# is one diagonal, for full, the first d rows are the first variance,
+# etc... In this case, the variance matrix should be k*d rows and d
+# colums
+w = N.array([0.2, 0.45, 0.35])
+mu = N.array([[4.1, 3], [1, 5], [-2, -3]])
+va = N.array([[1, 1.5], [3, 4], [2, 3.5]])
+
+#-----------------------------------------
+# First method: directly from parameters:
+# Both methods are equivalents.
+gm = GM.fromvalues(w, mu, va)
+
+#-------------------------------------
+# Second method to build a GM instance:
+gm = GM(d, k, mode = 'diag')
+# The set_params checks that w, mu, and va corresponds to k, d and m
+gm.set_param(w, mu, va)
+
+# Once set_params is called, both methods are equivalent. The 2d
+# method is useful when using a GM object for learning (where
+# the learner class will set the params), whereas the first one
+# is useful when there is a need to quickly sample a model
+# from existing values, without a need to give the hyper parameters
+
+# Create a Gaussian Mixture from the parameters, and sample
+# 1000 items from it (one row = one 2 dimension sample)
+data = gm.sample(1000)
+
+# Plot the samples
+P.plot(data[:, 0], data[:, 1], '.')
+# Plot the ellipsoids of confidence with a level a 75 %
+gm.plot(level = 0.75)
diff --git a/scikits/learn/pyem/basic_example2.py b/scikits/learn/pyem/basic_example2.py
new file mode 100644
index 0000000000000000000000000000000000000000..6ff2fc6878021cbf5605aa430539f4d37ebe5933
--- /dev/null
+++ b/scikits/learn/pyem/basic_example2.py
@@ -0,0 +1,45 @@
+from numpy.random import seed
+
+from scipy.sandbox.pyem import GM, GMM, EM
+import copy
+
+# To reproduce results, fix the random seed
+seed(1)
+
+#+++++++++++++++++++++++++++++
+# Meta parameters of the model
+# - k: Number of components
+# - d: dimension of each Gaussian
+# - mode: Mode of covariance matrix: full or diag (string)
+# - nframes: number of frames (frame = one data point = one
+# row of d elements)
+k = 2
+d = 2
+mode = 'diag'
+nframes = 1e3
+
+#+++++++++++++++++++++++++++++++++++++++++++
+# Create an artificial GM model, samples it
+#+++++++++++++++++++++++++++++++++++++++++++
+w, mu, va = GM.gen_param(d, k, mode, spread = 1.5)
+gm = GM.fromvalues(w, mu, va)
+
+# Sample nframes frames from the model
+data = gm.sample(nframes)
+
+#++++++++++++++++++++++++
+# Learn the model with EM
+#++++++++++++++++++++++++
+
+# Create a Model from a Gaussian mixture with kmean initialization
+lgm = GM(d, k, mode)
+gmm = GMM(lgm, 'kmean')
+
+# The actual EM, with likelihood computation. The threshold
+# is compared to the (linearly appromixated) derivative of the likelihood
+em = EM()
+like = em.train(data, gmm, maxiter = 30, thresh = 1e-8)
+
+# The computed parameters are in gmm.gm, which is the same than lgm
+# (remember, python does not copy most objects by default). You can for example
+# plot lgm against gm to compare
diff --git a/scikits/learn/pyem/basic_example3.py b/scikits/learn/pyem/basic_example3.py
new file mode 100644
index 0000000000000000000000000000000000000000..d680584dc8674227b88397361bfd511836f066af
--- /dev/null
+++ b/scikits/learn/pyem/basic_example3.py
@@ -0,0 +1,64 @@
+import numpy as N
+from numpy.random import seed
+
+from scipy.sandbox.pyem import GM, GMM, EM
+import copy
+
+seed(2)
+
+k = 4
+d = 2
+mode = 'diag'
+nframes = 1e3
+
+#+++++++++++++++++++++++++++++++++++++++++++
+# Create an artificial GMM model, samples it
+#+++++++++++++++++++++++++++++++++++++++++++
+w, mu, va = GM.gen_param(d, k, mode, spread = 1.0)
+gm = GM.fromvalues(w, mu, va)
+
+# Sample nframes frames from the model
+data = gm.sample(nframes)
+
+#++++++++++++++++++++++++
+# Learn the model with EM
+#++++++++++++++++++++++++
+
+# List of learned mixtures lgm[i] is a mixture with i+1 components
+lgm = []
+kmax = 6
+bics = N.zeros(kmax)
+em = EM()
+for i in range(kmax):
+ lgm.append(GM(d, i+1, mode))
+
+ gmm = GMM(lgm[i], 'kmean')
+ em.train(data, gmm, maxiter = 30, thresh = 1e-10)
+ bics[i] = gmm.bic(data)
+
+print "Original model has %d clusters, bics says %d" % (k, N.argmax(bics)+1)
+
+#+++++++++++++++
+# Draw the model
+#+++++++++++++++
+import pylab as P
+P.subplot(3, 2, 1)
+
+for k in range(kmax):
+ P.subplot(3, 2, k+1)
+ level = 0.9
+ P.plot(data[:, 0], data[:, 1], '.', label = '_nolegend_')
+
+ # h keeps the handles of the plot, so that you can modify
+ # its parameters like label or color
+ h = lgm[k].plot(level = level)
+ [i.set_color('r') for i in h]
+ h[0].set_label('EM confidence ellipsoides')
+
+ h = gm.plot(level = level)
+ [i.set_color('g') for i in h]
+ h[0].set_label('Real confidence ellipsoides')
+
+P.legend(loc = 0)
+# depending on your configuration, you may have to call P.show()
+# to actually display the figure
diff --git a/scikits/learn/pyem/example.py b/scikits/learn/pyem/demo1.py
similarity index 100%
rename from scikits/learn/pyem/example.py
rename to scikits/learn/pyem/demo1.py
diff --git a/scikits/learn/pyem/example2.py b/scikits/learn/pyem/demo2.py
similarity index 100%
rename from scikits/learn/pyem/example2.py
rename to scikits/learn/pyem/demo2.py
diff --git a/scikits/learn/pyem/examples.py b/scikits/learn/pyem/examples.py
new file mode 100644
index 0000000000000000000000000000000000000000..0f9a91422a1b4eef6399a63a9a200ad02ace3709
--- /dev/null
+++ b/scikits/learn/pyem/examples.py
@@ -0,0 +1,14 @@
+def ex1():
+ import basic_example1
+
+def ex2():
+ import basic_example2
+
+def ex3():
+ import basic_example3
+
+if __name__ == '__main__':
+ ex1()
+ ex2()
+ ex3()
+
diff --git a/scikits/learn/pyem/gauss_mix.py b/scikits/learn/pyem/gauss_mix.py
index fdc66be1c47a51c59681c79baf6e186dcbfea6b6..bacdcf7997cf48733f6152e132c156e81eba5cf2 100644
--- a/scikits/learn/pyem/gauss_mix.py
+++ b/scikits/learn/pyem/gauss_mix.py
@@ -1,5 +1,5 @@
# /usr/bin/python
-# Last Change: Thu Nov 09 06:00 PM 2006 J
+# Last Change: Thu Nov 16 08:00 PM 2006 J
# Module to implement GaussianMixture class.
@@ -82,10 +82,10 @@ class GM:
k, d, mode = check_gmm_param(weights, mu, sigma)
if not k == self.k:
raise GmParamError("Number of given components is %d, expected %d"
- % (shape(k), shape(self.k)))
+ % (k, self.k))
if not d == self.d:
raise GmParamError("Dimension of the given model is %d, expected %d"
- % (shape(d), shape(self.d)))
+ % (d, self.d))
if not mode == self.mode and not d == 1:
raise GmParamError("Given covariance mode is %s, expected %s"
% (mode, self.mode))
diff --git a/scikits/learn/pyem/gmm_em.py b/scikits/learn/pyem/gmm_em.py
index d5d6aa9f676349315256727764c5681d1c2a0faa..e700c059be3ca27183fdfe7df96b58fa150da5e3 100644
--- a/scikits/learn/pyem/gmm_em.py
+++ b/scikits/learn/pyem/gmm_em.py
@@ -374,7 +374,7 @@ def multiple_gauss_den(data, mu, va):
K = mu.shape[0]
n = data.shape[0]
- d = data.shape[1]
+ d = mu.shape[1]
y = N.zeros((K, n))
if mu.size == va.size:
diff --git a/scikits/learn/pyem/tests/test_examples.py b/scikits/learn/pyem/tests/test_examples.py
new file mode 100644
index 0000000000000000000000000000000000000000..708c83bf6e757977bc2373dae929dbf611bca599
--- /dev/null
+++ b/scikits/learn/pyem/tests/test_examples.py
@@ -0,0 +1,26 @@
+#! /usr/bin/env python
+# Last Change: Thu Nov 16 09:00 PM 2006 J
+
+from numpy.testing import *
+
+set_package_path()
+from pyem.examples import ex1, ex2, ex3
+restore_path()
+
+# #Optional:
+# set_local_path()
+# # import modules that are located in the same directory as this file.
+# restore_path()
+
+class test_examples(NumpyTestCase):
+ def check_ex1(self, level = 5):
+ ex1()
+
+ def check_ex2(self, level = 5):
+ ex2()
+
+ def check_ex3(self, level = 5):
+ ex3()
+
+if __name__ == "__main__":
+ NumpyTest().run()
diff --git a/scikits/learn/pyem/tests/test_online_em.py b/scikits/learn/pyem/tests/test_online_em.py
index ddbe4190b786182276bae78fa05a8d8c2b49b3df..90573e8f72296525b0d1e0c1dc5788edcbeae1c7 100644
--- a/scikits/learn/pyem/tests/test_online_em.py
+++ b/scikits/learn/pyem/tests/test_online_em.py
@@ -1,5 +1,5 @@
#! /usr/bin/env python
-# Last Change: Mon Oct 23 07:00 PM 2006 J
+# Last Change: Thu Nov 16 09:00 PM 2006 J
import copy
@@ -61,7 +61,7 @@ class test_on_off_eq(OnlineEmTest):
self._create_model(d, k, mode, nframes, emiter)
self._check(d, k, mode, nframes, emiter)
- def check_2d(self, level = 2):
+ def check_2d(self, level = 1):
d = 2
k = 2
mode = 'diag'
@@ -72,7 +72,7 @@ class test_on_off_eq(OnlineEmTest):
self._create_model(d, k, mode, nframes, emiter)
self._check(d, k, mode, nframes, emiter)
- def check_5d(self, level = 2):
+ def check_5d(self, level = 5):
d = 5
k = 2
mode = 'diag'