New Dataset: MurphyLab Hela-2d SLF7dna features

This is a homegrown feature set & problem, but it's useful to have.

milksets/murphy_hela_slf7dna/__init__.py

@@ -0,0 +1,24 @@
+# -*- coding: utf-8 -*-
+# Copyright (C) 2009, Luís Pedro Coelho <lpc@cmu.edu>
+# 
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+#  of this software and associated documentation files (the "Software"), to deal
+#  in the Software without restriction, including without limitation the rights
+#  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+#  copies of the Software, and to permit persons to whom the Software is
+#  furnished to do so, subject to the following conditions:
+# 
+# The above copyright notice and this permission notice shall be included in
+#  all copies or substantial portions of the Software.
+# 
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+#  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+#  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+#  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+#  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+#  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+#  THE SOFTWARE.
+
+from .murphy_hela2d_slf7dna import *
+
+# vim: set ts=4 sts=4 sw=4 expandtab smartindent:

milksets/murphy_hela_slf7dna/data/compute.py

@@ -0,0 +1,13 @@
+import numpy as np
+MURPHYLAB_HELA2D_PATH = '/home/luispedro/work/murphylab/images/hela-2d/'
+print r'''\
+This is only to be run if you have got the Murphylab images installed at
+    %s
+
+Otherwise, you will get errors!
+''' % MURPHYLAB_HELA2D_PATH
+import pyslic
+imgs = pyslic.image.io.dirtransversal.dirtransversal(MURPHYLAB_HELA2D_PATH)
+labels = np.array([img.label for img in imgs])
+features = pyslic.computefeatures(imgs, 'SLF7DNA')
+np.savez('murphylab.npz', features=features, labels=labels)

milksets/murphy_hela_slf7dna/murphy_hela2d_slf7dna.py

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+# Copyright (C) 2009, Luís Pedro Coelho <lpc@cmu.edu>
+# 
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+#  of this software and associated documentation files (the "Software"), to deal
+#  in the Software without restriction, including without limitation the rights
+#  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+#  copies of the Software, and to permit persons to whom the Software is
+#  furnished to do so, subject to the following conditions:
+# 
+# The above copyright notice and this permission notice shall be included in
+#  all copies or substantial portions of the Software.
+# 
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+#  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+#  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+#  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+#  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+#  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+#  THE SOFTWARE.
+
+from __future__ import division
+import numpy as np
+from os.path import dirname
+from ..vtypes import continuous
+from ..utils import standard_properties, standard_classification_loader
+
+__all__ = ['load'] + standard_properties
+
+name = 'Murphy Lab 2D HeLa (SLF7DNA)'
+short_name = 'Hela2D'
+long_name = name
+reference = '''\
+'''
+url = 'http://murphylab.cbi.cmu.edu/download'
+data_source = 'MurphyLab'
+label_names = ['dap', 'erdak', 'giant', 'gpp130', 'h4b4', 'mc151', 'nucle', 'phal', 'tfr', 'tubul']
+missing_values = False
+value_types = [
+    continuous('_%s' % i) for i in xrange(90)
+    ]
+
+_datafile = dirname(__file__)+'/data/murphylab.npz'
+
+@standard_classification_loader(name)
+def load(force_contiguous=True):
+    data = np.load(_datafile)
+    features = data['features']
+    labels = np.array([label_names.index(lab) for lab in data['labels']])
+    if force_contiguous:
+        features = np.ascontiguousarray(features)
+        labels = np.ascontiguousarray(labels)
+    return features,labels
+
+# vim: set ts=4 sts=4 sw=4 expandtab smartindent:

tests/test_classification_loaders.py

@@ -10,4 +10,5 @@ def test_loader(module):
         assert (features.std(0)**2).sum() > 1e-8
     yield test_loader, milksets.wine
     yield test_loader, milksets.yeast
+    yield test_loader, milksets.murphy_hela_slf7dna