Automatically fetch datasets and first init. attempt for mocap

GPy/util/datasets.py

@@ -5,6 +5,8 @@ import GPy
 import scipy.sparse
 import scipy.io
 import cPickle as pickle
+import urllib2 as url
+
 data_path = os.path.join(os.path.dirname(__file__), 'datasets')
 default_seed = 10000
 
@@ -15,6 +17,18 @@ def sample_class(f):
     c = np.where(c, 1, -1)
     return c
 
+def fetch_dataset(resource, file_name, messages = True):
+    if messages:
+        print "Downloading resource: " , resource, " ... "
+    response = url.urlopen(resource)
+    # TODO: Some error checking...
+    html = response.read()
+    response.close()
+    with open(file_name, "w") as text_file:
+        text_file.write("%s"%html)
+    if messages:
+        print "Done!"
+
 def della_gatta_TRP63_gene_expression(gene_number=None):
     mat_data = scipy.io.loadmat(os.path.join(data_path, 'DellaGattadata.mat'))
     X = np.double(mat_data['timepoints'])

GPy/util/mocap_fetch.py

@@ -0,0 +1,13 @@
+import GPy
+import urllib2
+
+# TODO...
+class mocap_fetch(base_url = 'http://mocap.cs.cmu.edu:8080/subjects/', skel_store_dir = './', motion_store_dir = './'):
+    def __init__(self):
+        self.base_url = base_url
+        self.store_dir = store_dir
+        self.motion_dict = []
+    
+    def fetch_motions(self, motion_dict = None):
+        response = urllib2.urlopen(...)
+        html = response.read()