Added from_file and to_file

system/dataset.py

@@ -1,6 +1,7 @@
-from scipy import atleast_2d,asarray,ArrayType,shape,nonzero
+from scipy import atleast_2d,asarray,ArrayType,shape,nonzero,io,transpose
 from scipy import sort as array_sort
 from itertools import izip
+import shelve
 
 class Dataset:
     """The Dataset base class.
@@ -37,14 +38,19 @@ class Dataset:
         self._dims = [] #existing dimensions in this dataset
         self._map = {} # internal mapping for dataset:  identifier <--> index
         self._name = name
+        self._identifiers = identifiers
+        self._type = 'n'
         if isinstance(array,ArrayType):
             array = atleast_2d(asarray(array))
+            # vectors are column vectors 
+            if array.shape[0]==1:
+                array = transpose(array)
             self.shape = array.shape
             if identifiers!=None:
                 self._set_identifiers(identifiers,self._all_dims)
             else:
-                ids = self._create_identifiers(self.shape,self._all_dims)
-                self._set_identifiers(ids,self._all_dims)
+                self._identifiers = self._create_identifiers(self.shape,self._all_dims)
+                self._set_identifiers(self._identifiers,self._all_dims)
             
             self._array = array
             
@@ -178,7 +184,6 @@ class Dataset:
             index = [self._map[dim][key] for key in idents]
         return asarray(index)        
         
-
 class CategoryDataset(Dataset):
     """The category dataset class.
 
@@ -203,6 +208,7 @@ class CategoryDataset(Dataset):
     def __init__(self,array,identifiers=None,name='C'):
         Dataset.__init__(self,array,identifiers=identifiers,name=name)
         self.has_dictlists = False
+        self._type = 'c'
             
     def as_dict_lists(self):
         """Returns data as dict of indices along first dim"""
@@ -226,6 +232,7 @@ class GraphDataset(Dataset):
     def __init__(self,array=None,identifiers=None,shape=None,all_dims=[],**kwds):
         Dataset.__init__(self,array=array,identifiers=identifiers,name='A')
         self.has_graph = False
+        self._type = 'g'
         
     def asnetworkx(self,nx_type='graph'):
         dim = self.get_dim_name()[0]
@@ -286,3 +293,34 @@ class ReverseDict(dict):
     def __setitem__(self, key, value):
         dict.__setitem__(self, key, value)
         self.reverse[value] = key
+
+def to_file(filepath,dataset,name=None):
+    """Write dataset to file. A file may contain multiple datasets.
+    append to file by using option mode='a'
+    """
+    if not name:
+        name = dataset._name
+    data = shelve.open(filepath,protocol=2)
+    if data: #we have an append 
+        names = data.keys()
+        if name in names:
+            print "Data with name: %s overwritten" %dataset._name
+    sub_data = {'array':dataset._array,'idents':dataset._identifiers,'type':dataset._type}
+    data[name] = sub_data 
+    data.close()
+
+def from_file(filepath):
+    """Read dataset from file """
+    data = shelve.open(filepath)
+    out_data = []
+    for name in data.keys():
+        sub_data = data[name]
+        if sub_data['type']=='c':
+            out_data.append(CategoryDataset(sub_data['array'],identifiers=sub_data['idents'],name=name))
+        elif sub_data['type']=='g':
+            out_data.append(GraphDataset(sub_data['array'],identifiers=sub_data['idents'],name=name))
+        else:
+            out_data.append(Dataset(sub_data['array'],identifiers=sub_data['idents'],name=name)) 
+            
+    return out_data
+