Projects/laydi
Projects
/
laydi
Archived
7
0
Fork 0
Code Issues Pull Requests Activity

copy() added to dataset. Does deepcopy. deepcopy issue fixed in ReverseDict

This commit is contained in:
Arnar Flatberg 2006-09-16 10:36:57 +00:00
parent c7f74f67ca
commit c370d9d250
1 changed files with 48 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
system/dataset.py
View File

@ -2,6 +2,7 @@ from scipy import ndarray,atleast_2d,asarray
from scipy import sort as array_sort from scipy import sort as array_sort
from itertools import izip from itertools import izip
import shelve import shelve
import copy
class Dataset: class Dataset:
"""The Dataset base class. """The Dataset base class.
@ -40,12 +41,16 @@ class Dataset:
self._name = name self._name = name
self._identifiers = identifiers self._identifiers = identifiers
self._type = 'n' self._type = 'n'
if isinstance(array,ndarray): try:
array = atleast_2d(asarray(array)) array = atleast_2d(asarray(array))
except:
print "Cant cast array as numpy-array"
return
# vectors are column vectors # vectors are column vectors
if array.shape[0]==1: if array.shape[0]==1:
array = array.T array = array.T
self.shape = array.shape self.shape = array.shape
if identifiers!=None: if identifiers!=None:
self._set_identifiers(identifiers,self._all_dims) self._set_identifiers(identifiers,self._all_dims)
else: else:
@ -54,9 +59,6 @@ class Dataset:
self._array = array self._array = array
else:
raise ValueError, "Array input must be of type ndarray"
def __iter__(self): def __iter__(self):
"""Returns an iterator over dimensions of dataset.""" """Returns an iterator over dimensions of dataset."""
return self._dims.__iter__() return self._dims.__iter__()
@ -189,6 +191,9 @@ class Dataset:
for key in idents if self._map[dim].has_key(key)] for key in idents if self._map[dim].has_key(key)]
return asarray(index) return asarray(index)
def copy(self):
return copy.deepcopy(self)
class CategoryDataset(Dataset): class CategoryDataset(Dataset):
"""The category dataset class. """The category dataset class.
@ -245,8 +250,9 @@ class CategoryDataset(Dataset):
class GraphDataset(Dataset): class GraphDataset(Dataset):
"""The graph dataset class. """The graph dataset class.
A dataset class for representing graphs using an adjacency matrix A dataset class for representing graphs using an (weighted)
(aka. restricted to square symmetric signed integers matrices) adjacency matrix
(aka. restricted to square symmetric matrices)
If the library NetworkX is installed, there is support for If the library NetworkX is installed, there is support for
representing the graph as a NetworkX.Graph, or NetworkX.XGraph structure. representing the graph as a NetworkX.Graph, or NetworkX.XGraph structure.
@ -254,7 +260,7 @@ class GraphDataset(Dataset):
def __init__(self,array=None,identifiers=None,shape=None,all_dims=[],**kwds): def __init__(self,array=None,identifiers=None,shape=None,all_dims=[],**kwds):
Dataset.__init__(self,array=array,identifiers=identifiers,name='A') Dataset.__init__(self,array=array,identifiers=identifiers,name='A')
self.has_graph = False self._graph = None
self._type = 'g' self._type = 'g'
def asnetworkx(self,nx_type='graph'): def asnetworkx(self,nx_type='graph'):
@ -262,34 +268,41 @@ class GraphDataset(Dataset):
ids = self.get_identifiers(dim,sorted=True) ids = self.get_identifiers(dim,sorted=True)
adj_mat = self.asarray() adj_mat = self.asarray()
G = self._graph_from_adj_matrix(adj_mat,labels=ids) G = self._graph_from_adj_matrix(adj_mat,labels=ids)
self.has_graph = True self._graph = G
return G return G
def _graph_from_adj_matrix(self,A,labels=None,nx_type='graph'): def _graph_from_adj_matrix(self,A,labels=None):
"""Creates a networkx graph class from adjacency matrix and """Creates a networkx graph class from adjacency
ordered labels. nx_type = ['graph',['xgraph']] labels = None, (possibly weighted) matrix and ordered labels.
results in string-numbered labels
nx_type = ['graph',['xgraph']]
labels = None, results in string-numbered labels
""" """
try:
import networkx as nx import networkx as nx
except:
print "Failed in import of NetworkX"
return
m,n = A.shape# adjacency matrix must be of type that evals to true/false for neigbours m,n = A.shape# adjacency matrix must be of type that evals to true/false for neigbours
if m!=n: if m!=n:
raise IOError, "Adjacency matrix must be square" raise IOError, "Adjacency matrix must be square"
if nx_type=='graph':
if A[A[:,0].nonzero()[0],0]==1: #unweighted graph
G = nx.Graph() G = nx.Graph()
elif nx_type=='x_graph':
G = nx.XGraph()
else: else:
raise IOError, "Unknown graph type: %s" %nx_type G = nx.XGraph()
if labels==None: # if labels not provided mark vertices with numbers if labels==None: # if labels not provided mark vertices with numbers
labels = [str(i) for i in range(m)] labels = [str(i) for i in range(m)]
for nbrs,head in izip(A,labels): for nbrs,head in izip(A,labels):
for i,nbr in enumerate(nbrs): for i,nbr in enumerate(nbrs):
if nbr: if nbr:
tail = labels[i] tail = labels[i]
if type(G)==nx.XGraph:
G.add_edge(head,tail,nbr)
else:
G.add_edge(head,tail) G.add_edge(head,tail)
return G return G
@ -310,7 +323,10 @@ class ReverseDict(dict):
def __setitem__(self, key, value): def __setitem__(self, key, value):
dict.__setitem__(self, key, value) dict.__setitem__(self, key, value)
try:
self.reverse[value] = key self.reverse[value] = key
except:
self.reverse = {value:key}
def to_file(filepath,dataset,name=None): def to_file(filepath,dataset,name=None):
"""Write dataset to file. A file may contain multiple datasets. """Write dataset to file. A file may contain multiple datasets.