def _(self, *edge: Union[str, Node], **kwargs: Any) -> None:
# get additional parameters
uid: Optional[str] = kwargs.pop('uid', None)
nodes: bool = kwargs.pop('nodes', True)
# check if all objects are node or str
if not all(isinstance(arg, (Node, str)) for arg in edge):
LOG.error('All objects have to be Node objects or str uids!')
raise TypeError
# if nodes is true add nodes
if nodes:
_nodes: tuple = ()
for node in edge:
if node not in self.nodes:
self.nodes.add(node)
_nodes += (self.nodes[node], )
# create new edge object and add it to the network
if _nodes not in self or self.multiedges:
self.add(self._edge_class(*_nodes, uid=uid, **kwargs))
# raise error if edge already exists
else:
self._if_exist(_nodes, **kwargs)
# add edge with unknown nodes
else:
self.add(self._edge_class(Node(), Node(), uid=edge[0], **kwargs))
def __init__(self,
*args: Union[Node, Edge],
uid: Optional[str] = None,
**kwargs: Any) -> None:
# initializing the parent classes
Node.__init__(self, uid, **kwargs)
Path.__init__(self, *args, uid=uid, **kwargs)
def _add_edge_from_str(self, edge: str, **kwargs: Any) -> None:
"""Helper function to add an edge from nodes."""
# check if edge with given uid str exists already
if edge not in self:
# if not add new node with provided uid str
self._add_edge(Edge(Node(), Node(), uid=edge, **kwargs))
else:
# raise error if node already exists
self._if_edge_exists(edge, **kwargs)
def __init__(self,
*args: Union[Node, Edge],
uid: Optional[str] = None,
**kwargs: Any) -> None:
# initializing the parent classes
Node.__init__(self, uid, **kwargs)
Path.__init__(self, *args, uid=uid, **kwargs)
self['label'] = '-'.join([n.uid for n in self.nodes])
def __init__(self,
*node: Union[str, PathPyObject],
uid: Optional[str] = None,
**kwargs: Any) -> None:
"""Initialize the node object."""
# initializing the parent classes
kwargs.pop('directed', None)
kwargs.pop('ordered', None)
Node.__init__(self, *node, uid=uid, **kwargs)
TemporalPathPyObject.__init__(self, uid=self.uid, **kwargs)
def to_network(frame: pd.DataFrame,
loops: bool = True,
directed: bool = True,
multiedges: bool = False,
**kwargs: Any) -> Network:
"""Read network from a pandas data frame."""
# if no v/w columns are included, pick first synonym
frame = _check_column_name(frame, 'v', config['edge']['v_synonyms'])
frame = _check_column_name(frame, 'w', config['edge']['w_synonyms'])
LOG.debug('Creating %s network', directed)
node_set = set(frame['v']).union(set(frame['w']))
if None in node_set:
LOG.error('DataFrame minimally needs columns \'v\' and \'w\'')
raise IOError
nodes = {n: Node(n) for n in node_set}
edges: list = []
edge_set: set = set()
# TODO: Make this for loop faster!
for row in frame.to_dict(orient='records'):
v = row.pop('v')
w = row.pop('w')
uid = row.pop('uid', None)
if (v, w) in edge_set and not multiedges:
LOG.warning(
'The edge (%s,%s) exist already '
'and will not be considered. '
'To capture this edge, please '
'enalbe multiedges and/or directed!', v, w)
elif loops or v != w:
edges.append(Edge(nodes[v], nodes[w], uid=uid, **row))
edge_set.add((v, w))
if not directed:
edge_set.add((w, v))
else:
continue
net = Network(directed=directed, multiedges=multiedges, **kwargs)
for node in nodes.values():
net.nodes.add(node)
for edge in edges:
net.edges._add(edge)
net._add_edge_properties()
return net
def lattice_network(start: int = 0, stop: int = 10, dims: int = 2):
"""
Generates a n-dimensional lattice network with coordinates in each dimension
ranging from start (inclusive) to stop (exclusive)
"""
network = Network(directed=False)
for pos in _multi_dim_range(start, stop, dims):
network.add_node(
Node("".join(str(i) + '-' for i in pos).strip('-'),
pos=np.array(pos)))
for v in network.nodes:
for w in network.nodes:
if np.sum(np.abs(v['pos'] - w['pos'])) == 1 and (
v.uid, w.uid) not in network.edges:
network.add_edge(v, w)
return network
def _add_path_from_edges(self, *edges: Union[str, Edge],
uid: Optional[str] = None, **kwargs: Any) -> None:
"""Helper function to add a path from edges."""
_edges: list = []
for edge in edges:
if edge not in self.edges or self.multiedges:
if isinstance(edge, str) and len(_edges) > 0:
self.edges.add(Edge(_edges[-1].w, Node(), uid=edge))
else:
self.edges.add(edge, nodes=False)
_edges.append(self.edges[edge])
_path = _edges
if _path not in self or self.multipaths:
self._add_path(self._path_class(*_path, uid=uid, **kwargs))
else:
# raise error if node already exists
self._if_exist(_path, **kwargs)
def read_graphml(filename: str):
"""Reads a pathyp.Network from a graphml file. This function supports typed Node and Edge attributes
including default values.
Warnings are issued if the type of Node or Edge attributes are undeclared, in which case the attribute type will fall back to string.
Parameters
----------
filename: str
The graphml file to read the graph from
"""
root = ET.parse(filename).getroot()
graph = root.find('{http://graphml.graphdrawing.org/xmlns}graph')
directed = graph.attrib['edgedefault'] != 'undirected'
uid = graph.attrib['id']
n = Network(directed=directed, uid=uid)
node_attributes = {}
edge_attributes = {}
# read attribute types and default values
for a in root.findall('{http://graphml.graphdrawing.org/xmlns}key'):
a_id = a.attrib['id']
a_name = a.attrib['attr.name']
a_type = a.attrib['attr.type']
a_for = a.attrib['for']
# store attribute info and assign data types
a_data = {'name': a_name}
if a_type == 'string':
a_data['type'] = str
elif a_type == 'float':
a_data['type'] = float
elif a_type == 'double':
a_data['type'] = float
elif a_type == 'int':
a_data['type'] = int
elif a_type == 'long':
a_data['type'] = int
elif a_type == 'boolean':
a_data['type'] = bool
else:
a_data['type'] = str
d = a.find('{http://graphml.graphdrawing.org/xmlns}default')
if d is not None:
a_data['default'] = a_data['type'](d.text)
if a_for == 'node':
node_attributes[a_name] = a_data
if a_for == 'edge':
edge_attributes[a_name] = a_data
# add nodes with uids and attributes
for node in graph.findall('{http://graphml.graphdrawing.org/xmlns}node'):
# create node
uid = node.attrib['id']
v = Node(uid=uid)
# set attribute values
for a in node.findall('{http://graphml.graphdrawing.org/xmlns}data'):
key = a.attrib['key']
val = a.text
if key not in node_attributes:
LOG.warning(
'Undeclared Node attribute "{}". Defaulting to string type.'
.format(key))
v.attributes[key] = val
else:
v.attributes[key] = node_attributes[key]['type'](val)
# set default values
for a_name in node_attributes:
if 'default' in node_attributes[
a_name] and v.attributes[a_name] is None:
v.attributes[a_name] = node_attributes[a_name]['default']
n.add_node(v)
# add edges with uids and attributes
for edge in graph.findall('{http://graphml.graphdrawing.org/xmlns}edge'):
# create edge
source = edge.attrib['source']
target = edge.attrib['target']
uid = edge.attrib['id']
e = Edge(n.nodes[source], n.nodes[target], uid=uid)
# set attribute values
for a in edge.findall('{http://graphml.graphdrawing.org/xmlns}data'):
key = a.attrib['key']
val = a.text
if key not in edge_attributes:
LOG.warning(
'Warning: Undeclared Edge attribute "{}". Defaulting to string type.'
.format(key))
e.attributes[key] = val
else:
e.attributes[key] = edge_attributes[key]['type'](val)
# set default values
for a_name in edge_attributes:
if 'default' in edge_attributes[
a_name] and e.attributes[a_name] is None:
e.attributes[a_name] = edge_attributes[a_name]['default']
n.add_edge(e)
return n
def Watts_Strogatz(n: int,
s: int,
p: float = 0.0,
loops: bool = False,
node_uids: Optional[list] = None) -> Network:
"""Undirected Watts-Strogatz lattice network
Generates an undirected Watts-Strogatz lattice network with lattice
dimensionality one.
Parameters
----------
n : int
The number of nodes in the generated network
s : float
The number of nearest neighbors that will be connected
in the ring lattice
p : float
The rewiring probability
Examples
--------
Generate a Watts-Strogatz network with 100 nodes
>>> import pathpy as pp
>>> small_world = pp.algorithms.random_graphs.Watts_Strogatz(n=100, s=2, p=0.1)
>>> print(small_world.summary())
...
"""
network = Network(directed=False)
if node_uids is None or len(node_uids) != n:
LOG.info('No valid node uids given, generating numeric node uids')
node_uids = []
for i in range(n):
network.add_node(Node(str(i)))
node_uids.append(str(i))
else:
for i in range(n):
network.add_node(node_uids[i])
# construct a ring lattice (dimension 1)
for i in range(n):
if loops:
x = 0
y = s
else:
x = 1
y = s + 1
for j in range(x, y):
v = network.nodes[node_uids[i]]
w = network.nodes[node_uids[(i + j) % n]]
if (v.uid, w.uid) not in network.edges:
network.add_edge(v, w)
if p == 0:
# nothing to do here
return network
# Rewire each link with probability p
for edge in tqdm(list(network.edges.values()), 'generating WS network'):
if np.random.rand() < p:
# Delete original link and remember source node
v = edge.v.uid
network.remove_edge(edge)
# Find new random tgt, which is not yet connected to src
new_target = None
# This loop repeatedly chooses a random target until we find
# a target not yet connected to src. Note that this could potentially
# result in an infinite loop depending on parameters.
while new_target is None:
x = str(np.random.randint(n))
if (x != v or loops) and (v, x) not in network.edges:
new_target = x
network.add_edge(v, new_target)
return network
def read_pathcollection(filename: str,
separator: str = ',',
frequency: bool = False,
directed: bool = True,
maxlines: int = None) -> PathCollection:
"""Read path in edgelist format
Reads data from a file containing multiple lines of *edges* of the form
"v,w,frequency,X" (where frequency is optional and X are arbitrary
additional columns). The default separating character ',' can be changed.
Parameters
----------
filename : str
path to edgelist file
separator : str
character separating the nodes
frequency : bool
is a frequency given? if ``True`` it is the last element in the
edge (i.e. ``a,b,2``)
directed : bool
are the edges directed or undirected
maxlines : int
number of lines to read (useful to test large files).
None means the entire file is read
"""
from pathpy.core.path import Path, PathCollection
nodes: dict = {}
edges: dict = {}
paths: dict = {}
with open(filename, 'r') as csv:
for n, line in enumerate(csv):
fields = line.rstrip().split(separator)
assert len(fields) >= 1, 'Error: empty line: {0}'.format(line)
if frequency:
path = tuple(fields[:-1])
freq = float(fields[-1])
else:
path = tuple(fields)
freq = 1.0
for node in path:
if node not in nodes:
nodes[node] = Node(node)
if len(path) == 1 and path not in paths:
paths[path] = Path(nodes[path[0]], frequency=freq)
else:
edge_list = []
for u, v in zip(path[:-1], path[1:]):
if (u, v) not in edges:
edges[(u, v)] = Edge(nodes[u], nodes[v])
edge_list.append(edges[(u, v)])
if path not in paths:
paths[path] = Path(*edge_list, frequency=freq)
if maxlines is not None and n >= maxlines:
break
ncoll = NodeCollection()
for node in nodes.values():
ncoll.add(node)
ecoll = EdgeCollection(nodes=ncoll)
for edge in edges.values():
ecoll._add(edge)
_paths = PathCollection(directed=directed, nodes=ncoll, edges=ecoll)
for _path in paths.values():
_paths._add(_path)
return _paths
def to_temporal_network(frame: pd.DataFrame,
loops: bool = True,
directed: bool = True,
multiedges: bool = False,
**kwargs: Any) -> TemporalNetwork:
"""Read temporal network from a pandas data frame."""
from pathpy.models.temporal_network import TemporalNetwork
# if no v/w columns are included, pick first synonym
frame = _check_column_name(frame, 'v', config['edge']['v_synonyms'])
frame = _check_column_name(frame, 'w', config['edge']['w_synonyms'])
_begin = config['temporal']['begin']
_end = config['temporal']['end']
_timestamp = config['temporal']['timestamp']
_duration = config['temporal']['duration']
_key_words = {
'begin': _begin,
'end': _end,
'timestamp': _timestamp,
'duration': _duration
}
for key, name in _key_words.items():
frame = _check_column_name(frame, name,
config['temporal'][key + '_synonyms'])
if _timestamp in frame.columns:
frame[_begin] = frame[_timestamp]
if _duration in frame.columns:
frame[_end] = frame[_timestamp] + frame[_duration]
else:
frame[_end] = frame[_timestamp] + \
config['temporal']['duration_value']
if _begin and _end not in frame.columns:
LOG.error(
'A TemporalNetwork needs "%s" and "%s" (or "%s" and "%s") '
'attributes!', _begin, _end, _timestamp, _duration)
raise IOError
LOG.debug('Creating %s network', directed)
node_set = set(frame['v']).union(set(frame['w']))
if None in node_set:
LOG.error('DataFrame minimally needs columns \'v\' and \'w\'')
raise IOError
nodes = {n: Node(n) for n in node_set}
net = TemporalNetwork(directed=directed, multiedges=multiedges, **kwargs)
for node in nodes.values():
net.nodes.add(node)
# TODO: Make this for loop faster!
#rows = []
#edges = {}
for row in frame.to_dict(orient='records'):
v = row.pop('v')
w = row.pop('w')
uid = row.pop('uid', None)
# if (v, w) not in edges:
# edge = Edge(nodes[v], nodes[w], uid=uid, **row)
# net.edges._add(edge)
# edges[(v, w)] = edge
# else:
# begin = row.pop(_begin)
# end = row.pop(_end)
# net.edges._intervals.addi(begin, end, edges[(v, w)])
# net.edges._interval_map[edges[(v, w)]].add((begin, end))
net.add_edge(nodes[v], nodes[w], uid=uid, **row)
# net.add_edge(nodes[v], nodes[w], uid=uid, **row)
# net._add_edge_properties()
return net
def read_file(cls,
filename: str,
separator: str = ',',
frequency: bool = False,
directed: bool = True,
maxlines: int = None) -> None:
"""
Read path in edgelist format
Reads data from a file containing multiple lines of *edges* of the
form "v,w,frequency,X" (where frequency is optional and X are
arbitrary additional columns). The default separating character ','
can be changed.
Parameters
----------
filename : str
path to edgelist file
separator : str
character separating the nodes
frequency : bool
is a frequency given? if ``True`` it is the last element in the
edge (i.e. ``a,b,2``)
directed : bool
are the edges directed or undirected
maxlines : int
number of lines to read (useful to test large files).
None means the entire file is read
"""
nodes = {}
edges = {}
paths = {}
with open(filename, 'r') as f:
for n, line in enumerate(f):
fields = line.rstrip().split(separator)
assert len(fields) >= 2, 'Error: malformed line: {0}'.format(
line)
if frequency:
path = tuple(fields[:-1])
f = int(fields[-1])
else:
path = tuple(fields)
f = 1
for node in path:
if node not in nodes:
nodes[node] = Node(node)
edge_list = []
for u, v in zip(path[:-1], path[1:]):
if (u, v) not in edges:
edges[(u, v)] = Edge(nodes[u],
nodes[v],
uid=u + '-' + v)
edge_list.append(edges[(u, v)])
if path not in paths:
paths[path] = Path(*edge_list, frequency=f)
if maxlines is not None and n >= maxlines:
break
nc = NodeCollection()
nc.add(*nodes.values())
ec = EdgeCollection(nodes=nc)
for edge in edges.values():
ec._add(edge)
p = PathCollection(nodes=nc, edges=ec)
for path in paths.values():
p._add(path)
return p
