def fast_min(state, beta, n_sweep, fast_tol, seed=None):
if seed:
gt.seed_rng(seed)
dS = 1
while np.abs(dS) > fast_tol:
dS, _, _ = state.multiflip_mcmc_sweep(beta=beta, niter=n_sweep)
return state
def __init__(self, n, seed_number=None, directed=False):
self.n = n
self.seed_number = seed_number
self.directed = directed
if seed_number:
gt.seed_rng(self.seed_number)
seed(self.seed_number)
def _generate_graph(self): np.random.seed(self.seed) gt.seed_rng(self.seed) if 'block_membership' in self.params and self.params['block_membership'] != None: self.graph, self.bm = self.generator(**self.params) else: self.graph = self.generator(**self.params) self.n_nodes = self.graph.num_vertices()
def draw_gviz(node_dict, size_multiple=50, random_seed=42, **kwargs):
""" Draw clonal network using graph-tool
More information: graphtool edge / vertex parameters and examples:
https://graph-tool.skewed.de/static/doc/draw.html#graph_tool.draw.graph_draw
http://ryancompton.net/2014/10/05/graph-tools-visualization-is-pretty-good/
Args:
node_dict (dict): nested dictionary of node properties
Generate this using df_generate_node_dict()
size_multiple (int): scaling factor for node size (for convenience)
**kwargs: keyword arguments passed to gt.graph-draw()
e.g. output='file.pdf', layout='neato', output_size=(300,300)
"""
import graph_tool.all as gt
g = gt.Graph()
vsizes = g.new_vertex_property("int")
vcolors = g.new_vertex_property('string')
vshapes = g.new_vertex_property('string')
vpenwidth = g.new_vertex_property("float") # stroke
for node_id, node_props in node_dict.items():
g.add_vertex()
vshapes[g.vertex(node_id)] = node_props['shape']
vcolors[g.vertex(node_id)] = node_props['color']
vsizes[g.vertex(node_id)] = node_props['size'] * size_multiple
vpenwidth[g.vertex(node_id)] = node_props['stroke']
# add edge to ancestor
if node_props['ancestor'] is not None:
g.add_edge(node_props['ancestor'], node_id)
# seeds enable graph reproduction
seed(random_seed)
gt.seed_rng(random_seed)
gt.graph_draw(
g,
vertex_size=vsizes,
vertex_fill_color=vcolors,
vertex_shape=vshapes,
vertex_pen_width=vpenwidth,
vertex_color='k', # stroke color
bg_color=[1, 1, 1, 1], # white
edge_end_marker='none',
**kwargs)
def fit(self):
"""
Fits the hSBM to the undirected, layered multigraph, where the graph in the doc-word layer is bipartite.
This uses the independent layer multilayer network where we have a degree-corrected SBM.
"""
# We need to impose constraints on vertices and edges to keep track which layer are they in.
state_args = {}
# Vertices with different label values will not be clustered in the same group
state_args["pclabel"] = self.g.vp["kind"]
# Split the network in discrete layers based on edgetype. 0 is for word-doc graph and 1 is for hyperlink graph.
state_args["ec"] = self.g.ep["edgeType"]
# Independent layers version of the model (instead of 'edge covariates')
state_args["layers"] = True
# Edge multiplicities based on occurrences.
state_args["eweight"] = self.g.ep.edgeCount
self.g.save("foo.gt.gz")
# Specify parameters for community detection inference
gt.seed_rng(self.random_seed)
mdl = np.inf
# Fit n_init random initializations to avoid local optimum of MDL.
for _ in range(self.n_init):
# Enables the use of LayeredBlockState. Use a degree-corrected layered SBM.
state_temp = gt.minimize_nested_blockmodel_dl(self.g, state_args=dict(base_type=gt.LayeredBlockState,
**state_args))
mdl_temp = state_temp.entropy()
if mdl_temp < mdl:
# We have found a new optimum
mdl = mdl_temp
state = state_temp.copy()
self.state = state
self.mdl = state.entropy()
n_levels = len(self.state.levels)
# Figure out group levels
if n_levels == 2:
# Bipartite network
self.groups = { 0: self.get_groupStats(l=0) }
self.n_levels = len(self.groups)
# Omit trivial levels: l=L-1 (single group), l=L-2 (bipartite)
else:
self.groups = { level: self.get_groupStats(l=level) for level in range(n_levels - 2) }
self.n_levels = len(self.groups)
def set_seed(seed: int) -> None:
"""Set random seed for reproducibility.
Take care of python random library and numpy.
Args:
seed (int): the value choosen as seed for the random generators
"""
global SEED
SEED = seed
random.seed(SEED)
np.random.seed(SEED)
da.random.seed(SEED)
try:
import graph_tool.all as gt
gt.seed_rng(SEED)
except ImportError:
pass
def test1():
gt.seed_rng(42)
seed(42)
NUMBER_OF_NODES = 20
points = random((NUMBER_OF_NODES, 2))
points[0] = [0, 0]
points[1] = [1, 1]
g, pos = gt.triangulation(points, type="delaunay")
g.set_directed(True)
edges = list(g.edges())
# reciprocate edges
for e in edges:
g.add_edge(e.target(), e.source())
# The capacity will be defined as the inverse euclidean distance
cap = g.new_edge_property("double")
for e in g.edges():
cap[e] = min(1.0 / norm(pos[e.target()].a - pos[e.source()].a), 10)
g.edge_properties["cap"] = cap
g.vertex_properties["pos"] = pos
g.save("flow-example.xml.gz")
gt.graph_draw(g, pos=pos, edge_pen_width=gt.prop_to_size(cap, mi=0, ma=3, power=1),
output="flow-example.pdf")
def generate_graph():
"""
brew tap homebrew/science
brew install graph-tool
"""
from graph_tool.all import price_network, sfdp_layout, graph_draw
from graph_tool.all import dfs_search, DFSVisitor, seed_rng
from numpy.random import seed
class AnnotationVisitor(DFSVisitor):
def __init__(self, pred, dist):
self.pred = pred
self.dist = dist
self.roots = {}
def tree_edge(self, e):
depth = self.dist[e.source()]
if depth == 1:
genre = int(e.source())
if genre not in self.roots:
self.roots[genre] = len(self.roots)
else:
genre = self.pred[e.source()]
self.pred[e.target()] = genre
self.dist[e.target()] = depth + 1
# For run-to-run stability, provide a constant seed:
seed(SEED)
seed_rng(SEED)
print 'Generating graph...'
g = price_network(2000)
print 'Performing layout...'
pos = sfdp_layout(g)
print 'Adding depths...'
dist = g.new_vertex_property("int")
pred = g.new_vertex_property("int64_t")
g.set_directed(False)
visitor = AnnotationVisitor(pred, dist)
dfs_search(g, g.vertex(0), visitor)
print 'Iterating over verts...'
flattened = []
maxp = [-9999, -9999]
minp = [+9999, +9999]
maxd = 0
for v in g.vertices():
root_id = pred.a[v]
if root_id not in visitor.roots:
continue
x, y, z = pos[v].a[0], pos[v].a[1], visitor.roots[root_id]
minp[0] = min(minp[0], x)
minp[1] = min(minp[1], y)
maxp[0] = max(maxp[0], x)
maxp[1] = max(maxp[1], y)
maxd = max(maxd, dist.a[v])
flattened += [x, y, z]
print 'max depth is', maxd
print 'nroots is', len(visitor.roots)
print 'ncolors is', len(COLORS)
extent = (maxp[0] - minp[0], maxp[1] - minp[1])
padding = extent[0] * PADDING_FRACTION
minp[0] -= padding
minp[1] -= padding
maxp[0] += padding
maxp[1] += padding
scale = [
1.0 / (maxp[0] - minp[0]),
1.0 / (maxp[1] - minp[1])]
scale = min(scale[0], scale[1])
midp = [
0.5 * (maxp[0] + minp[0]),
0.5 * (maxp[1] + minp[1])]
flatarray = []
for v in g.vertices():
root_id = pred.a[v]
if root_id not in visitor.roots:
continue
x, y, root = pos[v].a[0], pos[v].a[1], visitor.roots[root_id]
x = (0.5 + (x - midp[0]) * scale)
y = (0.5 + (y - midp[1]) * scale)
prom = int(dist.a[v])
flatarray += [x, y, root, prom]
return flatarray
# * node (gene) degree in the eADAGE graph # * edge weight in the eADAGE graph # * [betweenness centrality](https://en.wikipedia.org/wiki/Betweenness_centrality) of generic vs. non-generic genes # * [PageRank](https://en.wikipedia.org/wiki/PageRank) (sometimes called PageRank centrality) of generic vs. non-generic genes, specifically the [undirected version](https://en.wikipedia.org/wiki/PageRank#PageRank_of_an_undirected_graph). # In[1]: import os import numpy as np import pandas as pd import graph_tool.all as gt import matplotlib.pyplot as plt import seaborn as sns gt.seed_rng(1) np.random.seed(1) # In[2]: # relevant file paths data_dir = './data' processed_graph = os.path.join(data_dir, 'eadage_generic_graph_unsigned.gt') # In[3]: G = gt.load_graph(processed_graph) # make sure vertex/edge properties exist print(G) print(list(G.vp.keys())) print(list(G.ep.keys()))
def generate_graph():
"""
brew tap homebrew/science
brew install graph-tool
"""
from graph_tool.all import price_network, sfdp_layout, graph_draw
from graph_tool.all import dfs_search, DFSVisitor, seed_rng
from numpy.random import seed
class AnnotationVisitor(DFSVisitor):
def __init__(self, pred, dist):
self.pred = pred
self.dist = dist
self.roots = {}
def tree_edge(self, e):
depth = self.dist[e.source()]
if depth == 1:
genre = int(e.source())
if genre not in self.roots:
self.roots[genre] = len(self.roots)
else:
genre = self.pred[e.source()]
self.pred[e.target()] = genre
self.dist[e.target()] = depth + 1
# For run-to-run stability, provide a constant seed:
seed(SEED)
seed_rng(SEED)
print 'Generating graph...'
g = price_network(2000)
print 'Performing layout...'
pos = sfdp_layout(g)
print 'Adding depths...'
dist = g.new_vertex_property("int")
pred = g.new_vertex_property("int64_t")
g.set_directed(False)
visitor = AnnotationVisitor(pred, dist)
dfs_search(g, g.vertex(0), visitor)
print 'Iterating over verts...'
flattened = []
maxp = [-9999, -9999]
minp = [+9999, +9999]
maxd = 0
for v in g.vertices():
root_id = pred.a[v]
if root_id not in visitor.roots:
continue
x, y, z = pos[v].a[0], pos[v].a[1], visitor.roots[root_id]
minp[0] = min(minp[0], x)
minp[1] = min(minp[1], y)
maxp[0] = max(maxp[0], x)
maxp[1] = max(maxp[1], y)
maxd = max(maxd, dist.a[v])
flattened += [x, y, z]
print 'max depth is', maxd
print 'nroots is', len(visitor.roots)
print 'ncolors is', len(COLORS)
extent = (maxp[0] - minp[0], maxp[1] - minp[1])
padding = extent[0] * PADDING_FRACTION
minp[0] -= padding
minp[1] -= padding
maxp[0] += padding
maxp[1] += padding
scale = [1.0 / (maxp[0] - minp[0]), 1.0 / (maxp[1] - minp[1])]
scale = min(scale[0], scale[1])
midp = [0.5 * (maxp[0] + minp[0]), 0.5 * (maxp[1] + minp[1])]
flatarray = []
for v in g.vertices():
root_id = pred.a[v]
if root_id not in visitor.roots:
continue
x, y, root = pos[v].a[0], pos[v].a[1], visitor.roots[root_id]
x = (0.5 + (x - midp[0]) * scale)
y = (0.5 + (y - midp[1]) * scale)
prom = int(dist.a[v])
flatarray += [x, y, root, prom]
return flatarray
rcParams["ps.usedistiller"] = "xpdf"
rcParams["pdf.compression"] = 9
rcParams["ps.useafm"] = True
rcParams["path.simplify"] = True
rcParams["text.latex.preamble"] = [ #r"\usepackage{times}",
#r"\usepackage{euler}",
r"\usepackage{amssymb}",
r"\usepackage{amsmath}"
]
import scipy
import scipy.stats
import numpy as np
from pylab import *
from numpy import *
import graph_tool.all as gt
import graph_tool.draw
import random as prandom
figure()
try:
gt.openmp_set_num_threads(1)
except RuntimeError:
pass
prandom.seed(42)
np.random.seed(42)
gt.seed_rng(42)
def planted_model(
adata: AnnData,
n_sweep: int = 10,
beta: float = np.inf,
tolerance=1e-6,
max_iterations: int = 1000000,
epsilon: float = 0,
equilibrate: bool = False,
wait: int = 1000,
nbreaks: int = 2,
collect_marginals: bool = False,
niter_collect: int = 10000,
deg_corr: bool = True,
n_init: int = 1,
beta_range: Tuple[float] = (1., 100.),
steps_anneal: int = 5,
resume: bool = False,
*,
restrict_to: Optional[Tuple[str, Sequence[str]]] = None,
random_seed: Optional[int] = None,
key_added: str = 'ppbm',
adjacency: Optional[sparse.spmatrix] = None,
neighbors_key: Optional[str] = 'neighbors',
directed: bool = False,
use_weights: bool = False,
copy: bool = False,
minimize_args: Optional[Dict] = {},
equilibrate_args: Optional[Dict] = {},
) -> Optional[AnnData]:
"""\
Cluster cells into subgroups [Peixoto14]_.
Cluster cells using the Stochastic Block Model [Peixoto14]_, performing
Bayesian inference on node groups. This function, in particular, uses
the Planted Block Model, which is particularly suitable in case of
assortative graphs and it returns the optimal number of communities
This requires having ran :func:`~scanpy.pp.neighbors` or
:func:`~scanpy.external.pp.bbknn` first.
Parameters
----------
adata
The annotated data matrix.
n_sweep
Number of MCMC sweeps to get the initial guess
beta
Inverse temperature for the initial MCMC sweep
tolerance
Difference in description length to stop MCMC sweep iterations
max_iterations
Maximal number of iterations to be performed by the equilibrate step.
epsilon
Relative changes in entropy smaller than epsilon will
not be considered as record-breaking.
equilibrate
Whether or not perform the mcmc_equilibrate step.
Equilibration should always be performed. Note, also, that without
equilibration it won't be possible to collect marginals.
collect_marginals
Whether or not collect node probability of belonging
to a specific partition.
niter_collect
Number of iterations to force when collecting marginals. This will
increase the precision when calculating probabilites
wait
Number of iterations to wait for a record-breaking event.
Higher values result in longer computations. Set it to small values
when performing quick tests.
nbreaks
Number of iteration intervals (of size `wait`) without
record-breaking events necessary to stop the algorithm.
deg_corr
Whether to use degree correction in the minimization step. In many
real world networks this is the case, although this doesn't seem
the case for KNN graphs used in scanpy.
n_init
Number of initial minimizations to be performed. The one with smaller
entropy is chosen
beta_range
Inverse temperature at the beginning and the end of the equilibration
steps_anneal
Number of steps in which the simulated annealing is performed
resume
Start from a previously created model, if any, without initializing a novel
model
key_added
`adata.obs` key under which to add the cluster labels.
adjacency
Sparse adjacency matrix of the graph, defaults to
`adata.uns['neighbors']['connectivities']` in case of scanpy<=1.4.6 or
`adata.obsp[neighbors_key][connectivity_key]` for scanpy>1.4.6
neighbors_key
The key passed to `sc.pp.neighbors`
directed
Whether to treat the graph as directed or undirected.
use_weights
If `True`, edge weights from the graph are used in the computation
(placing more emphasis on stronger edges). Note that this
increases computation times
copy
Whether to copy `adata` or modify it inplace.
random_seed
Random number to be used as seed for graph-tool
Returns
-------
`adata.obs[key_added]`
Array of dim (number of samples) that stores the subgroup id
(`'0'`, `'1'`, ...) for each cell.
`adata.uns['sbm']['params']`
A dict with the values for the parameters `resolution`, `random_state`,
and `n_iterations`.
`adata.uns['sbm']['stats']`
A dict with the values returned by mcmc_sweep
`adata.uns['sbm']['cell_affinity']`
A `np.ndarray` with cell probability of belonging to a specific group
`adata.uns['sbm']['state']`
The BlockModel state object
"""
# first things first
check_gt_version()
if resume:
equilibrate = True
if resume and (key_added not in adata.uns
or 'state' not in adata.uns[key_added]):
# let the model proceed as default
logg.warning('Resuming has been specified but a state was not found\n'
'Will continue with default minimization step')
resume = False
if random_seed:
np.random.seed(random_seed)
gt.seed_rng(random_seed)
if collect_marginals:
logg.warning('Collecting marginals has a large impact on running time')
if not equilibrate:
raise ValueError(
"You can't collect marginals without MCMC equilibrate "
"step. Either set `equlibrate` to `True` or "
"`collect_marginals` to `False`")
start = logg.info('minimizing the Planted Partition Block Model')
adata = adata.copy() if copy else adata
# are we clustering a user-provided graph or the default AnnData one?
if adjacency is None:
if neighbors_key not in adata.uns:
raise ValueError('You need to run `pp.neighbors` first '
'to compute a neighborhood graph.')
elif 'connectivities_key' in adata.uns[neighbors_key]:
# scanpy>1.4.6 has matrix in another slot
conn_key = adata.uns[neighbors_key]['connectivities_key']
adjacency = adata.obsp[conn_key]
else:
# scanpy<=1.4.6 has sparse matrix here
adjacency = adata.uns[neighbors_key]['connectivities']
if restrict_to is not None:
restrict_key, restrict_categories = restrict_to
adjacency, restrict_indices = restrict_adjacency(
adata,
restrict_key,
restrict_categories,
adjacency,
)
# convert it to igraph
g = get_graph_tool_from_adjacency(adjacency, directed=directed)
recs = []
rec_types = []
if use_weights:
# this is not ideal to me, possibly we may need to transform
# weights. More tests needed.
recs = [g.ep.weight]
rec_types = ['real-normal']
if resume:
# create the state and make sure sampling is performed
state = adata.uns[key_added]['state'].copy()
g = state.g
else:
if n_init < 1:
n_init = 1
# initialize the block states
states = [gt.PPBlockState(g) for x in range(n_init)]
# perform a mcmc sweep on each
# no list comprehension as I need to collect stats
_dS = np.zeros(n_init)
_nattempts = np.zeros(n_init)
_nmoves = np.zeros(n_init)
for x in range(n_init):
t_ds = 1
while np.abs(t_ds) > tolerance:
# perform sweep until a tolerance is reached
t_ds, t_natt, t_nm = states[x].multiflip_mcmc_sweep(
beta=beta, niter=n_sweep)
_dS[x] += t_ds
_nattempts[x] += t_natt
_nmoves[x] += t_nm
_amin = np.argmin([s.entropy() for s in states])
state = states[_amin]
dS = _dS[_amin]
nattempts = _nattempts[_amin]
nmoves = _nmoves[_amin]
logg.info(' done', time=start)
# equilibrate the Markov chain
if equilibrate:
logg.info('running MCMC equilibration step')
equilibrate_args['wait'] = wait
equilibrate_args['nbreaks'] = nbreaks
equilibrate_args['max_niter'] = max_iterations
equilibrate_args['mcmc_args'] = {'niter': 10}
dS, nattempts, nmoves = gt.mcmc_anneal(
state,
mcmc_equilibrate_args=equilibrate_args,
niter=steps_anneal,
beta_range=beta_range)
if collect_marginals and equilibrate:
# we here only retain level_0 counts, until I can't figure out
# how to propagate correctly counts to higher levels
# I wonder if this should be placed after group definition or not
logg.info(' collecting marginals')
group_marginals = np.zeros(g.num_vertices() + 1)
def _collect_marginals(s):
group_marginals[s.get_B()] += 1
gt.mcmc_equilibrate(state,
wait=wait,
nbreaks=nbreaks,
epsilon=epsilon,
max_niter=max_iterations,
multiflip=True,
force_niter=niter_collect,
mcmc_args=dict(niter=10),
callback=_collect_marginals)
logg.info(' done', time=start)
# everything is in place, we need to fill all slots
# first build an array with
groups = pd.Series(state.get_blocks().get_array()).astype('category')
new_cat_names = dict([(cx, u'%s' % cn)
for cn, cx in enumerate(groups.cat.categories)])
groups.cat.rename_categories(new_cat_names, inplace=True)
if restrict_to is not None:
groups.index = adata.obs[restrict_key].index
else:
groups.index = adata.obs_names
# add column names
adata.obs.loc[:, key_added] = groups
# add some unstructured info
adata.uns[key_added] = {}
adata.uns[key_added]['stats'] = dict(dS=dS,
nattempts=nattempts,
nmoves=nmoves,
modularity=gt.modularity(
g, state.get_blocks()))
adata.uns[key_added]['state'] = state
# now add marginal probabilities.
if collect_marginals:
# cell marginals will be a list of arrays with probabilities
# of belonging to a specific group
adata.uns[key_added]['group_marginals'] = group_marginals
# calculate log-likelihood of cell moves over the remaining levels
# adata.uns[key_added]['cell_affinity'] = {'1':get_cell_loglikelihood(state, as_prob=True, rescale=True)}
# last step is recording some parameters used in this analysis
adata.uns[key_added]['params'] = dict(epsilon=epsilon,
wait=wait,
nbreaks=nbreaks,
equilibrate=equilibrate,
collect_marginals=collect_marginals,
random_seed=random_seed)
logg.info(
' finished',
time=start,
deep=(
f'found {state.get_B()} clusters and added\n'
f' {key_added!r}, the cluster labels (adata.obs, categorical)'),
)
return adata if copy else None
def nested_model(
adata: AnnData,
max_iterations: int = 1000000,
epsilon: float = 0,
equilibrate: bool = False,
wait: int = 1000,
nbreaks: int = 2,
collect_marginals: bool = False,
niter_collect: int = 10000,
hierarchy_length: int = 10,
deg_corr: bool = True,
multiflip: bool = True,
fast_model: bool = False,
fast_tol: float = 1e-6,
n_sweep: int = 10,
beta: float = np.inf,
n_init: int = 1,
beta_range: Tuple[float] = (1., 1000.),
steps_anneal: int = 3,
resume: bool = False,
*,
restrict_to: Optional[Tuple[str, Sequence[str]]] = None,
random_seed: Optional[int] = None,
key_added: str = 'nsbm',
adjacency: Optional[sparse.spmatrix] = None,
neighbors_key: Optional[str] = 'neighbors',
directed: bool = False,
use_weights: bool = False,
prune: bool = False,
return_low: bool = False,
copy: bool = False,
minimize_args: Optional[Dict] = {},
equilibrate_args: Optional[Dict] = {},
) -> Optional[AnnData]:
"""\
Cluster cells into subgroups [Peixoto14]_.
Cluster cells using the nested Stochastic Block Model [Peixoto14]_,
a hierarchical version of Stochastic Block Model [Holland83]_, performing
Bayesian inference on node groups. NSBM should circumvent classical
limitations of SBM in detecting small groups in large graphs
replacing the noninformative priors used by a hierarchy of priors
and hyperpriors.
This requires having ran :func:`~scanpy.pp.neighbors` or
:func:`~scanpy.external.pp.bbknn` first.
Parameters
----------
adata
The annotated data matrix.
max_iterations
Maximal number of iterations to be performed by the equilibrate step.
epsilon
Relative changes in entropy smaller than epsilon will
not be considered as record-breaking.
equilibrate
Whether or not perform the mcmc_equilibrate step.
Equilibration should always be performed. Note, also, that without
equilibration it won't be possible to collect marginals.
collect_marginals
Whether or not collect node probability of belonging
to a specific partition.
niter_collect
Number of iterations to force when collecting marginals. This will
increase the precision when calculating probabilites
wait
Number of iterations to wait for a record-breaking event.
Higher values result in longer computations. Set it to small values
when performing quick tests.
nbreaks
Number of iteration intervals (of size `wait`) without
record-breaking events necessary to stop the algorithm.
hierarchy_length
Initial length of the hierarchy. When large values are
passed, the top-most levels will be uninformative as they
will likely contain the very same groups. Increase this valus
if a very large number of cells is analyzed (>100.000).
deg_corr
Whether to use degree correction in the minimization step. In many
real world networks this is the case, although this doesn't seem
the case for KNN graphs used in scanpy.
multiflip
Whether to perform MCMC sweep with multiple simultaneous moves to sample
network partitions. It may result in slightly longer runtimes, but under
the hood it allows for a more efficient space exploration.
fast_model
Whether to skip initial minization step and let the MCMC find a solution.
This approach tend to be faster and consume less memory, but may be
less accurate.
fast_tol
Tolerance for fast model convergence.
n_sweep
Number of iterations to be performed in the fast model MCMC greedy approach
beta
Inverse temperature for MCMC greedy approach
n_init
Number of initial minimizations to be performed. The one with smaller
entropy is chosen
beta_range
Inverse temperature at the beginning and the end of the equilibration
steps_anneal
Number of steps in which the simulated annealing is performed
resume
Start from a previously created model, if any, without initializing a novel
model
key_added
`adata.obs` key under which to add the cluster labels.
adjacency
Sparse adjacency matrix of the graph, defaults to
`adata.uns['neighbors']['connectivities']` in case of scanpy<=1.4.6 or
`adata.obsp[neighbors_key][connectivity_key]` for scanpy>1.4.6
neighbors_key
The key passed to `sc.pp.neighbors`
directed
Whether to treat the graph as directed or undirected.
use_weights
If `True`, edge weights from the graph are used in the computation
(placing more emphasis on stronger edges). Note that this
increases computation times
prune
Some high levels in hierarchy may contain the same information in terms of
cell assignments, even if they apparently have different group names. When this
option is set to `True`, the function only returns informative levels.
Note, however, that cell affinities are still reported for all levels. Pruning
does not rename group levels
return_low
Whether or not return nsbm_level_0 in adata.obs. This level usually contains
so many groups that it cannot be plot anyway, but it may be useful for particular
analysis. By default it is not returned
copy
Whether to copy `adata` or modify it inplace.
random_seed
Random number to be used as seed for graph-tool
Returns
-------
`adata.obs[key_added]`
Array of dim (number of samples) that stores the subgroup id
(`'0'`, `'1'`, ...) for each cell.
`adata.uns['nsbm']['params']`
A dict with the values for the parameters `resolution`, `random_state`,
and `n_iterations`.
`adata.uns['nsbm']['stats']`
A dict with the values returned by mcmc_sweep
`adata.uns['nsbm']['cell_affinity']`
A `np.ndarray` with cell probability of belonging to a specific group
`adata.uns['nsbm']['state']`
The NestedBlockModel state object
"""
if resume:
# if the fast_model is chosen perform equilibration anyway
# also if a model has previously created
equilibrate = True
if resume and ('nsbm' not in adata.uns
or 'state' not in adata.uns['nsbm']):
# let the model proceed as default
logg.warning('Resuming has been specified but a state was not found\n'
'Will continue with default minimization step')
resume = False
if random_seed:
np.random.seed(random_seed)
gt.seed_rng(random_seed)
if collect_marginals:
logg.warning('Collecting marginals has a large impact on running time')
if not equilibrate:
raise ValueError(
"You can't collect marginals without MCMC equilibrate "
"step. Either set `equlibrate` to `True` or "
"`collect_marginals` to `False`")
start = logg.info('minimizing the nested Stochastic Block Model')
adata = adata.copy() if copy else adata
# are we clustering a user-provided graph or the default AnnData one?
if adjacency is None:
if neighbors_key not in adata.uns:
raise ValueError('You need to run `pp.neighbors` first '
'to compute a neighborhood graph.')
elif 'connectivities_key' in adata.uns[neighbors_key]:
# scanpy>1.4.6 has matrix in another slot
conn_key = adata.uns[neighbors_key]['connectivities_key']
adjacency = adata.obsp[conn_key]
else:
# scanpy<=1.4.6 has sparse matrix here
adjacency = adata.uns[neighbors_key]['connectivities']
if restrict_to is not None:
restrict_key, restrict_categories = restrict_to
adjacency, restrict_indices = restrict_adjacency(
adata,
restrict_key,
restrict_categories,
adjacency,
)
# convert it to igraph
g = get_graph_tool_from_adjacency(adjacency, directed=directed)
recs = []
rec_types = []
if use_weights:
# this is not ideal to me, possibly we may need to transform
# weights. More tests needed.
recs = [g.ep.weight]
rec_types = ['real-normal']
if n_init < 1:
n_init = 1
if fast_model:
# do not minimize, start with a dummy state and perform only equilibrate
states = [
gt.NestedBlockState(g=g,
state_args=dict(deg_corr=deg_corr,
recs=recs,
rec_types=rec_types))
for n in range(n_init)
]
for x in range(n_init):
dS = 1
while np.abs(dS) > fast_tol:
# perform sweep until a tolerance is reached
dS, _, _ = states[x].multiflip_mcmc_sweep(beta=beta,
niter=n_sweep)
_amin = np.argmin([s.entropy() for s in states])
state = states[_amin]
# dS = 1
# while np.abs(dS) > fast_tol:
# dS, nattempts, nmoves = state.multiflip_mcmc_sweep(niter=10, beta=np.inf)
bs = state.get_bs()
logg.info(' done', time=start)
elif resume:
# create the state and make sure sampling is performed
state = adata.uns['nsbm']['state'].copy(sampling=True)
bs = state.get_bs()
# get the graph from state
g = state.g
else:
states = [
gt.minimize_nested_blockmodel_dl(
g,
deg_corr=deg_corr,
state_args=dict(recs=recs, rec_types=rec_types),
**minimize_args) for n in range(n_init)
]
state = states[np.argmin([s.entropy() for s in states])]
# state = gt.minimize_nested_blockmodel_dl(g, deg_corr=deg_corr,
# state_args=dict(recs=recs,
# rec_types=rec_types),
# **minimize_args)
logg.info(' done', time=start)
bs = state.get_bs()
if len(bs) <= hierarchy_length:
# increase hierarchy length up to the specified value
# according to Tiago Peixoto 10 is reasonably large as number of
# groups decays exponentially
bs += [np.zeros(1)] * (hierarchy_length - len(bs))
else:
logg.warning(
f'A hierarchy length of {hierarchy_length} has been specified\n'
f'but the minimized model contains {len(bs)} levels')
pass
# create a new state with inferred blocks
state = gt.NestedBlockState(g,
bs,
state_args=dict(recs=recs,
rec_types=rec_types),
sampling=True)
# equilibrate the Markov chain
if equilibrate:
logg.info('running MCMC equilibration step')
# equlibration done by simulated annealing
equilibrate_args['wait'] = wait
equilibrate_args['nbreaks'] = nbreaks
equilibrate_args['max_niter'] = max_iterations
equilibrate_args['multiflip'] = multiflip
equilibrate_args['mcmc_args'] = {'niter': 10}
dS, nattempts, nmoves = gt.mcmc_anneal(
state,
mcmc_equilibrate_args=equilibrate_args,
niter=steps_anneal,
beta_range=beta_range)
if collect_marginals and equilibrate:
# we here only retain level_0 counts, until I can't figure out
# how to propagate correctly counts to higher levels
# I wonder if this should be placed after group definition or not
logg.info(' collecting marginals')
group_marginals = [
np.zeros(g.num_vertices() + 1) for s in state.get_levels()
]
def _collect_marginals(s):
levels = s.get_levels()
for l, sl in enumerate(levels):
group_marginals[l][sl.get_nonempty_B()] += 1
gt.mcmc_equilibrate(state,
wait=wait,
nbreaks=nbreaks,
epsilon=epsilon,
max_niter=max_iterations,
multiflip=True,
force_niter=niter_collect,
mcmc_args=dict(niter=10),
callback=_collect_marginals)
logg.info(' done', time=start)
# everything is in place, we need to fill all slots
# first build an array with
groups = np.zeros((g.num_vertices(), len(bs)), dtype=int)
for x in range(len(bs)):
# for each level, project labels to the vertex level
# so that every cell has a name. Note that at this level
# the labels are not necessarily consecutive
groups[:, x] = state.project_partition(x, 0).get_array()
groups = pd.DataFrame(groups).astype('category')
# rename categories from 0 to n
for c in groups.columns:
new_cat_names = dict([
(cx, u'%s' % cn)
for cn, cx in enumerate(groups.loc[:, c].cat.categories)
])
groups.loc[:, c].cat.rename_categories(new_cat_names, inplace=True)
if restrict_to is not None:
groups.index = adata.obs[restrict_key].index
else:
groups.index = adata.obs_names
# add column names
groups.columns = [
"%s_level_%d" % (key_added, level) for level in range(len(bs))
]
# remove any column with the same key
keep_columns = [
x for x in adata.obs.columns
if not x.startswith('%s_level_' % key_added)
]
adata.obs = adata.obs.loc[:, keep_columns]
# concatenate obs with new data, skipping level_0 which is usually
# crap. In the future it may be useful to reintegrate it
# we need it in this function anyway, to match groups with node marginals
if return_low:
adata.obs = pd.concat([adata.obs, groups], axis=1)
else:
adata.obs = pd.concat([adata.obs, groups.iloc[:, 1:]], axis=1)
# add some unstructured info
adata.uns['nsbm'] = {}
adata.uns['nsbm']['stats'] = dict(level_entropy=np.array(
[state.level_entropy(x) for x in range(len(state.levels))]),
modularity=np.array([
gt.modularity(
g, state.project_partition(x, 0))
for x in range(len((state.levels)))
]))
if equilibrate:
adata.uns['nsbm']['stats']['dS'] = dS
adata.uns['nsbm']['stats']['nattempts'] = nattempts
adata.uns['nsbm']['stats']['nmoves'] = nmoves
adata.uns['nsbm']['state'] = state
# now add marginal probabilities.
if collect_marginals:
# refrain group marginals. We collected data in vector as long as
# the number of cells, cut them into appropriate length data
adata.uns['nsbm']['group_marginals'] = {}
for nl, level_marginals in enumerate(group_marginals):
idx = np.where(level_marginals > 0)[0] + 1
adata.uns['nsbm']['group_marginals'][nl] = np.array(
level_marginals[:np.max(idx)])
# prune uninformative levels, if any
if prune:
to_remove = prune_groups(groups)
logg.info(f' Removing levels f{to_remove}')
adata.obs.drop(to_remove, axis='columns', inplace=True)
# calculate log-likelihood of cell moves over the remaining levels
# we have to calculate events at level 0 and propagate to upper levels
logg.info(' calculating cell affinity to groups')
levels = [
int(x.split('_')[-1]) for x in adata.obs.columns
if x.startswith(f'{key_added}_level')
]
adata.uns['nsbm']['cell_affinity'] = dict.fromkeys(
[str(x) for x in levels])
p0 = get_cell_loglikelihood(state, level=0, as_prob=True)
adata.uns['nsbm']['cell_affinity'][0] = p0
l0 = "%s_level_0" % key_added
for nl, level in enumerate(groups.columns[1:]):
cross_tab = pd.crosstab(groups.loc[:, l0], groups.loc[:, level])
cl = np.zeros((p0.shape[0], cross_tab.shape[1]), dtype=p0.dtype)
for x in range(cl.shape[1]):
# sum counts of level_0 groups corresponding to
# this group at current level
cl[:, x] = p0[:, np.where(cross_tab.iloc[:, x] > 0)[0]].sum(axis=1)
adata.uns['nsbm']['cell_affinity'][str(nl + 1)] = cl / np.sum(
cl, axis=1)[:, None]
# last step is recording some parameters used in this analysis
adata.uns['nsbm']['params'] = dict(
epsilon=epsilon,
wait=wait,
nbreaks=nbreaks,
equilibrate=equilibrate,
fast_model=fast_model,
collect_marginals=collect_marginals,
hierarchy_length=hierarchy_length,
random_seed=random_seed,
prune=prune,
)
logg.info(
' finished',
time=start,
deep=
(f'found {state.get_levels()[1].get_nonempty_B()} clusters at level_1, and added\n'
f' {key_added!r}, the cluster labels (adata.obs, categorical)'),
)
return adata if copy else None
#!/usr/bin/env python
import sys,os
import time
import pylab as plt
from sbmtm import sbmtm
import graph_tool.all as gt
import numpy as np
from matplotlib import pyplot as plt
gt.openmp_set_num_threads(int(sys.argv[1])) #set num threads
gt.seed_rng(42) #same results
print("Welcome to Topic Modelling")
print("using ",gt.openmp_get_num_threads(), " threads")
if __name__ == '__main__':
start = time.time()
print("initialised")
gt.seed_rng(42)
print("seed set")
model = sbmtm()
print("model created")
model.load_graph(filename = '/home/filippo/files/graph.xml.gz')
print("graph loaded")
print(model.g)
model.fit(n_init=1, parallel=True, verbose=True)
#model.fit_overlap(n_init=1, verbose=True, parallel=True)
#model.plot()
model.save_data()
model.dump_model()
os.system("mv *.csv *.png *.txt *.pkl /home/filippo/files/.")
# --------------------
print(datetime.now())
# Visually separate analyses
print('-'*40)
if __name__ == '__main__':
# Networks for analysis
netfiles = ['citenet0']
#netfiles = ['autnet0']
#netfiles = ['autnet1']
#netfiles = ['autnet1', 'autnet0', 'citenet0']
# Comparison networks
#compnet_files = ['phnet.graphml']
compnet_files = ['phnet.graphml', 'ptnet.graphml']
# Set up logging
logging.basicConfig(level=logging.INFO, format = '%(message)s')
logger = logging.getLogger()
logger.addHandler(logging.FileHandler('output/' + str(date.today()) + '.log', 'w'))
print = logger.info
print('-'*40)
for netfile in netfiles:
seed(24680)
gt.seed_rng(24680)
run_analysis(netfile, compnet_files)
print(datetime.now())
def draw_graph(
adata: AnnData,
layout: _Layout = 'sfdp',
# init_pos: Union[str, bool, None] = None,
# root: Optional[int] = None,
use_tree: bool = False,
random_seed: Optional[int] = None,
adjacency: Optional[spmatrix] = None,
key_added_ext: Optional[str] = None,
key: Optional[str] = 'schist',
copy: bool = False,
**kwds,
):
"""\
Extends scanpy.tools.draw_graph function using some layouts available in
graph-tool library. Three layouts are available here:
- SFDP spring-block layout.
- ARF spring-block layout.
- Fruchterman-Reingold spring-block layout.
Fruchterman-Reingold is already available in scanpy, but here can be used
to render the nested model tree.
In order to use these plotting function, the NestedBlockState needs to be
saved when building the model, so `save_state=True` needs to be set.
Parameters
----------
adata
Annotated data matrix. A NestedBlockState object needs to be saved
layout
A layout among 'sfdp', 'fr' or 'arf'. Other graph-tool layouts haven't been
implemented.
use_tree
When this is set, the tree of the nested model is used to generate layout,
otherwise the layout only accounts for the neighborhood graph.
random_seed
Random number to be used as seed for graph-tool
adjacency
Sparse adjacency matrix of the graph, defaults to
`adata.uns['neighbors']['connectivities']`.
key_added_ext
By default, append `layout`.
key
The slot in `AnnData.uns` containing the state. Default is 'nsbm'
copy
Return a copy instead of writing to adata.
**kwds
Parameters of chosen igraph layout. See e.g. `fruchterman-reingold`_
[Fruchterman91]_. One of the most important ones is `maxiter`.
.. _fruchterman-reingold: http://igraph.org/python/doc/igraph.Graph-class.html#layout_fruchterman_reingold
Returns
-------
Depending on `copy`, returns or updates `adata` with the following field.
**X_draw_graph_layout** : `adata.obsm`
Coordinates of graph layout. E.g. for layout='fa' (the default),
the field is called 'X_draw_graph_fa'
"""
if random_seed:
np.random.seed(random_seed)
gt.seed_rng(random_seed)
n_cells = adata.shape[0]
start = logg.info(f'drawing single-cell graph using layout {layout!r}')
if layout not in _LAYOUTS:
raise ValueError(f'Provide a valid layout, one of {_LAYOUTS}.')
adata = adata.copy() if copy else adata
if adjacency is None and 'neighbors' not in adata.uns:
raise ValueError('You need to run `pp.neighbors` first '
'to compute a neighborhood graph.')
if not key in adata.uns:
raise ValueError(
'You need to run `nested_model` before trying to run this function '
)
if use_tree and 'state' not in adata.uns[key]:
raise ValueError(
'When `use_tree` is set to `True`, a state should be saved'
'running `nested_model(adata, save_state=True)`.')
if adjacency is None:
adjacency = adata.uns['neighbors']['connectivities']
g = get_graph_tool_from_adjacency(adjacency)
weights = g.ep['weight']
if use_tree:
state = state_from_blocks(adata)
g, _, _ = gt.get_hierarchy_tree(state, empty_branches=False)
weights = None
# actual drawing
positions = np.zeros((n_cells, 2))
if layout == 'fr':
positions = gt.fruchterman_reingold_layout(g, weight=weights)
positions = np.array([x for x in positions][:n_cells])
elif layout == 'sfdp':
positions = gt.sfdp_layout(g)
positions = np.array([x for x in positions][:n_cells])
elif layout == 'arf':
positions = gt.arf_layout(g)
positions = np.array([x for x in positions][:n_cells])
adata.uns['draw_graph'] = {}
adata.uns['draw_graph']['params'] = dict(layout=layout,
random_seed=random_seed)
key_added = f'X_draw_graph_{layout}'
adata.obsm[key_added] = positions
logg.info(
' finished',
time=start,
deep=('added\n'
f' {key_added!r}, graph_drawing coordinates (adata.obsm)'),
)
return adata if copy else None
def run_analysis(netfile, compnet_files):
'''
Run the analysis.
:param netfile: Filename of the network to analyze
:param compnet_files: List of filenames of the comparison networks, viz.,
the high-energy physics networks.
'''
# Timestamp
# --------------------
print(datetime.now())
# Load the network
# --------------------
net, outfile_pre, core_pmap, core_vertices = load_net(netfile + '.graphml',
core = True,
filter = True)
output_folder = 'output/'
outfile_pre = output_folder + outfile_pre
# Plotting
print('Plotting')
layout = layout_and_plot(net, core_pmap, outfile_pre)
# Store the layout in the net
net.vp['layout'] = layout
# Show only the core vertices
net.set_vertex_filter(core_pmap)
layout_and_plot(net, core_pmap, outfile_pre, filename_mod = '.core.net',
reverse_colors = True)
net.set_vertex_filter(None)
# Vertex statistics
# --------------------
# ECDF for out-degree distribution
degree_dist(net, core_vertices, outfile = outfile_pre,
show_plot = False, save_plot = True)
# ECDF for eigenvector centrality
## Currently this is causing a segmentation fault
# ev_centrality_dist(net, core_vertices, outfile = outfile_pre,
# show_plot = False, save_plot = True)
# Modularity
# --------------------
# Calculate modularity, using the core vertices as the partition
modularity = gtcomm.modularity(net, core_pmap)
print('Observed modularity: ' + str(modularity))
obs_ins = insularity(net, core_pmap)
print('Observed insularity: ' + str(obs_ins))
# Calculate the number of core vertices
n_core = len(core_vertices)
# Construct a sampling distribution for the modularity statistic
# And use it to calculate a p-value for the modularity
print('Random sample modularity')
modularity_sample_dist(net, n_core, modularity,
outfile = outfile_pre + '.mod',
show_plot = False, save_plot = True)
print('Random sample insularities')
modularity_sample_dist(net, n_core, obs_ins,
mod_func = insularity,
outfile = outfile_pre + '.ins',
show_plot = False, save_plot = True)
# Information-theoretic partitioning
print('Information-theoretic partitioning')
# Calculate the partition
gt.seed_rng(5678)
np.random.seed(5678)
part_block = gt.minimize_blockmodel_dl(net, B_min = 2, B_max = 2,
verbose = True,
overlap = False)
# Extract the block memberships as a pmap
net.vp['partition'] = part_block.get_blocks()
# Calculate the modularity
block_modularity = gtcomm.modularity(net, net.vp['partition'])
print('Partion modularity: ' + str(block_modularity))
print('Partition insularities')
block_insularities = partition_insularity(net, net.vp['partition'])
for community in block_insularities:
print('Community ' + str(community) + ': ' +
str(block_insularities[community]))
print('Plotting')
size_pmap = gt.prop_to_size(core_pmap, mi = 10, ma = 20)
layout_and_plot(net, net.vp['partition'], outfile_pre,
size_pmap = size_pmap, filename_mod = '.partition')
# Modularity optimization
optimal_sample_dist(net, modularity, obs_ins,
outfile = outfile_pre,
show_plot = False, save_plot = True)
# Save results
# --------------------
# The above covers all of the analysis to be written into the output files,
# so we'll go ahead and save things now.
print('Saving')
# Save in graph-tool's binary format
net.save(outfile_pre + '.out' + '.gt')
# Replace vector-type properties with strings
#net.list_properties()
properties = net.vertex_properties
for property_key in properties.keys():
property = properties[property_key]
if 'vector' in property.value_type():
properties[property_key] = property.copy(value_type = 'string')
# Save as graphml
net.save(outfile_pre + '.out' + '.graphml')
# Comparison networks
# --------------------
for compnet_file in compnet_files:
# Load the comparison network
compnet, compnet_outfile = load_net(compnet_file)
# Set it to the same directedness as the network of interest
compnet.set_directed(net.is_directed())
# Size of compnet
n_compnet = compnet.num_vertices()
# Num vertices in compnet to use in each random partition
k_compnet = round(n_core / net.num_vertices() * n_compnet)
# Sample distribution based on random partition
print('Random sample modularities')
print('Observed modularity: ' + str(modularity))
modularity_sample_dist(compnet, k_compnet, modularity,
outfile = outfile_pre + '.mod.' + compnet_outfile,
show_plot = False, save_plot = True)
print('Random sample insularities')
print('Observed insularity: ' + str(obs_ins))
modularity_sample_dist(compnet, k_compnet, obs_ins,
mod_func = insularity,
outfile = outfile_pre + '.ins.' + compnet_outfile,
show_plot = False, save_plot = True)
# Sample distribution based on optimizing modularity
# optimal_sample_dist(compnet, modularity, n_samples = 300,
# outfile = outfile_pre + '.mod.' + compnet_outfile,
# show_plot = False)
# Timestamp
# --------------------
print(datetime.now())
# Visually separate analyses
print('-'*40)
def find_communities(nnodes, edges, alg, params=None):
def membership2cs(membership):
cs = {}
for i, m in enumerate(membership):
cs.setdefault(m, []).append(i)
return cs.values()
def connected_subgraphs(G: nx.Graph):
for comp in nx.connected_components(G):
sub = nx.induced_subgraph(G, comp)
sub = nx.convert_node_labels_to_integers(sub,
label_attribute='old')
yield sub
def apply_subgraphs(algorithm, **params):
cs = []
for sub in connected_subgraphs(G):
if len(sub.nodes) <= 3:
coms = [sub.nodes] # let it be a cluster
else:
coms = algorithm(sub, **params)
if hasattr(coms, 'communities'):
coms = coms.communities
for com in coms:
cs.append([sub.nodes[i]['old'] for i in set(com)])
return cs
def karate_apply(algorithm, graph, **params):
model = algorithm(**params)
model.fit(graph)
return membership2cs(model.get_memberships().values())
if alg == 'big_clam':
c = -1 if params['c'] == 'auto' else int(params['c'])
cs = BigClam('../../snap').run(edges, c=c, xc=int(params['xc']))
elif alg in ('gmm', 'kclique', 'lprop', 'lprop_async', 'fluid',
'girvan_newman', 'angel', 'congo', 'danmf', 'egonet_splitter',
'lfm', 'multicom', 'nmnf', 'nnsed', 'node_perception', 'slpa',
'GEMSEC', 'EdMot', 'demon'):
G = nx.Graph()
G.add_edges_from(edges)
if alg == 'gmm':
cs = community.greedy_modularity_communities(G)
elif alg == 'kclique':
params = {k: float(v) for k, v in params.items()}
cs = community.k_clique_communities(G, **params)
elif alg == 'lprop':
cs = community.label_propagation_communities(G)
elif alg == 'lprop_async':
cs = community.asyn_lpa_communities(G, seed=0)
elif alg == 'fluid':
params = {k: int(v) for k, v in params.items()}
params['seed'] = 0
cs = apply_subgraphs(community.asyn_fluidc, **params)
elif alg == 'girvan_newman':
comp = community.girvan_newman(G)
for cs in itertools.islice(comp, int(params['k'])):
pass
elif alg == 'angel':
params = {k: float(v) for k, v in params.items()}
cs = cdlib.angel(G, **params).communities
elif alg == 'congo': # too slow
ncoms = int(params['number_communities'])
cs = []
for sub in connected_subgraphs(G):
if len(sub.nodes) <= max(3, ncoms):
cs.append(sub.nodes) # let it be a cluster
else:
coms = cdlib.congo(sub,
number_communities=ncoms,
height=int(params['height']))
for com in coms.communities:
cs.append([sub.nodes[i]['old'] for i in set(com)])
elif alg == 'danmf': # no overlapping
cs = apply_subgraphs(cdlib.danmf)
elif alg == 'egonet_splitter':
params['resolution'] = float(params['resolution'])
cs = apply_subgraphs(cdlib.egonet_splitter, **params)
elif alg == 'lfm':
coms = cdlib.lfm(G, float(params['alpha']))
cs = coms.communities
elif alg == 'multicom':
cs = cdlib.multicom(G, seed_node=0).communities
elif alg == 'nmnf':
params = {k: int(v) for k, v in params.items()}
cs = apply_subgraphs(cdlib.nmnf, **params)
elif alg == 'nnsed':
cs = apply_subgraphs(cdlib.nnsed)
elif alg == 'node_perception': # not usable
params = {k: float(v) for k, v in params.items()}
cs = cdlib.node_perception(G, **params).communities
elif alg == 'slpa':
params["t"] = int(params["t"])
params["r"] = float(params["r"])
cs = cdlib.slpa(G, **params).communities
elif alg == 'demon':
params = {k: float(v) for k, v in params.items()}
cs = cdlib.demon(G, **params).communities
elif alg == 'GEMSEC':
# gamma = float(params.pop('gamma'))
params = {k: int(v) for k, v in params.items()}
# params['gamma'] = gamma
params['seed'] = 0
_wrap = partial(karate_apply, karateclub.GEMSEC)
cs = apply_subgraphs(_wrap, **params)
elif alg == 'EdMot':
params = {k: int(v) for k, v in params.items()}
_wrap = partial(karate_apply, karateclub.EdMot)
cs = apply_subgraphs(_wrap, **params)
elif alg in ('infomap', 'community_leading_eigenvector', 'leig',
'multilevel', 'optmod', 'edge_betweenness', 'spinglass',
'walktrap', 'leiden', 'hlc'):
G = igraph.Graph()
G.add_vertices(nnodes)
G.add_edges(edges)
if alg == 'infomap':
vcl = G.community_infomap(trials=int(params['trials']))
cs = membership2cs(vcl.membership)
elif alg == 'leig':
clusters = None if params['clusters'] == 'auto' else int(
params['clusters'])
vcl = G.community_leading_eigenvector(clusters=clusters)
cs = membership2cs(vcl.membership)
elif alg == 'multilevel':
vcl = G.community_multilevel()
cs = membership2cs(vcl.membership)
elif alg == 'optmod': # too long
membership, modularity = G.community_optimal_modularity()
cs = membership2cs(vcl.membership)
elif alg == 'edge_betweenness':
clusters = None if params['clusters'] == 'auto' else int(
params['clusters'])
dendrogram = G.community_edge_betweenness(clusters, directed=False)
try:
clusters = dendrogram.as_clustering()
except:
return []
cs = membership2cs(clusters.membership)
elif alg == 'spinglass': # only for connected graph
vcl = G.community_spinglass(parupdate=True,
update_rule=params['update_rule'],
start_temp=float(params['start_temp']),
stop_temp=float(params['stop_temp']))
cs = membership2cs(vcl.membership)
elif alg == 'walktrap':
dendrogram = G.community_walktrap(steps=int(params['steps']))
try:
clusters = dendrogram.as_clustering()
except:
return []
cs = membership2cs(clusters.membership)
elif alg == 'leiden':
vcl = G.community_leiden(
objective_function=params['objective_function'],
resolution_parameter=float(params['resolution_parameter']),
n_iterations=int(params['n_iterations']))
cs = membership2cs(vcl.membership)
elif alg == 'hlc':
algorithm = HLC(G, min_size=int(params['min_size']))
cs = algorithm.run(None)
elif alg in ("sbm", "sbm_nested"):
np.random.seed(42)
gt.seed_rng(42)
G = gt.Graph(directed=False)
G.add_edge_list(edges)
deg_corr = bool(params['deg_corr'])
B_min = None if params['B_min'] == 'auto' else int(params['B_min'])
B_max = None if params['B_max'] == 'auto' else int(params['B_max'])
if alg == "sbm":
state = gt.minimize_blockmodel_dl(G,
deg_corr=deg_corr,
B_min=B_min,
B_max=B_max)
membership = state.get_blocks()
cs = membership2cs(membership)
if alg == "sbm_nested":
state = gt.minimize_nested_blockmodel_dl(G,
deg_corr=deg_corr,
B_min=B_min,
B_max=B_max)
levels = state.get_bs()
level_max = int(params['level'])
membership = {}
for nid in range(nnodes):
cid = nid
level_i = len(levels)
for level in levels:
cid = level[cid]
if level_i == level_max:
membership.setdefault(cid, []).append(nid)
break
level_i -= 1
cs = membership.values()
else:
return None
return list(cs)
rcParams["figure.subplot.bottom"] = 0.2
rcParams["image.cmap"] = "hot"
rcParams["text.usetex"] = True
rcParams["ps.usedistiller"] = "xpdf"
rcParams["pdf.compression"] = 9
rcParams["ps.useafm"] = True
rcParams["path.simplify"] = True
rcParams["text.latex.preamble"] = [#"\usepackage{times}",
#"\usepackage{euler}",
r"\usepackage{amssymb}",
r"\usepackage{amsmath}"]
import scipy
import scipy.stats
import numpy as np
from pylab import *
from numpy import *
import graph_tool.all as gt
figure()
try:
gt.openmp_set_num_threads(1)
except RuntimeError:
pass
np.random.seed(42)
gt.seed_rng(42)
