def get_reinitz_data(**kwargs):
ofs = kwargs.get('ofs',0)
do_plot_coords = kwargs.get('plot_coords',False)
do_plot_vals = kwargs.get('plot_vals',False)
idm= id_map()
df = datafiles(**mem.rc(kwargs))
#I'm not sure exactly how this dataset works but
#each nuclei has a bunch of numbers that appear to be
#monotonically increasing.
#
#I just take the first instance.
nums = dict([(k,v[:,0]) for k, v in df.iteritems()])
nuc_count = len(set(nums.values()[2]))
values = dict([(k,v[nuc_count *ofs: nuc_count *(ofs + 1),-1])
for k, v in df.iteritems()])
coords = dict([(k,v[nuc_count *ofs :nuc_count *(ofs + 1),1:3]) for k, v in df.iteritems()])
#to check the basic consistency of the data, enable the plot routines.
#I suppose that I could do this for all of the nuclei occurences...
#right now, only the first is used.
if do_plot_coords:
f = myplots.fignum(1,(8,8))
ax = f.add_subplot(111)
ct = mycolors.getct(len(values))
for i,k in enumerate(values.keys()):
ax.scatter(coords[k][:,0][::1], coords[k][:,1][::1], 10,
edgecolor = 'none', alpha = .25,c =ct[i],
label = k, )
f.savefig(myplots.figpath( 'reinitz_exprdata_coords_nuc_offset={0}'.format(ofs)))
if do_plot_vals:
f = myplots.fignum(1,(8,8))
ax = f.add_subplot(111)
ct = mycolors.getct(len(values))
for i,k in enumerate(values.keys()):
ax.scatter(coords[k][:,0][::1], values[k][::1], 10,
edgecolor = 'none',alpha = .25,c =ct[i],
label = k, )
f.savefig(myplots.figpath( 'reinitz_exprdata_ap_vals_nuc_offset={0}'.format(ofs)))
return coords, values
def check_network(net_name = 'binding',
dataset_name = 'reinitz',
data_ofs = 4,
max_edges = -1,
node_restriction = 'reinitz'):
reinitz_keys =set( get_reinitz_data()[1].keys())
if dataset_name == 'reinitz':
coords, values = get_reinitz_data(ofs = data_ofs)
elif dataset_name == 'bdtnp':
data = nio.getBDTNP()
meta = nio.getBDTNP(misc = True)
values = dict([( k, v['vals'][:,data_ofs] ) for k,v in data.iteritems()])
coords = array([meta['x']['vals'][:,data_ofs],meta['y']['vals'][:,data_ofs]])
elif dataset_name == 'tc':
data = nio.getTC()
if node_restriction == 'reinitz':
data = dict([(k,v) for k,v in data.iteritems() if k in reinitz_keys])
#values = dict([( k, v['vals'][:,data_ofs] ) for k,v in data.iteritems()])
#coords = array([meta['x']['vals'][:,data_ofs],meta['y']['vals'][:,data_ofs]])
values = data
else:
raise Exception('data set {0} not yet implemented'.format(dataset_name))
nets = comp.get_graphs()
if net_name == 'binding':
network = nets['bn']
elif net_name == 'unsup':
network = nets['unsup']
elif net_name == 'logistic':
network = nets['logistic']
elif net_name =='clusters':
network = get_soheil_network(max_edges = max_edges,
node_restriction = values.keys())
else:
raise Exception('type not implemented: {0}'.format(net_name))
nodes = values.keys()
nodes_allowed = set(nodes)
f = myplots.fignum(1,(8,8))
ax = f.add_subplot(111)
targets = {}
edges = []
for n in nodes:
targets[n] = []
if n in network:
targets[n] = nodes_allowed.intersection(network[n].keys())
xax = linspace(-1,1,20)
edges = list(it.chain(*[[(e,v2) for v2 in v] for e, v in targets.iteritems()]))
ccofs = [e for e in [ corrcoef(values[tf], values[tg])[0,1] for tf, tg in edges] if not isnan(e)]
count, kde = make_kde(ccofs)
ax.hist(ccofs,xax,label = net_name)
h =histogram(ccofs,xax)
ax.fill_between(xax,kde(xax)*max(h[0]),label = net_name,zorder = 1,alpha = .5)
myplots.maketitle(ax,'edge correlations kde for {0}'.format('\n{2} data (data offset={0})\n(net_name={1})\n(max_edges={3})'
.format(data_ofs, net_name, dataset_name, max_edges) ),\
subtitle = 'n_edges = {0}'.format(len(edges)))
ax.legend()
f.savefig(myplots.figpath('network_edge_corrs_data_ofs={0}_net={1}_expr={2}_max_edges={3}'
.format(data_ofs,net_name,dataset_name, max_edges)))