def run(input_file: KGTKFiles, directed, compute_degrees, compute_pagerank, compute_hits, log_file, output_stats,
vertex_in_degree, vertex_out_degree, vertex_pagerank, vertex_auth, vertex_hubs):
from kgtk.exceptions import KGTKException
def infer_index(h, options=[]):
for o in options:
if o in h:
return h.index(o)
return -1
def infer_predicate(h, options=[]):
for o in options:
if o in h:
return o
return ''
v_prop_dict = {
'vertex_pagerank': vertex_pagerank,
'vertex_hubs': vertex_hubs,
'vertex_auth': vertex_auth
}
try:
# import modules locally
import socket
from graph_tool import load_graph_from_csv
from graph_tool import centrality
import kgtk.gt.analysis_utils as gtanalysis
from pathlib import Path
import sys
import csv
csv.field_size_limit(sys.maxsize)
filename: Path = KGTKArgumentParser.get_input_file(input_file)
# hardcoded values useful for the script. Perhaps some of them should be exposed as arguments later
directions = ['in', 'out', 'total']
id_col = 'name'
with open(filename, 'r') as f:
header = next(f).split('\t')
header=[h.strip() for h in header]
subj_index = infer_index(header, options=['node1', 'subject'])
obj_index = infer_index(header, options=['node2', 'object', 'value'])
predicate = infer_predicate(header, options=['label', 'predicate', 'relation', 'relationship'])
p = []
for i, header_col in enumerate(header):
if i in [subj_index, obj_index]: continue
p.append(header_col)
with open(log_file, 'w') as writer:
writer.write('loading the TSV graph now ...\n')
G2 = load_graph_from_csv(str(filename),
skip_first=True,
directed=directed,
hashed=True,
ecols=[subj_index, obj_index],
eprop_names=p,
csv_options={'delimiter': '\t'})
writer.write('graph loaded! It has %d nodes and %d edges\n' % (G2.num_vertices(), G2.num_edges()))
writer.write('\n###Top relations:\n')
for rel, freq in gtanalysis.get_topN_relations(G2, pred_property=predicate):
writer.write('%s\t%d\n' % (rel, freq))
if compute_degrees:
writer.write('\n###Degrees:\n')
for direction in directions:
degree_data = gtanalysis.compute_node_degree_hist(G2, direction)
max_degree = len(degree_data) - 1
mean_degree, std_degree = gtanalysis.compute_avg_node_degree(G2, direction)
writer.write(
'%s degree stats: mean=%f, std=%f, max=%d\n' % (direction, mean_degree, std_degree, max_degree))
if compute_pagerank:
writer.write('\n###PageRank\n')
v_pr = G2.new_vertex_property('float')
centrality.pagerank(G2, prop=v_pr)
G2.properties[('v', 'vertex_pagerank')] = v_pr
writer.write('Max pageranks\n')
result = gtanalysis.get_topn_indices(G2, 'vertex_pagerank', 5, id_col)
for n_id, n_label, pr in result:
writer.write('%s\t%s\t%f\n' % (n_id, n_label, pr))
if compute_hits:
writer.write('\n###HITS\n')
hits_eig, G2.vp['vertex_hubs'], G2.vp['vertex_auth'] = gtanalysis.compute_hits(G2)
writer.write('HITS hubs\n')
main_hubs = gtanalysis.get_topn_indices(G2, 'vertex_hubs', 5, id_col)
for n_id, n_label, hubness in main_hubs:
writer.write('%s\t%s\t%f\n' % (n_id, n_label, hubness))
writer.write('HITS auth\n')
main_auth = gtanalysis.get_topn_indices(G2, 'vertex_auth', 5, id_col)
for n_id, n_label, authority in main_auth:
writer.write('%s\t%s\t%f\n' % (n_id, n_label, authority))
sys.stdout.write('node1\tlabel\tnode2\tid\n')
id_count = 0
if not output_stats:
for e in G2.edges():
sid, oid = e
lbl = G2.ep[predicate][e]
sys.stdout.write(
'%s\t%s\t%s\t%s\n' % (G2.vp[id_col][sid], lbl, G2.vp[id_col][oid],
'{}-{}-{}'.format(G2.vp[id_col][sid], lbl, id_count)))
id_count += 1
id_count = 0
for v in G2.vertices():
v_id = G2.vp[id_col][v]
sys.stdout.write(
'{}\t{}\t{}\t{}\n'.format(v_id, vertex_in_degree, v.in_degree(),
'{}-{}-{}'.format(v_id, vertex_in_degree, id_count)))
id_count += 1
sys.stdout.write(
'{}\t{}\t{}\t{}\n'.format(v_id, vertex_out_degree, v.out_degree(),
'{}-{}-{}'.format(v_id, vertex_out_degree, id_count)))
id_count += 1
for vprop in G2.vertex_properties.keys():
if vprop == id_col: continue
sys.stdout.write(
'%s\t%s\t%s\t%s\n' % (v_id, v_prop_dict[vprop], G2.vp[vprop][v],
'{}-{}-{}'.format(v_id, v_prop_dict[vprop], id_count)))
id_count += 1
except Exception as e:
raise KGTKException('Error: ' + str(e))
print('Max pageranks')
gtanalysis.get_topn_indices(g, 'vertex_pagerank', 5)
prs = g.vp['vertex_pagerank'].a
print('pagerank max', np.max(prs))
print('pagerank min', np.min(prs))
pr_data = {}
pr_data['PageRank'] = list(np.sort(prs))
pr_data['x'] = list(np.arange(len(prs)))
pr_df = pd.DataFrame(pr_data)
fig = plt.figure(figsize=(8, 6))
plt.loglog(np.flip(np.sort(prs))) #, basey=base)
plt.ylabel('PageRank')
plt.xlabel('nodes')
plt.title('PageRank value distribution')
fig.savefig(f'../img/pagerank_{name}.png')
hits_eig, g.vp['vertex_hubs'], g.vp[
'vertex_auth'] = gtanalysis.compute_hits(g)
print('HITS eig:', hits_eig)
print('HITS hubs')
gtanalysis.get_topn_indices(g, 'vertex_hubs', 5)
print('HITS auth')
gtanalysis.get_topn_indices(g, 'vertex_auth', 5)
def run(
input_file: KGTKFiles,
output_file: KGTKFiles,
undirected: bool,
compute_degrees: bool,
compute_pagerank: bool,
compute_hits: bool,
log_file: str,
statistics_only: bool,
vertex_in_degree: str,
vertex_out_degree: str,
vertex_pagerank: str,
vertex_auth: str,
vertex_hubs: str,
top_n: int,
errors_to_stdout: bool,
errors_to_stderr: bool,
show_options: bool,
verbose: bool,
very_verbose: bool,
**kwargs, # Whatever KgtkFileOptions and KgtkValueOptions want.
):
# import modules locally
from pathlib import Path
import sys
from graph_tool import centrality
from kgtk.exceptions import KGTKException
import kgtk.gt.analysis_utils as gtanalysis
from kgtk.gt.gt_load import load_graph_from_kgtk
from kgtk.io.kgtkreader import KgtkReader, KgtkReaderOptions
from kgtk.io.kgtkwriter import KgtkWriter
from kgtk.value.kgtkvalueoptions import KgtkValueOptions
v_prop_dict = {
'vertex_pagerank': vertex_pagerank,
'vertex_hubs': vertex_hubs,
'vertex_auth': vertex_auth
}
try:
# Select where to send error messages, defaulting to stderr.
error_file: typing.TextIO = sys.stdout if errors_to_stdout else sys.stderr
# Build the option structures.
reader_options: KgtkReaderOptions = KgtkReaderOptions.from_dict(kwargs)
value_options: KgtkValueOptions = KgtkValueOptions.from_dict(kwargs)
input_kgtk_file: Path = KGTKArgumentParser.get_input_file(input_file)
output_kgtk_file: Path = KGTKArgumentParser.get_output_file(
output_file)
# hardcoded values useful for the script. Perhaps some of them should be exposed as arguments later
directions = ['in', 'out', 'total']
id_col = 'name'
output_columns = ["node1", "label", "node2", "id"]
if verbose:
print('loading the KGTK input file...\n',
file=error_file,
flush=True)
kr: KgtkReader = KgtkReader.open(
input_kgtk_file,
error_file=error_file,
options=reader_options,
value_options=value_options,
verbose=verbose,
very_verbose=very_verbose,
)
sub: int = kr.get_node1_column_index()
if sub < 0:
print("Missing node1 (subject) column.",
file=error_file,
flush=True)
pred: int = kr.get_label_column_index()
if pred < 0:
print("Missing label (predicate) column.",
file=error_file,
flush=True)
obj: int = kr.get_node2_column_index()
if obj < 0:
print("Missing node2 (object) column", file=error_file, flush=True)
if sub < 0 or pred < 0 or obj < 0:
kr.close()
raise KGTKException("Exiting due to missing columns.")
predicate: str = kr.column_names[pred]
G2 = load_graph_from_kgtk(kr,
directed=not undirected,
ecols=(sub, obj),
verbose=verbose,
out=error_file)
if verbose:
print('graph loaded! It has %d nodes and %d edges.' %
(G2.num_vertices(), G2.num_edges()),
file=error_file,
flush=True)
kw: KgtkWriter = KgtkWriter.open(output_columns,
output_kgtk_file,
mode=KgtkWriter.Mode.EDGE,
require_all_columns=True,
prohibit_extra_columns=True,
fill_missing_columns=False,
verbose=verbose,
very_verbose=very_verbose)
with open(log_file, 'w') as writer:
writer.write('graph loaded! It has %d nodes and %d edges\n' %
(G2.num_vertices(), G2.num_edges()))
writer.write('\n###Top relations:\n')
for rel, freq in gtanalysis.get_topN_relations(
G2, pred_property=predicate):
writer.write('%s\t%d\n' % (rel, freq))
if compute_degrees:
writer.write('\n###Degrees:\n')
for direction in directions:
degree_data = gtanalysis.compute_node_degree_hist(
G2, direction)
max_degree = len(degree_data) - 1
mean_degree, std_degree = gtanalysis.compute_avg_node_degree(
G2, direction)
writer.write(
'%s degree stats: mean=%f, std=%f, max=%d\n' %
(direction, mean_degree, std_degree, max_degree))
if compute_pagerank:
writer.write('\n###PageRank\n')
v_pr = G2.new_vertex_property('float')
centrality.pagerank(G2, prop=v_pr)
G2.properties[('v', 'vertex_pagerank')] = v_pr
writer.write('Max pageranks\n')
result = gtanalysis.get_topn_indices(G2, 'vertex_pagerank',
top_n, id_col)
for n_id, n_label, pr in result:
writer.write('%s\t%s\t%f\n' % (n_id, n_label, pr))
if compute_hits:
writer.write('\n###HITS\n')
hits_eig, G2.vp['vertex_hubs'], G2.vp[
'vertex_auth'] = gtanalysis.compute_hits(G2)
writer.write('HITS hubs\n')
main_hubs = gtanalysis.get_topn_indices(
G2, 'vertex_hubs', top_n, id_col)
for n_id, n_label, hubness in main_hubs:
writer.write('%s\t%s\t%f\n' % (n_id, n_label, hubness))
writer.write('HITS auth\n')
main_auth = gtanalysis.get_topn_indices(
G2, 'vertex_auth', top_n, id_col)
for n_id, n_label, authority in main_auth:
writer.write('%s\t%s\t%f\n' % (n_id, n_label, authority))
id_count = 0
if not statistics_only:
for e in G2.edges():
sid, oid = e
lbl = G2.ep[predicate][e]
kw.write([
G2.vp[id_col][sid], lbl, G2.vp[id_col][oid],
'{}-{}-{}'.format(G2.vp[id_col][sid], lbl, id_count)
])
id_count += 1
id_count = 0
for v in G2.vertices():
v_id = G2.vp[id_col][v]
kw.write([
v_id, vertex_in_degree,
str(v.in_degree()), '{}-{}-{}'.format(v_id, vertex_in_degree,
id_count)
])
id_count += 1
kw.write([
v_id, vertex_out_degree,
str(v.out_degree()), '{}-{}-{}'.format(v_id, vertex_out_degree,
id_count)
])
id_count += 1
for vprop in G2.vertex_properties.keys():
if vprop == id_col:
continue
kw.write([
v_id, v_prop_dict[vprop],
str(G2.vp[vprop][v]),
'{}-{}-{}'.format(v_id, v_prop_dict[vprop], id_count)
])
id_count += 1
kw.close()
kr.close()
except Exception as e:
raise KGTKException('Error: ' + str(e))
import kgtk.gt.io_utils as gtio
import kgtk.gt.analysis_utils as gtanalysis
datadir='data/'
mowgli_nodes=f'{datadir}nodes_v002.csv'
mowgli_edges=f'{datadir}edges_v002.csv'
output_gml=f'{datadir}graph.graphml'
g=gtio.load_gt_graph(output_gml.replace(".graphml", '.gt'))
print('graph loaded. now computing centrality.')
node_pagerank=gtanalysis.compute_pagerank(g)
print('pagerank computed')
hits=gtanalysis.compute_hits(g)
print('hits computed')
bt=gtanalysis.compute_betweenness(g)
print('bt computed')