def test_pagerank_calculation(self):
"""Create a few items and fake citation relation among them, then
run the pagerank algorithm. Check whether this simple case can get the
correct result.
"""
# calculate pagerank of these 3 document
comm = Command()
self.verbosity = 1
comm.do_pagerank(chown=False)
# read in the pagerank file, converting to a dict
pr_values_from_file = {}
data_path = get_data_dir('collection1') + "external_pagerank"
with open(data_path) as f:
for line in f:
pk, value = line.split('=')
pr_values_from_file[pk] = float(value.strip())
# Verify that whether the answer is correct, based on calculations in
# Gephi
answers = {
'1': 0.369323534954,
'2': 0.204581549974,
'3': 0.378475867453,
}
for key, value in answers.items():
self.assertTrue(
abs(pr_values_from_file[key] - value) < 0.0001,
msg="The answer for item %s was %s when it should have been "
"%s" % (key, pr_values_from_file[key],
answers[key],)
)
def test_pagerank_calculation(self):
"""Create a few items and fake citation relation among them, then
run the pagerank algorithm. Check whether this simple case can get the
correct result.
"""
# calculate pagerank of these 3 document
comm = Command()
self.verbosity = 1
comm.do_pagerank(chown=False)
# read in the pagerank file, converting to a dict
pr_values_from_file = {}
data_path = get_data_dir('collection1') + "external_pagerank"
with open(data_path) as f:
for line in f:
pk, value = line.split('=')
pr_values_from_file[pk] = float(value.strip())
# Verify that whether the answer is correct, based on calculations in
# Gephi
answers = {
'1': 0.369323534954,
'2': 0.204581549974,
'3': 0.378475867453,
}
for key, value in answers.items():
self.assertTrue(
abs(pr_values_from_file[key] - value) < 0.0001,
msg="The answer for item %s was %s when it should have been "
"%s" % (
key,
pr_values_from_file[key],
answers[key],
))
def handle(self, *args, **options):
super(Command, self).handle(*args, **options)
pr_results = self.do_pagerank()
pr_dest_dir = settings.SOLR_PAGERANK_DEST_DIR
make_sorted_pr_file(pr_results, pr_dest_dir)
normal_dest_dir = get_data_dir('collection1') + "external_pagerank"
print("Pagerank file created at %s. Because of distributed servers, "
"you may need to copy it to its final destination. Somewhere "
"like: %s." % (pr_dest_dir, normal_dest_dir))
class Command(BaseCommand):
args = '<args>'
help = 'Calculate pagerank value for every case'
RESULT_FILE_PATH = get_data_dir('collection1') + "external_pagerank"
def do_pagerank(self, chown=True):
g = make_and_populate_nx_graph()
pr_results = g.pagerank()
make_sorted_pr_file(pr_results, self.RESULT_FILE_PATH)
reload_pagerank_external_file_cache()
cp_pr_file_to_bulk_dir(self.RESULT_FILE_PATH, chown)
def handle(self, *args, **options):
self.do_pagerank()
