def import_fp(fp_file_name):
dataset_dict = {}
i = 0
with open('survey_datasets.csv') as survey_datasets:
for line in survey_datasets:
if i > 0:
sline = line.split(',')
dataset_dict[sline[4]] = sline
i += 1
#Load datasets
with open(fp_file_name) as fp_file:
for line in fp_file:
sline = line.split(';')
source_dataset_name = sline[0].replace('.g', '').replace('\n', '')
target_dataset_name = sline[1].replace('.g', '').replace('\n', '')
try:
source_dataset = Dataset.objects.get(nick=source_dataset_name)
except:
source_dataset = create_dataset(dataset_dict[source_dataset_name])
try:
target_dataset = Dataset.objects.get(nick=target_dataset_name)
except:
target_dataset = create_dataset(dataset_dict[target_dataset_name])
similarity_source = Similarity.objects.filter(source_dataset=source_dataset, target_dataset=target_dataset)
similarity_target = Similarity.objects.filter(source_dataset=target_dataset, target_dataset=source_dataset)
for i in range(3 - len(similarity_source) - len(similarity_target)):
print 'Creating similarity for %s - %s' % (source_dataset.nick, target_dataset.nick)
similarity = Similarity()
similarity.source_dataset = source_dataset
similarity.target_dataset = target_dataset
similarity.similarity = None
similarity.save()
try:
dataset = Dataset.objects.get(datahub_url=sline[1])
dataset.nick = sline[4]
dataset.save()
except Exception as e:
print e
print sline[1]
with open('relations.csv') as f:
for line in f:
sline = line.split(';')
source_dataset = Dataset.objects.get(nick=sline[0])
target_dataset = Dataset.objects.get(nick=sline[1])
similarity_source = Similarity.objects.filter(source_dataset=source_dataset, target_dataset=target_dataset)
similarity_target = Similarity.objects.filter(source_dataset=target_dataset, target_dataset=source_dataset)
if len(similarity_target) <= 0:
for i in range(3 - len(similarity_source)):
print 'Creating similarity for %s - %s' % (source_dataset.nick, target_dataset.nick)
similarity = Similarity()
similarity.source_dataset = source_dataset
similarity.target_dataset = target_dataset
similarity.similarity = None
similarity.save()
else:
for i in range(3 - len(similarity_target)):
print 'Creating similarity for %s - %s' % (target_dataset.nick, source_dataset.nick)
similarity = Similarity()
similarity.source_dataset = source_dataset
similarity.target_dataset = target_dataset
similarity.similarity = None
similarity.save()
