with open(filename) as f:
for line in f:
yield line.strip()
db = cachedb.CacheDB()
if __name__ == "__main__":
datasets = {"mini": "testmini", "all": "testbig"}
datasetlengths = {"all": 99072112, "mini": 4692576}
for dataset in ["all", "mini"]:
length = datasetlengths[dataset]
records = load_records("nfp/%s.txt" % dataset)
sitename = datasets[dataset]
print
print "Inserting %i records into %s" % (length, sitename)
i = 0
for record in records:
if i % 1000 == 0:
print_status("Inserting record %i" % i, i, length)
i += 1
(user, movie, rating, date) = record.split(",")
datestamp = "%s%s" % (date.replace("-", ""), "120000000")
db.insert_without_timestamp(sitename, ("user", user), ("movie", movie), ("rating", rating, datestamp))
print_status()
print "Finished importing %s" % dataset
time.sleep(5)
while True:
time.sleep(1)
#print type(l)
#print l
if __name__ == '__main__':
datasets = {'mini': 'testmini', 'all': 'testbig'}
datasetlengths = {'all': 99072112, 'mini': 4692576}
for dataset in ['mini', 'all']:
length = datasetlengths[dataset]
records = load_records('nfp/%s.txt' % dataset)
sitename = datasets[dataset]
print
print 'Testing %i records into %s' % (length, sitename)
i = 0
users = {}
for record in records:
if (i % 1000 == 0): print_status('Testing record %i' % i, i, length)
i += 1
(user, movie, rating, date) = record.split(',')
if user not in users:
users[user] = db.get_key(sitename, ('user', user))
#record = db.get_subkey(sitename, ('user', user), ('movie', movie))
record = users[user][('movie', movie)]
datestamp = '%s%s' % (date.replace('-', ''), '120000000')
expected = [('rating', rating, datestamp)]
test = (record == expected)
if not test:
print 'fail: %s != %s' % (record, expected)
#ns.insert(('user', user), ('movie', movie), ('rating', rating, date), add_timestamp=False)
print_status()
print 'Finished testing %s' % dataset
time.sleep(5)
