def make_datum(row, args):
title, authors, groups, keywords, topics, abstract = row
d = Datum()
d.add_string("title", title)
if args.abstract:
d.add_string("abstract", abstract)
return d
def test_str(self):
d = Datum()
d.add_string('name', 'john')
d.add_number('age', 20)
d.add_binary('image', '0101')
self.assertEquals('datum{string_values: [[\'name\', \'john\']], num_values: [[\'age\', 20.0]], binary_values: [[\'image\', \'0101\']]}',
str(d))
def test_str(self):
d = Datum()
d.add_string('name', 'john')
d.add_number('age', 20)
d.add_binary('image', b('0101'))
s = str(d)
self.assertTrue('datum{string_values: [[\'name\', \'john\']], num_values: [[\'age\', 20.0]], binary_values: [[\'image\', \'0101\']]}' == s or 'datum{string_values: [[\'name\', \'john\']], num_values: [[\'age\', 20.0]], binary_values: [[\'image\', b\'0101\']]}' == s)
def test_add_string(self):
d = Datum()
d.add_string('key', 'value')
self.assertEqual(Datum({'key': 'value'}).to_msgpack(), d.to_msgpack())
d = Datum()
d.add_string(u('key'), u('value'))
self.assertEqual(Datum({'key': 'value'}).to_msgpack(), d.to_msgpack())
def make_datum_binary(title=None, text=None, picture=None):
d = Datum()
if title:
d.add_string("title", title)
if text:
d.add_string("text", text)
if picture:
d.add_binary("img", picture)
return d
def test_add_string(self):
d = Datum()
d.add_string('key', 'value')
self.assertEquals(Datum({'key': 'value'}).to_msgpack(),
d.to_msgpack())
d = Datum()
d.add_string(u'key', u'value')
self.assertEquals(Datum({'key': 'value'}).to_msgpack(),
d.to_msgpack())
def make_datum(title=None, text=None, picture=None):
d = Datum()
if title:
d.add_string("title", title)
if text:
d.add_string("text", text)
if picture:
with open(picture, "rb") as f:
d.add_binary("img", f.read())
return d
def test_str(self):
d = Datum()
d.add_string('name', 'john')
d.add_number('age', 20)
d.add_binary('image', b('0101'))
s = str(d)
self.assertTrue(
'datum{string_values: [[\'name\', \'john\']], num_values: [[\'age\', 20.0]], binary_values: [[\'image\', \'0101\']]}'
== s or
'datum{string_values: [[\'name\', \'john\']], num_values: [[\'age\', 20.0]], binary_values: [[\'image\', b\'0101\']]}'
== s)
def convert(self, args):
if len(args) % 2 != 0:
raise ValueError('value for the last datum key ({0}) is missing'.format(args[len(args) - 1]))
d = Datum()
for i in range(int(len(args) / 2)):
feat_key = args[i*2]
feat_val = args[i*2+1]
try:
d.add_number(feat_key, float(feat_val))
except ValueError:
d.add_string(feat_key, feat_val)
return (len(args), d)
def convert(self, args):
if len(args) % 2 != 0:
raise ValueError(
'value for the last datum key ({0}) is missing'.format(
args[len(args) - 1]))
d = Datum()
for i in range(int(len(args) / 2)):
feat_key = args[i * 2]
feat_val = args[i * 2 + 1]
try:
d.add_number(feat_key, float(feat_val))
except ValueError:
d.add_string(feat_key, feat_val)
return (len(args), d)
# 2. prepare training data
with open('../kddcup.data_10_percent.txt', mode='r') as file:
for line in file:
duration, protocol_type, service, flag, src_bytes, dst_bytes, land, wrong_fragment, urgent, hot, num_failed_logins, logged_in, num_compromised, root_shell, su_attempted, num_root, num_file_creations, num_shells, num_access_files, num_outbound_cmds, is_host_login, is_guest_login, count, srv_count, serror_rate, srv_serror_rate, rerror_rate, srv_rerror_rate, same_srv_rate, diff_srv_rate, srv_diff_host_rate, dst_host_count, dst_host_srv_count, dst_host_same_srv_rate, dst_host_diff_srv_rate, dst_host_same_src_port_rate, dst_host_srv_diff_host_rate, dst_host_serror_rate, dst_host_srv_serror_rate, dst_host_rerror_rate, dst_host_srv_rerror_rate, label = line[:-1].split(",")
datum = Datum()
for (k, v) in [
["protocol_type", protocol_type],
["service", service],
["flag", flag],
["land", land],
["logged_in", logged_in],
["is_host_login", is_host_login],
["is_guest_login", is_guest_login],
]:
datum.add_string(k, v)
for (k, v) in [
["duration",float(duration)],
["src_bytes", float(src_bytes)],
["dst_bytes", float(dst_bytes)],
["wrong_fragment", float(wrong_fragment)],
["urgent", float(urgent)],
["hot", float(hot)],
["num_failed_logins", float(num_failed_logins)],
["num_compromised", float(num_compromised)],
["root_shell", float(root_shell)],
["su_attempted", float(su_attempted)],
["num_root", float(num_root)],
["num_file_creations", float(num_file_creations)],
["num_shells", float(num_shells)],
import sys, json
from jubatus.clustering import client
from jubatus.clustering import types
from jubatus.common import Datum
NAME = "clustering_compounds"
if __name__ == '__main__':
clustering = client.Clustering("127.0.0.1", 9199, NAME)
for line in open("../../bench_data/demo4096.smi"):
smiles, id = line.split(" ")
datum = Datum()
datum.add_string("SMILES", smiles)
clustering.push([datum])
center_list = clustering.get_k_center()
members = clustering.get_core_members()
for i in range(0,4):
for j in range(len(members[i])):
print "%d, %d, %s " %(i, j, members[i][j])
# print "%s \n" % center_list[4]
# for i in range(len(center_list)):
# print "%s \n" % center_list[i]
def make_datum():
d = Datum()
d.add_string('string-key', 'str')
d.add_number('number-key', 1.0)
d.add_binary('binary-key', b'bin')
return d
import json, sys
import jubatus
from jubatus.common import Datum
headlines = {}
#keys = ["HeadLine", "DateLine", "Language", "DateId", "NewsItemId", "article", "Genre1", "Genre2"]
with open(sys.argv[1], "r") as f:
client = jubatus.Recommender("127.0.0.1", 9199, "hoge", 0)
feeds = json.load(f, encoding="utf-8")
for feed in feeds:
d = Datum()
keys = list(feed.keys())
headlines[feed["NewsItemId"]] = feed["HeadLine"]
for key in keys:
try:
if key == "article":
d.add_string(key, " ".join(feed[key]))
elif key == "NewsItemId":
article_id = feed[key].encode('utf-8')
elif key == "HeadLine":
d.add_string(key, feed[key].encode('utf-8'))
else:
d.add_string(key, feed[key].encode('utf-8'))
except TypeError:
print("ignore", key, " ".join(feed[key]))
except AttributeError:
print("ignore", key, feed[key])
client.update_row(article_id, d)
res = client.similar_row_from_id(article_id, 10)
client.save("jubatus_hackathon")
for r in res:
print(r.id, r.score, headlines[r.id])
import sys, json
from jubatus.clustering import client
from jubatus.clustering import types
from jubatus.common import Datum
NAME = "clustering_compounds"
if __name__ == '__main__':
clustering = client.Clustering("127.0.0.1", 9199, NAME)
datum = Datum()
datum.add_string("SMILES", "cccccccc")
print clustering.get_nearest_center(datum)
# print "%s \n" % center_list[4]
# for i in range(len(center_list)):
# print "%s \n" % center_list[i]
from jubatus.common import Datum
import jubatus
client = jubatus.Weight("127.0.0.1", 9199, "")
d = Datum()
d.add_number("user/age", 25)
d.add_number("user/income", 1000)
d.add_string("user/name", "Loren")
d.add_string("message", "Hello")
res = client.calc_weight(d)
print(res)
with open('../kddcup.data_10_percent.txt', mode='r') as file:
for line in file:
duration, protocol_type, service, flag, src_bytes, dst_bytes, land, wrong_fragment, urgent, hot, num_failed_logins, logged_in, num_compromised, root_shell, su_attempted, num_root, num_file_creations, num_shells, num_access_files, num_outbound_cmds, is_host_login, is_guest_login, count, srv_count, serror_rate, srv_serror_rate, rerror_rate, srv_rerror_rate, same_srv_rate, diff_srv_rate, srv_diff_host_rate, dst_host_count, dst_host_srv_count, dst_host_same_srv_rate, dst_host_diff_srv_rate, dst_host_same_src_port_rate, dst_host_srv_diff_host_rate, dst_host_serror_rate, dst_host_srv_serror_rate, dst_host_rerror_rate, dst_host_srv_rerror_rate, label = line[:-1].split(
",")
datum = Datum()
for (k, v) in [
["protocol_type", protocol_type],
["service", service],
["flag", flag],
["land", land],
["logged_in", logged_in],
["is_host_login", is_host_login],
["is_guest_login", is_guest_login],
]:
datum.add_string(k, v)
for (k, v) in [
["duration", float(duration)],
["src_bytes", float(src_bytes)],
["dst_bytes", float(dst_bytes)],
["wrong_fragment", float(wrong_fragment)],
["urgent", float(urgent)],
["hot", float(hot)],
["num_failed_logins",
float(num_failed_logins)],
["num_compromised", float(num_compromised)],
["root_shell", float(root_shell)],
["su_attempted", float(su_attempted)],
["num_root", float(num_root)],
["num_file_creations",
