def query(file_path):
retry_max = 3 # 再実行の上限回数
retry_interval = 3 # 再実行の間隔（秒）
# データ読み込み
with open(file_path) as f:
dic = {}
line = f.readline()
for line in f:
line = line.rstrip()
ls = line.split('\t')
if len(ls) == 2:
my_id = ls[0]
my_value = float(ls[1])
dic[my_id] = my_value
d = Datum(dic)
var_nam = os.path.basename(file_path)
client = jubatus.Classifier(host, port, name, 300)
for i in range(1, retry_max + 1):
try:
# RPC実行
res = client.classify([d])
ret = ""
for j in range(len(res[0])):
ret += "{0}\t{1}\t{2}\t{3}\n".format(res[0][j].label,
res[0][j].score, var_nam,
argvs[2])
client.get_client().close()
return ret
except (msgpackrpc.error.TransportError, msgpackrpc.error.TimeoutError,
msgpackrpc.error.RPCError) as e:
client.get_client().close()
client = jubatus.Classifier(host, port, name, 60)
print(e)
print("Re-try Querying time:{0} file:{1}".format(i, file_path))
time.sleep(retry_interval)
except (jubatus.common.client.InterfaceMismatch) as e:
print(e)
print("Failed Querying___{0}".format(file_path))
client.get_client().close()
ret = "Failed Querying {0}\n".format(file_path)
return ret
def learn(cat, file_path):
# 形成済みデータファイルをもらって1回だけ学習する
retry_max = 10 # 再実行の回数上限
retry_interval = 3 # 再実行の間隔（秒）
# データ読み込み
with open(file_path) as f:
dic = {}
line = f.readline()
for line in f:
line = line.rstrip()
ls = line.split('\t')
if len(ls) == 2:
my_id = ls[0]
my_value = float(ls[1])
dic[my_id] = my_value
d = Datum(dic)
t_d = [[cat, d]]
client = jubatus.Classifier(host, port, name, 60)
for i in range(1, retry_max + 1):
try:
client.train(t_d)
print("Finish training {0}".format(file_path))
client.get_client().close()
return file_path, 1
except (msgpackrpc.error.TransportError, msgpackrpc.error.TimeoutError,
msgpackrpc.error.RPCError) as e:
client.get_client().close()
client = jubatus.Classifier(host, port, name, 60)
print(e)
print("Re-try Learning time:{0} file:{1}".format(i, file_path))
time.sleep(retry_interval)
except (jubatus.common.client.InterfaceMismatch) as e:
print(e)
print("Failed Learning___{0}".format(file_path))
client.get_client().close()
return file_path, 0
def dim2_classifier_train(self, datafile):
import jubatus
from jubatus.common import Datum
import pandas as pd
host = "127.0.0.1"
port = 9199
name = "2dim_classifier"
client = jubatus.Classifier(host, port, name)
df = pd.read_csv(datafile, names=('x', 'y', 'label'))
for ix, row in df.iterrows():
client.train([(str(row['label']),
Datum({
'x': row['x'],
'y': row['y']
}))])
# print "ix:{0}".format(ix)
self.query_num = ix + 1
self.query_type = "2dim_classifier_train"
def post():
title = u"Train"
if request.method == 'POST':
mongo_server_ip = request.form['mongo_server_ip']
mongo_server_port = request.form['mongo_server_port']
jubatus_server_ip = request.form['jubatus_server_ip']
jubatus_server_port = request.form['jubatus_server_port']
db_name = request.form['db_name']
collection_name = request.form['collection_name']
# POSTで得られる値はstr型なのでintに変換する
jubatus_server_port = int(jubatus_server_port)
mongo_server_port = int(mongo_server_port)
# jubaclassifierのtrainの実行および表示
client = jubatus.Classifier(jubatus_server_ip, jubatus_server_port,
name)
lux_classifier = LuxClassifier()
result_list = lux_classifier.train(client, mongo_server_ip,
mongo_server_port, db_name,
collection_name)
# データフレームの取得
convert_mongo = convertMongo()
train_sensors_dic = convert_mongo.getTrainSensorsDic(
mongo_server_ip, mongo_server_port, db_name, collection_name)
data_frame = convert_mongo.getTable(train_sensors_dic)
# とりあえずターミナル上に表示
print data_frame
return render_template('index.html',
title=title,
jubatus_server_ip=jubatus_server_ip,
jubatus_server_port=jubatus_server_port,
mongo_server_ip=mongo_server_ip,
mongo_server_port=mongo_server_port,
result_list=result_list)
else:
# エラーなどでリダイレクトしたい場合はこんな感じで
print train_sensor_data
return redirect(url_for('hello'))
# training data must be shuffled on online learning!
random.shuffle(train_data)
# run train
client.train(train_data)
def predict(client):
# predict the last shogun
data = [
Datum({'name': u'慶喜'}),
Datum({'name': u'義昭'}),
Datum({'name': u'守時'}),
]
for d in data:
res = client.classify([d])
# get the predicted shogun name
sys.stdout.write(max(res[0], key=lambda x: x.score).label)
sys.stdout.write(' ')
sys.stdout.write(d.string_values[0][1].encode('utf-8'))
sys.stdout.write('\n')
if __name__ == '__main__':
# connect to the jubatus
client = jubatus.Classifier(host, port, name)
# run example
train(client)
predict(client)
#!/usr/bin/env python
# -*- coding:utf-8 -*-
from requests_oauthlib import OAuth1Session
import jubatus
import time
from lux_classifier import LuxClassifier
client = jubatus.Classifier('127.0.0.1', 9199, 'test')
previous_result = 'previous'
oath_key_dict = {
"consumer_key": "a71iiYuMoJrhSSZBQBWF5bDVm",
"consumer_secret": "bhKEUnaccqA75t9JWjHJ6A7E76RlU4ce1N23p8Y61muh8NvF2k",
"access_token": "2587234754-SBW9JesNhQEOPlsrqwSpt3YlhwYCliMDfyAbvPU",
"access_token_secret": "ntqzPEeLlvXsG14KCEkdxeGLSKRKIVrQT3dg3E9rA7njj"
}
CK = oath_key_dict["consumer_key"]
CS = oath_key_dict["consumer_secret"]
AT = oath_key_dict["access_token"]
AS = oath_key_dict["access_token_secret"]
# ツイート投稿用のURL
url = "https://api.twitter.com/1.1/statuses/update.json"
# ツイート本文
for d in range(0, 10):
params = {"status": d}
twitter = OAuth1Session(CK, CS, AT, AS)
req = twitter.post(url, params=params)
