def setUp(self):
self.srv = TestUtil.fork_process("classifier", port)
self.cli = classifier(host, port)
method = "AROW"
self.converter = '{\n"string_filter_types":{}, \n"string_filter_rules":[], \n"num_filter_types":{}, \n"num_filter_rules":[], \n"string_types":{}, \n"string_rules":\n[{"key":"*", "type":"space", \n"sample_weight":"bin", "global_weight":"bin"}\n], \n"num_types":{}, \n"num_rules":[\n{"key":"*", "type":"num"}\n]\n}'
cd = config_data(method, self.converter)
self.cli.set_config("name", cd)
class TweetAnalyzer(StreamListener):
classifier = client.classifier(host, port)
def __init__(self, highlight):
super(TweetAnalyzer, self).__init__()
self.highlight = highlight
def on_status(self, status):
if not hasattr(status, 'text'):
return
d = types.datum([], [])
d.string_values = [
['text', status.text],
]
result = self.classifier.classify(instance_name, [d])
if len(result) > 0 and len(result[0]) > 0:
# sort the result in order of score
est = sorted(result[0], key=lambda est: est.score, reverse=True)
print_green(est[0].label, end=" ")
if est[0].label == self.highlight:
print_red(status.text)
else:
print(status.text)
def main():
args = parse_options()
client = classifier('127.0.0.1', 9199)
# train
num = 0
if args.traindata:
with open(args.traindata, 'rU') as traindata:
for data in traindata:
# skip comments
if not len(data) or data.startswith('#'):
continue
num += 1
season, avetemp, maxtemp, mintemp, pressure, humidity = map(str.strip, data.strip().split(','))
num_values = [
['avetemp', float(avetemp)],
['maxtemp', float(maxtemp)],
['mintemp', float(mintemp)],
['pressure', float(pressure)],
['humidity', float(humidity)]
]
d = datum([], num_values)
train_data = [[season, d]]
# train
client.train('', train_data)
# print train number
print 'train ...', num
# save train model
print "save :", client.save('', "weather")
# anaylze
with open(args.analyzedata, 'r') as analyzedata:
weather = yaml.load(analyzedata)
for k, v in weather.iteritems():
print str(k), "(", str(v['season']), ")"
num_values = [
['avetemp', float(v['avetemp'])],
['maxtemp', float(v['maxtemp'])],
['mintemp', float(v['mintemp'])],
['pressure', float(v['pressure'])],
['humidity', float(v['humidity'])]
]
d = datum([], num_values)
analyze_data = [d]
results = client.classify('', analyze_data)
results[0].sort(key=lambda x: x.score, reverse=True)
for result in results:
for i in range(5):
print result[i].label, result[i].score
print
def setUp(self):
self.config = {
"method": "AROW",
"converter": {
"string_filter_types": {},
"string_filter_rules": [],
"num_filter_types": {},
"num_filter_rules": [],
"string_types": {},
"string_rules": [{"key": "*", "type": "str", "sample_weight": "bin", "global_weight": "bin"}],
"num_types": {},
"num_rules": [{"key": "*", "type": "num"}],
},
"parameter": {"regularization_weight": 1.001},
}
TestUtil.write_file("config_classifier.json", json.dumps(self.config))
self.srv = TestUtil.fork_process("classifier", port, "config_classifier.json")
self.cli = classifier(host, port)
class Trainer(StreamListener):
classifier = client.classifier(host, port)
def __init__(self, locations):
super(Trainer, self).__init__()
self.locations = locations
'''
Format of 'status' can be found in:
https://dev.twitter.com/docs/platform-objects/tweets
'''
def on_status(self, status):
if not hasattr(status, 'text'):
return
if not hasattr(status, 'coordinates'):
return
if not status.coordinates or not 'coordinates' in status.coordinates:
return
loc = None
for l in self.locations:
coordinates = status.coordinates['coordinates']
if l.is_inside(coordinates[0], coordinates[1]):
loc = l
break
if not loc:
# Unknown location
return
hashtags = status.entities['hashtags']
detagged_text = remove_hashtags_from_tweet(status.text, hashtags)
# Create datum for Jubatus
d = types.datum([], [])
d.string_values = [('text', detagged_text)]
# Send training data to Jubatus
self.classifier.train(instance_name, [(loc.name, d)])
# Print trained tweet
print_green(loc.name, ' ')
print detagged_text
def estimate_location_for(text):
classifier = client.classifier(host, port)
# Create datum for Jubatus
d = types.datum([], [])
d.string_values = [('text', text)]
# Send estimation query to Jubatus
result = classifier.classify(instance_name, [d])
if len(result[0]) > 0:
# Sort results by score
est = sorted(result[0], key=lambda e: e.score, reverse=True)
# Print the result
print "Estimated Location for %s:" % text
for e in est:
print " " + e.label + " (" + str(e.score) + ")"
else:
# No estimation results; maybe we haven't trained enough
print "No estimation results available."
print "Train more tweets or try using another text."
def estimate_location_for(text):
classifier = client.classifier(host, port)
# Create datum for Jubatus
d = types.datum([], [])
d.string_values = [('text', text)]
# Send estimation query to Jubatus
result = classifier.classify(instance_name, [d])
if len(result[0]) > 0:
# Sort results by score
est = sorted(result[0], key=lambda e: e.score, reverse=True)
# Print the result
print "Estimated Location for %s:" % text
for e in est:
print " " + e.label + " (" + str(e.score) + ")"
else:
# No estimation results; maybe we haven't trained enough
print "No estimation results available."
print "Train more tweets or try using another text."
def train_wikipedia_abstract(label, xmlfile):
classifier = client.classifier(host, port)
parser = xml.sax.make_parser()
parser.setContentHandler(Handler(classifier, label))
parser.parse(xmlfile)
return result
def parse_args():
from optparse import OptionParser, OptionValueError
p = OptionParser()
p.add_option('-s', '--server_ip', action='store',
dest='server_ip', type='string', default='192.168.170.129')
p.add_option('-p', '--server_port', action='store',
dest='server_port', type='int', default='9199')
p.add_option('-n', '--name', action='store',
dest='name', type='string', default='tutorial')
return p.parse_args()
if __name__ == '__main__':
options,remainder=parse_args()
classifier=client.classifier(options.server_ip,options.server_port)
pname=options.name
print classifier.get_config(pname)
print classifier.get_status(pname)
for line in open('adult.data'):
age,workclass,fnlwgt,education,education_num,marital_status,occupation,relationship,race,sex,capital_gain,capital_loss,hours_per_week,native_country,income=line[:-1].split(',')
datum=types.datum([('workclass',workclass),('sex',sex),('occupation',occupation),('education',education),('marital_status',marital_status),('native_country',native_country),('race',race),('relationship',relationship)],[('age',float(age)),('hours_per_week',float(hours_per_week)),('education_num',float(education_num))])
classifier.train(pname,[(income,datum)])
pass
print classifier.get_status(pname)
print classifier.save(pname, "tutorial")
#!/usr/bin/env python
import sys, json, subprocess
import random
from jubatus.classifier import client
from jubatus.classifier import types
NAME = "a"
classifier = client.classifier("127.0.0.1", 9199)
file_list = subprocess.check_output(["ls | grep _train.txt"],
shell=True).split('\n')[0:-1]
fds = map(lambda x: [x.replace("_train.txt", ""), open(x, "r")], file_list)
while fds != []:
[label, fd] = random.choice(fds)
text = fd.readline()
if text == "":
fds.remove([label, fd])
print("finished train of label %s \n" % (label))
continue
text_strip = text.rstrip()
datum = types.datum([["text", text_strip]], [])
print("train %s : %s ..." % (label, text_strip))
classifier.train(NAME, [(label, datum)])
#!/usr/bin/env python
import json, commands
from jubatus.classifier import client
from jubatus.classifier import types
while True:
buf = raw_input("> ")
if buf == "":
break
classifier = client.classifier("127.0.0.1", 9199)
datum = types.datum([["text", buf.rstrip()]], [])
result = classifier.classify("", [datum])
if len(result[0]) == 0:
print("nothing")
continue
result[0].sort(key=lambda x:x.score, reverse=True)
for res in result[0]:
print(res.label + " -> " + str(res.score))
def train_wikipedia_abstract(label, xmlfile):
classifier = client.classifier(host, port)
parser = xml.sax.make_parser()
parser.setContentHandler(Handler(classifier, label))
parser.parse(xmlfile)
