def run_weather_bot(serve_forever=True):
interpreter = RasaNLUInterpreter(getData()["model_directory"] +
'/default/' + getData()["model_name"])
agent = Agent.load(getData()["dialogue"], interpreter=interpreter)
if serve_forever == True:
agent.handle_channel(ConsoleInputChannel())
return agent
def train_dialogue(): #domain_file,model_path,training_data_file):
utils.configure_colored_logging(loglevel='INFO')
agent = Agent(getData()["domain"],
policies=[MemoizationPolicy(max_history=2),
KerasPolicy()])
training_data = agent.load_data(getData()["stories"])
agent.train(training_data,
epochs=400,
batch_size=100,
validation_split=0.2)
agent.persist(getData()["dialogue"])
return agent
from config import getData print(getData()["data"])
from rasa_core.policies.memoization import MemoizationPolicy
from rasa_core.interpreter import RasaNLUInterpreter
from config import getData
def run_weather_online(input_channel, interpreter, domain_file,
training_data_file):
agent = Agent(domain_file,
policies=[MemoizationPolicy(max_history=3),
KerasPolicy()],
interpreter=interpreter)
training_data = agent.load_data(training_data_file)
agent.train_online(training_data,
input_channel=input_channel,
epochs=400,
batch_size=100,
validation_split=0.2)
if __name__ == '__main__':
utils.configure_colored_logging(loglevel='INFO')
nlu_interpretter = RasaNLUInterpreter(getData()["model_directory"] +
'/default/' +
getData()["model_name"])
run_weather_online(ConsoleInputChannel(), nlu_interpretter,
getData()["domain"],
getData()["stories"])
from rasa_nlu import config
from rasa_nlu.model import Interpreter
import json
import sys
from config import getData
def run_nlu(model, spacy_config):
interpreter = Interpreter.load(model) #, config.load(spacy_config))
result = interpreter.parse(sys.argv[1])
print(json.dumps(result, indent=4, sort_keys=True))
if __name__ == '__main__':
#train_nlu('./data/data.json','./config_spacy.json','./models/nlu')
run_nlu(
getData()["model_directory"] + '/default/' + getData()["model_name"],
getData()["config_spacy"])
def doit(reqid,reqno,times,score,guess):
post_url = 'http://qx8888cp.com/Servers/Game/pcdd/pcddsubmit.ashx?CaiID=15'
params = config.getData(reqid,reqno,times,score,guess)
print('期号：%s , 下注倍数：%d,下注钱数：%d' % (reqno,times,score) )
post = requests.post(post_url,data=json.dumps(params),cookies=config.c_dict,headers=config.headers)
print(post.text)
from rasa_core.channels import HttpInputChannel
from rasa_core.agent import Agent
from rasa_core.interpreter import RasaNLUInterpreter
from rasa_slack_connector import SlackInput
from config import getData
nlu_interpreter = RasaNLUInterpreter(getData()["model_directory"] + '/default/' + getData()["model_name"])
agent = Agent.load(getData()["dialogue"],interpreter= nlu_interpreter)
input_channel = SlackInput(getData()["slack"]["oauth_access_token"],
getData()["slack"]["user_oauth_access_token"],
getData()["slack"]["verification_token"],True)
agent.handle_channel(HttpInputChannel(5004,'/',input_channel))
from __future__ import absolute_import,division,unicode_literals
from rasa_core import utils
from rasa_core.agent import Agent
from rasa_core.policies.keras_policy import KerasPolicy
from rasa_core.policies.memoization import MemoizationPolicy
from config import getData
if __name__ == '__main__':
utils.configure_colored_logging(loglevel='INFO')
domain = getData()["domain"]
stories = getData()["stories"]
dialogue=getData()["dialogue"]
agent = Agent(domain,policies=[MemoizationPolicy(max_history=2)
,KerasPolicy()])
training_data = agent.load_data(stories)
agent.train(training_data,
epochs=400,
batch_size=100,
validation_split=0.2
)
agent.persist(dialogue)
def train_nlu(data, spacy_config, model_dir):
training_data = load_data(data)
trainer = Trainer(config.load(spacy_config))
trainer.train(training_data)
model_directory = trainer.persist(model_dir,
fixed_model_name=getData()["model_name"])
from rasa_nlu.training_data import load_data
from rasa_nlu import config
from rasa_nlu.model import Trainer, Interpreter, Metadata
from config import getData
import json
def train_nlu(data, spacy_config, model_dir):
training_data = load_data(data)
trainer = Trainer(config.load(spacy_config))
trainer.train(training_data)
model_directory = trainer.persist(model_dir,
fixed_model_name=getData()["model_name"])
if __name__ == '__main__':
train_nlu(getData()["data"],
getData()["config_spacy"],
getData()["model_directory"])