Not able to train online_train.py

[Nikhileshorg]

Hello @JustinaPetr. Please help me with this issue.
Rasa core version : 0.14.0a1
Rasa nlu version : 0.14.4

For newer versions of rasa nlu and rasa core. Can we follow the same steps followed in your video tutorial. Because I have noticed that in the older version of your video tutorial. I can see in the online_train.py file doesn't have action_endpoint but in the new version of your online train file. It has action_endpoint. As you told, I have tried using the code from your repository. When I am using that updated code. I am getting this error.

Traceback (most recent call last):
File "training_online.py", line 35, in
nlu_interpreter = RasaNLUInterpreter('./models/nlu/default/weathernlu')
File "c:\users\kastu\chatbot\rasa_core\rasa_core\interpreter.py", line 231, in init
self._load_interpreter()
File "c:\users\kastu\chatbot\rasa_core\rasa_core\interpreter.py", line 247, in load_interpreter
self.interpreter = Interpreter.load(self.model_directory)
File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\rasa_nlu\model.py", line 293, in load
skip_validation)
File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\rasa_nlu\model.py", line 320, in create
model_metadata, **context)
File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\rasa_nlu\components.py", line 419, in load_component
cached_component, **context)
File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\rasa_nlu\registry.py", line 133, in load_component_by_name
return component_clz.load(model_dir, metadata, cached_component, **kwargs)
File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\rasa_nlu\utils\spacy_utils.py", line 126, in load
nlp = spacy.load(model_name, parser=False)
File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\spacy_init.py", line 21, in load
return util.load_model(name, **overrides)
File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\spacy\util.py", line 119, in load_model
raise IOError(Errors.E050.format(name=name))
OSError: [E050] Can't find model 'None'. It doesn't seem to be a shortcut link, a Python package or a valid path to a data directory.

Please help me. Let me know where I am going wrong. Thanks.

The content of the online_train.py file :

from future import absolute_import
from future import division
from future import print_function
from future import unicode_literals

import logging

from rasa_core.agent import Agent
from rasa_core.policies.keras_policy import KerasPolicy
from rasa_core.policies.memoization import MemoizationPolicy
from rasa_core.interpreter import RasaNLUInterpreter
from rasa_core.train import interactive
from rasa_core.utils import EndpointConfig

logger = logging.getLogger(name)

def run_weather_online(interpreter,
domain_file="weather_domain.yml",
training_data_file='data/stories.md'):
action_endpoint = EndpointConfig(url="http://localhost:5055/webhook")
agent = Agent(domain_file,
policies=[MemoizationPolicy(max_history=2), KerasPolicy(max_history=3, epochs=3, batch_size=50)],
interpreter=interpreter,
action_endpoint=action_endpoint)

data = agent.load_data(training_data_file)
agent.train(data)
interactive.run_interactive_learning(agent, training_data_file)
return agent
if name == 'main':
logging.basicConfig(level="INFO")
nlu_interpreter = RasaNLUInterpreter('./models/nlu/default/weathernlu')
run_weather_online(nlu_interpreter)