def save_dict(self):
"""Saves the updated dictionary to file
"""
file_name = "dictionary.gensim"
file_path = get_training_file_path(file_name)
self._dictionary.save(file_path)
def file_path(self):
"""str: the name of the model's file. It is of the form
lda-num-topics.model
"""
file_name = "lda-{num_topics}.model".format(
num_topics=self._num_topics)
return get_training_file_path(file_name)
def get_file_path():
"""
Returns:
str: the path to the file containing the corpus' data. The file name
is 'lda-corpus.dat'.
"""
file_name = "lda-corpus.dat"
return get_training_file_path(file_name)
def get_file_path():
"""
Returns:
str: the path to the file containing the preprocessed data. The file
name is 'tf-idf-corpus.dat'.
"""
file_name = "tf-idf-corpus.dat"
return get_training_file_path(file_name)
def load_model():
"""This function loads a tf-idf model
Returns:
a tf-idf model (TFIDFVectorizer)
"""
file_name = get_training_file_path('tf-idf.model')
with open(file_name, "rb") as model_file:
model = pickle.load(model_file)
return model
def load_dictionary():
"""This function is used to load a gensim dictionary from the models
folder.
Returns:
:obj:`gensim.corpora.dictionary.Dictionary`: The dictionary found
in ucla_topic_analysis/model/dictionary.gensim or None if there was
no dictionary.
"""
file_name = "dictionary.gensim"
file_path = get_training_file_path(file_name)
if os.path.isfile(file_path):
return Dictionary.load(file_path)
return None
async def coroutine(self, data):
"""This function dictionaries to a json file for using in LightTag
data sets.
Args:
data (:obj:`dict`): A dictionary containing data that needs to be
tagged
"""
file_path = get_training_file_path("LightTag-dataset.json")
is_new_file = create_file(file_path, "[\n]")
data_string = json.dumps(data)
prefix = "\n" if is_new_file else ",\n"
insertion_string = "{0}{1}".format(prefix, data_string)
with open(file_path, "r+") as json_file:
json_file.seek(0, 2)
position = json_file.tell() - 2
insert(insertion_string, json_file, position)
def get_file_path():
"""str: the name of the model's file. It is of the form
tf-idf.model
"""
file_name = "tf-idf.model"
return get_training_file_path(file_name)