def train(self, corpus, backend_params=None):
"""train the project using documents from a metadata source"""
corpus.set_subject_index(self.subjects)
if backend_params is None:
backend_params = {}
beparams = backend_params.get(self.backend.backend_id, {})
self.backend.train(corpus, beparams)
def load_documents(self, corpus):
"""load training documents from a metadata source"""
corpus.set_subject_index(self.subjects)
self._create_vectorizer(corpus)
for backend, _ in self.backends:
backend.load_corpus(corpus, project=self)
def train(self, corpus, backend_params=None, jobs=0):
"""train the project using documents from a metadata source"""
if corpus != 'cached':
corpus.set_subject_index(self.subjects)
corpus = self.transform.transform_corpus(corpus)
if backend_params is None:
backend_params = {}
beparams = backend_params.get(self.backend.backend_id, {})
self.backend.train(corpus, beparams, jobs)
def learn(self, corpus):
"""further train the project using documents from a metadata source"""
corpus.set_subject_index(self.subjects)
if isinstance(self.backend,
annif.backend.backend.AnnifLearningBackend):
self.backend.learn(corpus, project=self)
else:
raise NotSupportedException("Learning not supported by backend",
project_id=self.project_id)
def learn(self, corpus, backend_params=None):
"""further train the project using documents from a metadata source"""
corpus.set_subject_index(self.subjects)
if backend_params is None:
backend_params = {}
beparams = backend_params.get(self.backend.backend_id, {})
if isinstance(self.backend,
annif.backend.backend.AnnifLearningBackend):
self.backend.learn(corpus, beparams)
else:
raise NotSupportedException("Learning not supported by backend",
project_id=self.project_id)
def train(self, corpus):
"""train the project using documents from a metadata source"""
corpus.set_subject_index(self.subjects)
self._create_vectorizer(corpus)
self.backend.train(corpus, project=self)