Fix docstrings forgensim.models.hdpmodel, gensim.models.lda_worker & gensim.models.lda_dispatcher(#1667)

gensim/models/lda_worker.py

@@ -4,13 +4,13 @@
 # Copyright (C) 2011 Radim Rehurek <[email protected]>
 # Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html
 
-"""
-Worker ("slave") process used in computing distributed LDA. Run this script \
-on every node in your cluster. If you wish, you may even run it multiple times \
-on a single machine, to make better use of multiple cores (just beware that \
-memory footprint increases accordingly).
+"""Worker ("slave") process used in computing distributed LDA.
 
+Run this script on every node in your cluster. If you wish, you may even 
+run it multiple times on a single machine, to make better use of multiple
+cores (just beware that memory footprint increases accordingly).
 Example: python -m gensim.models.lda_worker
+
 """
 
 
@@ -40,11 +40,35 @@
 
 
 class Worker(object):
+    """Used as a Pyro class with exposed methods.
+
+    Exposes every non-private method and property of the class automatically
+    to be available for remote access.
+
+    Attributes
+    ----------
+    model : :obj: of :class:`~gensim.models.ldamodel.LdaModel`
+
+    """
+
     def __init__(self):
+        """Partly initializes the model."""
         self.model = None
 
     @Pyro4.expose
     def initialize(self, myid, dispatcher, **model_params):
+        """Fully initializes the worker.
+
+        Parameters
+        ----------
+        myid : int
+            An ID number used to identify this worker in the dispatcher object.
+        dispatcher : :class:`~gensim.models.lda_dispatcher.Dispatcher`
+            The dispatcher responsible for scheduling this worker.
+        **model_params
+            Keyword parameters to initialize the inner LDA model, see :class:`~gensim.models.ldamodel.LdaModel`.
+
+        """
         self.lock_update = threading.Lock()
         self.jobsdone = 0  # how many jobs has this worker completed?
         # id of this worker in the dispatcher; just a convenience var for easy access/logging TODO remove?
@@ -59,6 +83,12 @@ def initialize(self, myid, dispatcher, **model_params):
     def requestjob(self):
         """
         Request jobs from the dispatcher, in a perpetual loop until `getstate()` is called.
+
+        Raises
+        ------
+        RuntimeError
+            Worker has to be initialised before receiving jobs.
+
         """
         if self.model is None:
             raise RuntimeError("worker must be initialized before receiving jobs")
@@ -79,6 +109,14 @@ def requestjob(self):
 
     @utils.synchronous('lock_update')
     def processjob(self, job):
+        """Incrementally processes the job and potentially logs progress.
+
+        Parameters
+        ----------
+        job : {iterable of list of (int, float), scipy.sparse.csc}
+            Stream of document vectors or sparse matrix of shape (`num_terms`, `num_documents`).
+
+        """
         logger.debug("starting to process job #%i", self.jobsdone)
         self.model.do_estep(job)
         self.jobsdone += 1
@@ -89,11 +127,20 @@ def processjob(self, job):
 
     @Pyro4.expose
     def ping(self):
+        """Test the connectivity with Worker."""
         return True
 
     @Pyro4.expose
     @utils.synchronous('lock_update')
     def getstate(self):
+        """Log and get the LDA model's current state.
+
+        Returns
+        -------
+        result : :obj: of `~gensim.models.ldamodel.LdaState`
+            The current state.
+
+        """
         logger.info("worker #%i returning its state after %s jobs", self.myid, self.jobsdone)
         result = self.model.state
         assert isinstance(result, ldamodel.LdaState)
@@ -104,6 +151,14 @@ def getstate(self):
     @Pyro4.expose
     @utils.synchronous('lock_update')
     def reset(self, state):
+        """Reset the worker by setting sufficient stats to 0.
+
+        Parameters
+        ----------
+        state : :obj: of :class:`~gensim.models.ldamodel.LdaState`
+            Encapsulates information for distributed computation of LdaModel objects.
+
+        """
         assert state is not None
         logger.info("resetting worker #%i", self.myid)
         self.model.state = state
@@ -113,11 +168,13 @@ def reset(self, state):
 
     @Pyro4.oneway
     def exit(self):
+        """Terminate the worker."""
         logger.info("terminating worker #%i", self.myid)
         os._exit(0)
 
 
 def main():
+    """Set up argument parser,logger and launches pyro daemon."""
     parser = argparse.ArgumentParser(description=__doc__)
     parser.add_argument("--host", help="Nameserver hostname (default: %(default)s)", default=None)
     parser.add_argument("--port", help="Nameserver port (default: %(default)s)", default=None, type=int)
@@ -146,4 +203,4 @@ def main():
 
 
 if __name__ == '__main__':
-    main()
+    main()