Remove mutable args. Fix 1561.

gensim/models/doc2vec.py

@@ -422,7 +422,7 @@ def init_sims(self, replace=False):
                     self.doctag_syn0norm = empty(self.doctag_syn0.shape, dtype=REAL)
                 np_divide(self.doctag_syn0, sqrt((self.doctag_syn0 ** 2).sum(-1))[..., newaxis], self.doctag_syn0norm)
 
-    def most_similar(self, positive=[], negative=[], topn=10, clip_start=0, clip_end=None, indexer=None):
+    def most_similar(self, positive=None, negative=None, topn=10, clip_start=0, clip_end=None, indexer=None):
         """
         Find the top-N most similar docvecs known from training. Positive docs contribute
         positively towards the similarity, negative docs negatively.
@@ -436,6 +436,11 @@ def most_similar(self, positive=[], negative=[], topn=10, clip_start=0, clip_end
         range of the underlying doctag_syn0norm vectors. (This may be useful if the ordering
         there was chosen to be significant, such as more popular tag IDs in lower indexes.)
         """
+        if positive is None:
+            positive = []
+        if negative is None:
+            negative = []
+
         self.init_sims()
         clip_end = clip_end or len(self.doctag_syn0norm)
 

gensim/models/keyedvectors.py

@@ -287,7 +287,7 @@ def word_vec(self, word, use_norm=False):
         else:
             raise KeyError("word '%s' not in vocabulary" % word)
 
-    def most_similar(self, positive=[], negative=[], topn=10, restrict_vocab=None, indexer=None):
+    def most_similar(self, positive=None, negative=None, topn=10, restrict_vocab=None, indexer=None):
         """
         Find the top-N most similar words. Positive words contribute positively towards the
         similarity, negative words negatively.
@@ -310,6 +310,11 @@ def most_similar(self, positive=[], negative=[], topn=10, restrict_vocab=None, i
           [('queen', 0.50882536), ...]
 
         """
+        if positive is None:
+            positive = []
+        if negative is None:
+            negative = []
+
         self.init_sims()
 
         if isinstance(positive, string_types) and not negative:
@@ -442,7 +447,7 @@ def nbow(document):
         # Compute WMD.
         return emd(d1, d2, distance_matrix)
 
-    def most_similar_cosmul(self, positive=[], negative=[], topn=10):
+    def most_similar_cosmul(self, positive=None, negative=None, topn=10):
         """
         Find the top-N most similar words, using the multiplicative combination objective
         proposed by Omer Levy and Yoav Goldberg in [4]_. Positive words still contribute
@@ -464,6 +469,11 @@ def most_similar_cosmul(self, positive=[], negative=[], topn=10):
         .. [4] Omer Levy and Yoav Goldberg. Linguistic Regularities in Sparse and Explicit Word Representations, 2014.
 
         """
+        if positive is None:
+            positive = []
+        if negative is None:
+            negative = []
+
         self.init_sims()
 
         if isinstance(positive, string_types) and not negative:

gensim/models/lda_dispatcher.py

@@ -56,14 +56,14 @@ class Dispatcher(object):
     There should never be more than one dispatcher running at any one time.
     """
 
-    def __init__(self, maxsize=MAX_JOBS_QUEUE, ns_conf={}):
+    def __init__(self, maxsize=MAX_JOBS_QUEUE, ns_conf=None):
         """
         Note that the constructor does not fully initialize the dispatcher;
         use the `initialize()` function to populate it with workers etc.
         """
         self.maxsize = maxsize
-        self.callback = None # a pyro proxy to this object (unknown at init time, but will be set later)
-        self.ns_conf = ns_conf
+        self.callback = None  # a pyro proxy to this object (unknown at init time, but will be set later)
+        self.ns_conf = ns_conf if ns_conf is not None else {}
 
     @Pyro4.expose
     def initialize(self, **model_params):

gensim/models/ldamodel.py

@@ -195,7 +195,7 @@ def __init__(self, corpus=None, num_topics=100, id2word=None,
                  distributed=False, chunksize=2000, passes=1, update_every=1,
                  alpha='symmetric', eta=None, decay=0.5, offset=1.0, eval_every=10,
                  iterations=50, gamma_threshold=0.001, minimum_probability=0.01,
-                 random_state=None, ns_conf={}, minimum_phi_value=0.01,
+                 random_state=None, ns_conf=None, minimum_phi_value=0.01,
                  per_word_topics=False, callbacks=None):
         """
         If given, start training from the iterable `corpus` straight away. If not given,
@@ -316,6 +316,9 @@ def __init__(self, corpus=None, num_topics=100, id2word=None,
             # set up distributed version
             try:
                 import Pyro4
+                if ns_conf is None:
+                    ns_conf = {}
+
                 with utils.getNS(**ns_conf) as ns:
                     from gensim.models.lda_dispatcher import LDA_DISPATCHER_PREFIX
                     self.dispatcher = Pyro4.Proxy(ns.list(prefix=LDA_DISPATCHER_PREFIX)[LDA_DISPATCHER_PREFIX])

gensim/models/word2vec.py

@@ -1231,7 +1231,7 @@ def intersect_word2vec_format(self, fname, lockf=0.0, binary=False, encoding='ut
                         self.syn0_lockf[self.wv.vocab[word].index] = lockf  # lock-factor: 0.0 stops further changes
         logger.info("merged %d vectors into %s matrix from %s" % (overlap_count, self.wv.syn0.shape, fname))
 
-    def most_similar(self, positive=[], negative=[], topn=10, restrict_vocab=None, indexer=None):
+    def most_similar(self, positive=None, negative=None, topn=10, restrict_vocab=None, indexer=None):
         """
         Deprecated. Use self.wv.most_similar() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.most_similar`
@@ -1245,7 +1245,7 @@ def wmdistance(self, document1, document2):
         """
         return self.wv.wmdistance(document1, document2)
 
-    def most_similar_cosmul(self, positive=[], negative=[], topn=10):
+    def most_similar_cosmul(self, positive=None, negative=None, topn=10):
         """
         Deprecated. Use self.wv.most_similar_cosmul() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.most_similar_cosmul`

gensim/summarization/graph.py

@@ -77,7 +77,7 @@ def add_node(self, node, attrs=None):
         pass
 
     @abstractmethod
-    def add_edge(self, edge, wt=1, label='', attrs=[]):
+    def add_edge(self, edge, wt=1, label='', attrs=None):
         """
         Add an edge to the graph connecting two nodes.
 
@@ -172,7 +172,9 @@ def neighbors(self, node):
     def has_node(self, node):
         return node in self.node_neighbors
 
-    def add_edge(self, edge, wt=1, label='', attrs=[]):
+    def add_edge(self, edge, wt=1, label='', attrs=None):
+        if attrs is None:
+            attrs = []
         u, v = edge
         if v not in self.node_neighbors[u] and u not in self.node_neighbors[v]:
             self.node_neighbors[u].append(v)

gensim/utils.py

@@ -1011,15 +1011,18 @@ def getNS(host=None, port=None, broadcast=True, hmac_key=None):
         raise RuntimeError("Pyro name server not found")
 
 
-def pyro_daemon(name, obj, random_suffix=False, ip=None, port=None, ns_conf={}):
+def pyro_daemon(name, obj, random_suffix=False, ip=None, port=None, ns_conf=None):
     """
     Register object with name server (starting the name server if not running
     yet) and block until the daemon is terminated. The object is registered under
     `name`, or `name`+ some random suffix if `random_suffix` is set.
 
     """
+    if ns_conf is None:
+        ns_conf = {}
     if random_suffix:
         name += '.' + hex(random.randint(0, 0xffffff))[2:]
+
     import Pyro4
     with getNS(**ns_conf) as ns:
         with Pyro4.Daemon(ip or get_my_ip(), port or 0) as daemon: