diff --git a/docs/notebooks/sklearn_wrapper.ipynb b/docs/notebooks/sklearn_wrapper.ipynb
index e98047dedc..cc5e85d3a2 100644
--- a/docs/notebooks/sklearn_wrapper.ipynb
+++ b/docs/notebooks/sklearn_wrapper.ipynb
@@ -65,15 +65,17 @@
    "outputs": [],
    "source": [
     "from gensim.corpora import Dictionary\n",
-    "texts = [['complier', 'system', 'computer'],\n",
-    " ['eulerian', 'node', 'cycle', 'graph', 'tree', 'path'],\n",
-    " ['graph', 'flow', 'network', 'graph'],\n",
-    " ['loading', 'computer', 'system'],\n",
-    " ['user', 'server', 'system'],\n",
-    " ['tree','hamiltonian'],\n",
-    " ['graph', 'trees'],\n",
-    " ['computer', 'kernel', 'malfunction','computer'],\n",
-    " ['server','system','computer']]\n",
+    "texts = [\n",
+    "    ['complier', 'system', 'computer'],\n",
+    "    ['eulerian', 'node', 'cycle', 'graph', 'tree', 'path'],\n",
+    "    ['graph', 'flow', 'network', 'graph'],\n",
+    "    ['loading', 'computer', 'system'],\n",
+    "    ['user', 'server', 'system'],\n",
+    "    ['tree', 'hamiltonian'],\n",
+    "    ['graph', 'trees'],\n",
+    "    ['computer', 'kernel', 'malfunction', 'computer'],\n",
+    "    ['server', 'system', 'computer']\n",
+    "]\n",
     "dictionary = Dictionary(texts)\n",
     "corpus = [dictionary.doc2bow(text) for text in texts]"
    ]
@@ -119,7 +121,7 @@
     }
    ],
    "source": [
-    "model=SklearnWrapperLdaModel(num_topics=2,id2word=dictionary,iterations=20, random_state=1)\n",
+    "model=SklearnWrapperLdaModel(num_topics=2, id2word=dictionary, iterations=20, random_state=1)\n",
     "model.fit(corpus)\n",
     "model.print_topics(2)\n",
     "model.transform(corpus)"
@@ -167,9 +169,7 @@
    "source": [
     "rand = np.random.mtrand.RandomState(1) # set seed for getting same result\n",
     "cats = ['rec.sport.baseball', 'sci.crypt']\n",
-    "data = fetch_20newsgroups(subset='train',\n",
-    "                        categories=cats,\n",
-    "                        shuffle=True)"
+    "data = fetch_20newsgroups(subset='train', categories=cats, shuffle=True)"
    ]
   },
   {
@@ -190,9 +190,9 @@
     "vec = CountVectorizer(min_df=10, stop_words='english')\n",
     "\n",
     "X = vec.fit_transform(data.data)\n",
-    "vocab = vec.get_feature_names() #vocab to be converted to id2word \n",
+    "vocab = vec.get_feature_names()  # vocab to be converted to id2word \n",
     "\n",
-    "id2word=dict([(i, s) for i, s in enumerate(vocab)])"
+    "id2word = dict([(i, s) for i, s in enumerate(vocab)])"
    ]
   },
   {
@@ -230,8 +230,8 @@
     }
    ],
    "source": [
-    "obj=SklearnWrapperLdaModel(id2word=id2word,num_topics=5,passes=20)\n",
-    "lda=obj.fit(X)\n",
+    "obj = SklearnWrapperLdaModel(id2word=id2word, num_topics=5, passes=20)\n",
+    "lda = obj.fit(X)\n",
     "lda.print_topics()"
    ]
   },
@@ -264,7 +264,7 @@
    },
    "outputs": [],
    "source": [
-    "def scorer(estimator, X,y=None):\n",
+    "def scorer(estimator, X, y=None):\n",
     "    goodcm = CoherenceModel(model=estimator, texts= texts, dictionary=estimator.id2word, coherence='c_v')\n",
     "    return goodcm.get_coherence()"
    ]
@@ -297,8 +297,8 @@
     }
    ],
    "source": [
-    "obj=SklearnWrapperLdaModel(id2word=dictionary,num_topics=5,passes=20)\n",
-    "parameters = {'num_topics':(2, 3, 5, 10), 'iterations':(1,20,50)}\n",
+    "obj = SklearnWrapperLdaModel(id2word=dictionary, num_topics=5, passes=20)\n",
+    "parameters = {'num_topics': (2, 3, 5, 10), 'iterations': (1, 20, 50)}\n",
     "model = GridSearchCV(obj, parameters, scoring=scorer, cv=5)\n",
     "model.fit(corpus)"
    ]
@@ -342,12 +342,14 @@
    "source": [
     "from sklearn.pipeline import Pipeline\n",
     "from sklearn import linear_model\n",
+    "\n",
+    "\n",
     "def print_features_pipe(clf, vocab, n=10):\n",
     "    ''' Better printing for sorted list '''\n",
     "    coef = clf.named_steps['classifier'].coef_[0]\n",
     "    print coef\n",
     "    print 'Positive features: %s' % (' '.join(['%s:%.2f' % (vocab[j], coef[j]) for j in np.argsort(coef)[::-1][:n] if coef[j] > 0]))\n",
-    "    print 'Negative features: %s' % (' '.join(['%s:%.2f' % (vocab[j], coef[j]) for j in np.argsort(coef)[:n] if coef[j] < 0]))\n"
+    "    print 'Negative features: %s' % (' '.join(['%s:%.2f' % (vocab[j], coef[j]) for j in np.argsort(coef)[:n] if coef[j] < 0]))"
    ]
   },
   {
@@ -358,7 +360,7 @@
    },
    "outputs": [],
    "source": [
-    "id2word=Dictionary(map(lambda x : x.split(),data.data))\n",
+    "id2word = Dictionary([_.split() for _ in data.data])\n",
     "corpus = [id2word.doc2bow(i.split()) for i in data.data]"
    ]
   },
@@ -391,8 +393,8 @@
     }
    ],
    "source": [
-    "model=SklearnWrapperLdaModel(num_topics=15,id2word=id2word,iterations=50, random_state=37)\n",
-    "clf=linear_model.LogisticRegression(penalty='l2', C=0.1) #l2 penalty used\n",
+    "model = SklearnWrapperLdaModel(num_topics=15, id2word=id2word, iterations=50, random_state=37)\n",
+    "clf = linear_model.LogisticRegression(penalty='l2', C=0.1)  # l2 penalty used\n",
     "pipe = Pipeline((('features', model,), ('classifier', clf)))\n",
     "pipe.fit(corpus, data.target)\n",
     "print_features_pipe(pipe, id2word.values())\n",
@@ -452,22 +454,13 @@
     }
    ],
    "source": [
-    "model=SklearnWrapperLsiModel(num_topics=15, id2word=id2word)\n",
-    "clf=linear_model.LogisticRegression(penalty='l2', C=0.1) #l2 penalty used\n",
+    "model = SklearnWrapperLsiModel(num_topics=15, id2word=id2word)\n",
+    "clf = linear_model.LogisticRegression(penalty='l2', C=0.1)  # l2 penalty used\n",
     "pipe = Pipeline((('features', model,), ('classifier', clf)))\n",
     "pipe.fit(corpus, data.target)\n",
     "print_features_pipe(pipe, id2word.values())\n",
     "print pipe.score(corpus, data.target)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
diff --git a/docs/notebooks/word2vec.ipynb b/docs/notebooks/word2vec.ipynb
index 4afe8f4134..61679cea4f 100644
--- a/docs/notebooks/word2vec.ipynb
+++ b/docs/notebooks/word2vec.ipynb
@@ -785,7 +785,7 @@
     }
    ],
    "source": [
-    "model.evaluate_word_pairs(test_data_dir +'wordsim353.tsv')"
+    "model.evaluate_word_pairs(test_data_dir + 'wordsim353.tsv')"
    ]
   },
   {
@@ -907,8 +907,7 @@
    ],
    "source": [
     "model = gensim.models.Word2Vec.load(temp_path)\n",
-    "more_sentences = [['Advanced', 'users', 'can', 'load', 'a', 'model', 'and', 'continue', \n",
-    "                  'training', 'it', 'with', 'more', 'sentences']]\n",
+    "more_sentences = [['Advanced', 'users', 'can', 'load', 'a', 'model', 'and', 'continue', 'training', 'it', 'with', 'more', 'sentences']]\n",
     "model.build_vocab(more_sentences, update=True)\n",
     "model.train(more_sentences, total_examples=model.corpus_count, epochs=model.iter)\n",
     "\n",
@@ -1023,7 +1022,7 @@
     }
    ],
    "source": [
-    "print(model.predict_output_word(['emergency','beacon','received']))"
+    "print(model.predict_output_word(['emergency', 'beacon', 'received']))"
    ]
   },
   {
diff --git a/gensim/corpora/dictionary.py b/gensim/corpora/dictionary.py
index 484684c26d..1ff89a5b31 100644
--- a/gensim/corpora/dictionary.py
+++ b/gensim/corpora/dictionary.py
@@ -194,9 +194,11 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000, keep_tokens=N
         # determine which tokens to keep
         if keep_tokens:
             keep_ids = [self.token2id[v] for v in keep_tokens if v in self.token2id]
-            good_ids =  (v for v in itervalues(self.token2id) 
-                         if no_below <= self.dfs.get(v, 0) <= no_above_abs 
-                         or v in keep_ids)
+            good_ids = (
+                v for v in itervalues(self.token2id)
+                if no_below <= self.dfs.get(v, 0) <= no_above_abs
+                or v in keep_ids
+            )
         else:
             good_ids = (
                 v for v in itervalues(self.token2id)
diff --git a/gensim/matutils.py b/gensim/matutils.py
index fbfa383a34..057e65a52f 100644
--- a/gensim/matutils.py
+++ b/gensim/matutils.py
@@ -532,8 +532,17 @@ def jaccard(vec1, vec2):
         return 1 - float(len(intersection)) / float(len(union))
 
 
-def jaccard_set(set1, set2):
-    return 1. - float(len(set1 & set2)) / float(len(set1 | set2))
+def jaccard_distance(set1, set2):
+    """
+    Calculate a distance between set representation (1 minus the intersection divided by union).
+    Return a value in range <0, 1> where values closer to 0 mean smaller distance and thus higher similarity.
+    """
+
+    union_cardinality = len(set1 | set2)
+    if union_cardinality == 0:  # Both sets are empty
+        return 1.
+
+    return 1. - float(len(set1 & set2)) / float(union_cardinality)
 
 
 def dirichlet_expectation(alpha):
diff --git a/gensim/models/hdpmodel.py b/gensim/models/hdpmodel.py
index ee6035a449..6937d928d4 100755
--- a/gensim/models/hdpmodel.py
+++ b/gensim/models/hdpmodel.py
@@ -33,7 +33,9 @@
 
 from __future__ import with_statement
 
-import logging, time
+import logging
+import time
+import warnings
 import numpy as np
 from scipy.special import gammaln, psi  # gamma function utils
 
@@ -614,16 +616,14 @@ def show_topics(self, num_topics=10, num_words=10, log=False, formatted=True):
 
     def print_topic(self, topic_id, topn= None, num_words=None):
         if num_words is not None:  # deprecated num_words is used
-            logger.warning("The parameter num_words for print_topic() would be deprecated in the updated version.")
-            logger.warning("Please use topn instead.")
+            warnings.warn("The parameter num_words for print_topic() would be deprecated in the updated version. Please use topn instead.")
             topn = num_words
 
         return self.show_topic(topic_id, topn, formatted=True)
 
     def show_topic(self, topic_id, topn=20, log=False, formatted=False, num_words= None,):
         if num_words is not None:  # deprecated num_words is used
-            logger.warning("The parameter num_words for show_topic() would be deprecated in the updated version.")
-            logger.warning("Please use topn instead.")
+            warnings.warn("The parameter num_words for show_topic() would be deprecated in the updated version. Please use topn instead.")
             topn = num_words
 
         lambdak = list(self.data[topic_id, :])
diff --git a/gensim/models/ldamodel.py b/gensim/models/ldamodel.py
index d9ab324d51..77f7e68be9 100755
--- a/gensim/models/ldamodel.py
+++ b/gensim/models/ldamodel.py
@@ -39,7 +39,7 @@
 from gensim import interfaces, utils, matutils
 from gensim.matutils import dirichlet_expectation
 from gensim.models import basemodel
-from gensim.matutils import kullback_leibler, hellinger, jaccard_set
+from gensim.matutils import kullback_leibler, hellinger, jaccard_distance
 
 from itertools import chain
 from scipy.special import gammaln, psi  # gamma function utils
@@ -989,9 +989,11 @@ def diff(self, other, distance="kulback_leibler", num_words=100, n_ann_terms=10,
         >>> print(annotation) # get array with positive/negative words for each topic pair from `m1` and `m2`
         """
 
-        distances = {"kulback_leibler": kullback_leibler,
-                     "hellinger": hellinger,
-                     "jaccard": jaccard_set}
+        distances = {
+            "kulback_leibler": kullback_leibler,
+            "hellinger": hellinger,
+            "jaccard": jaccard_distance,
+        }
 
         if distance not in distances:
             valid_keys = ", ".join("`{}`".format(x) for x in distances.keys())
@@ -1019,7 +1021,7 @@ def diff(self, other, distance="kulback_leibler", num_words=100, n_ann_terms=10,
             if np.abs(np.max(z)) > 1e-8:
                 z /= np.max(z)
 
-        annotation = [[None for _ in range(t1_size)] for _ in range(t2_size)]
+        annotation = [[None] * t1_size for _ in range(t2_size)]
 
         for topic1 in range(t1_size):
             for topic2 in range(t2_size):
@@ -1118,7 +1120,7 @@ def load(cls, fname, *args, **kwargs):
         kwargs['mmap'] = kwargs.get('mmap', None)
         result = super(LdaModel, cls).load(fname, *args, **kwargs)
 
-        # check if `random_state` attribute has been set after main pickel load
+        # check if `random_state` attribute has been set after main pickle load
         # if set -> the model to be loaded was saved using a >= 0.13.2 version of Gensim
         # if not set -> the model to be loaded was saved using a < 0.13.2 version of Gensim, so set `random_state` as the default value
         if not hasattr(result, 'random_state'):
@@ -1134,7 +1136,7 @@ def load(cls, fname, *args, **kwargs):
         id2word_fname = utils.smart_extension(fname, '.id2word')
         # check if `id2word_fname` file is present on disk
         # if present -> the model to be loaded was saved using a >= 0.13.2 version of Gensim, so set `result.id2word` using the `id2word_fname` file
-        # if not present -> the model to be loaded was saved using a < 0.13.2 version of Gensim, so `result.id2word` already set after the main pickel load
+        # if not present -> the model to be loaded was saved using a < 0.13.2 version of Gensim, so `result.id2word` already set after the main pickle load
         if (os.path.isfile(id2word_fname)):
             try:
                 result.id2word = utils.unpickle(id2word_fname)
diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py
index aaa15660a1..85aeefe173 100644
--- a/gensim/models/word2vec.py
+++ b/gensim/models/word2vec.py
@@ -205,7 +205,6 @@ def score_sentence_sg(model, sentence, work=None):
         will use the optimized version from word2vec_inner instead.
 
         """
-
         log_prob_sentence = 0.0
         if model.negative:
             raise RuntimeError("scoring is only available for HS=True")
@@ -483,7 +482,6 @@ def __init__(
                 logger.warning("The rule, if given, is only used to prune vocabulary during build_vocab() and is not stored as part of the model. ")
                 logger.warning("Model initialized without sentences. trim_rule provided, if any, will be ignored." )
 
-
     def initialize_word_vectors(self):
         self.wv = KeyedVectors()
 
@@ -1208,7 +1206,6 @@ def most_similar(self, positive=[], negative=[], topn=10, restrict_vocab=None, i
         Deprecated. Use self.wv.most_similar() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.most_similar`
         """
-
         return self.wv.most_similar(positive, negative, topn, restrict_vocab, indexer)
 
     def wmdistance(self, document1, document2):
@@ -1216,7 +1213,6 @@ def wmdistance(self, document1, document2):
         Deprecated. Use self.wv.wmdistance() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.wmdistance`
         """
-
         return self.wv.wmdistance(document1, document2)
 
     def most_similar_cosmul(self, positive=[], negative=[], topn=10):
@@ -1224,7 +1220,6 @@ def most_similar_cosmul(self, positive=[], negative=[], topn=10):
         Deprecated. Use self.wv.most_similar_cosmul() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.most_similar_cosmul`
         """
-
         return self.wv.most_similar_cosmul(positive, negative, topn)
 
     def similar_by_word(self, word, topn=10, restrict_vocab=None):
@@ -1232,7 +1227,6 @@ def similar_by_word(self, word, topn=10, restrict_vocab=None):
         Deprecated. Use self.wv.similar_by_word() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.similar_by_word`
         """
-
         return self.wv.similar_by_word(word, topn, restrict_vocab)
 
     def similar_by_vector(self, vector, topn=10, restrict_vocab=None):
@@ -1240,7 +1234,6 @@ def similar_by_vector(self, vector, topn=10, restrict_vocab=None):
         Deprecated. Use self.wv.similar_by_vector() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.similar_by_vector`
         """
-
         return self.wv.similar_by_vector(vector, topn, restrict_vocab)
 
     def doesnt_match(self, words):
@@ -1248,7 +1241,6 @@ def doesnt_match(self, words):
         Deprecated. Use self.wv.doesnt_match() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.doesnt_match`
         """
-
         return self.wv.doesnt_match(words)
 
     def __getitem__(self, words):
@@ -1256,7 +1248,6 @@ def __getitem__(self, words):
         Deprecated. Use self.wv.__getitem__() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.__getitem__`
         """
-
         return self.wv.__getitem__(words)
 
     def __contains__(self, word):
@@ -1264,7 +1255,6 @@ def __contains__(self, word):
         Deprecated. Use self.wv.__contains__() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.__contains__`
         """
-
         return self.wv.__contains__(word)
 
     def similarity(self, w1, w2):
@@ -1272,7 +1262,6 @@ def similarity(self, w1, w2):
         Deprecated. Use self.wv.similarity() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.similarity`
         """
-
         return self.wv.similarity(w1, w2)
 
     def n_similarity(self, ws1, ws2):
@@ -1280,7 +1269,6 @@ def n_similarity(self, ws1, ws2):
         Deprecated. Use self.wv.n_similarity() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.n_similarity`
         """
-
         return self.wv.n_similarity(ws1, ws2)
 
     def predict_output_word(self, context_words_list, topn=10):
@@ -1347,7 +1335,6 @@ def log_evaluate_word_pairs(pearson, spearman, oov, pairs):
         Deprecated. Use self.wv.log_evaluate_word_pairs() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.log_evaluate_word_pairs`
         """
-
         return KeyedVectors.log_evaluate_word_pairs(pearson, spearman, oov, pairs)
 
     def evaluate_word_pairs(self, pairs, delimiter='\t', restrict_vocab=300000, case_insensitive=True, dummy4unknown=False):
@@ -1355,7 +1342,6 @@ def evaluate_word_pairs(self, pairs, delimiter='\t', restrict_vocab=300000, case
         Deprecated. Use self.wv.evaluate_word_pairs() instead.
         Refer to the documentation for `gensim.models.KeyedVectors.evaluate_word_pairs`
         """
-
         return self.wv.evaluate_word_pairs(pairs, delimiter, restrict_vocab, case_insensitive, dummy4unknown)
 
     def __str__(self):
diff --git a/gensim/models/wrappers/dtmmodel.py b/gensim/models/wrappers/dtmmodel.py
index 54356812c7..94a2e5eb1a 100644
--- a/gensim/models/wrappers/dtmmodel.py
+++ b/gensim/models/wrappers/dtmmodel.py
@@ -22,6 +22,7 @@
 
 import logging
 import random
+import warnings
 import tempfile
 import os
 from subprocess import PIPE
@@ -93,7 +94,7 @@ def __init__(
             lencorpus = sum(1 for _ in corpus)
         if lencorpus == 0:
             raise ValueError("cannot compute DTM over an empty corpus")
-        if model == "fixed" and any([i == 0 for i in [len(text) for text in corpus]]):
+        if model == "fixed" and any(not text for text in corpus):
             raise ValueError("""There is a text without words in the input corpus.
                     This breaks method='fixed' (The DIM model).""")
         if lencorpus != sum(time_slices):
@@ -308,8 +309,7 @@ def show_topic(self, topicid, time, topn=50, num_words=None):
     def print_topic(self, topicid, time, topn=10, num_words=None):
         """Return the given topic, formatted as a string."""
         if num_words is not None:  # deprecated num_words is used
-            logger.warning("The parameter num_words for print_topic(() would be deprecated in the updated version.")
-            logger.warning("Please use topn instead.")
+            warnings.warn("The parameter num_words for print_topic() would be deprecated in the updated version. Please use topn instead.")
             topn = num_words
 
         return ' + '.join(['%.3f*%s' % v for v in self.show_topic(topicid, time, topn)])
diff --git a/gensim/models/wrappers/ldamallet.py b/gensim/models/wrappers/ldamallet.py
index d97a51e501..640cf11dd8 100644
--- a/gensim/models/wrappers/ldamallet.py
+++ b/gensim/models/wrappers/ldamallet.py
@@ -43,7 +43,7 @@
 from smart_open import smart_open
 
 from gensim import utils, matutils
-from gensim.utils import check_output
+from gensim.utils import check_output, revdict
 from gensim.models.ldamodel import LdaModel
 from gensim.models import basemodel
 
@@ -190,7 +190,7 @@ def load_word_topics(self):
         if hasattr(self.id2word, 'token2id'):
             word2id = self.id2word.token2id
         else:
-            word2id = dict((v, k) for k, v in iteritems(dict(self.id2word)))
+            word2id = revdict(self.id2word)
 
         with utils.smart_open(self.fstate()) as fin:
             _ = next(fin)  # header
diff --git a/gensim/models/wrappers/wordrank.py b/gensim/models/wrappers/wordrank.py
index 7620093e37..efeb020199 100644
--- a/gensim/models/wrappers/wordrank.py
+++ b/gensim/models/wrappers/wordrank.py
@@ -52,7 +52,7 @@ def train(cls, wr_path, corpus_file, out_name, size=100, window=15, symmetric=1,
         `wr_path` is the path to the Wordrank directory.
         `corpus_file` is the filename of the text file to be used for training the Wordrank model.
         Expects file to contain space-separated tokens in a single line
-        `out_name` is name of the directory which will be created(in wordrank folder) to save embeddings and training data.
+        `out_name` is name of the directory which will be created (in wordrank folder) to save embeddings and training data.
         `size` is the dimensionality of the feature vectors.
         `window` is the number of context words to the left (and to the right, if symmetric = 1).
         `symmetric` if 0, only use left context words, else use left and right both.
@@ -98,13 +98,13 @@ def train(cls, wr_path, corpus_file, out_name, size=100, window=15, symmetric=1,
         input_fnames = [corpus_file.split('/')[-1], corpus_file.split('/')[-1], cooccurrence_file]
         output_fnames = [temp_vocab_file, cooccurrence_file, cooccurrence_shuf_file]
 
-        logger.info("Prepare training data using glove code")
+        logger.info("Prepare training data (%s) using glove code", ", ".join(input_fnames))
         for command, input_fname, output_fname in zip(commands, input_fnames, output_fnames):
             with smart_open(input_fname, 'rb') as r:
                 with smart_open(output_fname, 'wb') as w:
                     utils.check_output(w, args=command, stdin=r)
 
-        logger.info("Delete frequencies from vocab file")
+        logger.info("Deleting frequencies from vocab file")
         with smart_open(vocab_file, 'wb') as w:
             utils.check_output(w, args=cmd_del_vocab_freq)
 
diff --git a/gensim/sklearn_integration/sklearn_wrapper_gensim_ldamodel.py b/gensim/sklearn_integration/sklearn_wrapper_gensim_ldamodel.py
index 003d313e6d..3eae9d0265 100644
--- a/gensim/sklearn_integration/sklearn_wrapper_gensim_ldamodel.py
+++ b/gensim/sklearn_integration/sklearn_wrapper_gensim_ldamodel.py
@@ -16,8 +16,6 @@
 from sklearn.base import TransformerMixin, BaseEstimator
 
 
-
-
 class SklearnWrapperLdaModel(models.LdaModel, TransformerMixin, BaseEstimator):
     """
     Base LDA module
@@ -68,7 +66,6 @@ def get_params(self, deep=True):
                 "gamma_threshold": self.gamma_threshold, "minimum_probability": self.minimum_probability,
                 "random_state": self.random_state}
 
-
     def set_params(self, **parameters):
         """
         Set all parameters.
@@ -81,7 +78,7 @@ def fit(self, X,  y=None):
         """
         For fitting corpus into the class object.
         Calls gensim.model.LdaModel:
-        >>>gensim.models.LdaModel(corpus=corpus,num_topics=num_topics,id2word=id2word,passes=passes,update_every=update_every,alpha=alpha,iterations=iterations,eta=eta,random_state=random_state)
+        >>> gensim.models.LdaModel(corpus=corpus, num_topics=num_topics, id2word=id2word, passes=passes, update_every=update_every, alpha=alpha, iterations=iterations, eta=eta, random_state=random_state)
         """
         if sparse.issparse(X):
             self.corpus = matutils.Sparse2Corpus(X)
@@ -106,16 +103,15 @@ def transform(self, docs, minimum_probability=None):
         # The input as array of array
         check = lambda x: [x] if isinstance(x[0], tuple) else x
         docs = check(docs)
-        X = [[] for i in range(0,len(docs))];
-        for k,v in enumerate(docs):
+        X = [[] for _ in range(0, len(docs))]
 
+        for k, v in enumerate(docs):
             doc_topics = self.get_document_topics(v, minimum_probability=minimum_probability)
             probs_docs = list(map(lambda x: x[1], doc_topics))
             # Everything should be equal in length
             if len(probs_docs) != self.num_topics:
                 probs_docs.extend([1e-12]*(self.num_topics - len(probs_docs)))
             X[k] = probs_docs
-            probs_docs = []
         return np.reshape(np.array(X), (len(docs), self.num_topics))
 
     def get_topic_dist(self, bow, minimum_probability=None, minimum_phi_value=None, per_word_topics=False):
@@ -134,4 +130,4 @@ def partial_fit(self, X):
         if sparse.issparse(X):
             X = matutils.Sparse2Corpus(X)
 
-        self.update(corpus=X)
\ No newline at end of file
+        self.update(corpus=X)
diff --git a/gensim/test/test_sklearn_integration.py b/gensim/test/test_sklearn_integration.py
index 6eb5db2776..cb6c514612 100644
--- a/gensim/test/test_sklearn_integration.py
+++ b/gensim/test/test_sklearn_integration.py
@@ -11,7 +11,7 @@
     from sklearn.feature_extraction.text import CountVectorizer
     from sklearn.datasets import load_files
     from sklearn import linear_model
-except:
+except ImportError:
     raise unittest.SkipTest("Test requires scikit-learn to be installed, which is not available")
 
 from gensim.sklearn_integration.sklearn_wrapper_gensim_ldamodel import SklearnWrapperLdaModel
@@ -19,18 +19,20 @@
 from gensim.corpora import Dictionary
 from gensim import matutils
 
-module_path = os.path.dirname(__file__) # needed because sample data files are located in the same folder
+module_path = os.path.dirname(__file__)  # needed because sample data files are located in the same folder
 datapath = lambda fname: os.path.join(module_path, 'test_data', fname)
 
-texts = [['complier', 'system', 'computer'],
-         ['eulerian', 'node', 'cycle', 'graph', 'tree', 'path'],
-         ['graph', 'flow', 'network', 'graph'],
-         ['loading', 'computer', 'system'],
-         ['user', 'server', 'system'],
-         ['tree', 'hamiltonian'],
-         ['graph', 'trees'],
-         ['computer', 'kernel', 'malfunction', 'computer'],
-         ['server', 'system', 'computer']]
+texts = [
+    ['complier', 'system', 'computer'],
+    ['eulerian', 'node', 'cycle', 'graph', 'tree', 'path'],
+    ['graph', 'flow', 'network', 'graph'],
+    ['loading', 'computer', 'system'],
+    ['user', 'server', 'system'],
+    ['tree', 'hamiltonian'],
+    ['graph', 'trees'],
+    ['computer', 'kernel', 'malfunction', 'computer'],
+    ['server', 'system', 'computer'],
+]
 dictionary = Dictionary(texts)
 corpus = [dictionary.doc2bow(text) for text in texts]
 
@@ -48,49 +50,49 @@ def testPrintTopic(self):
             self.assertTrue(isinstance(k, int))
 
     def testTransform(self):
-        texts_new = ['graph','eulerian']
+        texts_new = ['graph', 'eulerian']
         bow = self.model.id2word.doc2bow(texts_new)
-        X = self.model.transform(bow)
-        self.assertTrue(X.shape[0], 1)
-        self.assertTrue(X.shape[1], self.model.num_topics)
-        texts_new = [['graph','eulerian'],['server', 'flow'], ['path', 'system']]
+        matrix = self.model.transform(bow)
+        self.assertTrue(matrix.shape[0], 1)
+        self.assertTrue(matrix.shape[1], self.model.num_topics)
+        texts_new = [['graph', 'eulerian'], ['server', 'flow'], ['path', 'system']]
         bow = []
         for i in texts_new:
             bow.append(self.model.id2word.doc2bow(i))
-        X = self.model.transform(bow)
-        self.assertTrue(X.shape[0], 3)
-        self.assertTrue(X.shape[1], self.model.num_topics)
+        matrix = self.model.transform(bow)
+        self.assertTrue(matrix.shape[0], 3)
+        self.assertTrue(matrix.shape[1], self.model.num_topics)
 
     def testGetTopicDist(self):
-        texts_new = ['graph','eulerian']
+        texts_new = ['graph', 'eulerian']
         bow = self.model.id2word.doc2bow(texts_new)
-        doc_topics, word_topics, phi_values = self.model.get_topic_dist(bow,per_word_topics=True)
+        doc_topics, word_topics, phi_values = self.model.get_topic_dist(bow, per_word_topics=True)
 
-        for k,v in word_topics:
+        for k, v in word_topics:
             self.assertTrue(isinstance(v, list))
             self.assertTrue(isinstance(k, int))
-        for k,v in doc_topics:
+        for k, v in doc_topics:
             self.assertTrue(isinstance(v, float))
             self.assertTrue(isinstance(k, int))
-        for k,v in phi_values:
+        for k, v in phi_values:
             self.assertTrue(isinstance(v, list))
             self.assertTrue(isinstance(k, int))
 
     def testPartialFit(self):
         for i in range(10):
             self.model.partial_fit(X=corpus)  # fit against the model again
-            doc=list(corpus)[0]  # transform only the first document
+            doc = list(corpus)[0]  # transform only the first document
             transformed = self.model[doc]
             transformed_approx = matutils.sparse2full(transformed, 2)  # better approximation
-        expected=[0.13, 0.87]
+        expected = [0.13, 0.87]
         passed = numpy.allclose(sorted(transformed_approx), sorted(expected), atol=1e-1)
         self.assertTrue(passed)
 
     def testCSRMatrixConversion(self):
-        Arr = numpy.array([[1, 2, 0], [0, 0, 3], [1, 0, 0]])
-        sArr = sparse.csr_matrix(Arr)
+        arr = numpy.array([[1, 2, 0], [0, 0, 3], [1, 0, 0]])
+        sarr = sparse.csr_matrix(arr)
         newmodel = SklearnWrapperLdaModel(num_topics=2, passes=100)
-        newmodel.fit(sArr)
+        newmodel.fit(sarr)
         topic = newmodel.print_topics()
         for k, v in topic:
             self.assertTrue(isinstance(v, six.string_types))
@@ -98,20 +100,21 @@ def testCSRMatrixConversion(self):
 
     def testPipeline(self):
         model = SklearnWrapperLdaModel(num_topics=2, passes=10, minimum_probability=0, random_state=numpy.random.seed(0))
-        with open(datapath('mini_newsgroup'),'rb') as f:
+        with open(datapath('mini_newsgroup'), 'rb') as f:
             compressed_content = f.read()
             uncompressed_content = codecs.decode(compressed_content, 'zlib_codec')
             cache = pickle.loads(uncompressed_content)
         data = cache
-        id2word=Dictionary(map(lambda x : x.split(), data.data))
+        id2word = Dictionary(map(lambda x: x.split(), data.data))
         corpus = [id2word.doc2bow(i.split()) for i in data.data]
-        rand = numpy.random.mtrand.RandomState(1) # set seed for getting same result
-        clf=linear_model.LogisticRegression(penalty='l2', C=0.1)
+        numpy.random.mtrand.RandomState(1)  # set seed for getting same result
+        clf = linear_model.LogisticRegression(penalty='l2', C=0.1)
         text_lda = Pipeline((('features', model,), ('classifier', clf)))
         text_lda.fit(corpus, data.target)
         score = text_lda.score(corpus, data.target)
         self.assertGreater(score, 0.40)
 
+
 class TestSklearnLSIWrapper(unittest.TestCase):
     def setUp(self):
         self.model = SklearnWrapperLsiModel(id2word=dictionary, num_topics=2)
@@ -124,39 +127,39 @@ def testModelSanity(self):
             self.assertTrue(isinstance(k, int))
 
     def testTransform(self):
-        texts_new = ['graph','eulerian']
+        texts_new = ['graph', 'eulerian']
         bow = self.model.id2word.doc2bow(texts_new)
-        X = self.model.transform(bow)
-        self.assertTrue(X.shape[0], 1)
-        self.assertTrue(X.shape[1], self.model.num_topics)
-        texts_new = [['graph','eulerian'],['server', 'flow'], ['path', 'system']]
+        matrix = self.model.transform(bow)
+        self.assertTrue(matrix.shape[0], 1)
+        self.assertTrue(matrix.shape[1], self.model.num_topics)
+        texts_new = [['graph', 'eulerian'], ['server', 'flow'], ['path', 'system']]
         bow = []
         for i in texts_new:
             bow.append(self.model.id2word.doc2bow(i))
-        X = self.model.transform(bow)
-        self.assertTrue(X.shape[0], 3)
-        self.assertTrue(X.shape[1], self.model.num_topics)
+        matrix = self.model.transform(bow)
+        self.assertTrue(matrix.shape[0], 3)
+        self.assertTrue(matrix.shape[1], self.model.num_topics)
 
     def testPartialFit(self):
         for i in range(10):
             self.model.partial_fit(X=corpus)  # fit against the model again
-            doc=list(corpus)[0]  # transform only the first document
+            doc = list(corpus)[0]  # transform only the first document
             transformed = self.model[doc]
             transformed_approx = matutils.sparse2full(transformed, 2)  # better approximation
-        expected=[1.39, 0.0]
+        expected = [1.39, 0.0]
         passed = numpy.allclose(sorted(transformed_approx), sorted(expected), atol=1e-1)
         self.assertTrue(passed)
 
     def testPipeline(self):
         model = SklearnWrapperLsiModel(num_topics=2)
-        with open(datapath('mini_newsgroup'),'rb') as f:
+        with open(datapath('mini_newsgroup'), 'rb') as f:
             compressed_content = f.read()
             uncompressed_content = codecs.decode(compressed_content, 'zlib_codec')
             cache = pickle.loads(uncompressed_content)
         data = cache
-        id2word=Dictionary(map(lambda x : x.split(), data.data))
+        id2word = Dictionary(map(lambda x: x.split(), data.data))
         corpus = [id2word.doc2bow(i.split()) for i in data.data]
-        clf=linear_model.LogisticRegression(penalty='l2', C=0.1)
+        clf = linear_model.LogisticRegression(penalty='l2', C=0.1)
         text_lda = Pipeline((('features', model,), ('classifier', clf)))
         text_lda.fit(corpus, data.target)
         score = text_lda.score(corpus, data.target)
diff --git a/gensim/test/test_tmdiff.py b/gensim/test/test_tmdiff.py
index 2a00f81b01..03a639e454 100644
--- a/gensim/test/test_tmdiff.py
+++ b/gensim/test/test_tmdiff.py
@@ -13,15 +13,17 @@
 
 class TestLdaDiff(unittest.TestCase):
     def setUp(self):
-        texts = [['human', 'interface', 'computer'],
-                 ['survey', 'user', 'computer', 'system', 'response', 'time'],
-                 ['eps', 'user', 'interface', 'system'],
-                 ['system', 'human', 'system', 'eps'],
-                 ['user', 'response', 'time'],
-                 ['trees'],
-                 ['graph', 'trees'],
-                 ['graph', 'minors', 'trees'],
-                 ['graph', 'minors', 'survey']]
+        texts = [
+            ['human', 'interface', 'computer'],
+            ['survey', 'user', 'computer', 'system', 'response', 'time'],
+            ['eps', 'user', 'interface', 'system'],
+            ['system', 'human', 'system', 'eps'],
+            ['user', 'response', 'time'],
+            ['trees'],
+            ['graph', 'trees'],
+            ['graph', 'minors', 'trees'],
+            ['graph', 'minors', 'survey'],
+        ]
         self.dictionary = Dictionary(texts)
         self.corpus = [self.dictionary.doc2bow(text) for text in texts]
         self.num_topics = 5
diff --git a/gensim/topic_coherence/probability_estimation.py b/gensim/topic_coherence/probability_estimation.py
index 8922c511a3..2d06d58d01 100644
--- a/gensim/topic_coherence/probability_estimation.py
+++ b/gensim/topic_coherence/probability_estimation.py
@@ -9,28 +9,28 @@
 """
 
 import logging
+from itertools import chain, islice
 import numpy as np
 
-from gensim.corpora import Dictionary
-
-from itertools import chain, islice
 
 logger = logging.getLogger(__name__)
 
+
 def _ret_top_ids(segmented_topics):
     """
     Helper function to return a set of all the unique topic ids in segmented topics.
     """
     top_ids = set()  # is a set of all the unique ids contained in topics.
     for s_i in segmented_topics:
-        for id in chain.from_iterable(s_i):
-            if isinstance(id, np.ndarray):
-                for i in id:
+        for t_id in chain.from_iterable(s_i):
+            if isinstance(t_id, np.ndarray):
+                for i in t_id:
                     top_ids.add(i)
             else:
-                top_ids.add(id)
+                top_ids.add(t_id)
     return top_ids
 
+
 def p_boolean_document(corpus, segmented_topics):
     """
     This function performs the boolean document probability estimation. Boolean document estimates the probability
@@ -49,17 +49,16 @@ def p_boolean_document(corpus, segmented_topics):
     top_ids = _ret_top_ids(segmented_topics)
     # Instantiate the dictionary with empty sets for each top_id
     per_topic_postings = {}
-    for id in top_ids:
-        per_topic_postings[id] = set()
+    for t_id in top_ids:
+        per_topic_postings[t_id] = set()
     # Iterate through the documents, appending the document number to the set for each top_id it contains
     for n, document in enumerate(corpus):
         doc_words = frozenset(x[0] for x in document)
-        top_ids_in_doc = top_ids.intersection(doc_words)
-        if len(top_ids_in_doc) > 0:
-            for id in top_ids_in_doc:
-                per_topic_postings[id].add(n)
+        for word_id in top_ids.intersection(doc_words):
+            per_topic_postings[word_id].add(n)
     num_docs = len(corpus)
-    return (per_topic_postings, num_docs)
+    return per_topic_postings, num_docs
+
 
 def p_boolean_sliding_window(texts, segmented_topics, dictionary, window_size):
     """
@@ -84,6 +83,7 @@ def p_boolean_sliding_window(texts, segmented_topics, dictionary, window_size):
     window_id = 0  # Each window assigned a window id.
     per_topic_postings = {}
     token2id_dict = dictionary.token2id
+
     def add_topic_posting(top_ids, window, per_topic_postings, window_id, token2id_dict):
         for word in window:
             word_id = token2id_dict[word]
@@ -91,9 +91,10 @@ def add_topic_posting(top_ids, window, per_topic_postings, window_id, token2id_d
                 if word_id in per_topic_postings:
                     per_topic_postings[word_id].add(window_id)
                 else:
-                    per_topic_postings[word_id] = set([window_id])
+                    per_topic_postings[word_id] = {window_id}
         window_id += 1
-        return (window_id, per_topic_postings)
+        return window_id, per_topic_postings
+
     # Apply boolean sliding window to each document in texts.
     for document in texts:
         it = iter(document)
diff --git a/gensim/utils.py b/gensim/utils.py
index 5fa91c5032..5884dc9234 100644
--- a/gensim/utils.py
+++ b/gensim/utils.py
@@ -943,7 +943,7 @@ def revdict(d):
     result (which one is kept is arbitrary).
 
     """
-    return dict((v, k) for (k, v) in iteritems(d))
+    return dict((v, k) for (k, v) in iteritems(dict(d)))
 
 
 def toptexts(query, texts, index, n=10):
@@ -1164,7 +1164,7 @@ def check_output(stdout=subprocess.PIPE, *popenargs, **kwargs):
     Added extra KeyboardInterrupt handling
     """
     try:
-        logger.debug("COMMAND: %s %s", str(popenargs), str(kwargs))
+        logger.debug("COMMAND: %s %s", popenargs, kwargs)
         process = subprocess.Popen(stdout=stdout, *popenargs, **kwargs)
         output, unused_err = process.communicate()
         retcode = process.poll()
diff --git a/setup.py b/setup.py
index 4b86cf78e2..2c8be1f896 100644
--- a/setup.py
+++ b/setup.py
@@ -226,11 +226,14 @@ def finalize_options(self):
 """
 
 
-test_env = ['testfixtures',
-            'unittest2',
-            'Morfessor==2.0.2a4',
-            'scikit-learn',
-            'pyemd']
+test_env = [
+    'testfixtures',
+    'unittest2',
+    'Morfessor==2.0.2a4',
+    'scikit-learn',
+    'pyemd',
+    'annoy',
+]
 
 setup(
     name='gensim',
@@ -287,7 +290,6 @@ def finalize_options(self):
         'scipy >= 0.7.0',
         'six >= 1.5.0',
         'smart_open >= 1.2.1',
-        'morfessor==2.0.2alpha4',
     ],
     tests_require=test_env,
     extras_require={