Add gensim-data repo to gensim.downloader & fix rendering of code …

…examples (#2327)
piskvorky · Jan 10, 2019 · a3dbdcc · a3dbdcc
1 parent 01f4ac8
commit a3dbdcc
Show file tree

Hide file tree

Showing 25 changed files with 23 additions and 39 deletions.
diff --git a/gensim/corpora/dictionary.py b/gensim/corpora/dictionary.py
@@ -231,7 +231,6 @@ def doc2bow(self, document, allow_update=False, return_missing=False):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import Dictionary
@@ -339,7 +338,6 @@ def filter_extremes(self, no_below=5, no_above=0.5, keep_n=100000, keep_tokens=N
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import Dictionary
@@ -392,7 +390,6 @@ def filter_n_most_frequent(self, remove_n):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import Dictionary
@@ -431,7 +428,6 @@ def filter_tokens(self, bad_ids=None, good_ids=None):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import Dictionary
@@ -556,7 +552,6 @@ def merge_with(self, other):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import Dictionary
@@ -612,7 +607,6 @@ def load_from_text(fname):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import Dictionary
@@ -677,7 +671,6 @@ def from_corpus(corpus, id2word=None):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import Dictionary

diff --git a/gensim/corpora/hashdictionary.py b/gensim/corpora/hashdictionary.py
@@ -173,7 +173,6 @@ def add_documents(self, documents):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import HashDictionary
@@ -331,7 +330,6 @@ def save_as_text(self, fname):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import HashDictionary

diff --git a/gensim/corpora/indexedcorpus.py b/gensim/corpora/indexedcorpus.py
@@ -93,7 +93,6 @@ def serialize(serializer, fname, corpus, id2word=None, index_fname=None,
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.corpora import MmCorpus

diff --git a/gensim/corpora/malletcorpus.py b/gensim/corpora/malletcorpus.py
@@ -115,7 +115,6 @@ def line2doc(self, line):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.test.utils import datapath

diff --git a/gensim/downloader.py b/gensim/downloader.py
@@ -1,6 +1,9 @@
 """
 This module is an API for downloading, getting information and loading datasets/models.
 
+See `RaRe-Technologies/gensim-data <https://github.com/RaRe-Technologies/gensim-data>`_ repo
+for more information about models/datasets/how-to-add-new/etc.
+
 Give information about available models/datasets:
 
 .. sourcecode:: pycon
@@ -12,6 +15,7 @@
 
 
 Model example:
+
 .. sourcecode:: pycon
 
     >>> import gensim.downloader as api
@@ -21,6 +25,7 @@
 
 
 Dataset example:
+
 .. sourcecode:: pycon
 
     >>> import gensim.downloader as api

diff --git a/gensim/models/atmodel.py b/gensim/models/atmodel.py
@@ -25,7 +25,6 @@
 
 Example
 -------
-
 .. sourcecode:: pycon
 
     >>> from gensim.models import AuthorTopicModel

diff --git a/gensim/models/callbacks.py b/gensim/models/callbacks.py
@@ -22,6 +22,7 @@
 To implement a Callback, inherit from this base class and override one or more of its methods.
 
 Create a callback to save the training model after each epoch
+
 .. sourcecode:: pycon
 
     >>> from gensim.test.utils import get_tmpfile

diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py
@@ -24,6 +24,7 @@
 --------------
 
 Initialize and train a model:
+
 .. sourcecode:: pycon
 
     >>> from gensim.test.utils import common_texts

diff --git a/gensim/models/keyedvectors.py b/gensim/models/keyedvectors.py
@@ -66,6 +66,7 @@
     >>> word_vectors = model.wv
 
 Persist the word vectors to disk with
+
 .. sourcecode:: pycon
 
     >>> from gensim.test.utils import get_tmpfile
@@ -90,6 +91,7 @@
 
 You can perform various syntactic/semantic NLP word tasks with the trained vectors.
 Some of them are already built-in
+
 .. sourcecode:: pycon
 
     >>> import gensim.downloader as api

diff --git a/gensim/models/ldamulticore.py b/gensim/models/ldamulticore.py
@@ -44,6 +44,7 @@
 Usage examples
 --------------
 The constructor estimates Latent Dirichlet Allocation model parameters based on a training corpus
+
 .. sourcecode:: pycon
 
     >>> from gensim.test.utils import common_corpus, common_dictionary

diff --git a/gensim/models/phrases.py b/gensim/models/phrases.py
@@ -14,7 +14,6 @@
 
 Examples
 --------
-
 .. sourcecode:: pycon
 
     >>> from gensim.test.utils import datapath

diff --git a/gensim/models/poincare.py b/gensim/models/poincare.py
@@ -21,7 +21,6 @@
 
 Examples
 --------
-
 Initialize and train a model from a list
 
 .. sourcecode:: pycon
@@ -32,6 +31,7 @@
     >>> model.train(epochs=50)
 
 Initialize and train a model from a file containing one relation per line
+
 .. sourcecode:: pycon
 
     >>> from gensim.models.poincare import PoincareModel, PoincareRelations
@@ -851,7 +851,6 @@ def word_vec(self, word):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.test.utils import datapath
@@ -1308,7 +1307,6 @@ def norm(self, node_or_vector):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.test.utils import datapath
@@ -1351,7 +1349,6 @@ def difference_in_hierarchy(self, node_or_vector_1, node_or_vector_2):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.test.utils import datapath

diff --git a/gensim/models/rpmodel.py b/gensim/models/rpmodel.py
@@ -12,7 +12,6 @@
 
 Examples
 --------
-
 .. sourcecode:: pycon
 
     >>> from gensim.models import RpModel
@@ -119,7 +118,6 @@ def __getitem__(self, bow):
 
         Examples
         ----------
-
         .. sourcecode:: pycon
 
             >>> from gensim.models import RpModel

diff --git a/gensim/models/translation_matrix.py b/gensim/models/translation_matrix.py
@@ -24,6 +24,7 @@
     >>> model_it = KeyedVectors.load_word2vec_format(datapath("IT.1-10.cbow1_wind5_hs0_neg10_size300_smpl1e-05.txt"))
 
 Define word pairs (that will be used for construction of translation matrix
+
 .. sourcecode:: pycon
 
     >>> word_pairs = [
@@ -34,18 +35,21 @@
     ... ]
 
 Fit :class:`~gensim.models.translation_matrix.TranslationMatrix`
+
 .. sourcecode:: pycon
 
     >>> trans_model = TranslationMatrix(model_en, model_it, word_pairs=word_pairs)
 
 Apply model (translate words "dog" and "one")
+
 .. sourcecode:: pycon
 
     >>> trans_model.translate(["dog", "one"], topn=3)
     OrderedDict([('dog', [u'cane', u'gatto', u'cavallo']), ('one', [u'uno', u'due', u'tre'])])
 
 
 Save / load model
+
 .. sourcecode:: pycon
 
     >>> with temporary_file("model_file") as fname:
@@ -57,6 +61,7 @@
 ==================================================================================
 
 Prepare data and models
+
 .. sourcecode:: pycon
 
     >>> from gensim.test.utils import datapath
@@ -171,7 +176,6 @@ class TranslationMatrix(utils.SaveLoad):
 
     Examples
     --------
-
     .. sourcecode:: pycon
 
         >>> from gensim.models import KeyedVectors

diff --git a/gensim/models/word2vec.py b/gensim/models/word2vec.py
@@ -48,13 +48,15 @@
 from disk on-the-fly, without loading the entire corpus into RAM.
 
 It also means you can continue training the model later:
+
 .. sourcecode:: pycon
 
     >>> model = Word2Vec.load("word2vec.model")
     >>> model.train([["hello", "world"]], total_examples=1, epochs=1)
     (0, 2)
 
 The trained word vectors are stored in a :class:`~gensim.models.keyedvectors.KeyedVectors` instance in `model.wv`:
+
 .. sourcecode:: pycon
 
     >>> vector = model.wv['computer']  # numpy vector of a word
@@ -1409,7 +1411,6 @@ def __init__(self, source, max_sentence_length=MAX_WORDS_IN_BATCH, limit=None):
 
         Examples
         --------
-
         .. sourcecode:: pycon
 
             >>> from gensim.test.utils import datapath

diff --git a/gensim/models/wrappers/dtmmodel.py b/gensim/models/wrappers/dtmmodel.py
@@ -25,7 +25,6 @@
 
 Examples
 --------
-
 .. sourcecode:: pycon
 
     >>> from gensim.test.utils import common_corpus, common_dictionary

diff --git a/gensim/models/wrappers/ldamallet.py b/gensim/models/wrappers/ldamallet.py
@@ -32,7 +32,6 @@
 
 Examples
 --------
-
 .. sourcecode:: pycon
 
     >>> from gensim.test.utils import common_corpus, common_dictionary

diff --git a/gensim/models/wrappers/ldavowpalwabbit.py b/gensim/models/wrappers/ldavowpalwabbit.py
@@ -31,6 +31,7 @@
 --------
 
 Train model
+
 .. sourcecode:: pycon
 
     >>> from gensim.test.utils import common_corpus, common_dictionary

diff --git a/gensim/parsing/preprocessing.py b/gensim/parsing/preprocessing.py
@@ -8,7 +8,7 @@
 * :func:`~gensim.parsing.preprocessing.remove_stopwords` - remove all stopwords from string
 * :func:`~gensim.parsing.preprocessing.preprocess_string` -  preprocess string (in default NLP meaning)
 
-Examples:
+Examples
 ---------
 .. sourcecode:: pycon
 
@@ -390,7 +390,6 @@ def preprocess_documents(docs):
 
     Examples
     --------
-
     .. sourcecode:: pycon
 
         >>> from gensim.parsing.preprocessing import preprocess_documents
-Original file line number
+Diff line change
@@ Expand Up @@
             Examples
             --------
             .. sourcecode:: pycon
                 >>> from gensim.corpora import MmCorpus
@@ Expand Down @@