Document accessing model's vocabulary

docs/src/auto_examples/core/run_topics_and_transformations.ipynb

@@ -116,7 +116,7 @@
       },
       "outputs": [],
       "source": [
-        "lsi = models.LsiModel(corpus_tfidf, id2word=dictionary, num_topics=2)  # initialize an LSI transformation\ncorpus_lsi = lsi[corpus_tfidf]  # create a double wrapper over the original corpus: bow->tfidf->fold-in-lsi"
+        "lsi_model = models.LsiModel(corpus_tfidf, id2word=dictionary, num_topics=2)  # initialize an LSI transformation\ncorpus_lsi = lsi_model[corpus_tfidf]  # create a double wrapper over the original corpus: bow->tfidf->fold-in-lsi"
       ]
     },
     {
@@ -134,7 +134,7 @@
       },
       "outputs": [],
       "source": [
-        "lsi.print_topics(2)"
+        "lsi_model.print_topics(2)"
       ]
     },
     {
@@ -170,7 +170,7 @@
       },
       "outputs": [],
       "source": [
-        "lsi.save('/tmp/model.lsi')  # same for tfidf, lda, ...\nlsi = models.LsiModel.load('/tmp/model.lsi')"
+        "import os\nimport tempfile\n\nwith tempfile.NamedTemporaryFile(prefix='model-', suffix='.lsi', delete=False) as tmp:\n    lsi_model.save(tmp.name)  # same for tfidf, lda, ...\n\nloaded_lsi_model = models.LsiModel.load(tmp.name)\n\nos.unlink(tmp.name)"
       ]
     },
     {
@@ -208,7 +208,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.5"
+      "version": "3.6.8"
     }
   },
   "nbformat": 4,

docs/src/auto_examples/core/run_topics_and_transformations.py

@@ -126,15 +126,15 @@
 #
 # Transformations can also be serialized, one on top of another, in a sort of chain:
 
-lsi = models.LsiModel(corpus_tfidf, id2word=dictionary, num_topics=2)  # initialize an LSI transformation
-corpus_lsi = lsi[corpus_tfidf]  # create a double wrapper over the original corpus: bow->tfidf->fold-in-lsi
+lsi_model = models.LsiModel(corpus_tfidf, id2word=dictionary, num_topics=2)  # initialize an LSI transformation
+corpus_lsi = lsi_model[corpus_tfidf]  # create a double wrapper over the original corpus: bow->tfidf->fold-in-lsi
 
 ###############################################################################
 # Here we transformed our Tf-Idf corpus via `Latent Semantic Indexing <http://en.wikipedia.org/wiki/Latent_semantic_indexing>`_
 # into a latent 2-D space (2-D because we set ``num_topics=2``). Now you're probably wondering: what do these two latent
 # dimensions stand for? Let's inspect with :func:`models.LsiModel.print_topics`:
 
-lsi.print_topics(2)
+lsi_model.print_topics(2)
 
 ###############################################################################
 # (the topics are printed to log -- see the note at the top of this page about activating
@@ -152,9 +152,15 @@
 
 ###############################################################################
 # Model persistency is achieved with the :func:`save` and :func:`load` functions:
+import os
+import tempfile
 
-lsi.save('/tmp/model.lsi')  # same for tfidf, lda, ...
-lsi = models.LsiModel.load('/tmp/model.lsi')
+with tempfile.NamedTemporaryFile(prefix='model-', suffix='.lsi', delete=False) as tmp:
+    lsi_model.save(tmp.name)  # same for tfidf, lda, ...
+
+loaded_lsi_model = models.LsiModel.load(tmp.name)
+
+os.unlink(tmp.name)
 
 ###############################################################################
 # The next question might be: just how exactly similar are those documents to each other?

docs/src/auto_examples/core/run_topics_and_transformations.py.md5

@@ -1 +1 @@
-7f6d3084a74333f89c5c6d06b1cc74fb
+844d2cd8ea4d13801165b3af2aecde49

docs/src/auto_examples/core/run_topics_and_transformations.rst

@@ -205,8 +205,8 @@ Transformations can also be serialized, one on top of another, in a sort of chai
 .. code-block:: default
 
 
-    lsi = models.LsiModel(corpus_tfidf, id2word=dictionary, num_topics=2)  # initialize an LSI transformation
-    corpus_lsi = lsi[corpus_tfidf]  # create a double wrapper over the original corpus: bow->tfidf->fold-in-lsi
+    lsi_model = models.LsiModel(corpus_tfidf, id2word=dictionary, num_topics=2)  # initialize an LSI transformation
+    corpus_lsi = lsi_model[corpus_tfidf]  # create a double wrapper over the original corpus: bow->tfidf->fold-in-lsi
 
 
 
@@ -222,7 +222,7 @@ dimensions stand for? Let's inspect with :func:`models.LsiModel.print_topics`:
 .. code-block:: default
 
 
-    lsi.print_topics(2)
+    lsi_model.print_topics(2)
 
 
 
@@ -257,15 +257,15 @@ remaining four documents to the first topic:
 
  .. code-block:: none
 
-    [(0, 0.06600783396090373), (1, -0.5200703306361856)] Human machine interface for lab abc computer applications
-    [(0, 0.19667592859142588), (1, -0.7609563167700043)] A survey of user opinion of computer system response time
-    [(0, 0.08992639972446417), (1, -0.7241860626752514)] The EPS user interface management system
-    [(0, 0.07585847652178135), (1, -0.6320551586003438)] System and human system engineering testing of EPS
-    [(0, 0.1015029918498023), (1, -0.573730848300295)] Relation of user perceived response time to error measurement
-    [(0, 0.7032108939378311), (1, 0.16115180214025807)] The generation of random binary unordered trees
-    [(0, 0.8774787673119832), (1, 0.16758906864659448)] The intersection graph of paths in trees
-    [(0, 0.9098624686818579), (1, 0.1408655362871908)] Graph minors IV Widths of trees and well quasi ordering
-    [(0, 0.6165825350569284), (1, -0.05392907566389287)] Graph minors A survey
+    [(0, 0.06600783396090627), (1, -0.520070330636184)] Human machine interface for lab abc computer applications
+    [(0, 0.1966759285914279), (1, -0.760956316770005)] A survey of user opinion of computer system response time
+    [(0, 0.08992639972446735), (1, -0.7241860626752503)] The EPS user interface management system
+    [(0, 0.07585847652178428), (1, -0.6320551586003422)] System and human system engineering testing of EPS
+    [(0, 0.10150299184980327), (1, -0.5737308483002963)] Relation of user perceived response time to error measurement
+    [(0, 0.7032108939378309), (1, 0.16115180214026148)] The generation of random binary unordered trees
+    [(0, 0.8774787673119828), (1, 0.16758906864659825)] The intersection graph of paths in trees
+    [(0, 0.9098624686818573), (1, 0.14086553628719417)] Graph minors IV Widths of trees and well quasi ordering
+    [(0, 0.6165825350569281), (1, -0.053929075663891594)] Graph minors A survey
 
 
 
@@ -274,9 +274,15 @@ Model persistency is achieved with the :func:`save` and :func:`load` functions:
 
 .. code-block:: default
 
+    import os
+    import tempfile
 
-    lsi.save('/tmp/model.lsi')  # same for tfidf, lda, ...
-    lsi = models.LsiModel.load('/tmp/model.lsi')
+    with tempfile.NamedTemporaryFile(prefix='model-', suffix='.lsi', delete=False) as tmp:
+        lsi_model.save(tmp.name)  # same for tfidf, lda, ...
+
+    loaded_lsi_model = models.LsiModel.load(tmp.name)
+
+    os.unlink(tmp.name)
 
 
 
@@ -429,17 +435,17 @@ References
 
  .. code-block:: none
 
-    /Volumes/work/workspace/gensim_misha/docs/src/gallery/core/run_topics_and_transformations.py:287: UserWarning: Matplotlib is currently using agg, which is a non-GUI backend, so cannot show the figure.
+    /home/misha/git/gensim/docs/src/gallery/core/run_topics_and_transformations.py:293: UserWarning: Matplotlib is currently using agg, which is a non-GUI backend, so cannot show the figure.
       plt.show()
 
 
 
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  0.743 seconds)
+   **Total running time of the script:** ( 0 minutes  0.844 seconds)
 
-**Estimated memory usage:**  7 MB
+**Estimated memory usage:**  44 MB
 
 
 .. _sphx_glr_download_auto_examples_core_run_topics_and_transformations.py:

docs/src/auto_examples/core/sg_execution_times.rst

@@ -5,9 +5,9 @@
 
 Computation times
 =================
-**00:02.671** total execution time for **auto_examples_core** files:
+**00:00.844** total execution time for **auto_examples_core** files:
 
-- **00:01.265**: :ref:`sphx_glr_auto_examples_core_run_core_concepts.py` (``run_core_concepts.py``)
-- **00:00.743**: :ref:`sphx_glr_auto_examples_core_run_topics_and_transformations.py` (``run_topics_and_transformations.py``)
-- **00:00.663**: :ref:`sphx_glr_auto_examples_core_run_similarity_queries.py` (``run_similarity_queries.py``)
+- **00:00.844**: :ref:`sphx_glr_auto_examples_core_run_topics_and_transformations.py` (``run_topics_and_transformations.py``)
+- **00:00.000**: :ref:`sphx_glr_auto_examples_core_run_core_concepts.py` (``run_core_concepts.py``)
 - **00:00.000**: :ref:`sphx_glr_auto_examples_core_run_corpora_and_vector_spaces.py` (``run_corpora_and_vector_spaces.py``)
+- **00:00.000**: :ref:`sphx_glr_auto_examples_core_run_similarity_queries.py` (``run_similarity_queries.py``)

docs/src/auto_examples/index.rst

@@ -452,13 +452,13 @@ Blog posts, tutorial videos, hackathons and other useful Gensim resources, from
 
   .. container:: sphx-glr-download
 
-    :download:`Download all examples in Python source code: auto_examples_python.zip <//Volumes/work/workspace/gensim_misha/docs/src/auto_examples/auto_examples_python.zip>`
+    :download:`Download all examples in Python source code: auto_examples_python.zip <//home/misha/git/gensim/docs/src/auto_examples/auto_examples_python.zip>`
 
 
 
   .. container:: sphx-glr-download
 
-    :download:`Download all examples in Jupyter notebooks: auto_examples_jupyter.zip <//Volumes/work/workspace/gensim_misha/docs/src/auto_examples/auto_examples_jupyter.zip>`
+    :download:`Download all examples in Jupyter notebooks: auto_examples_jupyter.zip <//home/misha/git/gensim/docs/src/auto_examples/auto_examples_jupyter.zip>`
 
 
 .. only:: html

docs/src/auto_examples/tutorials/run_word2vec.ipynb

@@ -54,6 +54,24 @@
         "import gensim.downloader as api\nwv = api.load('word2vec-google-news-300')"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "A common operation is to retrieve the vocabulary of a model.  That is trivial:\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "for i, word in enumerate(wv.vocab):\n    if i == 10:\n        break\n    print(word)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -87,7 +105,7 @@
       },
       "outputs": [],
       "source": [
-        "try:\n    vec_weapon = wv['cameroon']\nexcept KeyError:\n    print(\"The word 'cameroon' does not appear in this model\")"
+        "try:\n    vec_cameroon = wv['cameroon']\nexcept KeyError:\n    print(\"The word 'cameroon' does not appear in this model\")"
       ]
     },
     {
@@ -198,6 +216,24 @@
         "vec_king = model.wv['king']"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Retrieving the vocabulary works the same way:\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "for i, word in enumerate(model.wv.vocab):\n    if i == 10:\n        break\n    print(word)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -548,7 +584,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.5"
+      "version": "3.6.8"
     }
   },
   "nbformat": 4,

docs/src/auto_examples/tutorials/run_word2vec.py

@@ -134,6 +134,13 @@
 import gensim.downloader as api
 wv = api.load('word2vec-google-news-300')
 
+###############################################################################
+# A common operation is to retrieve the vocabulary of a model.  That is trivial:
+for i, word in enumerate(wv.vocab):
+    if i == 10:
+        break
+    print(word)
+
 ###############################################################################
 # We can easily obtain vectors for terms the model is familiar with:
 #
@@ -145,7 +152,7 @@
 # out the FastText model.
 #
 try:
-    vec_weapon = wv['cameroon']
+    vec_cameroon = wv['cameroon']
 except KeyError:
     print("The word 'cameroon' does not appear in this model")
 
@@ -220,6 +227,13 @@ def __iter__(self):
 #
 vec_king = model.wv['king']
 
+###############################################################################
+# Retrieving the vocabulary works the same way:
+for i, word in enumerate(model.wv.vocab):
+    if i == 10:
+        break
+    print(word)
+
 ###############################################################################
 # Storing and loading models
 # --------------------------

docs/src/auto_examples/tutorials/run_word2vec.py.md5

@@ -1 +1 @@
-776cde9e7148f94e2cbff78b00854edd
+0d41144f740af100c7576b2284b03d0a