[MRG] Fix similarity bug in NMSLIB indexer + documentation fixes

docs/src/auto_examples/tutorials/run_annoy.ipynb

@@ -112,7 +112,7 @@
       },
       "outputs": [],
       "source": [
-        "# Set up the model and vector that we are using in the comparison\nmodel.init_sims()\nannoy_index = AnnoyIndexer(model, 100)\n\n# Dry run to make sure both indexes are fully in RAM\nvector = model.wv.vectors_norm[0]\nmodel.wv.most_similar([vector], topn=5, indexer=annoy_index)\nmodel.wv.most_similar([vector], topn=5)\n\nimport time\nimport numpy as np\n\ndef avg_query_time(annoy_index=None, queries=1000):\n    \"\"\"Average query time of a most_similar method over 1000 random queries.\"\"\"\n    total_time = 0\n    for _ in range(queries):\n        rand_vec = model.wv.vectors_norm[np.random.randint(0, len(model.wv))]\n        start_time = time.process_time()\n        model.wv.most_similar([rand_vec], topn=5, indexer=annoy_index)\n        total_time += time.process_time() - start_time\n    return total_time / queries\n\nqueries = 1000\n\ngensim_time = avg_query_time(queries=queries)\nannoy_time = avg_query_time(annoy_index, queries=queries)\nprint(\"Gensim (s/query):\\t{0:.5f}\".format(gensim_time))\nprint(\"Annoy (s/query):\\t{0:.5f}\".format(annoy_time))\nspeed_improvement = gensim_time / annoy_time\nprint (\"\\nAnnoy is {0:.2f} times faster on average on this particular run\".format(speed_improvement))"
+        "# Set up the model and vector that we are using in the comparison\nmodel.init_sims()\nannoy_index = AnnoyIndexer(model, 100)\n\n# Dry run to make sure both indexes are fully in RAM\nnormed_vectors = model.wv.get_normed_vectors()\nvector = normed_vectors[0]\nmodel.wv.most_similar([vector], topn=5, indexer=annoy_index)\nmodel.wv.most_similar([vector], topn=5)\n\nimport time\nimport numpy as np\n\ndef avg_query_time(annoy_index=None, queries=1000):\n    \"\"\"Average query time of a most_similar method over 1000 random queries.\"\"\"\n    total_time = 0\n    for _ in range(queries):\n        rand_vec = normed_vectors[np.random.randint(0, len(model.wv))]\n        start_time = time.process_time()\n        model.wv.most_similar([rand_vec], topn=5, indexer=annoy_index)\n        total_time += time.process_time() - start_time\n    return total_time / queries\n\nqueries = 1000\n\ngensim_time = avg_query_time(queries=queries)\nannoy_time = avg_query_time(annoy_index, queries=queries)\nprint(\"Gensim (s/query):\\t{0:.5f}\".format(gensim_time))\nprint(\"Annoy (s/query):\\t{0:.5f}\".format(annoy_time))\nspeed_improvement = gensim_time / annoy_time\nprint (\"\\nAnnoy is {0:.2f} times faster on average on this particular run\".format(speed_improvement))"
       ]
     },
     {
@@ -234,7 +234,7 @@
       },
       "outputs": [],
       "source": [
-        "exact_results = [element[0] for element in model.wv.most_similar([model.wv.vectors_norm[0]], topn=100)]\n\nx_values = []\ny_values_init = []\ny_values_accuracy = []\n\nfor x in range(1, 300, 10):\n    x_values.append(x)\n    start_time = time.time()\n    annoy_index = AnnoyIndexer(model, x)\n    y_values_init.append(time.time() - start_time)\n    approximate_results = model.wv.most_similar([model.wv.vectors_norm[0]], topn=100, indexer=annoy_index)\n    top_words = [result[0] for result in approximate_results]\n    y_values_accuracy.append(len(set(top_words).intersection(exact_results)))"
+        "exact_results = [element[0] for element in model.wv.most_similar([normed_vectors[0]], topn=100)]\n\nx_values = []\ny_values_init = []\ny_values_accuracy = []\n\nfor x in range(1, 300, 10):\n    x_values.append(x)\n    start_time = time.time()\n    annoy_index = AnnoyIndexer(model, x)\n    y_values_init.append(time.time() - start_time)\n    approximate_results = model.wv.most_similar([normed_vectors[0]], topn=100, indexer=annoy_index)\n    top_words = [result[0] for result in approximate_results]\n    y_values_accuracy.append(len(set(top_words).intersection(exact_results)))"
       ]
     },
     {

docs/src/auto_examples/tutorials/run_annoy.py

@@ -120,7 +120,8 @@
 annoy_index = AnnoyIndexer(model, 100)
 
 # Dry run to make sure both indexes are fully in RAM
-vector = model.wv.vectors_norm[0]
+normed_vectors = model.wv.get_normed_vectors()
+vector = normed_vectors[0]
 model.wv.most_similar([vector], topn=5, indexer=annoy_index)
 model.wv.most_similar([vector], topn=5)
 
@@ -131,7 +132,7 @@ def avg_query_time(annoy_index=None, queries=1000):
     """Average query time of a most_similar method over 1000 random queries."""
     total_time = 0
     for _ in range(queries):
-        rand_vec = model.wv.vectors_norm[np.random.randint(0, len(model.wv))]
+        rand_vec = normed_vectors[np.random.randint(0, len(model.wv))]
         start_time = time.process_time()
         model.wv.most_similar([rand_vec], topn=5, indexer=annoy_index)
         total_time += time.process_time() - start_time
@@ -286,7 +287,7 @@ def f(process_id):
 # Build dataset of Initialization times and accuracy measures:
 #
 
-exact_results = [element[0] for element in model.wv.most_similar([model.wv.vectors_norm[0]], topn=100)]
+exact_results = [element[0] for element in model.wv.most_similar([normed_vectors[0]], topn=100)]
 
 x_values = []
 y_values_init = []
@@ -297,7 +298,7 @@ def f(process_id):
     start_time = time.time()
     annoy_index = AnnoyIndexer(model, x)
     y_values_init.append(time.time() - start_time)
-    approximate_results = model.wv.most_similar([model.wv.vectors_norm[0]], topn=100, indexer=annoy_index)
+    approximate_results = model.wv.most_similar([normed_vectors[0]], topn=100, indexer=annoy_index)
     top_words = [result[0] for result in approximate_results]
     y_values_accuracy.append(len(set(top_words).intersection(exact_results)))
 

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

@@ -1 +1 @@
-a18f2e2cf524dea755eb70bb385bf7fe
+c6cd2a0225bbe49d97dc66c96d2b7f1c