Merge pull request #88 from bio-ontology-research-group/docs

Docs
bio-ontology-research-group · Nov 19, 2024 · fab9ff6 · fab9ff6
2 parents f3a05fe + f6e4195
commit fab9ff6
Show file tree

Hide file tree

Showing 47 changed files with 73 additions and 3,218 deletions.
diff --git a/docs/source/corpus/index.rst b/docs/source/corpus/index.rst
@@ -71,10 +71,6 @@ To train a Word2Vec model with a generated corpus, we can use the class: :class:
    model.generate_corpus(save=True, with_annotations=True)
    model.train()
 
-.. testoutput::
-
-   Corpus saved in test
-
 .. attention::
    The ``set_w2v_model`` receives the same arguments as the :class:`gensim.models.word2vec.Word2Vec` model.
 
diff --git a/docs/source/evaluation/index.rst b/docs/source/evaluation/index.rst
@@ -6,24 +6,23 @@ Evaluating the embeddings
 
 The evaluation of models is specific to the task, which is given by the dataset. For example, when using the |ppidataset|, we will use the |ppievaluator|. For example, a typical pipeline to train a model would be:
 
+
+
 .. testcode::
 
    from mowl.datasets.builtin import PPIYeastSlimDataset
    from mowl.models import SyntacticPlusW2VModel
-
+   from mowl.evaluation import PPIEvaluator
+
+   dataset = PPIYeastSlimDataset()
    model = SyntacticPlusW2VModel(dataset, corpus_filepath="test")
+   model.set_evaluator(PPIEvaluator)
    model.set_w2v_model(min_count=1)
+
    model.generate_corpus(save=True, with_annotations=True)
    model.train()
 
-To evaluate, we first need to assign the evaluator:
-
-.. testcode::
-
-   from mowl.evaluation import PPIEvaluator
-   model.set_evaluator(PPIEvaluator)
-   model.evaluate()
-
+   model.evaluate(dataset.testing) 
 
 What characterizes each evaluator class are two things:
 

diff --git a/docs/source/examples/elmodels/images/thumb/sphx_glr_plot_1_elembeddings_thumb.png b/docs/source/examples/elmodels/images/thumb/sphx_glr_plot_1_elembeddings_thumb.png
diff --git a/...source/examples/elmodels/images/thumb/sphx_glr_plot_2_elboxembeddings_thumb.png b/...source/examples/elmodels/images/thumb/sphx_glr_plot_2_elboxembeddings_thumb.png
diff --git a/docs/source/examples/elmodels/plot_1_elembeddings.ipynb b/docs/source/examples/elmodels/plot_1_elembeddings.ipynb
@@ -54,7 +54,7 @@
       },
       "outputs": [],
       "source": [
-        "from mowl.datasets.builtin import PPIYeastSlimDataset\nfrom mowl.models.elembeddings.examples.model_ppi import ELEmPPI\n\ndataset = PPIYeastSlimDataset()\n\nmodel = ELEmPPI(dataset,\n                embed_dim=30,\n                margin=0.1,\n                reg_norm=1,\n                learning_rate=0.001,\n                epochs=20,\n                batch_size=4096,\n                model_filepath=None,\n                device='cpu')\n\nmodel.train()"
+        "from mowl.datasets.builtin import PPIYeastSlimDataset\nfrom mowl.models.elembeddings.examples.model_ppi import ELEmPPI\n\ndataset = PPIYeastSlimDataset()\n\nmodel = ELEmPPI(dataset,\n                embed_dim=30,\n                margin=0.1,\n                reg_norm=1,\n                learning_rate=0.001,\n                epochs=20,\n                batch_size=20000,\n                model_filepath=None,\n                device='cuda')\n\nmodel.train()"
       ]
     },
     {
@@ -72,7 +72,7 @@
       },
       "outputs": [],
       "source": [
-        "from mowl.evaluation import PPIEvaluator\n\nmodel.set_evaluator(PPIEvaluator)\nmodel.evaluate()"
+        "from mowl.evaluation import PPIEvaluator\n\nmodel.set_evaluator(PPIEvaluator)\nmodel.evaluate(dataset.testing)\n\nprint(model.metrics)"
       ]
     }
   ],
@@ -92,7 +92,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.9.19"
+      "version": "3.9.20"
     }
   },
   "nbformat": 4,

diff --git a/docs/source/examples/elmodels/plot_1_elembeddings.py b/docs/source/examples/elmodels/plot_1_elembeddings.py
@@ -75,9 +75,9 @@
                 reg_norm=1,
                 learning_rate=0.001,
                 epochs=20,
-                batch_size=4096,
+                batch_size=20000,
                 model_filepath=None,
-                device='cpu')
+                device='cuda')
 
 model.train()
 
@@ -93,5 +93,6 @@
 from mowl.evaluation import PPIEvaluator
 
 model.set_evaluator(PPIEvaluator)
-model.evaluate()
+model.evaluate(dataset.testing)
 
+print(model.metrics)
diff --git a/docs/source/examples/elmodels/plot_1_elembeddings.py.md5 b/docs/source/examples/elmodels/plot_1_elembeddings.py.md5
@@ -1 +1 @@
-2ddd5683746cd97d8125b7a8921302ed
+08e8036ed8ba5df4a24e22223004d627
diff --git a/docs/source/examples/elmodels/plot_1_elembeddings.rst b/docs/source/examples/elmodels/plot_1_elembeddings.rst
@@ -109,9 +109,9 @@ Training the model
                     reg_norm=1,
                     learning_rate=0.001,
                     epochs=20,
-                    batch_size=4096,
+                    batch_size=20000,
                     model_filepath=None,
-                    device='cpu')
+                    device='cuda')
 
     model.train()
 
@@ -124,8 +124,7 @@ Training the model
 
  .. code-block:: none
 
-    Number of evaluation classes: 6039
-      0%|          | 0/20 [00:00<?, ?it/s]      5%|▌         | 1/20 [00:15<04:55, 15.58s/it]     10%|█         | 2/20 [00:15<01:57,  6.53s/it]     15%|█▌        | 3/20 [00:15<01:01,  3.63s/it]     20%|██        | 4/20 [00:16<00:36,  2.28s/it]     25%|██▌       | 5/20 [00:16<00:22,  1.52s/it]     30%|███       | 6/20 [00:16<00:14,  1.07s/it]     35%|███▌      | 7/20 [00:16<00:10,  1.28it/s]     40%|████      | 8/20 [00:16<00:07,  1.68it/s]     45%|████▌     | 9/20 [00:17<00:05,  2.13it/s]     50%|█████     | 10/20 [00:17<00:03,  2.60it/s]     55%|█████▌    | 11/20 [00:17<00:02,  3.07it/s]     60%|██████    | 12/20 [00:17<00:02,  3.51it/s]     65%|██████▌   | 13/20 [00:17<00:01,  3.89it/s]     70%|███████   | 14/20 [00:18<00:01,  4.20it/s]     75%|███████▌  | 15/20 [00:18<00:01,  4.45it/s]     80%|████████  | 16/20 [00:18<00:00,  4.64it/s]     85%|████████▌ | 17/20 [00:18<00:00,  4.76it/s]     90%|█████████ | 18/20 [00:18<00:00,  4.87it/s]     95%|█████████▌| 19/20 [00:19<00:00,  4.92it/s]    100%|██████████| 20/20 [00:19<00:00,  4.98it/s]    100%|██████████| 20/20 [00:19<00:00,  1.04it/s]
+      0%|          | 0/20 [00:00<?, ?it/s]      5%|▌         | 1/20 [00:14<04:42, 14.84s/it]     70%|███████   | 14/20 [00:14<00:04,  1.31it/s]    100%|██████████| 20/20 [00:14<00:00,  1.33it/s]
 
     1
 
@@ -139,7 +138,7 @@ Evaluating the model
 Now, it is time to evaluate embeddings. For this, we use the
 :class:`ModelRankBasedEvaluator <mowl.evaluation.ModelRankBasedEvaluator>` class.
 
-.. GENERATED FROM PYTHON SOURCE LINES 91-98
+.. GENERATED FROM PYTHON SOURCE LINES 91-99
 
 .. code-block:: Python
 
@@ -148,8 +147,9 @@ Now, it is time to evaluate embeddings. For this, we use the
     from mowl.evaluation import PPIEvaluator
 
     model.set_evaluator(PPIEvaluator)
-    model.evaluate()
+    model.evaluate(dataset.testing)
 
+    print(model.metrics)
 
 
 
@@ -158,21 +158,17 @@ Now, it is time to evaluate embeddings. For this, we use the
 
  .. code-block:: none
 
-    Number of evaluation classes: 6039
-    Evaluating in device: cpu
-    Evaluating with deductive closure: False
-    Excluding testing set: False
-    Filtering deductive closure: False
+    {'mr': 2464.669435215947, 'mrr': 0.0024686094502139495, 'f_mr': 2464.669435215947, 'f_mrr': 0.0024686094502139495, 'auc': 0.5919726009910654, 'f_auc': 0.5919726009910654, 'hits@1': 0.00016611295681063124, 'hits@3': 0.0009966777408637873, 'hits@10': 0.0027408637873754154, 'hits@50': 0.016777408637873754, 'hits@100': 0.03106312292358804, 'f_hits@1': 0.00016611295681063124, 'f_hits@3': 0.0009966777408637873, 'f_hits@10': 0.0027408637873754154, 'f_hits@50': 0.016777408637873754, 'f_hits@100': 0.03106312292358804}
 
 
 
 
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (1 minutes 19.804 seconds)
+   **Total running time of the script:** (0 minutes 36.813 seconds)
 
-**Estimated memory usage:**  4175 MB
+**Estimated memory usage:**  2066 MB
 
 
 .. _sphx_glr_download_examples_elmodels_plot_1_elembeddings.py:

diff --git a/docs/source/examples/elmodels/plot_2_elboxembeddings.ipynb b/docs/source/examples/elmodels/plot_2_elboxembeddings.ipynb
@@ -54,7 +54,7 @@
       },
       "outputs": [],
       "source": [
-        "from mowl.datasets.builtin import PPIYeastSlimDataset\nfrom mowl.models.elboxembeddings.examples.model_ppi import ELBoxPPI\n\ndataset = PPIYeastSlimDataset()\n\nmodel = ELBoxPPI(dataset,\n                 embed_dim=30,\n                 margin=-0.05,\n                 reg_norm=1,\n                 learning_rate=0.001,\n                 epochs=20,\n                 batch_size=4096,\n                 model_filepath=None,\n                 device='cpu')\n\nmodel.train()"
+        "from mowl.datasets.builtin import PPIYeastSlimDataset\nfrom mowl.models.elboxembeddings.examples.model_ppi import ELBoxPPI\n\ndataset = PPIYeastSlimDataset()\n\nmodel = ELBoxPPI(dataset,\n                 embed_dim=30,\n                 margin=-0.05,\n                 reg_norm=1,\n                 learning_rate=0.001,\n                 epochs=20,\n                 batch_size=20000,\n                 model_filepath=None,\n                 device='cpu')\n\nmodel.train()"
       ]
     },
     {
@@ -72,7 +72,7 @@
       },
       "outputs": [],
       "source": [
-        "from mowl.evaluation import PPIEvaluator\n\nmodel.set_evaluator(PPIEvaluator)\nmodel.evaluate()"
+        "from mowl.evaluation import PPIEvaluator\n\nmodel.set_evaluator(PPIEvaluator)\nmodel.evaluate(dataset.testing)"
       ]
     }
   ],
@@ -92,7 +92,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.9.19"
+      "version": "3.9.20"
     }
   },
   "nbformat": 4,

diff --git a/docs/source/examples/elmodels/plot_2_elboxembeddings.py b/docs/source/examples/elmodels/plot_2_elboxembeddings.py
@@ -72,7 +72,7 @@
                  reg_norm=1,
                  learning_rate=0.001,
                  epochs=20,
-                 batch_size=4096,
+                 batch_size=20000,
                  model_filepath=None,
                  device='cpu')
 
@@ -91,4 +91,4 @@
 from mowl.evaluation import PPIEvaluator
 
 model.set_evaluator(PPIEvaluator)
-model.evaluate()
+model.evaluate(dataset.testing)
diff --git a/docs/source/examples/elmodels/plot_2_elboxembeddings.py.md5 b/docs/source/examples/elmodels/plot_2_elboxembeddings.py.md5
@@ -1 +1 @@
-a24176821130d17727870b9907ea387d
+00584b1a2fc4ce8970b4ecedb98dc6f4
diff --git a/docs/source/examples/elmodels/plot_2_elboxembeddings.rst b/docs/source/examples/elmodels/plot_2_elboxembeddings.rst
@@ -99,7 +99,7 @@ Training the model
                      reg_norm=1,
                      learning_rate=0.001,
                      epochs=20,
-                     batch_size=4096,
+                     batch_size=20000,
                      model_filepath=None,
                      device='cpu')
 
@@ -115,8 +115,7 @@ Training the model
 
  .. code-block:: none
 
-    Number of evaluation classes: 6039
-      0%|          | 0/20 [00:00<?, ?it/s]      5%|▌         | 1/20 [00:00<00:06,  2.99it/s]     10%|█         | 2/20 [00:00<00:05,  3.08it/s]     15%|█▌        | 3/20 [00:00<00:05,  3.06it/s]     20%|██        | 4/20 [00:01<00:05,  2.99it/s]     25%|██▌       | 5/20 [00:01<00:04,  3.02it/s]     30%|███       | 6/20 [00:02<00:04,  2.96it/s]     35%|███▌      | 7/20 [00:02<00:04,  2.95it/s]     40%|████      | 8/20 [00:02<00:04,  2.94it/s]     45%|████▌     | 9/20 [00:03<00:03,  2.94it/s]     50%|█████     | 10/20 [00:03<00:03,  2.97it/s]     55%|█████▌    | 11/20 [00:03<00:03,  2.95it/s]     60%|██████    | 12/20 [00:04<00:02,  2.95it/s]     65%|██████▌   | 13/20 [00:04<00:02,  2.95it/s]     70%|███████   | 14/20 [00:04<00:02,  2.99it/s]     75%|███████▌  | 15/20 [00:05<00:01,  2.93it/s]     80%|████████  | 16/20 [00:05<00:01,  2.94it/s]     85%|████████▌ | 17/20 [00:05<00:01,  2.93it/s]     90%|█████████ | 18/20 [00:06<00:00,  2.94it/s]     95%|█████████▌| 19/20 [00:06<00:00,  2.93it/s]    100%|██████████| 20/20 [00:06<00:00,  2.95it/s]    100%|██████████| 20/20 [00:06<00:00,  2.96it/s]
+      0%|          | 0/20 [00:00<?, ?it/s]      5%|▌         | 1/20 [00:00<00:05,  3.60it/s]     10%|█         | 2/20 [00:00<00:04,  4.13it/s]     15%|█▌        | 3/20 [00:00<00:03,  4.37it/s]     20%|██        | 4/20 [00:00<00:03,  4.53it/s]     25%|██▌       | 5/20 [00:01<00:03,  4.65it/s]     30%|███       | 6/20 [00:01<00:02,  4.70it/s]     35%|███▌      | 7/20 [00:01<00:02,  4.50it/s]     40%|████      | 8/20 [00:01<00:02,  4.57it/s]     45%|████▌     | 9/20 [00:01<00:02,  4.60it/s]     50%|█████     | 10/20 [00:02<00:02,  4.57it/s]     55%|█████▌    | 11/20 [00:02<00:01,  4.61it/s]     60%|██████    | 12/20 [00:02<00:01,  4.66it/s]     65%|██████▌   | 13/20 [00:02<00:01,  4.55it/s]     70%|███████   | 14/20 [00:03<00:01,  4.60it/s]     75%|███████▌  | 15/20 [00:03<00:01,  4.64it/s]     80%|████████  | 16/20 [00:03<00:00,  4.50it/s]     85%|████████▌ | 17/20 [00:03<00:00,  4.59it/s]     90%|█████████ | 18/20 [00:03<00:00,  4.46it/s]     95%|█████████▌| 19/20 [00:04<00:00,  4.42it/s]    100%|██████████| 20/20 [00:04<00:00,  4.33it/s]    100%|██████████| 20/20 [00:04<00:00,  4.49it/s]
 
     1
 
@@ -139,26 +138,20 @@ Now, it is time to evaluate embeddings. For this, we use the
     from mowl.evaluation import PPIEvaluator
 
     model.set_evaluator(PPIEvaluator)
-    model.evaluate()
+    model.evaluate(dataset.testing)
 
 
 
 
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
-    Number of evaluation classes: 6039
-
 
 
 
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (1 minutes 30.418 seconds)
+   **Total running time of the script:** (0 minutes 37.188 seconds)
 
-**Estimated memory usage:**  3174 MB
+**Estimated memory usage:**  1681 MB
 
 
 .. _sphx_glr_download_examples_elmodels_plot_2_elboxembeddings.py:

diff --git a/docs/source/examples/elmodels/sg_execution_times.rst b/docs/source/examples/elmodels/sg_execution_times.rst
@@ -6,7 +6,7 @@
 
 Computation times
 =================
-**02:50.222** total execution time for 2 files **from examples/elmodels**:
+**01:14.002** total execution time for 2 files **from examples/elmodels**:
 
 .. container::
 
@@ -33,8 +33,8 @@ Computation times
      - Time
      - Mem (MB)
    * - :ref:`sphx_glr_examples_elmodels_plot_2_elboxembeddings.py` (``plot_2_elboxembeddings.py``)
-     - 01:30.418
-     - 3174.5
+     - 00:37.188
+     - 1681.3
    * - :ref:`sphx_glr_examples_elmodels_plot_1_elembeddings.py` (``plot_1_elembeddings.py``)
-     - 01:19.804
-     - 4175.1
+     - 00:36.813
+     - 2065.5
diff --git a/docs/source/examples/graph_based/images/thumb/sphx_glr_plot_1_dl2vec_thumb.png b/docs/source/examples/graph_based/images/thumb/sphx_glr_plot_1_dl2vec_thumb.png
diff --git a/docs/source/examples/graph_based/plot_1_dl2vec.ipynb b/docs/source/examples/graph_based/plot_1_dl2vec.ipynb
@@ -58,7 +58,7 @@
       },
       "outputs": [],
       "source": [
-        "from mowl.evaluation import GDAEvaluator\nmodel.set_evaluator(GDAEvaluator)\nmodel.evaluate()"
+        "from mowl.evaluation import GDAEvaluator\nmodel.set_evaluator(GDAEvaluator)\nmodel.evaluate(dataset.testing)"
       ]
     }
   ],
@@ -78,7 +78,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.9.19"
+      "version": "3.9.20"
     }
   },
   "nbformat": 4,

diff --git a/docs/source/examples/graph_based/plot_1_dl2vec.py b/docs/source/examples/graph_based/plot_1_dl2vec.py
@@ -51,5 +51,5 @@
 
 from mowl.evaluation import GDAEvaluator
 model.set_evaluator(GDAEvaluator)
-model.evaluate()
+model.evaluate(dataset.testing)
 
diff --git a/docs/source/examples/graph_based/plot_1_dl2vec.py.md5 b/docs/source/examples/graph_based/plot_1_dl2vec.py.md5
@@ -1 +1 @@
-7a4c447f2412785f8362abe44cff19c2
+fed90cad2165a3cd8374233ec981339b
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		2ddd5683746cd97d8125b7a8921302ed
		08e8036ed8ba5df4a24e22223004d627
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		a24176821130d17727870b9907ea387d
		00584b1a2fc4ce8970b4ecedb98dc6f4
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		7a4c447f2412785f8362abe44cff19c2
		fed90cad2165a3cd8374233ec981339b