Merge pull request #67 from bio-ontology-research-group/dependabot/pi…

…p/pykeen-1.10.2

⬆️ Bump pykeen from 1.10.1 to 1.10.2 and update from develop branch

CHANGELOG.md

@@ -11,6 +11,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Deprecated
 ### Removed
 ### Fixed
+- Fix bug in GCI2 score for ELEmbeddings
+- Fix bottleneck in ELBE example for PPI.
+- Fix bugs in BoxSquaredEL model.
+
 ### Security
 
 ## [0.3.0]

mowl/base_models/elmodel.py

@@ -1,8 +1,10 @@
 from mowl.ontology.normalize import ELNormalizer
 from mowl.base_models.model import Model
+from mowl.datasets.el import ELDataset
+from mowl.projection import projector_factory
 import torch as th
 from torch.utils.data import DataLoader, default_collate
-from mowl.datasets.el import ELDataset
+
 from deprecated.sphinx import versionadded
 
 from org.semanticweb.owlapi.model import OWLClassExpression, OWLClass, OWLObjectSomeValuesFrom, OWLObjectIntersectionOf
@@ -48,6 +50,7 @@ def __init__(self, dataset, embed_dim, batch_size, extended=True, model_filepath
         self._validation_datasets = None
         self._testing_datasets = None
 
+        self._loaded_eval = False
 
     def init_module(self):
         raise NotImplementedError
@@ -379,3 +382,43 @@ def from_pretrained(self, model):
         #self._kge_method = kge_method
 
 
+
+
+    def load_pairwise_eval_data(self):
+
+        if self._loaded_eval:
+            return
+
+        eval_property = self.dataset.get_evaluation_property()
+        head_classes, tail_classes = self.dataset.evaluation_classes
+        self._head_entities = head_classes.as_str
+        self._tail_entities = tail_classes.as_str
+
+        eval_projector = projector_factory('taxonomy_rels', taxonomy=False,
+                                           relations=[eval_property])
+
+        self._training_set = eval_projector.project(self.dataset.ontology)
+        self._testing_set = eval_projector.project(self.dataset.testing)
+
+        self._loaded_eval = True
+
+
+    @property
+    def training_set(self):
+        self.load_pairwise_eval_data()
+        return self._training_set
+
+    @property
+    def testing_set(self):
+        self.load_pairwise_eval_data()
+        return self._testing_set
+
+    @property
+    def head_entities(self):
+        self.load_pairwise_eval_data()
+        return self._head_entities
+
+    @property
+    def tail_entities(self):
+        self.load_pairwise_eval_data()
+        return self._tail_entities

mowl/evaluation/rank_based.py

@@ -125,7 +125,7 @@ def load_training_scores(self):
             c, d = self.head_name_indexemb[c], self.tail_name_indexemb[d]
             c, d = self.head_indexemb_indexsc[c], self.tail_indexemb_indexsc[d]
 
-            self.training_scores[c, d] = 1000000
+            self.training_scores[c, d] = 10000
 
         logging.info("Training scores created")
         self._loaded_tr_scores = True
@@ -231,6 +231,7 @@ def activation(x):
             print(f'Hits@100: {top100:.2f} Filtered:   {ftop100:.2f}')
             print(f'MR:       {mean_rank:.2f} Filtered: {fmean_rank:.2f}')
             print(f'AUC:      {rank_auc:.2f} Filtered:   {frank_auc:.2f}')
+            print(f"Tail entities: {num_tail_entities}")
 
         self.metrics = {
             "hits@1": top1,

mowl/models/__init__.py

@@ -6,6 +6,8 @@
 from mowl.models.elboxembeddings.examples.model_ppi import ELBoxPPI
 from mowl.models.elboxembeddings.examples.model_gda import ELBoxGDA
 
+from mowl.models.boxsquaredel.model import BoxSquaredEL
+
 from mowl.models.graph_random_walk.random_walk_w2v_model import RandomWalkPlusW2VModel
 from mowl.models.graph_kge.graph_pykeen_model import GraphPlusPyKEENModel
 from mowl.models.syntactic.w2v_model import SyntacticPlusW2VModel

mowl/models/boxsquaredel/evaluate.py

@@ -0,0 +1,130 @@
+from mowl.evaluation.base import AxiomsRankBasedEvaluator
+from mowl.projection.factory import projector_factory
+from mowl.projection.edge import Edge
+import logging
+import numpy as np
+from scipy.stats import rankdata
+import torch as th
+
+
+class BoxSquaredELPPIEvaluator(AxiomsRankBasedEvaluator):
+
+    def __init__(
+            self,
+            axioms,
+            eval_method,
+            axioms_to_filter,
+            class_name_indexemb,
+            rel_name_indexemb,
+            device="cpu",
+            verbose=False
+    ):
+
+        super().__init__(axioms, eval_method, axioms_to_filter, device, verbose)
+
+        self.class_name_indexemb = class_name_indexemb
+        self.relation_name_indexemb = rel_name_indexemb
+
+        self._loaded_training_scores = False
+        self._loaded_eval_data = False
+        self._loaded_ht_data = False
+
+    def _load_head_tail_entities(self):
+        if self._loaded_ht_data:
+            return
+
+        ents, _ = Edge.getEntitiesAndRelations(self.axioms)
+        ents_filter, _ = Edge.getEntitiesAndRelations(self.axioms_to_filter)
+
+        entities = list(set(ents) | set(ents_filter))
+
+        self.head_entities = set()
+        for e in entities:
+            if e in self.class_name_indexemb:
+                self.head_entities.add(e)
+            else:
+                logging.info("Entity %s not present in the embeddings dictionary. Ignoring it.", e)
+
+        self.tail_entities = set()
+        for e in entities:
+            if e in self.class_name_indexemb:
+                self.tail_entities.add(e)
+            else:
+                logging.info("Entity %s not present in the embeddings dictionary. Ignoring it.", e)
+
+        self.head_name_indexemb = {k: self.class_name_indexemb[k] for k in self.head_entities}
+        self.tail_name_indexemb = {k: self.class_name_indexemb[k] for k in self.tail_entities}
+
+        self.head_indexemb_indexsc = {v: k for k, v in enumerate(self.head_name_indexemb.values())}
+        self.tail_indexemb_indexsc = {v: k for k, v in enumerate(self.tail_name_indexemb.values())}
+
+        self._loaded_ht_data = True
+
+    def _load_training_scores(self):
+        if self._loaded_training_scores:
+            return self.training_scores
+
+        self._load_head_tail_entities()
+
+        training_scores = np.ones((len(self.head_entities), len(self.tail_entities)),
+                                  dtype=np.int32)
+
+        if self._compute_filtered_metrics:
+            # careful here: c must be in head entities and d must be in tail entities
+            for axiom in self.axioms_to_filter:
+                c, _, d = axiom.astuple()
+                if (c not in self.head_entities) or not (d in self.tail_entities):
+                    continue
+
+                c, d = self.head_name_indexemb[c], self.tail_name_indexemb[d]
+                c, d = self.head_indexemb_indexsc[c], self.tail_indexemb_indexsc[d]
+
+                training_scores[c, d] = 10000
+
+            logging.info("Training scores created")
+
+        self._loaded_training_scores = True
+        return training_scores
+
+    def _init_axioms(self, axioms):
+
+        if axioms is None:
+            return None
+
+        projector = projector_factory("taxonomy_rels", relations=["http://interacts_with"])
+
+        edges = projector.project(axioms)
+        return edges  # List of Edges
+
+    def compute_axiom_rank(self, axiom):
+
+        self.training_scores = self._load_training_scores()
+
+        c, r, d = axiom.astuple()
+
+        if not (c in self.head_entities) or not (d in self.tail_entities):
+            return None, None, None
+
+        # Embedding indices
+        c_emb_idx, d_emb_idx = self.head_name_indexemb[c], self.tail_name_indexemb[d]
+
+        # Scores matrix labels
+        c_sc_idx, d_sc_idx = self.head_indexemb_indexsc[c_emb_idx],
+        self.tail_indexemb_indexsc[d_emb_idx]
+
+        r = self.relation_name_indexemb[r]
+
+        data = th.tensor([
+            [c_emb_idx, r, self.tail_name_indexemb[x]] for x in
+            self.tail_entities]).to(self.device)
+
+        res = self.eval_method(data).squeeze().cpu().detach().numpy()
+
+        # self.testing_predictions[c_sc_idx, :] = res
+        index = rankdata(res, method='average')
+        rank = index[d_sc_idx]
+
+        findex = rankdata((res * self.training_scores[c_sc_idx, :]), method='average')
+        frank = findex[d_sc_idx]
+
+        return rank, frank, len(self.tail_entities)

mowl/models/boxsquaredel/model.py

@@ -0,0 +1,77 @@
+
+from mowl.nn import BoxSquaredELModule
+from mowl.base_models.elmodel import EmbeddingELModel
+from mowl.models.boxsquaredel.evaluate import BoxSquaredELPPIEvaluator
+import torch as th
+from torch import nn
+
+
+class BoxSquaredEL(EmbeddingELModel):
+    """
+    Implementation based on [peng2020]_.
+    """
+
+    def __init__(self,
+                 dataset,
+                 embed_dim=50,
+                 margin=0.02,
+                 reg_norm=1,
+                 learning_rate=0.001,
+                 epochs=1000,
+                 batch_size=4096 * 8,
+                 delta=2.5,
+                 reg_factor=0.2,
+                 num_negs=4,
+                 model_filepath=None,
+                 device='cpu'
+                 ):
+        super().__init__(dataset, embed_dim, batch_size, extended=True, model_filepath=model_filepath)
+
+
+        self.margin = margin
+        self.reg_norm = reg_norm
+        self.delta = delta
+        self.reg_factor = reg_factor
+        self.num_negs = num_negs
+        self.learning_rate = learning_rate
+        self.epochs = epochs
+        self.device = device
+        self._loaded = False
+        self.extended = False
+        self.init_module()
+
+    def init_module(self):
+        self.module = BoxSquaredELModule(
+            len(self.class_index_dict),
+            len(self.object_property_index_dict),
+            embed_dim=self.embed_dim,
+            gamma=self.margin,
+            delta=self.delta,
+            reg_factor=self.reg_factor
+
+        ).to(self.device)
+
+    def train(self):
+        raise NotImplementedError
+
+
+    def eval_method(self, data):
+        return self.module.gci2_score(data)
+
+    def get_embeddings(self):
+        self.init_module()
+
+        print('Load the best model', self.model_filepath)
+        self.load_best_model()
+
+        ent_embeds = {k: v for k, v in zip(self.class_index_dict.keys(),
+                                           self.module.class_embed.weight.cpu().detach().numpy())}
+        rel_embeds = {k: v for k, v in zip(self.object_property_index_dict.keys(),
+                                           self.module.rel_embed.weight.cpu().detach().numpy())}
+        return ent_embeds, rel_embeds
+
+    def load_best_model(self):
+        self.init_module()
+        self.module.load_state_dict(th.load(self.model_filepath))
+        self.module.eval()
+

mowl/models/elboxembeddings/examples/model_ppi.py

@@ -20,7 +20,7 @@ class ELBoxPPI(ELBoxEmbeddings):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
 
-    def train(self):
+    def train(self, validate_every=1000):
         criterion = nn.MSELoss()
         optimizer = th.optim.Adam(self.module.parameters(), lr=self.learning_rate)
         best_loss = float('inf')
@@ -29,6 +29,9 @@ def train(self):
             k: v.data for k, v in self.training_datasets.items()}
         validation_dataset = self.validation_datasets["gci2"][:]
 
+        prots = [self.class_index_dict[p] for p
+                 in self.dataset.evaluation_classes.as_str]
+
         for epoch in trange(self.epochs):
             self.module.train()
 
@@ -37,16 +40,13 @@ def train(self):
             for gci_name, gci_dataset in training_datasets.items():
                 if len(gci_dataset) == 0:
                     continue
-                rand_index = np.random.choice(len(gci_dataset), size=512)
-                dst = self.module(gci_dataset[rand_index], gci_name)
+                dst = self.module(gci_dataset, gci_name)
+
                 mse_loss = criterion(dst, th.zeros(dst.shape, requires_grad=False).to(self.device))
                 loss += mse_loss
 
                 if gci_name == "gci2":
-                    rand_index = np.random.choice(len(gci_dataset), size=512)
-                    gci_batch = gci_dataset[rand_index]
-                    prots = [self.class_index_dict[p] for p
-                             in self.dataset.evaluation_classes.as_str]
+                    gci_batch = gci_dataset
                     idxs_for_negs = np.random.choice(prots, size=len(gci_batch), replace=True)
                     rand_prot_ids = th.tensor(idxs_for_negs).to(self.device)
                     neg_data = th.cat([gci_batch[:, :2], rand_prot_ids.unsqueeze(1)], dim=1)
@@ -61,20 +61,22 @@ def train(self):
             optimizer.step()
             train_loss += loss.detach().item()
 
-            with th.no_grad():
-                self.module.eval()
-                valid_loss = 0
-                gci2_data = validation_dataset
 
-                dst = self.module(gci2_data, "gci2")
-                loss = criterion(dst, th.zeros(dst.shape, requires_grad=False).to(self.device))
-                valid_loss += loss.detach().item()
+            if (epoch + 1) % validate_every == 0:
+                with th.no_grad():
+                    self.module.eval()
+                    valid_loss = 0
+                    gci2_data = validation_dataset
+
+                    dst = self.module(gci2_data, "gci2")
+                    loss = criterion(dst, th.zeros(dst.shape, requires_grad=False).to(self.device))
+                    valid_loss += loss.detach().item()
 
-            if best_loss > valid_loss:
-                best_loss = valid_loss
-                print("Saving model..")
-                th.save(self.module.state_dict(), self.model_filepath)
-            print(f'Epoch {epoch}: Train loss: {train_loss} Valid loss: {valid_loss}')
+                if valid_loss < best_loss:
+                    best_loss = valid_loss
+                    print("Saving model..")
+                    th.save(self.module.state_dict(), self.model_filepath)
+                print(f'Epoch {epoch+1}: Train loss: {train_loss} Valid loss: {valid_loss}')
 
         return 1