ppi eval

eval_scripts/ppi_eval.py

@@ -5,6 +5,13 @@ import numpy as np
 from networkx.readwrite import json_graph
 from argparse import ArgumentParser
 
+''' To evaluate the embeddings, we run a logistic regression.
+Run this script after running unsupervised training.
+Baseline of using features-only can be run by setting data_dir as 'feat'
+Example:
+  python eval_scripts/ppi_eval.py ../data/ppi unsup-ppi/n2v_big_0.000010 test
+'''
+
 def run_regression(train_embeds, train_labels, test_embeds, test_labels):
     np.random.seed(1)
     from sklearn.linear_model import SGDClassifier
@@ -15,8 +22,12 @@ def run_regression(train_embeds, train_labels, test_embeds, test_labels):
     dummy.fit(train_embeds, train_labels)
     log = MultiOutputClassifier(SGDClassifier(loss="log"), n_jobs=10)
     log.fit(train_embeds, train_labels)
-    print("F1 score", f1_score(test_labels, log.predict(test_embeds), average="micro"))
+
-    print("Random baseline F1 score", f1_score(test_labels, dummy.predict(test_embeds), average="micro"))
+    f1 = 0
+    for i in range(test_labels.shape[1]):
+        print("F1 score", f1_score(test_labels[:,i], log.predict(test_embeds)[:,i], average="micro"))
+    for i in range(test_labels.shape[1]):
+        print("Random baseline F1 score", f1_score(test_labels[:,i], dummy.predict(test_embeds)[:,i], average="micro"))
 
 if __name__ == '__main__':
     parser = ArgumentParser("Run evaluation on PPI data.")
@@ -30,12 +41,14 @@ if __name__ == '__main__':
 
     print("Loading data...")
     G = json_graph.node_link_graph(json.load(open(dataset_dir + "/ppi-G.json")))
-    labels = json.load(open("/dfs/scratch0/graphnet/ppi/ppi-class_map.json"))
+    labels = json.load(open(dataset_dir + "/ppi-class_map.json"))
     labels = {int(i):l for i, l in labels.iteritems()}
     
     train_ids = [n for n in G.nodes() if not G.node[n]['val'] and not G.node[n]['test']]
     test_ids = [n for n in G.nodes() if G.node[n][setting]]
     train_labels = np.array([labels[i] for i in train_ids])
+    if train_labels.ndim == 1:
+        train_labels = np.expand_dims(train_labels, 1)
     test_labels = np.array([labels[i] for i in test_ids])
     print("running", data_dir)
 
@@ -45,7 +58,7 @@ if __name__ == '__main__':
         ## Logistic gets thrown off by big counts, so log transform num comments and score
         feats[:,0] = np.log(feats[:,0]+1.0)
         feats[:,1] = np.log(feats[:,1]-min(np.min(feats[:,1]), -1))
-        feat_id_map = json.load(open("/dfs/scratch0/graphnet/ppi/ppi-id_map.json"))
+        feat_id_map = json.load(open(dataset_dir + "/ppi-id_map.json"))
         feat_id_map = {int(id):val for id,val in feat_id_map.iteritems()}
         train_feats = feats[[feat_id_map[id] for id in train_ids]] 
         test_feats = feats[[feat_id_map[id] for id in test_ids]] 

graphsage/minibatch.py

@@ -125,6 +125,9 @@ class EdgeMinibatchIterator(object):
         batch_edges = self.train_edges[start : start + self.batch_size]
         return self.batch_feed_dict(batch_edges)
 
+    def num_training_batches(self):
+        return len(self.train_edges) // self.batch_size + 1
+
     def val_feed_dict(self, size=None):
         edge_list = self.val_edges
         if size is None:
@@ -287,6 +290,9 @@ class NodeMinibatchIterator(object):
         ret_val = self.batch_feed_dict(val_node_subset)
         return ret_val[0], ret_val[1], (iter_num+1)*size >= len(val_nodes), val_node_subset
 
+    def num_training_batches(self):
+        return len(self.train_nodes) // self.batch_size + 1
+
     def next_minibatch_feed_dict(self):
         start = self.batch_num * self.batch_size
         self.batch_num += 1

graphsage/utils.py

@@ -81,4 +81,4 @@ if __name__ == "__main__":
     G = G.subgraph(nodes)
     pairs = run_random_walks(G, nodes)
     with open(out_file, "w") as fp:
-        fp.write("\n".join([p[0] + "\t" + p[1] for p in pairs]))
+        fp.write("\n".join([str(p[0]) + "\t" + str(p[1]) for p in pairs]))