Erostrate9
commented
4 weeks ago Thanks for sharing this code. I'm trying to run it and I encountered an issue with Join2Vec (cf. error message below). It seems that there is a problem with data format in example data (And it may be helpful to guide how to generate the example data in Join2Vec 🙂) Thanks, in advance!
INFO:root:Loaded 2 graph file names form ../example_data/datasets/node_edges INFO:root:Dumped subgraph2vec sentences for all 2 graphs in ../example_data/datasets/node_edges in 0.0 sec INFO:root:The embedding file: ../embeddings/node_edges_dims_4_epochs_3_embeddings.txt is already present, hence NOT training skipgram model for subgraph vectors INFO:root:Trained the skipgram model in 0.0 sec. INFO:gensim.models.utils_any2vec:loading projection weights from ../embeddings/node_edges_dims_4_epochs_3_embeddings.txt INFO:gensim.models.utils_any2vec:loaded (22, 4) matrix from ../embeddings/node_edges_dims_4_epochs_3_embeddings.txt INFO:root:Loaded gensim model of subgraph vectors INFO:root:Vocab consists of 22 subgraph features INFO:root:Loaded 2 graph WL kernel files for performing classification INFO:root:X (sample) matrix shape: (2, 22) ['../example_data/datasets/node_edges/0.WL2', '../example_data/datasets/node_edges/1.WL2'] INFO:root:Y (label) matrix shape: (2,) INFO:root:Train and Test matrix shapes: (1, 22), (1, 22), (1,), (1,) Traceback (most recent call last): File "main.py", line 105, in <module> main(args) File "main.py", line 53, in main perform_classification (corpus_dir, wl_extn, embedding_fname, class_labels_fname) File "/data/pjz_data/sql/vldb2021_fauce/queries_featurization/Joins2Vec/classify.py", line 128, in perform_classification linear_kernel_svm_classify(X_train, X_test, Y_train, Y_test) File "/data/pjz_data/sql/vldb2021_fauce/queries_featurization/Joins2Vec/classify.py", line 55, in linear_kernel_svm_classify classifier.fit(train_kernel.toarray(), Y_train) File "/home/zju/anaconda3/envs/gensim/lib/python2.7/site-packages/sklearn/svm/base.py", line 150, in fit y = self._validate_targets(y) File "/home/zju/anaconda3/envs/gensim/lib/python2.7/site-packages/sklearn/svm/base.py", line 525, in _validate_targets " class" % len(cls)) ValueError: The number of classes has to be greater than one; got 1 class请问最后解决了吗？我不明白gexf文件里attvalue是什么含义。为什么example_data里有0.gexf和1.gexf两个不同的图呢？
Thanks for sharing this code. I'm trying to run it and I encountered an issue with Join2Vec (cf. error message below). It seems that there is a problem with data format in example data (And it may be helpful to guide how to generate the example data in Join2Vec 🙂) Thanks, in advance!