train_test_split_no_unseen¶
-
ampligraph.evaluation.
train_test_split_no_unseen
(X, test_size=5000, seed=0)¶ Split into train and test sets.
Test set contains only entities and relations which also occur in the training set.Parameters: - X (ndarray, size[n, 3]) – The dataset to split.
- test_size (int, float) – If int, the number of triples in the test set. If float, the percentage of total triples.
- seed (int) – A random seed used to split the dataset.
Returns: - X_train (ndarray, size[n, 3]) – The training set
- X_test (ndarray, size[n, 3]) – The test set