Skip to content

Commit

Permalink
[doc] update YAML spec (#6812)
Browse files Browse the repository at this point in the history
  • Loading branch information
@Rhett-Ying
Rhett-Ying authored Dec 22, 2023
1 parent 3e59b1d commit 017b6bb
Show file tree
Hide file tree
Showing 2 changed files with 58 additions and 65 deletions.
96 changes: 46 additions & 50 deletions notebooks/stochastic_training/ondisk_dataset_heterograph.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -524,105 +524,101 @@
" - name: node_classification\n",
" num_classes: 10\n",
" train_set:\n",
" - data:\n",
" - type: user\n",
" name: seed_nodes\n",
" - type: user\n",
" data:\n",
" - name: seed_nodes\n",
" format: numpy\n",
" path: {os.path.basename(nc_train_user_ids_path)}\n",
" - type: user\n",
" name: labels\n",
" - name: labels\n",
" format: torch\n",
" path: {os.path.basename(nc_train_user_labels_path)}\n",
" - type: item\n",
" name: seed_nodes\n",
" - type: item\n",
" data:\n",
" - name: seed_nodes\n",
" format: numpy\n",
" path: {os.path.basename(nc_train_item_ids_path)}\n",
" - type: item\n",
" name: labels\n",
" - name: labels\n",
" format: torch\n",
" path: {os.path.basename(nc_train_item_labels_path)}\n",
" validation_set:\n",
" - data:\n",
" - type: user\n",
" name: seed_nodes\n",
" - type: user\n",
" data:\n",
" - name: seed_nodes\n",
" format: numpy\n",
" path: {os.path.basename(nc_val_user_ids_path)}\n",
" - type: user\n",
" name: labels\n",
" - name: labels\n",
" format: torch\n",
" path: {os.path.basename(nc_val_user_labels_path)}\n",
" - type: item\n",
" name: seed_nodes\n",
" - type: item\n",
" data:\n",
" - name: seed_nodes\n",
" format: numpy\n",
" path: {os.path.basename(nc_val_item_ids_path)}\n",
" - type: item\n",
" name: labels\n",
" - name: labels\n",
" format: torch\n",
" path: {os.path.basename(nc_val_item_labels_path)}\n",
" test_set:\n",
" - data:\n",
" - type: user\n",
" name: seed_nodes\n",
" - type: user\n",
" data:\n",
" - name: seed_nodes\n",
" format: numpy\n",
" path: {os.path.basename(nc_test_user_ids_path)}\n",
" - type: user\n",
" name: labels\n",
" - name: labels\n",
" format: torch\n",
" path: {os.path.basename(nc_test_user_labels_path)}\n",
" - type: item\n",
" name: seed_nodes\n",
" - type: item\n",
" data:\n",
" - name: seed_nodes\n",
" format: numpy\n",
" path: {os.path.basename(nc_test_item_ids_path)}\n",
" - type: item\n",
" name: labels\n",
" - name: labels\n",
" format: torch\n",
" path: {os.path.basename(nc_test_item_labels_path)}\n",
" - name: link_prediction\n",
" num_classes: 10\n",
" train_set:\n",
" - data:\n",
" - type: \"user:like:item\"\n",
" name: node_pairs\n",
" - type: \"user:like:item\"\n",
" data:\n",
" - name: node_pairs\n",
" format: numpy\n",
" path: {os.path.basename(lp_train_like_node_pairs_path)}\n",
" - type: \"user:follow:user\"\n",
" name: node_pairs\n",
" - type: \"user:follow:user\"\n",
" data:\n",
" - name: node_pairs\n",
" format: numpy\n",
" path: {os.path.basename(lp_train_follow_node_pairs_path)}\n",
" validation_set:\n",
" - data:\n",
" - type: \"user:like:item\"\n",
" name: node_pairs\n",
" - type: \"user:like:item\"\n",
" data:\n",
" - name: node_pairs\n",
" format: numpy\n",
" path: {os.path.basename(lp_val_like_node_pairs_path)}\n",
" - type: \"user:like:item\"\n",
" name: negative_dsts\n",
" - name: negative_dsts\n",
" format: torch\n",
" path: {os.path.basename(lp_val_like_neg_dsts_path)}\n",
" - type: \"user:follow:user\"\n",
" name: node_pairs\n",
" - type: \"user:follow:user\"\n",
" data:\n",
" - name: node_pairs\n",
" format: numpy\n",
" path: {os.path.basename(lp_val_follow_node_pairs_path)}\n",
" - type: \"user:follow:user\"\n",
" name: negative_dsts\n",
" - name: negative_dsts\n",
" format: torch\n",
" path: {os.path.basename(lp_val_follow_neg_dsts_path)}\n",
" test_set:\n",
" - data:\n",
" - type: \"user:like:item\"\n",
" name: node_pairs\n",
" - type: \"user:like:item\"\n",
" data:\n",
" - name: node_pairs\n",
" format: numpy\n",
" path: {os.path.basename(lp_test_like_node_pairs_path)}\n",
" - type: \"user:like:item\"\n",
" name: negative_dsts\n",
" - name: negative_dsts\n",
" format: torch\n",
" path: {os.path.basename(lp_test_like_neg_dsts_path)}\n",
" - type: \"user:follow:user\"\n",
" name: node_pairs\n",
" - type: \"user:follow:user\"\n",
" data:\n",
" - name: node_pairs\n",
" format: numpy\n",
" path: {os.path.basename(lp_test_follow_node_pairs_path)}\n",
" - type: \"user:follow:user\"\n",
" name: negative_dsts\n",
" - name: negative_dsts\n",
" format: torch\n",
" path: {os.path.basename(lp_test_follow_neg_dsts_path)}\n",
"\"\"\"\n",
Expand Down
27 changes: 12 additions & 15 deletions python/dgl/graphbolt/impl/ondisk_dataset.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -319,34 +319,31 @@ class OnDiskDataset(Dataset):
- name: "edge_classification"
num_classes: 10
train_set:
- data: # multiple data sources could be specified.
- type: paper
name: node_pairs
- type: paper # could be omitted for homogeneous graph.
data: # multiple data sources could be specified.
- name: node_pairs
format: numpy # Can be numpy or torch.
in_memory: true # If not specified, default to true.
path: set/paper-train-node_pairs.npy
- type: paper
name: labels
- name: labels
format: numpy
path: set/paper-train-labels.npy
validation_set:
- data:
- type: paper
name: node_pairs
- type: paper
data:
- name: node_pairs
format: numpy
path: set/paper-validation-node_pairs.npy
- type: paper
name: labels
- name: labels
format: numpy
path: set/paper-validation-labels.npy
test_set:
- data:
- type: paper
name: node_pairs
- type: paper
data:
- name: node_pairs
format: numpy
path: set/paper-test-node_pairs.npy
- type: paper
name: labels
- name: labels
format: numpy
path: set/paper-test-labels.npy
Expand Down

0 comments on commit 017b6bb

Please sign in to comment.