Creation of arxiv-2023 folder

datasets/arxiv-2023/LICENSE

@@ -0,0 +1,8 @@
+The MIT License (MIT)
+Copyright (c) 2016 Zhilin Yang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

datasets/arxiv-2023/README.md

@@ -0,0 +1,82 @@
+# ARXIV-2023
+
+## Dataset Description
+
+A text attributed graph dataset where each node is associated with multiple text attributes.
+It is collected to be compared with ogbn-arxiv. Both datasets represent directed citation networks where each node corresponds to a paper published on arXiv and each edge indicates one paper citing another.
+
+Statistics:
+- Nodes: 33868
+- Edges: 305672
+- Number of Classes: 40
+
+#### Citation
+
+- Original Source
+	+ [Website](https://github.com/TRAIS-Lab/LLM-Structured-Data)
+
+
+
+```
+@misc{huang2023llms,
+      title={Can LLMs Effectively Leverage Graph Structural Information: When and Why}, 
+      author={Jin Huang and Xingjian Zhang and Qiaozhu Mei and Jiaqi Ma},
+      year={2023},
+      eprint={2309.16595},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+
+- Current Version
+	+ [Website](https://github.com/TRAIS-Lab/LLM-Structured-Data)
+
+
+
+```
+@misc{huang2023llms,
+      title={Can LLMs Effectively Leverage Graph Structural Information: When and Why}, 
+      author={Jin Huang and Xingjian Zhang and Qiaozhu Mei and Jiaqi Ma},
+      year={2023},
+      eprint={2309.16595},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+
+
+## Available Tasks
+
+
+- Task type: `NodeClassification`
+
+
+#### Citation
+
+```
+@misc{huang2023llms,
+      title={Can LLMs Effectively Leverage Graph Structural Information: When and Why}, 
+      author={Jin Huang and Xingjian Zhang and Qiaozhu Mei and Jiaqi Ma},
+      year={2023},
+      eprint={2309.16595},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+
+<!-- Insert the BibTeX citation into the above code block. -->
+
+## Preprocessing
+
+The data files and task config file in GLI format are transformed in arxiv-2023.ipynb file. Raw data aquried in TRAIS-Lab/LLM-Structured-Data folder.
+
+### Requirements
+
+```
+openai
+pytorch
+PyG
+ogb
+```
+
+

datasets/arxiv-2023/arxiv-2023.ipynb

@@ -0,0 +1,194 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# arxiv-2023 conversion script"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/51/yl5_04f90f13_y68cyyqz0j80000gn/T/ipykernel_48974/3045227301.py:3: DeprecationWarning: \n",
+      "Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0),\n",
+      "(to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries)\n",
+      "but was not found to be installed on your system.\n",
+      "If this would cause problems for you,\n",
+      "please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466\n",
+      "        \n",
+      "  import pandas as pd\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import torch\n",
+    "import pandas as pd\n",
+    "import numpy\n",
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_path=\"./LLM/dataset/arxiv_2023\"\n",
+    "# Load processed data\n",
+    "edge_index = torch.load(os.path.join(base_path, \"processed\", \"edge_index.pt\"))\n",
+    "    \n",
+    "# Load raw data\n",
+    "# edge_df = pd.read_csv(os.path.join(base_path, \"raw\", \"edge.csv.gz\"), compression='gzip')\n",
+    "titles_df = pd.read_csv(os.path.join(base_path, \"raw\", \"titles.csv.gz\"), compression='gzip')\n",
+    "abstracts_df = pd.read_csv(os.path.join(base_path, \"raw\", \"abstracts.csv.gz\"), compression='gzip')\n",
+    "ids_df = pd.read_csv(os.path.join(base_path, \"raw\", \"ids.csv.gz\"), compression='gzip')\n",
+    "labels_df = pd.read_csv(os.path.join(base_path, \"raw\", \"labels.csv.gz\"), compression='gzip')\n",
+    "    \n",
+    "# Load split data\n",
+    "train_id_df = pd.read_csv(os.path.join(base_path, \"split\", \"train.csv.gz\"), compression='gzip')\n",
+    "val_id_df = pd.read_csv(os.path.join(base_path, \"split\", \"valid.csv.gz\"), compression='gzip')\n",
+    "test_id_df = pd.read_csv(os.path.join(base_path, \"split\", \"test.csv.gz\"), compression='gzip')\n",
+    "    \n",
+    "num_nodes = len(ids_df)\n",
+    "titles = titles_df['titles'].tolist()\n",
+    "abstracts = abstracts_df['abstracts'].tolist()\n",
+    "ids = ids_df['ids'].tolist()\n",
+    "labels = labels_df['labels'].tolist()\n",
+    "train_id = train_id_df['train_id'].tolist()\n",
+    "val_id = val_id_df['val_id'].tolist()\n",
+    "test_id = test_id_df['test_id'].tolist()\n",
+    "\n",
+    "features = torch.load(os.path.join(base_path, \"processed\", \"features.pt\"))\n",
+    "\n",
+    "y = torch.load(os.path.join(base_path, \"processed\", \"labels.pt\"))\n",
+    "    \n",
+    "train_mask = torch.tensor([x in train_id for x in range(num_nodes)])\n",
+    "val_mask = torch.tensor([x in val_id for x in range(num_nodes)])\n",
+    "test_mask = torch.tensor([x in test_id for x in range(num_nodes)])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from gli.io import save_graph, Attribute\n",
+    "node_attrs=[\n",
+    "  Attribute(\n",
+    "    \"Titles\",\n",
+    "    numpy.array(titles),\n",
+    "    \"Title of each node\",\n",
+    "    \"str\",\n",
+    "    \"Tensor\",\n",
+    "  ),\n",
+    "  Attribute(\n",
+    "    \"Abstracts\",\n",
+    "    numpy.array(abstracts),\n",
+    "    \"Abstract of each article(node)\",\n",
+    "    \"str\",\n",
+    "    \"Tensor\",\n",
+    "  ),\n",
+    "  Attribute(\n",
+    "    \"Ids\",\n",
+    "    numpy.array([str(id) for id in ids]),\n",
+    "    \"Id of each article(node)\",\n",
+    "    \"str\",\n",
+    "    \"Tensor\",\n",
+    "  ),\n",
+    "  Attribute(\n",
+    "    \"Labels\",\n",
+    "    numpy.array(labels),\n",
+    "    \"Label\",\n",
+    "    \"str\",\n",
+    "    \"Tensor\",\n",
+    "  ),\n",
+    "  \n",
+    "]\n",
+    "\n",
+    "metadata = save_graph(\n",
+    "  name=\"arxiv-2023\",\n",
+    "  edge=numpy.array(edge_index).T,\n",
+    "  num_nodes=num_nodes,\n",
+    "  node_attrs=node_attrs,\n",
+    "  description=\"ARXIV-2023 dataset.\",\n",
+    "  cite=\"@misc{huang2023llms,\\ntitle={Can LLMs Effectively Leverage Graph Structural Information: When and Why},\\nauthor={Jin Huang and Xingjian Zhang and Qiaozhu Mei and Jiaqi Ma},\\nyear={2023},\\neprint={2309.16595},\\narchivePrefix={arXiv},\\nprimaryClass={cs.LG}\\n}\",\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([    4,     6,     9, ..., 33865, 33866, 33867])"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from gli.io import save_task_node_classification\n",
+    "\n",
+    "task_data = save_task_node_classification(\n",
+    "  name=\"arxiv-2023\",\n",
+    "  description=\"Node classification on arxiv-2023 dataset.\",\n",
+    "  feature=[\"Node/Titles\",\"Node/Abstracts\"],\n",
+    "  target=\"Node/Labels\",\n",
+    "  num_classes=40,\n",
+    "  train_set=train_mask.nonzero().squeeze().numpy(),\n",
+    "  val_set=val_mask.nonzero().nonzero().squeeze().numpy(),\n",
+    "  test_set=test_mask.nonzero().nonzero().squeeze().numpy(),\n",
+    "  task_id=\"1\"\n",
+    ")\n",
+    "train_mask.nonzero().squeeze().numpy()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

datasets/arxiv-2023/metadata.json

@@ -0,0 +1,48 @@
+{
+    "description": "ARXIV-2023 dataset.",
+    "data": {
+        "Node": {
+            "Titles": {
+                "description": "Title of each node",
+                "type": "str",
+                "format": "Tensor",
+                "file": "arxiv-2023__graph__4c1b3c1c22882e1d9660a6e5cafcd1a4.npz",
+                "key": "Node_Titles"
+            },
+            "Abstracts": {
+                "description": "Abstract of each article(node)",
+                "type": "str",
+                "format": "Tensor",
+                "file": "arxiv-2023__graph__4c1b3c1c22882e1d9660a6e5cafcd1a4.npz",
+                "key": "Node_Abstracts"
+            },
+            "Ids": {
+                "description": "Id of each article(node)",
+                "type": "str",
+                "format": "Tensor",
+                "file": "arxiv-2023__graph__4c1b3c1c22882e1d9660a6e5cafcd1a4.npz",
+                "key": "Node_Ids"
+            },
+            "Labels": {
+                "description": "Label",
+                "type": "str",
+                "format": "Tensor",
+                "file": "arxiv-2023__graph__4c1b3c1c22882e1d9660a6e5cafcd1a4.npz",
+                "key": "Node_Labels"
+            }
+        },
+        "Edge": {
+            "_Edge": {
+                "file": "arxiv-2023__graph__4c1b3c1c22882e1d9660a6e5cafcd1a4.npz",
+                "key": "Edge_Edge"
+            }
+        },
+        "Graph": {
+            "_NodeList": {
+                "file": "arxiv-2023__graph__Graph_NodeList__a133ca6cee0eff3cc4ae10d024cc0c02.sparse.npz"
+            }
+        }
+    },
+    "citation": "@misc{huang2023llms,\ntitle={Can LLMs Effectively Leverage Graph Structural Information: When and Why},\nauthor={Jin Huang and Xingjian Zhang and Qiaozhu Mei and Jiaqi Ma},\nyear={2023},\neprint={2309.16595},\narchivePrefix={arXiv},\nprimaryClass={cs.LG}\n}",
+    "is_heterogeneous": false
+}

datasets/arxiv-2023/task_node_classification_1.json

@@ -0,0 +1,22 @@
+{
+    "description": "Node classification on arxiv-2023 dataset.",
+    "type": "NodeClassification",
+    "feature": [
+        "Node/Titles",
+        "Node/Abstracts"
+    ],
+    "target": "Node/Labels",
+    "num_classes": 40,
+    "train_set": {
+        "file": "arxiv-2023__task_node_classification_1__707e9444940a9744a72ae8a990fe9136.npz",
+        "key": "train_set"
+    },
+    "val_set": {
+        "file": "arxiv-2023__task_node_classification_1__707e9444940a9744a72ae8a990fe9136.npz",
+        "key": "val_set"
+    },
+    "test_set": {
+        "file": "arxiv-2023__task_node_classification_1__707e9444940a9744a72ae8a990fe9136.npz",
+        "key": "test_set"
+    }
+}