swift

04-data2swift.py

@@ -1,27 +1,48 @@
 import json
 import random
 
-input_file = "arxiv-metadata-oai-snapshot--ratio.json"   # 20000条原始数据文件路径
-output_file = "arxiv-metadata-oai-snapshot--swift.json"
+input_file = "arxiv-metadata-oai-snapshot--26-500.json"   # 20000条原始数据文件路径
+output_file = "arxiv-metadata-oai-snapshot--swift-26-500.json"
 
 # 类别对应选项映射
 label_map = {
-    "astro-ph": "A",
-    "cond-mat.mes-hall": "B",
-    "cond-mat.mtrl-sci": "C",
-    "cs.CL": "D",
-    "cs.CV": "E",
-    "cs.LG": "F",
-    "gr-qc": "G",
-    "hep-ph": "H",
-    "hep-th": "I",
-    "quant-ph": "J"
+        'quant-ph': 'A',
+        'physics.chem-ph': 'B', 
+        'physics.atom-ph': 'C',
+        'cond-mat.soft': 'D',
+        'cs.RO': 'E',
+        'cs.CL': 'F',
+        'cs.SE': 'G',
+        'cs.IR': 'H',
+        'hep-th': 'I',
+        'hep-ph': 'J',
+        'physics.optics': 'K',
+        'cs.AI': 'L',
+        'cs.CV': 'M',
+        'nucl-th': 'N',
+        'astro-ph': 'O',
+        'math.PR': 'P',
+        'cs.OS': 'Q',
+        'eess.SP': 'R',
+        'math.OC': 'S',
+        'math.DS': 'T',
+        'math.DG': 'U',
+        'math.MP': 'V',
+        'cs.MM': 'W',
+        'stat.ME': 'X',
+        'math.CO': 'Y',
+        'cs.NE': 'Z'
 }
 
-options_text = (
-    "\n\nA. astro-ph\nB. cond-mat.mes-hall\nC. cond-mat.mtrl-sci\nD. cs.CL\n"
-    "E. cs.CV\nF. cs.LG\nG. gr-qc\nH. hep-ph\nI. hep-th\nJ. quant-ph"
-)
+options = [
+    "A. quant-ph", "B. physics.chem-ph", "C. physics.atom-ph", "D. cond-mat.soft",
+    "E. cs.RO", "F. cs.CL", "G. cs.SE", "H. cs.IR", "I. hep-th", "J. hep-ph",
+    "K. physics.optics", "L. cs.AI", "M. cs.CV", "N. nucl-th", "O. astro-ph",
+    "P. math.PR", "Q. cs.OS", "R. eess.SP", "S. math.OC", "T. math.DS",
+    "U. math.DG", "V. math.MP", "W. cs.MM", "X. stat.ME", "Y. math.CO", "Z. cs.NE"
+]
+
+options_text = "\n".join(options)
 
 # 读取所有数据
 with open(input_file, 'r', encoding='utf-8') as f: