OpenI
/
graphkit-learn
Not watched
1
0
Fork 0
Code
Releases 2 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
Tree: 819b256335
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '819b256335'
${ noResults }
graphkit-learn/datasets/ds.py

186 lines
6.6 kB
Raw Blame History 

  1. dslist = [

  2.     {

  3.         'name': 'Acyclic',

  4.         'dataset': '../datasets/acyclic/dataset_bps.ds',

  5.         'task': 'regression'

  6.     },  # node symb

  7.     #     {'name': 'COIL-DEL', 'dataset': '../datasets/COIL-DEL/COIL-DEL_A.txt'}, # edge symb, node nsymb

  8.     {

  9.         'name': 'PAH',

  10.         'dataset': '../datasets/PAH/dataset.ds',

  11.     },  # unlabeled

  12.     {

  13.         'name': 'MAO',

  14.         'dataset': '../datasets/MAO/dataset.ds',

  15.     },  # node/edge symb

  16.     {

  17.         'name': 'MUTAG',

  18.         'dataset': '../datasets/MUTAG/MUTAG.mat',

  19.         'extra_params': {

  20.             'am_sp_al_nl_el': [0, 0, 3, 1, 2]

  21.         }

  22.     },  # node/edge symb

  23.     {

  24.         'name': 'Alkane',

  25.         'dataset': '../datasets/Alkane/dataset.ds',

  26.         'task': 'regression',

  27.         'dataset_y': '../datasets/Alkane/dataset_boiling_point_names.txt',

  28.     },  # contains single node graph, node symb

  29.     #     {'name': 'BZR', 'dataset': '../datasets/BZR_txt/BZR_A_sparse.txt'}, # node symb/nsymb

  30.     #     {'name': 'COX2', 'dataset': '../datasets/COX2_txt/COX2_A_sparse.txt'}, # node symb/nsymb

  31.     {

  32.         'name': 'Mutagenicity',

  33.         'dataset': '../datasets/Mutagenicity/Mutagenicity_A.txt'

  34.     },  # node/edge symb

  35.     {

  36.         'name': 'ENZYMES',

  37.         'dataset': '../datasets/ENZYMES_txt/ENZYMES_A_sparse.txt'

  38.     },  # node symb/nsymb

  39.     #     {'name': 'Fingerprint', 'dataset': '../datasets/Fingerprint/Fingerprint_A.txt'},

  40.     {

  41.         'name': 'Letter-med',

  42.         'dataset': '../datasets/Letter-med/Letter-med_A.txt'

  43.     },

  44.     #     {'name': 'DHFR', 'dataset': '../datasets/DHFR_txt/DHFR_A_sparse.txt'}, # node symb/nsymb

  45.     #     {'name': 'SYNTHETIC', 'dataset': '../datasets/SYNTHETIC_txt/SYNTHETIC_A_sparse.txt'}, # node symb/nsymb

  46.     #     {'name': 'MSRC9', 'dataset': '../datasets/MSRC_9_txt/MSRC_9_A.txt'}, # node symb

  47.     #     {'name': 'MSRC21', 'dataset': '../datasets/MSRC_21_txt/MSRC_21_A.txt'}, # node symb

  48.     #     {'name': 'FIRSTMM_DB', 'dataset': '../datasets/FIRSTMM_DB/FIRSTMM_DB_A.txt'}, # node symb/nsymb ,edge nsymb

  49. 

  50.     #     {'name': 'PROTEINS', 'dataset': '../datasets/PROTEINS_txt/PROTEINS_A_sparse.txt'}, # node symb/nsymb

  51.     #     {'name': 'PROTEINS_full', 'dataset': '../datasets/PROTEINS_full_txt/PROTEINS_full_A_sparse.txt'}, # node symb/nsymb

  52.     {

  53.         'name': 'D&D',

  54.         'dataset': '../datasets/D&D/DD.mat',

  55.         'extra_params': {

  56.             'am_sp_al_nl_el': [0, 1, 2, 1, -1]

  57.         }

  58.     },  # node symb

  59.     #     {'name': 'AIDS', 'dataset': '../datasets/AIDS/AIDS_A.txt'}, # node symb/nsymb, edge symb

  60.     #     {'name': 'NCI1', 'dataset': '../datasets/NCI1/NCI1.mat',

  61.     #         'extra_params': {'am_sp_al_nl_el': [1, 1, 2, 0, -1]}}, # node symb

  62.     #     {'name': 'NCI109', 'dataset': '../datasets/NCI109/NCI109.mat',

  63.     #         'extra_params': {'am_sp_al_nl_el': [1, 1, 2, 0, -1]}}, # node symb

  64.     #     {'name': 'NCI-HIV', 'dataset': '../datasets/NCI-HIV/AIDO99SD.sdf',

  65.     #         'dataset_y': '../datasets/NCI-HIV/aids_conc_may04.txt',}, # node/edge symb

  66. 

  67.     #     # not working below

  68.     #     {'name': 'PTC_FM', 'dataset': '../datasets/PTC/Train/FM.ds',},

  69.     #     {'name': 'PTC_FR', 'dataset': '../datasets/PTC/Train/FR.ds',},

  70.     #     {'name': 'PTC_MM', 'dataset': '../datasets/PTC/Train/MM.ds',},

  71.     #     {'name': 'PTC_MR', 'dataset': '../datasets/PTC/Train/MR.ds',},

  72. ]

  73. 

  74. # dslist = [

  75. #     {

  76. #         'name': 'Acyclic',

  77. #         'dataset': '../datasets/acyclic/dataset_bps.ds',

  78. #         'task': 'regression'

  79. #     },  # node_labeled

  80. #     {

  81. #         'name': 'COIL-DEL',

  82. #         'dataset': '../datasets/COIL-DEL/COIL-DEL_A.txt'

  83. #     },  # edge_labeled

  84. #     {

  85. #         'name': 'PAH',

  86. #         'dataset': '../datasets/PAH/dataset.ds',

  87. #     },  # unlabeled

  88. #     {

  89. #         'name': 'Mutagenicity',

  90. #         'dataset': '../datasets/Mutagenicity/Mutagenicity_A.txt'

  91. #     },  # fully_labeled

  92. #     {

  93. #         'name': 'MAO',

  94. #         'dataset': '../datasets/MAO/dataset.ds',

  95. #     },

  96. #     {

  97. #         'name': 'MUTAG',

  98. #         'dataset': '../datasets/MUTAG/MUTAG.mat',

  99. #         'extra_params': {

  100. #             'am_sp_al_nl_el': [0, 0, 3, 1, 2]

  101. #         }

  102. #     },

  103. #     {

  104. #         'name': 'Alkane',

  105. #         'dataset': '../datasets/Alkane/dataset.ds',

  106. #         'task': 'regression',

  107. #         'dataset_y': '../datasets/Alkane/dataset_boiling_point_names.txt',

  108. #     },

  109. #     {

  110. #         'name': 'BZR',

  111. #         'dataset': '../datasets/BZR_txt/BZR_A_sparse.txt'

  112. #     },

  113. #     {

  114. #         'name': 'COX2',

  115. #         'dataset': '../datasets/COX2_txt/COX2_A_sparse.txt'

  116. #     },

  117. #     {

  118. #         'name': 'ENZYMES',

  119. #         'dataset': '../datasets/ENZYMES_txt/ENZYMES_A_sparse.txt'

  120. #     },

  121. #     {

  122. #         'name': 'DHFR',

  123. #         'dataset': '../datasets/DHFR_txt/DHFR_A_sparse.txt'

  124. #     },

  125. #     {

  126. #         'name': 'SYNTHETIC',

  127. #         'dataset': '../datasets/SYNTHETIC_txt/SYNTHETIC_A_sparse.txt'

  128. #     },

  129. #     {

  130. #         'name': 'MSRC9',

  131. #         'dataset': '../datasets/MSRC_9_txt/MSRC_9_A.txt'

  132. #     },

  133. #     {

  134. #         'name': 'MSRC21',

  135. #         'dataset': '../datasets/MSRC_21_txt/MSRC_21_A.txt'

  136. #     },

  137. #     {

  138. #         'name': 'FIRSTMM_DB',

  139. #         'dataset': '../datasets/FIRSTMM_DB/FIRSTMM_DB_A.txt'

  140. #     },

  141. #     {

  142. #         'name': 'PROTEINS',

  143. #         'dataset': '../datasets/PROTEINS_txt/PROTEINS_A_sparse.txt'

  144. #     },

  145. #     {

  146. #         'name': 'PROTEINS_full',

  147. #         'dataset': '../datasets/PROTEINS_full_txt/PROTEINS_full_A_sparse.txt'

  148. #     },

  149. #     {

  150. #         'name': 'D&D',

  151. #         'dataset': '../datasets/D&D/DD.mat',

  152. #         'extra_params': {

  153. #             'am_sp_al_nl_el': [0, 1, 2, 1, -1]

  154. #         }

  155. #     },

  156. #     {

  157. #         'name': 'AIDS',

  158. #         'dataset': '../datasets/AIDS/AIDS_A.txt'

  159. #     },

  160. #     {

  161. #         'name': 'NCI1',

  162. #         'dataset': '../datasets/NCI1/NCI1.mat',

  163. #         'extra_params': {

  164. #             'am_sp_al_nl_el': [1, 1, 2, 0, -1]

  165. #         }

  166. #     },

  167. #     {

  168. #         'name': 'NCI109',

  169. #         'dataset': '../datasets/NCI109/NCI109.mat',

  170. #         'extra_params': {

  171. #             'am_sp_al_nl_el': [1, 1, 2, 0, -1]

  172. #         }

  173. #     },

  174. #     {

  175. #         'name': 'NCI-HIV',

  176. #         'dataset': '../datasets/NCI-HIV/AIDO99SD.sdf',

  177. #         'dataset_y': '../datasets/NCI-HIV/aids_conc_may04.txt',

  178. #     },

  179. 

  180. #     #     # not working below

  181. #     #     {'name': 'PTC_FM', 'dataset': '../datasets/PTC/Train/FM.ds',},

  182. #     #     {'name': 'PTC_FR', 'dataset': '../datasets/PTC/Train/FR.ds',},

  183. #     #     {'name': 'PTC_MM', 'dataset': '../datasets/PTC/Train/MM.ds',},

  184. #     #     {'name': 'PTC_MR', 'dataset': '../datasets/PTC/Train/MR.ds',},

  185. # ]