[Model] Implement model Unimp

gammagl/datasets/OgbGraphData.csv

@@ -0,0 +1,16 @@
+,ogbg-molbace,ogbg-molbbbp,ogbg-molclintox,ogbg-molmuv,ogbg-molpcba,ogbg-molsider,ogbg-moltox21,ogbg-moltoxcast,ogbg-molhiv,ogbg-molesol,ogbg-molfreesolv,ogbg-mollipo,ogbg-molchembl,ogbg-ppa,ogbg-code2
+num tasks,1,1,2,17,128,27,12,617,1,1,1,1,1310,1,1
+eval metric,rocauc,rocauc,rocauc,ap,ap,rocauc,rocauc,rocauc,rocauc,rmse,rmse,rmse,rocauc,acc,F1
+download_name,bace,bbbp,clintox,muv,pcba,sider,tox21,toxcast,hiv,esol,freesolv,lipophilicity,chembl,ogbg_ppi_medium,code2
+version,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
+url,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/bace.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/bbbp.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/clintox.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/muv.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/pcba.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/sider.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/tox21.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/toxcast.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/hiv.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/esol.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/freesolv.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/lipophilicity.zip,http://snap.stanford.edu/ogb/data/graphproppred/csv_mol_download/chembl.zip,http://snap.stanford.edu/ogb/data/graphproppred/ogbg_ppi_medium.zip,http://snap.stanford.edu/ogb/data/graphproppred/code2.zip
+add_inverse_edge,True,True,True,True,True,True,True,True,True,True,True,True,True,True,False
+data type,mol,mol,mol,mol,mol,mol,mol,mol,mol,mol,mol,mol,mol,,
+has_node_attr,True,True,True,True,True,True,True,True,True,True,True,True,True,False,True
+has_edge_attr,True,True,True,True,True,True,True,True,True,True,True,True,True,True,False
+task type,binary classification,binary classification,binary classification,binary classification,binary classification,binary classification,binary classification,binary classification,binary classification,regression,regression,regression,binary classification,multiclass classification,subtoken prediction
+num classes,2,2,2,2,2,2,2,2,2,-1,-1,-1,2,37,-1
+split,scaffold,scaffold,scaffold,scaffold,scaffold,scaffold,scaffold,scaffold,scaffold,scaffold,scaffold,scaffold,scaffold,species,project
+additional node files,None,None,None,None,None,None,None,None,None,None,None,None,None,None,"node_is_attributed,node_dfs_order,node_depth"
+additional edge files,None,None,None,None,None,None,None,None,None,None,None,None,None,None,None
+binary,False,False,False,False,False,False,False,False,False,False,False,False,False,False,False

gammagl/datasets/OgbLinkData.csv

@@ -0,0 +1,14 @@
+,ogbl-ppa,ogbl-collab,ogbl-citation2,ogbl-wikikg2,ogbl-ddi,ogbl-biokg,ogbl-vessel
+eval metric,hits@100,hits@50,mrr,mrr,hits@20,mrr,rocauc
+task type,link prediction,link prediction,link prediction,KG completion,link prediction,KG completion,link prediction
+download_name,ppassoc,collab,citation-v2,wikikg-v2,ddi,biokg,vessel
+version,1,1,1,1,1,1,1
+url,http://snap.stanford.edu/ogb/data/linkproppred/ppassoc.zip,http://snap.stanford.edu/ogb/data/linkproppred/collab.zip,http://snap.stanford.edu/ogb/data/linkproppred/citation-v2.zip,http://snap.stanford.edu/ogb/data/linkproppred/wikikg-v2.zip,http://snap.stanford.edu/ogb/data/linkproppred/ddi.zip,http://snap.stanford.edu/ogb/data/linkproppred/biokg.zip,http://snap.stanford.edu/ogb/data/linkproppred/vessel.zip
+add_inverse_edge,True,True,False,False,True,False,False
+has_node_attr,True,True,True,False,False,False,True
+has_edge_attr,False,False,False,False,False,False,True
+split,throughput,time,time,time,target,random,spatial
+additional node files,None,None,node_year,None,None,None,None
+additional edge files,None,"edge_weight,edge_year",None,edge_reltype,None,edge_reltype,None
+is hetero,False,False,False,False,False,True,False
+binary,False,False,False,False,False,False,True

gammagl/datasets/OgbNodeData.csv

@@ -0,0 +1,16 @@
+,ogbn-proteins,ogbn-products,ogbn-arxiv,ogbn-mag,ogbn-papers100M
+num tasks,112,1,1,1,1
+num classes,2,47,40,349,172
+eval metric,rocauc,acc,acc,acc,acc
+task type,binary classification,multiclass classification,multiclass classification,multiclass classification,multiclass classification
+download_name,proteins,products,arxiv,mag,papers100M-bin
+version,1,1,1,2,1
+url,http://snap.stanford.edu/ogb/data/nodeproppred/proteins.zip,http://snap.stanford.edu/ogb/data/nodeproppred/products.zip,http://snap.stanford.edu/ogb/data/nodeproppred/arxiv.zip,http://snap.stanford.edu/ogb/data/nodeproppred/mag.zip,http://snap.stanford.edu/ogb/data/nodeproppred/papers100M-bin.zip
+add_inverse_edge,True,True,False,False,False
+has_node_attr,False,True,True,True,True
+has_edge_attr,True,False,False,False,False
+split,species,sales_ranking,time,time,time
+additional node files,node_species,None,node_year,node_year,node_year
+additional edge files,None,None,None,edge_reltype,None
+is hetero,False,False,False,True,False
+binary,False,False,False,False,True

gammagl/datasets/ogb_graph.py

@@ -0,0 +1,156 @@
+import pandas as pd
+import shutil, os
+import os.path as osp
+import numpy as np
+from gammagl.data import InMemoryDataset
+from gammagl.data.download import download_url
+from gammagl.data.extract import extract_zip
+from gammagl.io.read_ogb import read_graph
+
+
+class OgbGraphDataset(InMemoryDataset):
+    def __init__(self, name, root = 'dataset', transform=None, pre_transform = None, meta_dict = None):
+        '''
+            - name (str): name of the dataset
+            - root (str): root directory to store the dataset folder
+            - transform, pre_transform (optional): transform/pre-transform graph objects
+
+            - meta_dict: dictionary that stores all the meta-information about data. Default is None, 
+                    but when something is passed, it uses its information. Useful for debugging for external contributers.
+        ''' 
+
+        self.name = name ## original name, e.g., ogbg-molhiv
+
+        if meta_dict is None:
+            self.dir_name = '_'.join(name.split('-')) 
+
+            # check if previously-downloaded folder exists.
+            # If so, use that one.
+            if osp.exists(osp.join(root, self.dir_name + '_gammagl')):
+                self.dir_name = self.dir_name + '_gammagl'
+
+            self.original_root = root
+            self.root = osp.join(root, self.dir_name)
+
+            master = pd.read_csv(os.path.join(os.path.dirname(__file__), 'OgbGraphData.csv'), index_col = 0)
+            if not self.name in master:
+                error_mssg = 'Invalid dataset name {}.\n'.format(self.name)
+                error_mssg += 'Available datasets are as follows:\n'
+                error_mssg += '\n'.join(master.keys())
+                raise ValueError(error_mssg)
+            self.meta_info = master[self.name]
+
+        else:
+            self.dir_name = meta_dict['dir_path']
+            self.original_root = ''
+            self.root = meta_dict['dir_path']
+            self.meta_info = meta_dict
+
+        # check version
+        # First check whether the dataset has been already downloaded or not.
+        # If so, check whether the dataset version is the newest or not.
+        # If the dataset is not the newest version, notify this to the user. 
+        if osp.isdir(self.root) and (not osp.exists(osp.join(self.root, 'RELEASE_v' + str(self.meta_info['version']) + '.txt'))):
+            print(self.name + ' has been updated.')
+            if input('Will you update the dataset now? (y/N)\n').lower() == 'y':
+                shutil.rmtree(self.root)
+
+        self.download_name = self.meta_info['download_name'] ## name of downloaded file, e.g., tox21
+
+        self.num_tasks = int(self.meta_info['num tasks'])
+        self.eval_metric = self.meta_info['eval metric']
+        self.task_type = self.meta_info['task type']
+        self.__num_classes__ = int(self.meta_info['num classes'])
+        self.binary = self.meta_info['binary'] == 'True'
+
+        super(OgbGraphDataset, self).__init__(self.root, transform, pre_transform)
+
+        self.data, self.slices = self.load_data(self.processed_paths[0])
+
+    def get_idx_split(self, split_type = None):
+        if split_type is None:
+            split_type = self.meta_info['split']
+
+        path = osp.join(self.root, 'split', split_type)
+
+        # short-cut if split_dict.pt exists
+        if os.path.isfile(os.path.join(path, 'split_dict.pt')):
+            return self.load_data(os.path.join(path, 'split_dict.pt'))
+
+        train_idx = pd.read_csv(osp.join(path, 'train.csv.gz'), compression='gzip', header = None).values.T[0]
+        valid_idx = pd.read_csv(osp.join(path, 'valid.csv.gz'), compression='gzip', header = None).values.T[0]
+        test_idx = pd.read_csv(osp.join(path, 'test.csv.gz'), compression='gzip', header = None).values.T[0]
+
+        return {'train': train_idx, 'valid': valid_idx, 'test': test_idx}
+
+    @property
+    def num_classes(self):
+        return self.__num_classes__
+
+    @property
+    def raw_file_names(self):
+        if self.binary:
+            return ['data.npz']
+        else:
+            file_names = ['edge']
+            if self.meta_info['has_node_attr'] == 'True':
+                file_names.append('node-feat')
+            if self.meta_info['has_edge_attr'] == 'True':
+                file_names.append('edge-feat')
+            return [file_name + '.csv.gz' for file_name in file_names]
+
+    @property
+    def processed_file_names(self):
+        return 'geometric_data_processed.pt'
+
+    def download(self):
+        url = self.meta_info['url']
+        path = download_url(url, self.original_root)
+        extract_zip(path, self.original_root)
+        os.unlink(path)
+        shutil.rmtree(self.root)
+        shutil.move(osp.join(self.original_root, self.download_name), self.root)
+
+
+    def process(self):
+        add_inverse_edge = self.meta_info['add_inverse_edge'] == 'True'
+
+        if self.meta_info['additional node files'] == 'None':
+            additional_node_files = []
+        else:
+            additional_node_files = self.meta_info['additional node files'].split(',')
+
+        if self.meta_info['additional edge files'] == 'None':
+            additional_edge_files = []
+        else:
+            additional_edge_files = self.meta_info['additional edge files'].split(',')
+
+        data_list = read_graph(self.raw_dir, add_inverse_edge = add_inverse_edge, additional_node_files = additional_node_files, additional_edge_files = additional_edge_files, binary=self.binary)
+
+        if self.task_type == 'subtoken prediction':
+            graph_label_notparsed = pd.read_csv(osp.join(self.raw_dir, 'graph-label.csv.gz'), compression='gzip', header = None).values
+            graph_label = [str(graph_label_notparsed[i][0]).split(' ') for i in range(len(graph_label_notparsed))]
+
+            for i, g in enumerate(data_list):
+                g.y = graph_label[i]
+
+        else:
+            if self.binary:
+                graph_label = np.load(osp.join(self.raw_dir, 'graph-label.npz'))['graph_label']
+            else:
+                graph_label = pd.read_csv(osp.join(self.raw_dir, 'graph-label.csv.gz'), compression='gzip', header = None).values
+
+            has_nan = np.isnan(graph_label).any()
+
+            for i, g in enumerate(data_list):
+                g.y = graph_label[i]
+
+        if self.pre_transform is not None:
+            data_list = [self.pre_transform(data) for data in data_list]
+
+        data, slices = self.collate(data_list)
+
+        print('Saving...')
+        self.save_data((data, slices), self.processed_paths[0])
+
+

gammagl/datasets/ogb_link.py

@@ -0,0 +1,139 @@
+import pandas as pd
+import shutil, os
+import os.path as osp
+import numpy as np
+from gammagl.data import InMemoryDataset
+from gammagl.data.download import download_url
+from gammagl.data.extract import extract_zip
+from gammagl.io.read_ogb import read_graph, read_heterograph
+
+class OgbLinkDataset(InMemoryDataset):
+    def __init__(self, name, root = 'dataset', transform=None, pre_transform=None, meta_dict = None):
+        '''
+            - name (str): name of the dataset
+            - root (str): root directory to store the dataset folder
+
+            - meta_dict: dictionary that stores all the meta-information about data. Default is None, 
+                    but when something is passed, it uses its information. Useful for debugging for external contributers.
+        '''          
+
+        self.name = name ## original name, e.g., ogbl-ppa
+
+        if meta_dict is None:
+            self.dir_name = '_'.join(name.split('-')) 
+
+            # check if previously-downloaded folder exists.
+            # If so, use that one.
+            if osp.exists(osp.join(root, self.dir_name + '_gammagl')):
+                self.dir_name = self.dir_name + '_gammagl'
+
+            self.original_root = root
+            self.root = osp.join(root, self.dir_name)
+
+            master = pd.read_csv(os.path.join(os.path.dirname(__file__), 'OgbLinkData.csv'), index_col = 0)
+            if not self.name in master:
+                error_mssg = 'Invalid dataset name {}.\n'.format(self.name)
+                error_mssg += 'Available datasets are as follows:\n'
+                error_mssg += '\n'.join(master.keys())
+                raise ValueError(error_mssg)
+            self.meta_info = master[self.name]
+
+        else:
+            self.dir_name = meta_dict['dir_path']
+            self.original_root = ''
+            self.root = meta_dict['dir_path']
+            self.meta_info = meta_dict
+
+        # check version
+        # First check whether the dataset has been already downloaded or not.
+        # If so, check whether the dataset version is the newest or not.
+        # If the dataset is not the newest version, notify this to the user. 
+        if osp.isdir(self.root) and (not osp.exists(osp.join(self.root, 'RELEASE_v' + str(self.meta_info['version']) + '.txt'))):
+            print(self.name + ' has been updated.')
+            if input('Will you update the dataset now? (y/N)\n').lower() == 'y':
+                shutil.rmtree(self.root)
+
+        self.download_name = self.meta_info['download_name'] ## name of downloaded file, e.g., ppassoc
+
+        self.task_type = self.meta_info['task type']
+        self.eval_metric = self.meta_info['eval metric']
+        self.is_hetero = self.meta_info['is hetero'] == 'True'
+        self.binary = self.meta_info['binary'] == 'True'
+
+        super(OgbLinkDataset, self).__init__(self.root, transform, pre_transform)
+        self.data, self.slices = self.load_data(self.processed_paths[0])
+
+    def get_edge_split(self, split_type = None):
+        if split_type is None:
+            split_type = self.meta_info['split']
+
+        path = osp.join(self.root, 'split', split_type)
+
+        # short-cut if split_dict.pt exists
+        if os.path.isfile(os.path.join(path, 'split_dict.pt')):
+            return self.load_data(os.path.join(path, 'split_dict.pt'))
+
+        train = self.load_data(osp.join(path, 'train.pt'))
+        valid = self.load_data(osp.join(path, 'valid.pt'))
+        test = self.load_data(osp.join(path, 'test.pt'))
+
+        return {'train': train, 'valid': valid, 'test': test}
+
+    @property
+    def raw_file_names(self):
+        if self.binary:
+            if self.is_hetero:
+                return ['edge_index_dict.npz']
+            else:
+                return ['data.npz']
+        else:
+            if self.is_hetero:
+                return ['num-node-dict.csv.gz', 'triplet-type-list.csv.gz']
+            else:
+                file_names = ['edge']
+                if self.meta_info['has_node_attr'] == 'True':
+                    file_names.append('node-feat')
+                if self.meta_info['has_edge_attr'] == 'True':
+                    file_names.append('edge-feat')
+                return [file_name + '.csv.gz' for file_name in file_names]
+
+    @property
+    def processed_file_names(self):
+        return osp.join('geometric_data_processed.pt')
+
+    def download(self):
+        url =  self.meta_info['url']
+        path = download_url(url, self.original_root)
+        extract_zip(path, self.original_root)
+        os.unlink(path)
+        shutil.rmtree(self.root)
+        shutil.move(osp.join(self.original_root, self.download_name), self.root)
+
+
+    def process(self):
+        add_inverse_edge = self.meta_info['add_inverse_edge'] == 'True'
+
+        if self.meta_info['additional node files'] == 'None':
+            additional_node_files = []
+        else:
+            additional_node_files = self.meta_info['additional node files'].split(',')
+
+        if self.meta_info['additional edge files'] == 'None':
+            additional_edge_files = []
+        else:
+            additional_edge_files = self.meta_info['additional edge files'].split(',')
+
+        if self.is_hetero:
+            data = read_heterograph(self.raw_dir, add_inverse_edge = add_inverse_edge, additional_node_files = additional_node_files, additional_edge_files = additional_edge_files, binary=self.binary)[0]
+        else:
+            data = read_graph(self.raw_dir, add_inverse_edge = add_inverse_edge, additional_node_files = additional_node_files, additional_edge_files = additional_edge_files, binary=self.binary)[0]
+
+        data = data if self.pre_transform is None else self.pre_transform(data)
+
+        print('Saving...')
+        self.save_data(self.collate([data]), self.processed_paths[0])
+
+    def __repr__(self):
+        return '{}()'.format(self.__class__.__name__)
+
+