add splitting nodes for node classification

Cora_Preprocessing/get_nodes.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+@author: Utaemon Toyota
+@project: Software Projekt
+@date: 25.12.2018
+"""
+
+import random
+import cora
+
+def get_graph(path_nodes, path_edges):
+    return cora.get_graph(path_nodes, path_edges)
+
+def dict_of_node_classes(path_nodes, path_edges):
+    cora = get_graph(path_nodes, path_edges)
+    class_dict = {}
+    for node in cora.node:
+        node_class = cora.node[node]["class"]
+        if not node_class in class_dict:
+            class_dict[node_class] = set()
+        class_dict[node_class].add(node)
+    return class_dict
+
+def get_random_num_nodes(set_elm, num):
+    return set(random.sample(set_elm, num))
+
+def get_num_random_nodes_for_all_classes(num = 3, path_nodes="/home/utaemon/SP/cora/cora.content", path_edges="/home/utaemon/SP/cora/cora.cites"):
+    """get specific number of nodes per class, same number for all classes"""
+    cora_dict = dict_of_node_classes(path_nodes, path_edges)
+    sampled_random_id_set = set()
+    for key in cora_dict:
+        for id in get_random_num_nodes(cora_dict[key], num):
+            sampled_random_id_set.add(id)
+    # if you want to return dict of class:random_ids
+    # cora_dict = dict_of_node_classes(path_nodes, path_edges)
+    # sampled_random_dict = {}
+    # for key in cora_dict:
+    #    sampled_random_dict[key] = get_random_num_nodes(cora_dict[key], num)
+    # return sampled_random_dict
+    return sampled_random_id_set
+
+#get random nodes
+def get_num_of_random_nodes(num = 3, path_nodes="/home/utaemon/SP/cora/cora.content", path_edges="/home/utaemon/SP/cora/cora.cites"):
+    """Get random nodes."""
+    cora_nodes = set(get_graph(path_nodes, path_edges).nodes)
+    return set(random.sample(cora_nodes, num))
+
+#get a dictionary with class: ids
+def get_dict_of_nodes(*args):
+    """*args: Tuple of Set_name and number of nodes in it, for example ("a", 10)."""
+    dict_of_sets = {}
+    for arg in args:
+        ids = get_num_of_random_nodes(arg[1])
+        dict_of_sets[arg[0]] = ids
+    return dict_of_sets
+
+#get features from nodes
+def get_features_for_nodes(path_nodes="/home/utaemon/SP/cora/cora.content", path_edges="/home/utaemon/SP/cora/cora.cites"):
+    cora_graph = get_graph(path_nodes, path_edges)
+    set_of_cora_nodes = get_num_of_random_nodes()
+    dict_of_id_and_features = {}
+    for id in set_of_cora_nodes:
+        dict_of_id_and_features[id] = cora_graph.node[id]
+    return dict_of_id_and_features
+