clean up

EP/Cora_node_classification/cora.py

 """
+@info
 Getting a networkx graph from Cora. Graph can be saved in txt file. CARE: numpy-arrays are converted to lists due to errors (NumPy array is not JSON serializable).
 Initialize Embeddings for n dimensions with initialize-module.
 Arrays are initialized in normal or uniform random format (default = normal).
 
-
-#Usage
-get_graph(path_nodes="/home/utaemon/SP/cora/cora.content", path_edges="/home/utaemon/SP/cora/cora.cites")
+@usage
+get_graph(path_nodes="/cora_data/cora.content", path_edges="/cora_data/cora.cites")
 -> return graph with nodes and edges
 To write the graph informations in file:
-def write_graph_to_file(path_nodes="/home/utaemon/SP/cora/cora.content", path_edges="/home/utaemon/SP/cora/cora.cites", path_output_graph = "/home/utaemon/SP/")
+def write_graph_to_file(path_nodes="/cora_data/cora.content", path_edges="/cora_data/cora.cites", path_output_graph = "")
 To write the dictionary with initalizing Embeddings in file:
-def write_dict_to_file(rand_type="normal_random", dimension = 128, quantity=1433, path_output_emb = "/home/utaemon/SP/")
+def write_dict_to_file(rand_type="normal_random", dimension = 128, quantity=1433, path_output_emb = "")
 """
 
 import networkx as nx
@@ -21,7 +21,7 @@ import pickle as pkl
 def list_of_classes():
     return ["Case_Based", "Genetic_Algorithms", "Neural_Networks", "Probabilistic_Methods", "Reinforcement_Learning", "Rule_Learning", "Theory"]
 
-def read_file_and_get_nodes(graph_name, path="/home/utaemon/SP/cora/cora.content"):
+def read_file_and_get_nodes(graph_name, path="/cora_data/cora.content"):
     class_list = list_of_classes()
     max_bow_len = 0
     node_mapping = {}
@@ -49,7 +49,7 @@ def read_file_and_get_nodes(graph_name, path="/home/utaemon/SP/cora/cora.content
     graph_name.graph["paper_id"] = {"maxlen": 1, "vocab": (len(graph_name)), "lengths": np.ones(len(graph_name))}
     return node_mapping
 
-def read_file_and_get_edges(graph_name, node_mapping, path="/home/utaemon/SP/cora/cora.cites"):
+def read_file_and_get_edges(graph_name, node_mapping, path="/cora_data/cora.cites"):
     with open(path) as file:
         for line in file.readlines():
             a, b = line.split()
@@ -114,12 +114,12 @@ def add_max_values_to_graph(path_nodes, path_edges):                    #update
 def get_init_emb(rand_type="normal_random", dimension = 128, quantity=1433):
     return initialize.get_embeddings(rand_type=rand_type, dimension = dimension, quantity=quantity)
 
-def write_pickle_graph_file(path_nodes="/home/utaemon/SP/cora/cora.content", path_edges="/home/utaemon/SP/cora/cora.cites", path_output_graph = "/home/utaemon/SP/"):
+def write_pickle_graph_file(path_nodes="/cora_data/cora.content", path_edges="/cora_data/cora.cites", path_output_graph = ""):
     g = add_max_values_to_graph(path_nodes, path_edges)
     with open(path_output_graph + "graph.pkl", "wb") as output:
         pkl.dump(g, output)
 
-def read_pickle_graph(path = "/home/utaemon/SP/graph.pkl"):
+def read_pickle_graph(path = "graph.pkl"):
     with open(path, 'rb') as f:
         graph = pkl.load(f)
     return graph
@@ -127,5 +127,5 @@ def read_pickle_graph(path = "/home/utaemon/SP/graph.pkl"):
 
 if __name__ == "__main__":
     # execute only if run as a script
-    get_graph(path_nodes="/home/utaemon/SP/cora/cora.content", path_edges="/home/utaemon/SP/cora/cora.cites")
+    get_graph(path_nodes="/cora_data/cora.content", path_edges="/cora_data/cora.cites")
     get_init_emb(rand_type="normal_random", dimension = 128, quantity=1433)

EP/Cora_node_classification/node_classification.py

@@ -4,6 +4,7 @@
 @author: Utaemon Toyota
 @date: 31.1.2019
 @project: Software Projekt @ Heidelberg University, Institute for Computational Linguistics
+@requirements: cora.py and random_nodes_for_node_classification.py as well as the cora data
 @usage: python3 node_classification.py [-g] [-e] [-s] [-i] [-n]
         -g / --graph        Path to pickled networkX-graph
         -e / --embeddings   Path to pickled embeddings

EP/Cora_node_classification/random_nodes_for_node_classification.py

+"""
+@requirements: cora.py
+@info: Will be imported from node_classification.
+"""
+
+
 import cora
 import pickle as pkl
 import random
@@ -21,7 +27,7 @@ def get_random_num_nodes(set_elm, num, seed):
     random.seed(seed)
     return set(random.sample(set_elm, num))
 
-def get_num_random_nodes_for_all_classes_read(path = "/home/utaemon/SP/graph.pkl", num = 20, seed = 1):
+def get_num_random_nodes_for_all_classes_read(path = "graph.pkl", num = 20, seed = 1):
     """get specific number of nodes per class, same number for all classes"""
     cora_dict = dict_of_node_classes_read(path)
     sampled_random_id_set = set()
@@ -29,17 +35,3 @@ def get_num_random_nodes_for_all_classes_read(path = "/home/utaemon/SP/graph.pkl
         for id in get_random_num_nodes(cora_dict[key], num, seed):
             sampled_random_id_set.add(id)
     return sampled_random_id_set
-
-
-#unused
-'''
-def get_num_of_random_nodes(path = "/home/utaemon/SP/graph.pkl", seed=0, num = 3):
-    """Get random nodes."""
-    random.seed(seed)
-    cora_nodes = set(read_graph(path).nodes)
-    return set(random.sample(cora_nodes, num))
-
-def pickle_output(method = get_num_random_nodes_for_all_classes_read(), output = "random_nodes.pkl"):
-    with open(output, "wb") as file:
-        pkl.dump(method, file)
-'''
\ No newline at end of file

EP/node_classification_1000.txt

-C=0.1
-
-max
-0.652
-avg
-0.5900960000000008
-
-[0.561, 0.574, 0.566, 0.595, 0.594, 0.578, 0.596, 0.578, 0.566, 0.54, 0.582, 0.591, 0.559, 0.581, 0.555, 0.618, 0.615, 0.6, 0.579, 0.572, 0.554, 0.599, 0.626, 0.614, 0.566, 0.585, 0.566, 0.597, 0.612, 0.613, 0.566, 0.579, 0.611, 0.562, 0.627, 0.624, 0.618, 0.599, 0.61, 0.612, 0.613, 0.551, 0.627, 0.581, 0.613, 0.587, 0.593, 0.574, 0.593, 0.572, 0.616, 0.606, 0.59, 0.576, 0.615, 0.589, 0.605, 0.572, 0.558, 0.553, 0.613, 0.597, 0.614, 0.575, 0.593, 0.621, 0.587, 0.55, 0.595, 0.597, 0.56, 0.599, 0.563, 0.6, 0.569, 0.584, 0.581, 0.574, 0.572, 0.618, 0.635, 0.591, 0.583, 0.549, 0.571, 0.593, 0.561, 0.594, 0.58, 0.597, 0.607, 0.6, 0.61, 0.571, 0.584, 0.61, 0.579, 0.583, 0.616, 0.608, 0.578, 0.584, 0.613, 0.617, 0.583, 0.557, 0.581, 0.595, 0.564, 0.562, 0.621, 0.613, 0.54, 0.6, 0.592, 0.613, 0.625, 0.577, 0.609, 0.606, 0.571, 0.611, 0.559, 0.62, 0.588, 0.604, 0.614, 0.565, 0.617, 0.604, 0.601, 0.62, 0.565, 0.585, 0.642, 0.553, 0.574, 0.599, 0.586, 0.599, 0.582, 0.627, 0.569, 0.608, 0.634, 0.618, 0.604, 0.565, 0.583, 0.564, 0.595, 0.587, 0.564, 0.564, 0.589, 0.589, 0.582, 0.594, 0.624, 0.595, 0.586, 0.629, 0.561, 0.568, 0.563, 0.6, 0.576, 0.575, 0.627, 0.591, 0.628, 0.636, 0.579, 0.573, 0.599, 0.633, 0.589, 0.578, 0.568, 0.623, 0.559, 0.585, 0.567, 0.622, 0.632, 0.617, 0.615, 0.592, 0.618, 0.596, 0.596, 0.588, 0.578, 0.564, 0.571, 0.572, 0.652, 0.55, 0.571, 0.638, 0.583, 0.558, 0.567, 0.608, 0.597, 0.538, 0.579, 0.601, 0.603, 0.593, 0.603, 0.598, 0.572, 0.604, 0.578, 0.595, 0.628, 0.603, 0.603, 0.588, 0.598, 0.557, 0.59, 0.586, 0.568, 0.582, 0.608, 0.589, 0.593, 0.59, 0.582, 0.576, 0.603, 0.577, 0.606, 0.579, 0.609, 0.615, 0.591, 0.559, 0.549, 0.591, 0.614, 0.607, 0.576, 0.586, 0.617, 0.594, 0.57, 0.606, 0.593, 0.553, 0.592, 0.581, 0.58, 0.613, 0.609, 0.579, 0.582, 0.615, 0.619, 0.569, 0.579, 0.599, 0.591, 0.61, 0.592, 0.572, 0.626, 0.619, 0.573, 0.608, 0.615, 0.579, 0.583, 0.574, 0.604, 0.603, 0.602, 0.618, 0.551, 0.616, 0.597, 0.576, 0.587, 0.586, 0.593, 0.581, 0.584, 0.589, 0.574, 0.594, 0.58, 0.585, 0.598, 0.597, 0.581, 0.62, 0.587, 0.626, 0.617, 0.613, 0.579, 0.57, 0.616, 0.594, 0.58, 0.616, 0.631, 0.558, 0.589, 0.598, 0.587, 0.562, 0.572, 0.594, 0.59, 0.587, 0.583, 0.6, 0.609, 0.588, 0.601, 0.568, 0.6, 0.624, 0.604, 0.564, 0.569, 0.618, 0.639, 0.566, 0.624, 0.609, 0.556, 0.579, 0.62, 0.59, 0.591, 0.521, 0.607, 0.597, 0.557, 0.597, 0.619, 0.573, 0.574, 0.608, 0.537, 0.603, 0.601, 0.587, 0.607, 0.635, 0.573, 0.603, 0.572, 0.59, 0.572, 0.619, 0.617, 0.552, 0.586, 0.594, 0.584, 0.604, 0.621, 0.591, 0.605, 0.567, 0.606, 0.601, 0.57, 0.606, 0.552, 0.572, 0.584, 0.577, 0.587, 0.612, 0.542, 0.584, 0.581, 0.589, 0.596, 0.588, 0.619, 0.559, 0.575, 0.602, 0.607, 0.616, 0.576, 0.631, 0.623, 0.595, 0.597, 0.568, 0.574, 0.602, 0.568, 0.613, 0.608, 0.599, 0.595, 0.632, 0.588, 0.589, 0.585, 0.596, 0.598, 0.634, 0.582, 0.613, 0.609, 0.632, 0.588, 0.597, 0.553, 0.56, 0.575, 0.567, 0.609, 0.531, 0.584, 0.579, 0.584, 0.568, 0.601, 0.601, 0.603, 0.573, 0.594, 0.564, 0.608, 0.593, 0.584, 0.581, 0.556, 0.584, 0.587, 0.585, 0.586, 0.625, 0.603, 0.615, 0.631, 0.611, 0.611, 0.591, 0.585, 0.559, 0.58, 0.573, 0.614, 0.612, 0.6, 0.605, 0.557, 0.575, 0.574, 0.576, 0.62, 0.624, 0.609, 0.571, 0.592, 0.58, 0.596, 0.613, 0.581, 0.595, 0.58, 0.587, 0.576, 0.602, 0.58, 0.585, 0.604, 0.623, 0.575, 0.603, 0.565, 0.596, 0.563, 0.604, 0.608, 0.593, 0.578, 0.603, 0.625, 0.598, 0.583, 0.605, 0.581, 0.551, 0.59, 0.556, 0.59, 0.597, 0.605, 0.585, 0.598, 0.618, 0.589, 0.576, 0.601, 0.591, 0.617, 0.565, 0.57, 0.568, 0.593, 0.591, 0.566, 0.581, 0.604, 0.61, 0.594, 0.595, 0.586, 0.607, 0.552, 0.614, 0.604, 0.619, 0.57, 0.564, 0.612, 0.639, 0.601, 0.626, 0.602, 0.564, 0.588, 0.592, 0.577, 0.56, 0.585, 0.579, 0.578, 0.583, 0.561, 0.609, 0.549, 0.598, 0.625, 0.607, 0.611, 0.587, 0.61, 0.614, 0.572, 0.602, 0.594, 0.601, 0.617, 0.579, 0.602, 0.583, 0.589, 0.608, 0.559, 0.604, 0.618, 0.611, 0.588, 0.614, 0.594, 0.601, 0.58, 0.567, 0.603, 0.531, 0.579, 0.646, 0.573, 0.598, 0.565, 0.58, 0.596, 0.587, 0.553, 0.586, 0.589, 0.599, 0.58, 0.6, 0.595, 0.563, 0.611, 0.618, 0.575, 0.586, 0.588, 0.588, 0.598, 0.563, 0.564, 0.594, 0.637, 0.58, 0.568, 0.6, 0.605, 0.609, 0.569, 0.589, 0.607, 0.588, 0.6, 0.602, 0.615, 0.577, 0.583, 0.613, 0.622, 0.576, 0.576, 0.616, 0.596, 0.57, 0.609, 0.555, 0.614, 0.601, 0.578, 0.569, 0.625, 0.576, 0.601, 0.57, 0.591, 0.569, 0.575, 0.593, 0.62, 0.557, 0.578, 0.559, 0.55, 0.586, 0.598, 0.565, 0.596, 0.577, 0.593, 0.557, 0.598, 0.562, 0.621, 0.606, 0.556, 0.593, 0.591, 0.577, 0.544, 0.588, 0.57, 0.585, 0.575, 0.596, 0.619, 0.567, 0.585, 0.58, 0.593, 0.559, 0.576, 0.587, 0.613, 0.594, 0.624, 0.603, 0.549, 0.585, 0.543, 0.585, 0.586, 0.596, 0.584, 0.578, 0.571, 0.601, 0.59, 0.557, 0.583, 0.584, 0.569, 0.575, 0.569, 0.595, 0.589, 0.597, 0.592, 0.556, 0.57, 0.558, 0.588, 0.635, 0.604, 0.634, 0.59, 0.62, 0.566, 0.58, 0.636, 0.565, 0.545, 0.617, 0.599, 0.611, 0.605, 0.562, 0.593, 0.571, 0.588, 0.627, 0.557, 0.549, 0.583, 0.615, 0.596, 0.62, 0.554, 0.604, 0.598, 0.589, 0.598, 0.614, 0.547, 0.61, 0.547, 0.582, 0.588, 0.578, 0.597, 0.613, 0.581, 0.549, 0.579, 0.553, 0.543, 0.584, 0.632, 0.568, 0.592, 0.612, 0.58, 0.567, 0.61, 0.562, 0.574, 0.551, 0.589, 0.603, 0.621, 0.576, 0.63, 0.613, 0.599, 0.599, 0.602, 0.578, 0.546, 0.596, 0.583, 0.622, 0.641, 0.575, 0.547, 0.589, 0.569, 0.601, 0.602, 0.567, 0.628, 0.584, 0.58, 0.567, 0.578, 0.599, 0.586, 0.58, 0.636, 0.593, 0.63, 0.582, 0.589, 0.605, 0.519, 0.585, 0.588, 0.595, 0.605, 0.585, 0.606, 0.587, 0.581, 0.579, 0.608, 0.54, 0.621, 0.618, 0.599, 0.614, 0.617, 0.609, 0.564, 0.639, 0.57, 0.577, 0.573, 0.61, 0.599, 0.55, 0.586, 0.52, 0.576, 0.617, 0.587, 0.61, 0.591, 0.597, 0.561, 0.558, 0.586, 0.596, 0.551, 0.509, 0.614, 0.587, 0.573, 0.616, 0.608, 0.57, 0.606, 0.601, 0.585, 0.587, 0.594, 0.528, 0.57, 0.625, 0.607, 0.603, 0.571, 0.62, 0.595, 0.593, 0.614, 0.604, 0.566, 0.592, 0.574, 0.594, 0.592, 0.604, 0.602, 0.603, 0.582, 0.615, 0.588, 0.589, 0.625, 0.603, 0.574, 0.574, 0.595, 0.588, 0.592, 0.565, 0.604, 0.562, 0.589, 0.565, 0.559, 0.572, 0.581, 0.557, 0.613, 0.584, 0.57, 0.592, 0.581, 0.589, 0.597, 0.577, 0.637, 0.59, 0.599, 0.568, 0.612, 0.634, 0.586, 0.586, 0.609, 0.581, 0.608, 0.58, 0.565, 0.595, 0.575, 0.584, 0.563, 0.56, 0.624, 0.589, 0.621, 0.597, 0.575, 0.57, 0.597, 0.566, 0.582, 0.575, 0.584, 0.618, 0.586, 0.63, 0.584, 0.613, 0.649, 0.603, 0.575, 0.574, 0.575, 0.577, 0.605, 0.608, 0.622, 0.582, 0.58, 0.573, 0.581, 0.584, 0.542, 0.572, 0.589, 0.577, 0.592, 0.577, 0.584, 0.6, 0.581, 0.628, 0.616, 0.564, 0.578, 0.574, 0.602, 0.587, 0.602, 0.596, 0.602, 0.57, 0.606, 0.572, 0.595, 0.554, 0.578, 0.591, 0.549, 0.598, 0.613, 0.545, 0.573, 0.635, 0.587, 0.611, 0.589, 0.598, 0.611, 0.611, 0.576, 0.564, 0.575, 0.566, 0.601, 0.642, 0.584, 0.616, 0.565, 0.608, 0.606, 0.585, 0.587, 0.592, 0.612, 0.583, 0.593, 0.612, 0.6, 0.583, 0.629, 0.616, 0.594, 0.598, 0.58, 0.572]
-
-
-C Bestimmung
-/usr/bin/python3 /home/utaemon/PycharmProjects/Softwareprojekt/node_classification.py
-Iteration/Random Seed: 0
-C = 0.01
-0.558
-C = 0.1
-0.564
-C = 0.5
-0.564
-C = 1.0
-0.561
-C = 5.0
-0.542
-C = 10.0
-0.544
-Iteration/Random Seed: 1
-C = 0.01
-0.642
-C = 0.1
-0.635
-C = 0.5
-0.628
-C = 1.0
-0.619
-C = 5.0
-0.611
-C = 10.0
-0.61
-Iteration/Random Seed: 2
-C = 0.01
-0.549
-C = 0.1
-0.57
-C = 0.5
-0.553
-C = 1.0
-0.548
-C = 5.0
-0.539
-C = 10.0
-0.538
-Iteration/Random Seed: 3
-C = 0.01
-0.629
-C = 0.1
-0.624
-C = 0.5
-0.608
-C = 1.0
-0.603
-C = 5.0
-0.578
-C = 10.0
-0.575
-Iteration/Random Seed: 4
-C = 0.01
-0.62
-C = 0.1
-0.638
-C = 0.5
-0.632
-C = 1.0
-0.632
-C = 5.0
-0.629
-C = 10.0
-0.631
-Iteration/Random Seed: 5
-C = 0.01
-0.595
-C = 0.1
-0.615
-C = 0.5
-0.62
-C = 1.0
-0.622
-C = 5.0
-0.616
-C = 10.0
-0.61
-Iteration/Random Seed: 6
-C = 0.01
-0.607
-C = 0.1
-0.626
-C = 0.5
-0.618
-C = 1.0
-0.61
-C = 5.0
-0.598
-C = 10.0
-0.589
-Iteration/Random Seed: 7
-C = 0.01
-0.596
-C = 0.1
-0.603
-C = 0.5
-0.587
-C = 1.0
-0.581
-C = 5.0
-0.563
-C = 10.0
-0.561
-Iteration/Random Seed: 8
-C = 0.01
-0.602
-C = 0.1
-0.619
-C = 0.5
-0.617
-C = 1.0
-0.611
-C = 5.0
-0.608
-C = 10.0
-0.605
-Iteration/Random Seed: 9
-C = 0.01
-0.58
-C = 0.1
-0.595
-C = 0.5
-0.585
-C = 1.0
-0.577
-C = 5.0
-0.563
-C = 10.0
-0.56
-
-Process finished with exit code 0
-