-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdata_preparation.py
275 lines (238 loc) · 16.5 KB
/
data_preparation.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
# -*- coding: utf-8 -*-
"""
-------------------------------------------------
File Name: data_preparation.py
Description: this code takes the original knowledge graph data which should be in N-triple format as input
and generates intermediate files required by downstream codes.
Author: Ruijie Wang (https://github.com/xjdwrj)
date: 14 Nov. 2019
-------------------------------------------------
"""
import torch
from tools.pickle_funcs import load_data, dump_data
from tools.log_text import log_text
class DataPreparation:
def __init__(self):
self.print_results_for_validation = False
self.dataset = "new_test"
self.input_path = "./datasets/%s/input/" % self.dataset
self.output_path = "./datasets/%s/output/" % self.dataset
self.log_path = "./logs/data_preparation_on_%s.log" % self.dataset
self.num_of_train_triples = 0
self.num_of_validate_triples = 0
self.num_of_test_triples = 0
self.num_of_entities = 0
self.num_of_relations = 0
self.string_train_triples = {"heads": [], "relations": [], "tails": []}
self.string_validate_triples = {"heads": [], "relations": [], "tails": []}
self.string_test_triples = {"heads": [], "relations": [], "tails": []}
self.id_train_triples = {"id_heads": [], "id_relations": [], "id_tails": []}
self.id_validate_triples = {"id_heads": [], "id_relations": [], "id_tails": []}
self.id_test_triples = {"id_heads": [], "id_relations": [], "id_tails": []}
self.entity2id = {} # {"entity_string": id}
self.relation2id = {} # {"relation_string": id}
self.train_head_relation_to_tail = {} # {head: {relation: [tails, ...]}}
self.train_tail_relation_to_head = {} # {tail: {relation: [heads, ...]}}
self.validate_head_relation_to_tail = {} # {head: {relation: [tails, ...]}}
self.validate_tail_relation_to_head = {} # {tail: {relation: [heads, ...]}}
self.test_head_relation_to_tail = {} # {head: {relation: [tails, ...]}}
self.test_tail_relation_to_head = {} # {tail: {relation: [heads, ...]}}
self.train_head_context_head = {} # {entity: {context_id: head}}
self.train_head_context_relation = {} # {entity: {context_id: relation}}
self.train_head_context_statistics = {} # {entity: ...}
self.train_tail_context_relation = {} # {entity: {context_id: relation}}
self.train_tail_context_tail = {} # {entity: {context_id: tail}}
self.train_tail_context_statistics = {} # {entity: ...}
self.validate_head_context_head = {} # {entity: {context_id: head}}
self.validate_head_context_relation = {} # {entity: {context_id: relation}}
self.validate_head_context_statistics = {} # {entity: ...}
self.validate_tail_context_relation = {} # {entity: {context_id: relation}}
self.validate_tail_context_tail = {} # {entity: {context_id: tail}}
self.validate_tail_context_statistics = {} # {entity: ...}
self.test_head_context_head = {} # {entity: {context_id: head}}
self.test_head_context_relation = {} # {entity: {context_id: relation}}
self.test_head_context_statistics = {} # {entity: ...}
self.test_tail_context_relation = {} # {entity: {context_id: relation}}
self.test_tail_context_tail = {} # {entity: {context_id: tail}}
self.test_tail_context_statistics = {} # {entity: ...}
self.run_functions()
def run_functions(self):
log_text(self.log_path, "\r\n---------------------Start-------------------------")
log_text(self.log_path, "...... Reading Data ......")
self.read_dataset()
log_text(self.log_path, "...... Head Relation to Tail and the Reverse ......")
self.head_relation_to_tail_and_reverse()
log_text(self.log_path, "...... Entity Context Extraction ......")
self.context_process()
log_text(self.log_path, "...... Other Operations ......")
self.train_triple_tensor_generation()
self.statistics()
if self.print_results_for_validation:
log_text(self.log_path, "...... Result Validation ......")
self.result_validation()
log_text(self.log_path, "---------------------End-------------------------")
def read_dataset(self):
names = ["train", "valid", "test"]
string_triples = [self.string_train_triples, self.string_validate_triples, self.string_test_triples]
id_triples = [self.id_train_triples, self.id_validate_triples, self.id_test_triples]
num_of_triples = [0, 0, 0]
for index in range(3):
name = names[index]
string_triple = string_triples[index]
id_triple = id_triples[index]
log_text(self.log_path, "reading file %s" % self.input_path + name + ".txt")
with open(self.input_path + name + ".txt") as data_reader:
tmp_line = data_reader.readline()
while tmp_line and tmp_line not in ["\n", "\r\n", "\r"]:
tmp_head = tmp_line.split()[0]
tmp_relation = tmp_line.split()[1]
tmp_tail = tmp_line.split()[2]
string_triple["heads"].append(tmp_head)
string_triple["relations"].append(tmp_relation)
string_triple["tails"].append(tmp_tail)
id_triple["id_heads"].append(self.entity_id_generation(tmp_head))
id_triple["id_relations"].append(self.relation_id_generation(tmp_relation))
id_triple["id_tails"].append(self.entity_id_generation(tmp_tail))
num_of_triples[index] += 1
tmp_line = data_reader.readline()
dump_data(string_triple, self.output_path + "string_%s_triples.pickle" % name, self.log_path, "string_%s_triples" % name)
dump_data(id_triple, self.output_path + "id_%s_triples.pickle" % name, self.log_path, "id_%s_triples" % name)
dump_data(self.entity2id, self.output_path + "entity2id.pickle", self.log_path, "self.entity2id")
dump_data(self.relation2id, self.output_path + "relation2id.pickle", self.log_path, "self.relation2id")
self.num_of_train_triples = num_of_triples[0]
self.num_of_validate_triples = num_of_triples[1]
self.num_of_test_triples = num_of_triples[2]
def head_relation_to_tail_and_reverse(self):
names = ["train", "valid", "test"]
num_of_triples = [self.num_of_train_triples, self.num_of_validate_triples, self.num_of_test_triples]
id_triples = [self.id_train_triples, self.id_validate_triples, self.id_test_triples]
head_relation_to_tails = [self.train_head_relation_to_tail, self.validate_head_relation_to_tail, self.test_head_relation_to_tail]
tail_relation_to_heads = [self.train_tail_relation_to_head, self.validate_tail_relation_to_head, self.test_tail_relation_to_head]
for index in range(3):
name = names[index]
num_of_triple = num_of_triples[index]
id_triple = id_triples[index]
head_relation_to_tail = head_relation_to_tails[index]
tail_relation_to_head = tail_relation_to_heads[index]
for triple_id in range(num_of_triple):
tmp_head = id_triple["id_heads"][triple_id]
tmp_relation = id_triple["id_relations"][triple_id]
tmp_tail = id_triple["id_tails"][triple_id]
if tmp_head not in head_relation_to_tail:
head_relation_to_tail[tmp_head] = {tmp_relation: []}
else:
if tmp_relation not in head_relation_to_tail[tmp_head]:
head_relation_to_tail[tmp_head][tmp_relation] = []
head_relation_to_tail[tmp_head][tmp_relation].append(tmp_tail)
if tmp_tail not in tail_relation_to_head:
tail_relation_to_head[tmp_tail] = {tmp_relation: []}
else:
if tmp_relation not in tail_relation_to_head[tmp_tail]:
tail_relation_to_head[tmp_tail][tmp_relation] = []
tail_relation_to_head[tmp_tail][tmp_relation].append(tmp_head)
dump_data(head_relation_to_tail, self.output_path + "%s_head_relation_to_tail.pickle" % name, self.log_path, "head_relation_to_tail")
dump_data(tail_relation_to_head, self.output_path + "%s_tail_relation_to_head.pickle" % name, self.log_path, "tail_relation_to_head")
def statistics(self):
log_text(self.log_path, "number of train triples: %d" % self.num_of_train_triples)
log_text(self.log_path, "number of validate triples: %d" % self.num_of_validate_triples)
log_text(self.log_path, "number of test triples: %d" % self.num_of_test_triples)
log_text(self.log_path, "number of entities: %d" % self.num_of_entities)
log_text(self.log_path, "number of relations: %d" % self.num_of_relations)
statistics = {"num_of_train_triples": self.num_of_train_triples,
"num_of_validate_triples": self.num_of_validate_triples,
"num_of_test_triples": self.num_of_test_triples,
"num_of_entities": self.num_of_entities,
"num_of_relations": self.num_of_relations,
"num_of_train_entities": None,
"num_of_validate_entities": None,
"num_of_test_entities": None}
dump_data(statistics, self.output_path + "statistics.pickle", self.log_path, "statistics")
def context_process(self):
names = ["train", "valid", "test"]
head_relation_to_tails = [self.train_head_relation_to_tail, self.validate_head_relation_to_tail, self.test_head_relation_to_tail]
tail_relation_to_heads = [self.train_tail_relation_to_head, self.validate_tail_relation_to_head, self.test_tail_relation_to_head]
head_context_heads = [self.train_head_context_head, self.validate_head_context_head, self.test_head_context_head]
head_context_relations = [self.train_head_context_relation, self.validate_head_context_relation, self.test_head_context_relation]
head_context_statistics_es = [self.train_head_context_statistics, self.validate_head_context_statistics, self.test_head_context_statistics]
tail_context_relations = [self.train_tail_context_relation, self.validate_tail_context_relation, self.test_tail_context_relation]
tail_context_tails = [self.train_tail_context_tail, self.validate_tail_context_tail, self.test_tail_context_tail]
tail_context_statistics_es = [self.train_tail_context_statistics, self.validate_tail_context_statistics, self.test_tail_context_statistics]
for index in range(3):
name = names[index]
head_relation_to_tail = head_relation_to_tails[index]
tail_relation_to_head = tail_relation_to_heads[index]
head_context_head = head_context_heads[index]
head_context_relation = head_context_relations[index]
head_context_statistics = head_context_statistics_es[index]
tail_context_relation = tail_context_relations[index]
tail_context_tail = tail_context_tails[index]
tail_context_statistics = tail_context_statistics_es[index]
for entity in range(self.num_of_entities):
num_of_head_context = 0
head_context_head[entity] = {}
head_context_relation[entity] = {}
if entity in tail_relation_to_head:
for relation in tail_relation_to_head[entity]:
for head in tail_relation_to_head[entity][relation]:
head_context_head[entity][num_of_head_context] = head
head_context_relation[entity][num_of_head_context] = relation
num_of_head_context += 1
head_context_statistics[entity] = num_of_head_context
num_of_tail_context = 0
tail_context_relation[entity] = {}
tail_context_tail[entity] = {}
if entity in head_relation_to_tail:
for relation in head_relation_to_tail[entity]:
for tail in head_relation_to_tail[entity][relation]:
tail_context_relation[entity][num_of_tail_context] = relation
tail_context_tail[entity][num_of_tail_context] = tail
num_of_tail_context += 1
tail_context_statistics[entity] = num_of_tail_context
dump_data(head_context_head, self.output_path + "%s_head_context_head.pickle" % name, self.log_path, "head_context_head")
dump_data(head_context_relation, self.output_path + "%s_head_context_relation.pickle" % name, self.log_path, "head_context_relation")
dump_data(head_context_statistics, self.output_path + "%s_head_context_statistics.pickle" % name, self.log_path, "head_context_statistics")
dump_data(tail_context_relation, self.output_path + "%s_tail_context_relation.pickle" % name, self.log_path, "tail_context_relation")
dump_data(tail_context_tail, self.output_path + "%s_tail_context_tail.pickle" % name, self.log_path, "tail_context_tail")
dump_data(tail_context_statistics, self.output_path + "%s_tail_context_statistics.pickle" % name, self.log_path, "tail_context_statistics")
def entity_id_generation(self, entity):
if entity not in self.entity2id:
self.entity2id[entity] = self.num_of_entities
self.num_of_entities += 1
return self.entity2id[entity]
def relation_id_generation(self, relation):
if relation not in self.relation2id:
self.relation2id[relation] = self.num_of_relations
self.num_of_relations += 1
return self.relation2id[relation]
def train_triple_tensor_generation(self):
train_triple_tensor = torch.zeros(self.num_of_train_triples, 3)
for index in range(self.num_of_train_triples):
train_triple_tensor[index][0] = self.id_train_triples["id_heads"][index]
train_triple_tensor[index][1] = self.id_train_triples["id_relations"][index]
train_triple_tensor[index][2] = self.id_train_triples["id_tails"][index]
dump_data(train_triple_tensor, self.output_path + "train_triple_tensor.pickle", self.log_path, "train_triple_tensor")
def result_validation(self):
names = ["train", "valid", "test"]
log_text(self.log_path, "......Result of Reading Data......")
for name in names:
log_text(self.log_path, load_data(self.output_path + "string_%s_triples.pickle" % name, self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "id_%s_triples.pickle" % name, self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "entity2id.pickle", self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "relation2id.pickle", self.log_path, ""))
log_text(self.log_path, "......Result of Head Relation to Tail and Reserve......")
for name in names:
log_text(self.log_path, load_data(self.output_path + "%s_head_relation_to_tail.pickle" % name, self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "%s_tail_relation_to_head.pickle" % name, self.log_path, ""))
log_text(self.log_path, "......Result of Entity Context Extraction......")
for name in names:
log_text(self.log_path, load_data(self.output_path + "%s_head_context_head.pickle" % name, self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "%s_head_context_relation.pickle" % name, self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "%s_head_context_statistics.pickle" % name, self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "%s_tail_context_relation.pickle" % name, self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "%s_tail_context_tail.pickle" % name, self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "%s_tail_context_statistics.pickle" % name, self.log_path, ""))
log_text(self.log_path, "......Other Results......")
log_text(self.log_path, load_data(self.output_path + "statistics.pickle", self.log_path, ""))
log_text(self.log_path, load_data(self.output_path + "train_triple_tensor.pickle", self.log_path, ""))
if __name__ == "__main__":
dataPrepare = DataPreparation()