link-prediction/main.py at master · raph-m/link-prediction · GitHub

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
# feature engineering

import time

start = time.time()
print("preprocessing:")
import feature_engineering.preprocessing

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("baseline_feature_engineering:")
import feature_engineering.baseline_feature_engineering

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("basic_features:")
import feature_engineering.basic_features

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("cosine_distance:")
import feature_engineering.cosine_distance

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("networkx_bigraph:")
import feature_engineering.networkx_bigraph

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("networkx_digraph:")
import feature_engineering.networkx_digraph

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("author's features:")
import feature_engineering.authors

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("author's features:")
import feature_engineering.authors_2

end = time.time()
print("done in: " + str(end - start))

# models : train them and store the output probits for stacking purposes

start = time.time()
print("SVM:")
import models.svm

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("Random Forest:")
import models.random_forest

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("LightGBM:")
import models.lgbm

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("shallow NN:")
import models.nn

end = time.time()
print("done in: " + str(end - start))

start = time.time()
print("deep NN:")
import models.nn_deep

end = time.time()
print("done in: " + str(end - start))

# train the model stack and generate final submission "stack_sub_rf.csv"

start = time.time()
print("stack :")
import stacking.stacking

end = time.time()
print("done in: " + str(end - start))