-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_data_splitter.py
187 lines (187 loc) · 6.13 KB
/
test_data_splitter.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
# import pytest
# import pandas as pd
# from rxn_negative_learning.data_splitter import SplittingMethod, DataSplitter
# from rxn_negative_learning.data_splitter import NotSuitableParametersError
#
# @pytest.fixture
# def dataframe():
# df = pd.DataFrame({
# "rxn": [
# "c1(ccn(n1)C)C(F)F.O=C1N(Br)C(=O)CC1>>Cn1nc(C(F)F)cc1Br",
# "c1c(ccc(c1)CSc1ccnc(c1)N)OC.BrBr>>COc1nccc2occ(-c3ccccc3Br)c12",
# "c1nc(c2c(c1)occ2c1ccccc1)OC.BrBr>>COc1nccc2occ(-c3ccccc3Br)c12",
# "n1cccn1c1ncccn1.BrBr>>Brc1ccnn1-c1ncccn1",
# "c1ccc2c(c1)nc(n2S(=O)(=O)C1CCCC1)N.C1CC(=O)N(C1=O)I>>Nc1cc(I)ccn1",
# "c1ccc(cn1)O.[Na]I.[Na+].[O-]Cl>>Oc1cncc(Cl)c1",
# "c1(nc(c2c(n1)occ2c1ccccc1)C(F)(F)F)SC.BrBr>>Nc1cc(I)ccn1",
# "c1cccc(n1)N.II>>Nc1cc(I)ccn1",
# "c1c(ncc(n1)N)C(=O)OCC.O=C1N(Br)C(=O)CC1>>CCOC(=O)c1ncc(N)nc1Br",
# "c1ccc2c(n1)ccn2c1ccc(cc1)OC.O=C1N(Br)C(=O)CC1>>Cn1nc(C(F)F)cc1Br"
# ]
# })
# return df
#
# def test_data_splitter_random(dataframe):
# old_dataframe = dataframe.copy()
# data_splitter = DataSplitter.split(
# df = dataframe,
# reaction_column_name='rxn',
# splitting_method=SplittingMethod.random,
# split_ratio=0.1,
# seed=22,
# validation_set=False)
# assert old_dataframe.rxn.to_list() == dataframe.rxn.to_list()
# assert dataframe.random_seed22.to_list() == [
# "train",
# "train",
# "test",
# "train",
# "train",
# "train",
# "train",
# "train",
# "train",
# "train"
# ]
#
# data_splitter = DataSplitter.split(
# df = dataframe,
# reaction_column_name='rxn',
# splitting_method=SplittingMethod.random,
# split_ratio=0.1,
# seed=22,
# validation_set=True)
#
# assert old_dataframe.rxn.to_list() == dataframe.rxn.to_list()
# assert dataframe.random_seed22.to_list() == [
# "train",
# "train",
# "test",
# "train",
# "train",
# "train",
# "train",
# "train",
# "train",
# "valid"
# ]
#
# def test_data_splitter_product(dataframe):
# old_dataframe = dataframe.copy()
# data_splitter = DataSplitter.split(
# df=dataframe,
# reaction_column_name='rxn',
# splitting_method=SplittingMethod.product,
# split_ratio=0.1,
# seed=22,
# validation_set=False)
# assert old_dataframe.rxn.to_list() == dataframe.rxn.to_list()
# assert dataframe.product_seed22.to_list() == [
# "train",
# "train",
# "train",
# "train",
# "train",
# "train",
# "train",
# "train",
# "test",
# "train"
# ]
# assert dataframe.product_seed22.to_list()[1:3] == ['train','train']
# assert dataframe.product_seed22.to_list()[6:8] == ['train','train']
#
# data_splitter = DataSplitter.split(
# df=dataframe,
# reaction_column_name='rxn',
# splitting_method=SplittingMethod.product,
# split_ratio=0.1,
# seed=22,
# validation_set=True)
#
# assert old_dataframe.rxn.to_list() == dataframe.rxn.to_list()
# assert dataframe.product_seed22.to_list() == [
# "train",
# "valid",
# "valid",
# "train",
# "train",
# "train",
# "train",
# "train",
# "test",
# "train",
# ]
#
# def test_data_splitter_product_hash(dataframe):
# old_dataframe = dataframe.copy()
# data_splitter = DataSplitter.split(
# df=dataframe,
# reaction_column_name='rxn',
# splitting_method=SplittingMethod.product_hash,
# split_ratio=0.1,
# seed=22,
# validation_set=False)
# assert old_dataframe.rxn.to_list() == dataframe.rxn.to_list()
# assert dataframe.product_hash_seed22.to_list() == [
# "train",
# "train",
# "train",
# "train",
# "train",
# "test",
# "train",
# "train",
# "train",
# "train",
# ]
#
# assert dataframe.product_hash_seed22.to_list()[1:3] == ['train','train']
# assert dataframe.product_hash_seed22.to_list()[6:8] == ['train','train']
#
# data_splitter = DataSplitter.split(
# df=dataframe,
# reaction_column_name='rxn',
# splitting_method=SplittingMethod.product_hash,
# split_ratio=0.1,
# seed=22,
# validation_set=True)
#
# assert old_dataframe.rxn.to_list() == dataframe.rxn.to_list()
# assert dataframe.product_hash_seed22.to_list() == [
# "train",
# "train",
# "train",
# "train",
# "valid",
# "test",
# "valid",
# "valid",
# "train",
# "train"
# ]
# assert dataframe.product_hash_seed22.to_list()[1:3] == ['train','train']
# assert dataframe.product_hash_seed22.to_list()[4] == 'valid'
# assert dataframe.product_hash_seed22.to_list()[6:8] == ['valid','valid']
#
# def test_data_splitter_product_hash_not_suitable_params(dataframe):
# old_dataframe = dataframe.copy()
# with pytest.raises(NotSuitableParametersError):
# data_splitter = DataSplitter.split(
# df=dataframe,
# reaction_column_name='rxn',
# splitting_method=SplittingMethod.product_hash,
# split_ratio=0.08,
# seed=122,
# validation_set=True)
#
# def test_data_splitter_product_tanimoto(dataframe):
# old_dataframe = dataframe.copy()
# with pytest.raises(NotImplementedError):
# data_splitter = DataSplitter.split(
# df=dataframe,
# reaction_column_name='rxn',
# splitting_method=SplittingMethod.product_tanimoto,
# split_ratio=0.1,
# seed=22,
# validation_set=False)