-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy patheval_method.py
199 lines (182 loc) · 7.26 KB
/
eval_method.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
from cornac.eval_methods import StratifiedSplit
from dataset import QuestERDataset
class QuestERStratifiedSplit(StratifiedSplit):
def __init__(
self,
data=None,
fmt="UIR",
rating_threshold=1.0,
seed=None,
exclude_unknowns=True,
verbose=False,
**kwargs
):
self.review_and_item_qa_text = kwargs.get("review_and_item_qa_text", None)
super().__init__(
data=data,
fmt=fmt,
rating_threshold=rating_threshold,
seed=seed,
exclude_unknowns=exclude_unknowns,
verbose=verbose,
**kwargs
)
def build(self, train_data, test_data, val_data=None):
if train_data is None or len(train_data) == 0:
raise ValueError("train_data is required but None or empty!")
if test_data is None or len(test_data) == 0:
raise ValueError("test_data is required but None or empty!")
self.global_uid_map.clear()
self.global_iid_map.clear()
self._build_datasets(train_data, test_data, val_data)
self._build_modalities()
return self
def _build_datasets(self, train_data, test_data, val_data=None):
self.train_set = QuestERDataset.build(
data=train_data,
fmt=self.fmt,
global_uid_map=self.global_uid_map,
global_iid_map=self.global_iid_map,
seed=self.seed,
exclude_unknowns=False,
)
if self.verbose:
print("---")
print("Training data:")
print("Number of users = {}".format(self.train_set.num_users))
print("Number of items = {}".format(self.train_set.num_items))
print("Number of ratings = {}".format(self.train_set.num_ratings))
print("Max rating = {:.1f}".format(self.train_set.max_rating))
print("Min rating = {:.1f}".format(self.train_set.min_rating))
print("Global mean = {:.1f}".format(self.train_set.global_mean))
self.test_set = QuestERDataset.build(
data=test_data,
fmt=self.fmt,
global_uid_map=self.global_uid_map,
global_iid_map=self.global_iid_map,
seed=self.seed,
exclude_unknowns=self.exclude_unknowns,
)
if self.verbose:
print("---")
print("Test data:")
print("Number of users = {}".format(len(self.test_set.uid_map)))
print("Number of items = {}".format(len(self.test_set.iid_map)))
print("Number of ratings = {}".format(self.test_set.num_ratings))
print(
"Number of unknown users = {}".format(
self.test_set.num_users - self.train_set.num_users
)
)
print(
"Number of unknown items = {}".format(
self.test_set.num_items - self.train_set.num_items
)
)
if val_data is not None and len(val_data) > 0:
self.val_set = QuestERDataset.build(
data=val_data,
fmt=self.fmt,
global_uid_map=self.global_uid_map,
global_iid_map=self.global_iid_map,
seed=self.seed,
exclude_unknowns=self.exclude_unknowns,
)
if self.verbose:
print("---")
print("Validation data:")
print("Number of users = {}".format(len(self.val_set.uid_map)))
print("Number of items = {}".format(len(self.val_set.iid_map)))
print("Number of ratings = {}".format(self.val_set.num_ratings))
if self.verbose:
print("---")
print("Total users = {}".format(self.total_users))
print("Total items = {}".format(self.total_items))
self.train_set.total_users = self.total_users
self.train_set.total_items = self.total_items
def _build_modalities(self):
for user_modality in [
self.user_feature,
self.user_text,
self.user_image,
self.user_graph,
]:
if user_modality is None:
continue
user_modality.build(
id_map=self.global_uid_map,
uid_map=self.train_set.uid_map,
iid_map=self.train_set.iid_map,
dok_matrix=self.train_set.dok_matrix,
)
for item_modality in [
self.item_feature,
self.item_text,
self.item_image,
self.item_graph,
]:
if item_modality is None:
continue
item_modality.build(
id_map=self.global_iid_map,
uid_map=self.train_set.uid_map,
iid_map=self.train_set.iid_map,
dok_matrix=self.train_set.dok_matrix,
)
for modality in [
self.sentiment,
self.review_text,
self.review_and_item_qa_text,
]:
if modality is None:
continue
modality.build(
uid_map=self.train_set.uid_map,
iid_map=self.train_set.iid_map,
dok_matrix=self.train_set.dok_matrix,
)
self.add_modalities(
user_feature=self.user_feature,
user_text=self.user_text,
user_image=self.user_image,
user_graph=self.user_graph,
item_feature=self.item_feature,
item_text=self.item_text,
item_image=self.item_image,
item_graph=self.item_graph,
sentiment=self.sentiment,
review_text=self.review_text,
review_and_item_qa_text=self.review_and_item_qa_text
)
def add_modalities(self, **kwargs):
"""
Add successfully built modalities to all datasets. This is handy for
seperately built modalities that are not invoked in the build method.
"""
self.user_feature = kwargs.get("user_feature", None)
self.user_text = kwargs.get("user_text", None)
self.user_image = kwargs.get("user_image", None)
self.user_graph = kwargs.get("user_graph", None)
self.item_feature = kwargs.get("item_feature", None)
self.item_text = kwargs.get("item_text", None)
self.item_image = kwargs.get("item_image", None)
self.item_graph = kwargs.get("item_graph", None)
self.sentiment = kwargs.get("sentiment", None)
self.review_text = kwargs.get("review_text", None)
self.review_and_item_qa_text = kwargs.get("review_and_item_qa_text", None)
for data_set in [self.train_set, self.test_set, self.val_set]:
if data_set is None:
continue
data_set.add_modalities(
user_feature=self.user_feature,
user_text=self.user_text,
user_image=self.user_image,
user_graph=self.user_graph,
item_feature=self.item_feature,
item_text=self.item_text,
item_image=self.item_image,
item_graph=self.item_graph,
sentiment=self.sentiment,
review_text=self.review_text,
review_and_item_qa_text=self.review_and_item_qa_text,
)