DP-federated-recommendation/Dataset.py at main · Amos58/DP-federated-recommendation · 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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
import scipy.sparse as sp
import numpy as np
import collections

class Dataset(object):

    def __init__(self, path):
        self.path = path
        self.num_users, self.num_items = self.get_train_data_shape()
    def get_train_data_shape(self):
        filename = self.path + ".train.rating"
        num_users=0
        num_items = 0
        with open(filename, "r") as f:
            line = f.readline()
            while line is not None and line != "":
                arr = line.split("\t")
                u, i = int(arr[0]), int(arr[1])
                num_users = max(num_users, u)
                num_items = max(num_items, i)
                line = f.readline()
        num_items += 1
        num_users += 1
        return num_users, num_items
    def load_test_file(self):
        filename = self.path + ".test.rating"
        ratingList = []
        with open(filename, "r") as f:
            line = f.readline()
            while line is not None and line != "":
                arr = line.split("\t")
                user, item = int(arr[0]), int(arr[1])
                ratingList.append([user, item])
                line = f.readline()
        return ratingList


    def load_negative_file(self):
        filename = self.path + ".test.negative"
        negativeList = []
        with open(filename, "r") as f:
            line = f.readline()
            while line is not None and line != "":
                arr = line.split("\t")
                negatives = []
                for x in arr[1:]:
                    negatives.append(int(x))
                negativeList.append(negatives)
                line = f.readline()
        return negativeList


    def load_train_file(self):
        filename = self.path + ".train.rating"
        num_users, num_items = self.get_train_data_shape()

        mat = sp.dok_matrix((num_users, num_items), dtype=np.float32)
        with open(filename, "r") as f:
            line = f.readline()
            while line is not None and line != "":
                arr = line.split("\t")
                user, item, rating = int(arr[0]), int(arr[1]), float(arr[2])
                #print("usr:{} item:{} score:{}".format(user,item,rating))
                if rating > 0:
                    mat[user, item] = 1.0
                line = f.readline()

        train_datas=[[],[],[]]
        with open(filename, "r") as f:
            for (usr, item) in mat.keys():
                train_datas[0].append(usr)
                train_datas[1].append(item)
                train_datas[2].append(1)
                line = f.readline()
                for t in range(4):
                    nega_item = np.random.randint(num_items)
                    while (usr, nega_item) in mat.keys():
                        nega_item = np.random.randint(num_items)
                train_datas[0].append(usr)
                train_datas[1].append(nega_item)
                train_datas[2].append(0)
        return train_datas


    def load_client_train_date(self):
        filename = self.path + ".train.rating"
        num_users, num_items = self.get_train_data_shape()

        mat = sp.dok_matrix((num_users, num_items), dtype=np.float32)
        with open(filename, "r") as f:
            line = f.readline()
            while line is not None and line != "":
                arr = line.split("\t")
                user, item, rating = int(arr[0]), int(arr[1]), float(arr[2])
                #print("usr:{} item:{} score:{}".format(user,item,rating))
                if rating > 0:
                    mat[user, item] = 1.0
                line = f.readline()

        client_datas=[[[],[],[]] for i in range(num_users)]
        with open(filename, "r") as f:
            for (usr, item) in mat.keys():
                client_datas[usr][0].append(usr)
                client_datas[usr][1].append(item)
                client_datas[usr][2].append(1)
                line = f.readline()
                for t in range(4):
                    nega_item = np.random.randint(num_items)
                    while (usr, nega_item) in mat.keys():
                        nega_item = np.random.randint(num_items)
                client_datas[usr][0].append(usr)
                client_datas[usr][1].append(nega_item)
                client_datas[usr][2].append(0)
        return client_datas