study/multicpu_yh.py at master · kjh1997/study · 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
121
122
123
124
125
126
127
128
129
130
131

from new_analyzer_yh import factor_integration
from multiprocessing import Process, Queue, freeze_support
from bson.objectid import ObjectId
from pymongo import MongoClient
import multiprocessing
from time import sleep
import os, sys


def __main__():
    f_id = 0 #input
    keyid = 747
    analyzer = run_factor_integration(keyid, f_id)
    analyzer.run()
    analyzer.factor_norm()

class run_factor_integration:
    def __init__(self, keyid, fid):
        self.cores = multiprocessing.cpu_count()
        if self.cores > 3 :
            self.cores -= 1
        self.client =  MongoClient('203.255.92.141:27017', connect=False)
        self.PUBLIC = self.client['PUBLIC']
        self.new_max_factor = self.PUBLIC['new_factor']
        self.ID = self.client['ID']
        self.Domestic = self.ID['Domestic']
        self.keyid = keyid
        self.fid = fid

    def run(self):
        print("??")
        authorSize = self.ID['Domestic'].find({"keyId":self.keyid, "fid":self.fid}).count()
        processList = []
        if None == self.new_max_factor.find_one({'keyId': self.keyid,"fid":self.fid}):
            # self.new_max_factor.insert({'keyId': self.keyid,"fid":self.fid},{'keyId': self.keyid,"fid":self.fid, 'Quality' : -1, 'accuracy' : -1, 'recentness' : -1, 'coop': -1 })
            self.new_max_factor.insert({'keyId': self.keyid,"fid":self.fid},{'keyId': self.keyid,"fid":self.fid, 'ntisQual' : -1, 'remainQual' : -1,'accuracy' : -1, 'recentness' : -1, 'coop': -1 })

        th = 100 # each core handle 100 or more data
        sizeDict = {}
        perData = int(authorSize / self.cores)
        if perData > th :
            last = 0
            for i in range(self.cores-1) :
                sizeDict[last] = last+perData
                last += perData
            sizeDict[last] = authorSize
        else :
            sizeDict[0] = authorSize
        # 이 코드는 코어수를 기반으로 총 data를 나눠준다. 하지만 총 데이터가 100개 이하이면 나누지 않는다.
        # print(sizeDict)

        processList = []
        for key in sizeDict :
            acl = None
            acl = factor_integration(key, sizeDict[key], self.fid ,self.keyid)

            print("run")
            if __name__ == "__main__":
                p = Process(target= acl.run)
                processList.append(p)
                p.start()

        for p in processList :
            p.join()

        self.factor_norm()

    def factor_norm(self):
        max_factor = self.new_max_factor.find_one({'keyId':self.keyid})

        # max_qual = max_factor['Quality']
        # real_qual = 1 / max_qual


        max_ntisQual = max_factor['ntisQual']
        max_remainQual = max_factor['remainQual']

        norm_ntisQual_factor = 1/ max_ntisQual
        norm_remainQual_factor = 1/ max_remainQual

        max_acc = max_factor['accuracy']
        max_recentness = max_factor['recentness']
        max_coop = max_factor['coop']
        real_recentness = 1 / max_recentness

        if max_coop == 0: real_coop = max_coop
        elif max_coop != 0: real_coop = 1/ max_coop
        self.ID['test'].update_many(
            {"keyId":self.keyid, "fid":self.fid}, [
                {"$set" : {
                    "factor.coop":{"$multiply": ["$factor.coop", real_coop]},
                    "factor.qunt":{
                        "$sum":[
                        {"$multiply": [real_recentness, "$factor.qunt", 0.5]},
                        "$factor.lct"
                        ]},
                    # "factor.qual":{"$multiply": ["$factor.qual", real_qual]},
                    "factor.qual":{
                        "$multiply": [
                            {"$sum":[
                                {"$multiply" : ["$factor.ntisQual", norm_ntisQual_factor]},
                                {"$multiply" : ["$factor.remainQual", norm_remainQual_factor]}
                            ]},
                            0.5]},
                    "score" : {'$sum':[
                        # {"$multiply": ["$factor.qual", real_qual, 25]},
                        {"$multiply": [
                            {"$multiply" : [{"$sum" : [
                                {"$multiply" : ["$factor.ntisQual", norm_ntisQual_factor]},
                                {"$multiply" : ["$factor.remainQual", norm_remainQual_factor]}
                            ]}, 0.5]}, 25]},
                        {"$multiply": ["$factor.acc", 25]},
                        {"$multiply": ["$factor.coop", real_coop, 25]},
                        {"$multiply": [
                            {"$sum":[
                                {"$multiply": [real_recentness, "$factor.qunt", 0.5]},
                                "$factor.lct"]}, 25]}
                            ]}}}])

        print("종료")

__main__()
# #[{"$multiply": ["$factor.qual", real_qual, 25]}]
#  db.test.updateMany({}, [

# {"$set" :
# {"score_t" :
# {'$sum':[{"$multiply": ["$factor.qual", 100, 25]}, {"$multiply": ["$factor.acc", 25]},{"$multiply": ["$factor.coop", 25]},{"$multiply": ["$factor.qunt", 25]}]

# }}}])