fix bugs

config/RSTE.conf

@@ -3,7 +3,7 @@ social=../dataset/FilmTrust/trust.txt
 ratings.setup=-columns 0 1 2
 social.setup=-columns 0 1 2
 recommender=RSTE
-evaluation.setup=-cv 3
+evaluation.setup=-ap 0.33
 item.ranking=off -topN 10 -ignore -1
 num.factors=10
 num.max.iter=30

data/rating.py

@@ -8,7 +8,7 @@
 
 class RatingDAO(object):
     'data access control'
-    def __init__(self,config,trainingSet = None, testSet = None):
+    def __init__(self,config,trainingSet = list(), testSet = list()):
         self.config = config
         self.ratingConfig = LineConfig(config['ratings.setup'])
         self.user = {} #used to store the order of users

data/social.py

@@ -6,7 +6,7 @@
 from re import split
 
 class SocialDAO(object):
-    def __init__(self,conf,relation):
+    def __init__(self,conf,relation=list()):
         self.config = conf
         self.user = {} #used to store the order of users
         self.relation = relation

main/RecQ.py

@@ -4,7 +4,7 @@
 from tool.file import FileIO
 from evaluation.dataSplit import *
 from multiprocessing import Process,Manager
-
+from tool.file import FileIO
 class RecQ(object):
     def __init__(self,config):
         self.trainingData = []  # training data
@@ -18,16 +18,16 @@ def __init__(self,config):
             self.evaluation = LineConfig(config['evaluation.setup'])
             if self.evaluation.contains('-testSet'):
                 #specify testSet
-                self.__loadDataSet(config['ratings'])
-                self.__loadDataSet(self.evaluation['-testSet'],bTest=True)
+                self.trainingData = FileIO.loadDataSet(config,config['ratings'])
+                self.testData = FileIO.loadDataSet(config,self.evaluation['-testSet'],bTest=True)
             elif self.evaluation.contains('-ap'):
                 #auto partition
-                self.__loadDataSet(config['ratings'])
+                self.trainingData = FileIO.loadDataSet(config,config['ratings'])
                 self.trainingData,self.testData = DataSplit.\
                     dataSplit(self.trainingData,test_ratio=float(self.evaluation['-ap']))
             elif self.evaluation.contains('-cv'):
                 #cross validation
-                self.__loadDataSet(config['ratings'])
+                self.trainingData = FileIO.loadDataSet(config,config['ratings'])
                 #self.trainingData,self.testData = DataSplit.crossValidation(self.trainingData,int(self.evaluation['-cv']))
 
         else:
@@ -36,62 +36,11 @@ def __init__(self,config):
 
         if config.contains('social'):
             self.socialConfig = LineConfig(self.config['social.setup'])
-            self.__loadRelationship(self.config['social'])
+            self.relation = FileIO.loadRelationship(config,self.config['social'])
 
 
-    def __loadDataSet(self, file, bTest=False):
-        if not bTest:
-            print 'loading training data...'
-        else:
-            print 'loading test data...'
-        with open(file) as f:
-            ratings = f.readlines()
-        # ignore the headline
-        if self.ratingConfig.contains('-header'):
-            ratings = ratings[1:]
-        # order of the columns
-        order = self.ratingConfig['-columns'].strip().split()
 
-        for lineNo, line in enumerate(ratings):
-            items = split(' |,|\t', line.strip())
-            if len(order) < 3:
-                print 'The rating file is not in a correct format. Error: Line num %d' % lineNo
-                exit(-1)
-            try:
-                userId = items[int(order[0])]
-                itemId = items[int(order[1])]
-                rating = items[int(order[2])]
-            except ValueError:
-                print 'Error! Have you added the option -header to the rating.setup?'
-                exit(-1)
-            if not bTest:
-                self.trainingData.append([userId, itemId, float(rating)])
-            else:
-                self.testData.append([userId, itemId, float(rating)])
 
-    def __loadRelationship(self, filePath):
-        print 'load social data...'
-        with open(filePath) as f:
-            relations = f.readlines()
-            # ignore the headline
-        if self.socialConfig.contains('-header'):
-            relations = relations[1:]
-        # order of the columns
-        order = self.socialConfig['-columns'].strip().split()
-        if len(order) <= 2:
-            print 'The social file is not in a correct format.'
-        for lineNo,line in enumerate(relations):
-            items = split(' |,|\t', line.strip())
-            if len(order) < 2:
-                print 'The social file is not in a correct format. Error: Line num %d' % lineNo
-                exit(-1)
-            userId1 = items[int(order[0])]
-            userId2 = items[int(order[1])]
-            if len(order) < 3:
-                weight = 1
-            else:
-                weight = float(items[int(order[2])])
-            self.relation.append([userId1, userId2, weight])
 
 
     def execute(self):

tool/file.py

@@ -1,6 +1,7 @@
 import os.path
 from os import makedirs,remove
-from re import compile,findall
+from re import compile,findall,split
+from config import LineConfig
 class FileIO(object):
     def __init__(self):
         pass
@@ -26,6 +27,72 @@ def deleteFile(filePath):
         if os.path.exists(filePath):
             remove(filePath)
 
+    @staticmethod
+    def loadDataSet(conf, file, bTest=False):
+        trainingData = []
+        testData = []
+        ratingConfig = LineConfig(conf['ratings.setup'])
+        if not bTest:
+            print 'loading training data...'
+        else:
+            print 'loading test data...'
+        with open(file) as f:
+            ratings = f.readlines()
+        # ignore the headline
+        if ratingConfig.contains('-header'):
+            ratings = ratings[1:]
+        # order of the columns
+        order = ratingConfig['-columns'].strip().split()
+
+        for lineNo, line in enumerate(ratings):
+            items = split(' |,|\t', line.strip())
+            if len(order) < 3:
+                print 'The rating file is not in a correct format. Error: Line num %d' % lineNo
+                exit(-1)
+            try:
+                userId = items[int(order[0])]
+                itemId = items[int(order[1])]
+                rating = items[int(order[2])]
+            except ValueError:
+                print 'Error! Have you added the option -header to the rating.setup?'
+                exit(-1)
+            if not bTest:
+                trainingData.append([userId, itemId, float(rating)])
+            else:
+                testData.append([userId, itemId, float(rating)])
+        if not bTest:
+            return trainingData
+        else:
+            return testData
+
+    @staticmethod
+    def loadRelationship(conf, filePath):
+        socialConfig = LineConfig(conf['social.setup'])
+        relation = []
+        print 'load social data...'
+        with open(filePath) as f:
+            relations = f.readlines()
+            # ignore the headline
+        if socialConfig.contains('-header'):
+            relations = relations[1:]
+        # order of the columns
+        order = socialConfig['-columns'].strip().split()
+        if len(order) <= 2:
+            print 'The social file is not in a correct format.'
+        for lineNo, line in enumerate(relations):
+            items = split(' |,|\t', line.strip())
+            if len(order) < 2:
+                print 'The social file is not in a correct format. Error: Line num %d' % lineNo
+                exit(-1)
+            userId1 = items[int(order[0])]
+            userId2 = items[int(order[1])]
+            if len(order) < 3:
+                weight = 1
+            else:
+                weight = float(items[int(order[2])])
+            relation.append([userId1, userId2, weight])
+        return relation
+
 
 
 

visual/display.py

@@ -6,17 +6,19 @@
 from tool.qmath import denormalize
 from os.path import abspath
 import webbrowser
-
+from tool.file import FileIO
 class Display(object):
     def __init__(self,conf):
         self.conf = conf
         if not conf.contains('ratings') and not conf.contains('social'):
             print 'The config file is not in the correct format!'
             exit(-1)
         if conf.contains('ratings'):
-            self.dao = RatingDAO(conf)
+            ratingData =  FileIO.loadDataSet(conf,conf['ratings'])
+            self.dao = RatingDAO(conf,ratingData)
         if conf.contains('social'):
-            self.sao = SocialDAO(conf)
+            relationData = FileIO.loadRelationship(conf,conf['social'])
+            self.sao = SocialDAO(conf,relationData)
 
 
     def draw(self):

visual/visualization/analysis.html

@@ -2,7 +2,7 @@
 <link rel='stylesheet' type='text/css' href='reportStyle.css'/></head>
 <body><div class='reportTitle'><div class='in'>Data Analysis</div></div>
 <div class='main'><div class='area1'>
-<div class='title'><h3>Data Files</h3></div><div class='text'><b>Rating Data</b>: C:\Users\123\Documents\GitHub\RecQ\dataset\FilmTrust\trainset.txt<br><b>Social Data</b>: C:\Users\123\Documents\GitHub\RecQ\dataset\FilmTrust\testset.txt</div></div><div style='padding-top:20px'><center><img src='images/header2.png'/></center></div>
+<div class='title'><h3>Data Files</h3></div><div class='text'><b>Rating Data</b>: C:\Users\Administrator\Desktop\RecQ\dataset\FilmTrust\trainset.txt<br><b>Social Data</b>: C:\Users\Administrator\Desktop\RecQ\dataset\FilmTrust\testset.txt</div></div><div style='padding-top:20px'><center><img src='images/header2.png'/></center></div>
 <div class='area1'><div class='title'><h3>Rating Data</h3></div>
 <div class='text'><b>Rating Scale</b>: 0.5 1.0 1.5 2.0 2.5 3.0 3.5 4.0</br><b>User Count</b>: 1494<br><b>Item Count</b>: 1994<br><b>Record Count</b>: 31851<br><b>Global Mean</b>: 3.105</div>
 <center><div class='img'><img src='images/rh.png' width='640px' height='480px'/></div></center>