u4 update

ss2013/1_Web Mining/Uebungen/4_Uebung/code/naive_bayes.py

@@ -7,26 +7,44 @@ import random
 
 
 # config variables
+actualDir = os.path.dirname(os.path.realpath(__file__))
+dataDir   = os.path.join(actualDir, '../data')
+trainDir  = os.path.join(dataDir, 'u4_train')
+testDir   = os.path.join(dataDir, 'u4_test')
 
 
-
-
-
+'''
+################################################################################################################################
+           --> CLASS Trainingsset <--
+################################################################################################################################
+'''
 
 class trainingsset:
-    actualDir = os.path.dirname(os.path.realpath(__file__))
-    dataDir   = os.path.join(actualDir, '../data')
-    trainDir  = os.path.join(dataDir, 'u4_train')
     
     #def __init__(self):
     
+    classes = ['adventure', 'belles_lettres', 'editorial', 'fiction', 'government', 'hobbies', 'learned', 'lore','mystery','news','romantic']
+    
+    def createTrainingsset(self):
+        self.splitTrainingsdataRandomly(self) # first split our data into trainings- and testdata
+        
+    
+    def getClassesToTrain(self):
+        for dirpath, dirnames, filenames in os.walk(trainDir):
+            # TODO: implement
+            pass
+            
+            
+        
+    # copies files randomly to new directories. Each directory will contain fileCount / 2 numbers of files
+    # If fileCount is uneven /trainingsdata will contain one file more than /testdata
     def splitTrainingsdataRandomly(self):
-        for dirpath, dirnames, filenames in os.walk(self.trainDir, topdown=False):
+        for dirpath, dirnames, filenames in os.walk(trainDir, topdown=False):
             newTrainDir = dirpath+'/trainingsdata'
             newTestDir  = dirpath+'/testdata'
             fileCount = len(filenames)
             
-            if(fileCount > 0):
+            if(fileCount > 0):                
                 #remove old dirs if they already exist
                 if os.path.isdir(newTrainDir):
                     shutil.rmtree(newTrainDir)                    
@@ -39,8 +57,6 @@ class trainingsset:
                 numberOfFilesInTraining = 0
                 numberOfFilesInTest     = 0
                 
-                # copies files randomly to new directories. Each directory will contain fileCount / 2 numbers of files
-                # If fileCount is uneven /trainingsdata will contain one file more than /testdata
                 for actualFile in filenames:
                     fileCopied = False
                                  
@@ -57,7 +73,57 @@ class trainingsset:
                                 shutil.copy(dirpath+'/'+actualFile, dirpath+'/testdata/'+actualFile)
 
 
+
+
+'''
+################################################################################################################################
+           --> CLASS MulticlassClassifier <--
+################################################################################################################################
+'''
+class multiclassClassifier:
+        
+        filesToPrediction = {};
+        testFiles = {}
+        
+        
+        def writePredictionFile(self):
+            with open(actualDir+'/../G22_predictions.txt', 'w') as f:
+                for k in sorted(self.filesToPrediction.iterkeys()):
+                    f.write(str(k)+'\t'+str(self.filesToPrediction[k])+'\n')                    
+            f.closed
+            return
+        
+        # reads all testData from /u4_train to the list 
+        def getTestData(self):
+            listing = os.listdir(testDir)                
+            for infile in listing:
+                f = open(testDir+'/'+infile, 'r')
+                self.testFiles[infile] = f.readline()
+                f.close()
+        
+        
+        def bayes(self, listOfFiles):
+                #TODO : implement
+                pass
+
+
+
+
+'''
+################################################################################################################################
+           --> Main method <--
+################################################################################################################################
+'''
+
 # main method
 if __name__ == '__main__':
-    bla = trainingsset()
-    bla.splitTrainingsdataRandomly();
+    ts = trainingsset()
+    #ts.splitTrainingsdataRandomly();
+    ts.getClassesToTrain();
+    
+    mc = multiclassClassifier()
+    #mc.getTestData()
+    #mc.writePredictionFile()
+    
+    
+