Adicionado threads

src/extraction/feature_extraction.py

@@ -11,7 +11,7 @@
 import io
 import itertools
 import os
-
+import threading
 from interface.interface import InterfaceException as IException
 
 from util.file_utils import File
@@ -22,20 +22,28 @@ from extractor import Extractor
 
 class FeatureExtractor(object):
     """Handle the feature extraction."""
-    
+
     def __init__(self, extractors):
         """Constructor.
-        
+
         Parameters
         ----------
         extractor : list of Extractor
             Initial set of active extractors.
         """
         self.extractors = extractors
-    
+
+
     def extract_all(self, dataset, output_file = None, dirs = None, overwrite = True):
+        self.labels=[]
+        self.types=[]
+
+        self.data=[]
+        self.threads=[]
+        self.labels=[]
+        self.types=[]
         """Runs the feature extraction algorithms on all images of dataset.
-        
+
         Parameters
         ----------
         dataset : string
@@ -46,12 +54,12 @@ class FeatureExtractor(object):
             List of directories to be serched. If not informed search in all directories with images inside dataset.
         overwrite : boolean, optional, default = True
             If False check if already exists a file containing the features.
-        
+
         Returns
         -------
-        out : tuple 
+        out : tuple
             Returns a tuple containing the name of output file and time spent in milliseconds.
-            
+
         Raises
         ------
         IException 'Please select at least one extractor'
@@ -63,55 +71,67 @@ class FeatureExtractor(object):
         """
         if len(self.extractors) == 0:
             raise IException("Please select at least one extractor")
-        
+
         if output_file is None:
             output_file = File.get_filename(dataset)
         output_file = File.make_path(dataset, output_file + '.arff')
-            
+
         # if already exists a output file and must not override, return current file
         if overwrite == False and os.path.isfile(output_file):
             return output_file, 0
-        
+
         start_time = TimeUtils.get_time()
-        
+
         classes = sorted(File.list_dirs(dataset))
         dirs = classes if dirs is None else dirs
-        
-        data = []
-        
+
+
+
         # Runs the feature extraction for all classes inside the dataset
         for cl in dirs:
-            items = sorted(os.listdir( File.make_path(dataset, cl)))
-            print("Processing class %s - %d itens" % (cl, len(items)))
-            
-            for item in items:
-                if item.startswith('.'):
-                    continue 
-                
-                try:
-                    filepath = File.make_path(dataset, cl, item)
-                    image = File.open_image(filepath, rgb = False )
-                except:
-                    raise IException("Image %s is possibly corrupt" % filepath)
-                
-                if len(data) > 0:
-                    values = list(itertools.chain.from_iterable(zip(*([extractor().run(image) for extractor in self.extractors]))[2] ))
-                else:          
-                    labels, types, values = [ list(itertools.chain.from_iterable(ret))
-                                                for ret in zip(*([extractor().run(image) for extractor in self.extractors])) ]
-                                                
-                data.append(values + [cl if cl in classes else classes[0]])
-                
-        if len(data) == 0:
+            # start job for each extractor
+            process = threading.Thread(target=self.job_extractor, args=[ dataset, cl, classes ])
+            process.start()
+            self.threads.append(process)
+        #wait jobs finish
+        for process in self.threads:
+            process.join()
+
+
+        if len(self.data) == 0:
             raise IException("There are no images in dataset: %s" % dataset)
-          
+
+
         # Save the output file in ARFF format
-        self._save_output(File.get_filename(dataset), classes, labels, types, data, output_file)
-        
+        self._save_output(File.get_filename(dataset), classes, self.labels, self.types, self.data, output_file)
+
         end_time = TimeUtils.get_time()
 
         return output_file, (end_time - start_time)
 
+    def job_extractor(self,dataset, cl, classes ):
+
+        items = sorted(os.listdir( File.make_path(dataset, cl)))
+        print("Processing class %s - %d itens" % (cl, len(items)))
+        for item in items:
+                values=[]
+                if item.startswith('.'):
+                    continue
+                try:
+                     filepath = File.make_path(dataset, cl, item)
+                     image = File.open_image(filepath, rgb = False )
+                except:
+                     raise IException("Image %s is possibly corrupt" % filepath)
+
+                if len(self.data) > 0:
+                     values = list(itertools.chain.from_iterable(zip(*([extractor().run(image) for extractor in self.extractors]))[2] ))
+                     self.data.append(values + [cl if cl in classes else classes[0]])
+                else:
+                     self.labels, self.types, values = [ list(itertools.chain.from_iterable(ret))
+                                    for ret in zip(*([extractor().run(image) for extractor in self.extractors])) ]
+                     self.data.append(values + [cl if cl in classes else classes[0]])
+
+
 
     def extract_one_file(self, dataset, image_path, output_file = None):
         """Runs the feature extraction algorithms on specific image.