prepare_instances.py 文件源码

def run(self):
        all_file_names = []
        all_labels = []

        for n, folder_name in enumerate(os.listdir(self.in_txtdir().path)):

            full_folder_name = self.in_txtdir().path+'/'+folder_name

            if os.path.isfile(full_folder_name):
                continue

            for file_name in os.listdir(full_folder_name):
                all_labels.append(n)
                all_file_names.append(full_folder_name+'/'+file_name)

        vectorizer = CountVectorizer(input='filename')
        vector = vectorizer.fit_transform(all_file_names)
        numpy.save(self.out_npy().path,vector)
        numpy.save('labels',numpy.array(all_labels)) #Where and how do we want to save this?

#This is just to test the tasks above