visualize_traindata.py 文件源码

def traffic_districution(self):
        data_dir = g_singletonDataFilePath.getTrainDir()
        df = self.load_trafficdf(data_dir)
        print df['traffic'].describe()
#         sns.distplot(self.gapdf['gap'],kde=False, bins=100);
        df['traffic'].plot(kind='hist', bins=100)
        plt.xlabel('Traffic')
        plt.title('Histogram of Traffic')

        return
#     def disp_gap_bydistrict(self, disp_ids = np.arange(34,67,1), cls1 = 'start_district_id', cls2 = 'time_id'):
# #         disp_ids = np.arange(1,34,1)
#         plt.figure()
#         by_district = self.gapdf.groupby(cls1)
#         size = len(disp_ids)
# #         size = len(by_district)
#         col_len = row_len = math.ceil(math.sqrt(size))
#         count = 1
#         for name, group in by_district:
#             if not name in disp_ids:
#                 continue
#             plt.subplot(row_len, col_len, count)
#             group.groupby(cls2)['gap'].mean().plot()
#             count += 1   
#         return