Format code

Author: reyoung

demo/traffic_prediction/dataprovider.py

@@ -18,6 +18,8 @@
 TERM_NUM = 24
 FORECASTING_NUM = 25
 LABEL_VALUE_NUM = 4
+
+
 def initHook(settings, file_list, **kwargs):
     """
     Init hook is invoked before process data. It will set obj.slots and store data meta.
@@ -27,8 +29,8 @@ def initHook(settings, file_list, **kwargs):
     :param file_list: the meta file object, which passed from trainer_config.py,but unused in this function.
     :param kwargs: unused other arguments.
     """
-    del kwargs #unused 
-   
+    del kwargs  #unused 
+
     settings.pool_size = sys.maxint
     #Use a time seires of the past as feature.
     #Dense_vector's expression form is [float,float,...,float]
@@ -38,40 +40,43 @@ def initHook(settings, file_list, **kwargs):
     for i in range(FORECASTING_NUM):
         settings.slots.append(integer_value(LABEL_VALUE_NUM))
 
-@provider(init_hook=initHook, cache=CacheType.CACHE_PASS_IN_MEM, should_shuffle=True)
+
+@provider(
+    init_hook=initHook, cache=CacheType.CACHE_PASS_IN_MEM, should_shuffle=True)
 def process(settings, file_name):
     with open(file_name) as f:
         #abandon fields name
         f.next()
-        for row_num, line in enumerate(f): 
-            speeds = map(int,line.rstrip('\r\n').split(",")[1:])
+        for row_num, line in enumerate(f):
+            speeds = map(int, line.rstrip('\r\n').split(",")[1:])
             # Get the max index.
             end_time = len(speeds)
             # Scanning and generating samples
-            for i in range(TERM_NUM,end_time - FORECASTING_NUM):
+            for i in range(TERM_NUM, end_time - FORECASTING_NUM):
                 # For dense slot
-                pre_spd = map(float,speeds[i-TERM_NUM:i])
+                pre_spd = map(float, speeds[i - TERM_NUM:i])
 
                 # Integer value need predicting, values start from 0, so every one minus 1.
-                fol_spd  = [i-1 for i in speeds[i:i + FORECASTING_NUM]]
-                
+                fol_spd = [i - 1 for i in speeds[i:i + FORECASTING_NUM]]
+
                 # Predicting label is missing, abandon the sample.
                 if -1 in fol_spd:
                     continue
                 yield [pre_spd] + fol_spd
 
+
 def predict_initHook(settings, file_list, **kwargs):
     settings.pool_size = sys.maxint
     settings.slots = [dense_vector(TERM_NUM)]
 
-@provider(init_hook=predict_initHook,should_shuffle=False)
+
+@provider(init_hook=predict_initHook, should_shuffle=False)
 def process_predict(settings, file_name):
     with open(file_name) as f:
         #abandon fields name
         f.next()
         for row_num, line in enumerate(f):
-            speeds = map(int,line.rstrip('\r\n').split(","))
+            speeds = map(int, line.rstrip('\r\n').split(","))
             end_time = len(speeds)
-            pre_spd = map(float,speeds[end_time-TERM_NUM:end_time])
+            pre_spd = map(float, speeds[end_time - TERM_NUM:end_time])
             yield pre_spd
-

demo/traffic_prediction/gen_result.py

@@ -1,39 +1,40 @@
 res = []
 with open('./rank-00000') as f:
     for line in f:
-        pred = map(int,line.strip('\r\n;').split(";"))
+        pred = map(int, line.strip('\r\n;').split(";"))
         #raw prediction range from 0 to 3
-        res.append([i+1 for i in pred])
+        res.append([i + 1 for i in pred])
 
 file_name = open('./data/pred.list').read().strip('\r\n')
 
-FORECASTING_NUM=24
-header=['id',
-        '201604200805',
-        '201604200810',
-        '201604200815',
-        '201604200820',
-        '201604200825',
-        '201604200830',
-        '201604200835',
-        '201604200840',
-        '201604200845',
-        '201604200850',
-        '201604200855',
-        '201604200900',
-        '201604200905',
-        '201604200910',
-        '201604200915',
-        '201604200920',
-        '201604200925',
-        '201604200930',
-        '201604200935',
-        '201604200940',
-        '201604200945',
-        '201604200950',
-        '201604200955',
-        '201604201000',
-        ]
+FORECASTING_NUM = 24
+header = [
+    'id',
+    '201604200805',
+    '201604200810',
+    '201604200815',
+    '201604200820',
+    '201604200825',
+    '201604200830',
+    '201604200835',
+    '201604200840',
+    '201604200845',
+    '201604200850',
+    '201604200855',
+    '201604200900',
+    '201604200905',
+    '201604200910',
+    '201604200915',
+    '201604200920',
+    '201604200925',
+    '201604200930',
+    '201604200935',
+    '201604200940',
+    '201604200945',
+    '201604200950',
+    '201604200955',
+    '201604201000',
+]
 ###################
 ## To CSV format ##
 ###################
@@ -43,5 +44,4 @@
     for row_num, line in enumerate(f):
         fields = line.rstrip('\r\n').split(',')
         linkid = fields[0]
-        print linkid+','+','.join(map(str,res[row_num]))
-
+        print linkid + ',' + ','.join(map(str, res[row_num]))

demo/traffic_prediction/trainer_config.py

@@ -2,42 +2,40 @@
 #-*python-*-
 from paddle.trainer_config_helpers import *
 
-
 ################################### DATA Configuration #############################################
 is_predict = get_config_arg('is_predict', bool, False)
 trn = './data/train.list' if not is_predict else None
 tst = './data/test.list' if not is_predict else './data/pred.list'
 process = 'process' if not is_predict else 'process_predict'
-define_py_data_sources2(train_list=trn,
-                        test_list=tst,
-                        module="dataprovider",
-                        obj=process)
+define_py_data_sources2(
+    train_list=trn, test_list=tst, module="dataprovider", obj=process)
 ################################### Parameter Configuaration #######################################
-TERM_NUM=24
-FORECASTING_NUM= 25
-emb_size=16
-batch_size=128 if not is_predict else 1
+TERM_NUM = 24
+FORECASTING_NUM = 25
+emb_size = 16
+batch_size = 128 if not is_predict else 1
 settings(
-    batch_size = batch_size,
-    learning_rate = 1e-3,
-    learning_method = RMSPropOptimizer()
-)
+    batch_size=batch_size,
+    learning_rate=1e-3,
+    learning_method=RMSPropOptimizer())
 ################################### Algorithm Configuration ########################################
 
 output_label = []
 
 link_encode = data_layer(name='link_encode', size=TERM_NUM)
 for i in xrange(FORECASTING_NUM):
     # Each task share same weight.
-    link_param = ParamAttr(name='_link_vec.w', initial_max=1.0, initial_min=-1.0)
-    link_vec = fc_layer(input=link_encode,size=emb_size, param_attr=link_param)
+    link_param = ParamAttr(
+        name='_link_vec.w', initial_max=1.0, initial_min=-1.0)
+    link_vec = fc_layer(input=link_encode, size=emb_size, param_attr=link_param)
     score = fc_layer(input=link_vec, size=4, act=SoftmaxActivation())
     if is_predict:
         maxid = maxid_layer(score)
         output_label.append(maxid)
     else:
         # Multi-task training.
-        label = data_layer(name='label_%dmin'%((i+1)*5), size=4)
-        cls = classification_cost(input=score,name="cost_%dmin"%((i+1)*5), label=label)
+        label = data_layer(name='label_%dmin' % ((i + 1) * 5), size=4)
+        cls = classification_cost(
+            input=score, name="cost_%dmin" % ((i + 1) * 5), label=label)
         output_label.append(cls)
 outputs(output_label)