style: add one space after commas for readability

nilmtk_contrib/disaggregate/WindowGRU.py

@@ -39,28 +39,25 @@ def __init__(self, params):
         self.max_val = 800
         self.batch_size = params.get('batch_size',512)
 
-    def partial_fit(self,train_main,train_appliances,do_preprocessing=True,**load_kwargs):
-
-
+    def partial_fit(self, train_main, train_appliances, do_preprocessing=True, **load_kwargs):
         if do_preprocessing:
             train_main, train_appliances = self.call_preprocessing(train_main, train_appliances, 'train')
 
         train_main = pd.concat(train_main,axis=0).values
-        train_main = train_main.reshape((-1,self.sequence_length,1))
-
+        train_main = train_main.reshape((-1, self.sequence_length, 1))
         new_train_appliances  = []
         for app_name, app_df in train_appliances:
-            app_df = pd.concat(app_df,axis=0).values
-            app_df = app_df.reshape((-1,1))
+            app_df = pd.concat(app_df, axis=0).values
+            app_df = app_df.reshape((-1, 1))
             new_train_appliances.append((app_name, app_df))
 
         train_appliances = new_train_appliances
         for app_name, app_df in train_appliances:
             if app_name not in self.models:
-                print("First model training for ", app_name)
+                print("First model training for", app_name)
                 self.models[app_name] = self.return_network()
             else:
-                print("Started re-training model for ", app_name)
+                print("Started re-training model for", app_name)
 
             model = self.models[app_name]
             mains = train_main.reshape((-1,self.sequence_length,1))
@@ -77,7 +74,6 @@ def partial_fit(self,train_main,train_appliances,do_preprocessing=True,**load_kw
             )
             model.load_weights(filepath)
 
-
     def disaggregate_chunk(self,test_main_list,model=None,do_preprocessing=True):
 
         if model is not None:

nilmtk_contrib/disaggregate/dae.py

@@ -19,7 +19,7 @@
 random.seed(10)
 np.random.seed(10)
 class DAE(Disaggregator):
-    
+
     def __init__(self, params):
         """
         Iniititalize the moel with the given parameters
@@ -37,10 +37,8 @@ def __init__(self, params):
         self.models = OrderedDict()
         if self.load_model_path:
             self.load_model()
-
 
-
-    def partial_fit(self, train_main, train_appliances, do_preprocessing=True,**load_kwargs):        
+    def partial_fit(self, train_main, train_appliances, do_preprocessing=True, **load_kwargs):
         """
         The partial fit function
         """
@@ -49,24 +47,26 @@ def partial_fit(self, train_main, train_appliances, do_preprocessing=True,**load
         if len(self.appliance_params) == 0:
             self.set_appliance_params(train_appliances)
 
-        # TO preprocess the data and bring it to a valid shape
+        # To preprocess the data and bring it to a valid shape
         if do_preprocessing:
-            print ("Doing Preprocessing")
-            train_main,train_appliances = self.call_preprocessing(train_main,train_appliances,'train')
-        train_main = pd.concat(train_main,axis=0).values
-        train_main = train_main.reshape((-1,self.sequence_length,1))
+            print ("Preprocessing")
+            train_main, train_appliances = self.call_preprocessing(train_main, train_appliances, 'train')
+        train_main = pd.concat(train_main, axis=0).values
+        train_main = train_main.reshape((-1, self.sequence_length, 1))
         new_train_appliances  = []
         for app_name, app_df in train_appliances:
-            app_df = pd.concat(app_df,axis=0).values
-            app_df = app_df.reshape((-1,self.sequence_length,1))
+            app_df = pd.concat(app_df, axis=0).values
+            app_df = app_df.reshape((-1, self.sequence_length, 1))
             new_train_appliances.append((app_name, app_df))
+
         train_appliances = new_train_appliances
         for appliance_name, power in train_appliances:
             if appliance_name not in self.models:
-                print ("First model training for ",appliance_name)
+                print("First model training for", appliance_name)
                 self.models[appliance_name] = self.return_network()
-                print (self.models[appliance_name].summary())
-            print ("Started Retraining model for ",appliance_name)    
+                print(self.models[appliance_name].summary())
+
+            print("Started Retraining model for", appliance_name)
             model = self.models[appliance_name]
             filepath = 'dae-temp-weights-'+str(random.randint(0,100000))+'.h5'
             checkpoint = ModelCheckpoint(filepath, monitor='val_loss', verbose=1, save_best_only=True, mode='min')

nilmtk_contrib/disaggregate/rnn.py

@@ -43,28 +43,23 @@ def __init__(self, params):
             print ("Sequence length should be odd!")
             raise (SequenceLengthError)
 
-    def partial_fit(self,train_main,train_appliances,do_preprocessing=True,
-            **load_kwargs):
-
+    def partial_fit(self, train_main, train_appliances, do_preprocessing=True, **load_kwargs):
         # If no appliance wise parameters are provided, then copmute them using the first chunk
         if len(self.appliance_params) == 0:
             self.set_appliance_params(train_appliances)
-
 
         print("...............RNN partial_fit running...............")
         # Do the pre-processing, such as  windowing and normalizing
-
         if do_preprocessing:
             train_main, train_appliances = self.call_preprocessing(
                 train_main, train_appliances, 'train')
 
-        train_main = pd.concat(train_main,axis=0)
-        train_main = train_main.values.reshape((-1,self.sequence_length,1))
-
+        train_main = pd.concat(train_main, axis=0)
+        train_main = train_main.values.reshape((-1, self.sequence_length, 1))
         new_train_appliances = []
         for app_name, app_df in train_appliances:
-            app_df = pd.concat(app_df,axis=0)
-            app_df_values = app_df.values.reshape((-1,1))
+            app_df = pd.concat(app_df, axis=0)
+            app_df_values = app_df.values.reshape(( -1, 1 ))
             new_train_appliances.append((app_name, app_df_values))
         train_appliances = new_train_appliances
 

nilmtk_contrib/disaggregate/seq2point.py

@@ -43,38 +43,34 @@ def __init__(self, params):
             print ("Sequence length should be odd!")
             raise (SequenceLengthError)
 
-    def partial_fit(self,train_main,train_appliances,do_preprocessing=True,
-            **load_kwargs):
-
+    def partial_fit(self, train_main, train_appliances, do_preprocessing=True, **load_kwargs):
         # If no appliance wise parameters are provided, then copmute them using the first chunk
         if len(self.appliance_params) == 0:
             self.set_appliance_params(train_appliances)
 
         print("...............Seq2Point partial_fit running...............")
         # Do the pre-processing, such as  windowing and normalizing
-
         if do_preprocessing:
             train_main, train_appliances = self.call_preprocessing(
                 train_main, train_appliances, 'train')
 
-        train_main = pd.concat(train_main,axis=0)
-        train_main = train_main.values.reshape((-1,self.sequence_length,1))
-
+        train_main = pd.concat(train_main, axis=0)
+        train_main = train_main.values.reshape((-1, self.sequence_length, 1))
         new_train_appliances = []
         for app_name, app_df in train_appliances:
-            app_df = pd.concat(app_df,axis=0)
-            app_df_values = app_df.values.reshape((-1,1))
+            app_df = pd.concat(app_df, axis=0)
+            app_df_values = app_df.values.reshape((-1, 1))
             new_train_appliances.append((app_name, app_df_values))
         train_appliances = new_train_appliances
 
         for appliance_name, power in train_appliances:
             # Check if the appliance was already trained. If not then create a new model for it
             if appliance_name not in self.models:
-                print("First model training for ", appliance_name)
+                print("First model training for", appliance_name)
                 self.models[appliance_name] = self.return_network()
             # Retrain the particular appliance
             else:
-                print("Started Retraining model for ", appliance_name)
+                print("Started Retraining model for", appliance_name)
 
             model = self.models[appliance_name]
             if train_main.size > 0:

nilmtk_contrib/disaggregate/seq2seq.py

@@ -45,26 +45,24 @@ def __init__(self, params):
             print ("Sequence length should be odd!")
             raise (SequenceLengthError)
 
-    def partial_fit(self,train_main,train_appliances,do_preprocessing=True,**load_kwargs):
-
+    def partial_fit(self, train_main, train_appliances, do_preprocessing=True, **load_kwargs):
         print("...............Seq2Seq partial_fit running...............")
         if len(self.appliance_params) == 0:
             self.set_appliance_params(train_appliances)
 
-        print (len(train_main))
         if do_preprocessing:
             train_main, train_appliances = self.call_preprocessing(
                 train_main, train_appliances, 'train')
-        train_main = pd.concat(train_main,axis=0)
-        train_main = train_main.values.reshape((-1,self.sequence_length,1))
-
+
+        train_main = pd.concat(train_main, axis=0)
+        train_main = train_main.values.reshape((-1, self.sequence_length, 1))
         new_train_appliances = []
         for app_name, app_dfs in train_appliances:
-            app_df = pd.concat(app_dfs,axis=0)
-            app_df_values = app_df.values.reshape((-1,self.sequence_length))
+            app_df = pd.concat(app_dfs, axis=0)
+            app_df_values = app_df.values.reshape((-1, self.sequence_length))
             new_train_appliances.append((app_name, app_df_values))
-        train_appliances = new_train_appliances
 
+        train_appliances = new_train_appliances
         for appliance_name, power in train_appliances:
             if appliance_name not in self.models:
                 print("First model training for ", appliance_name)