Fix user input check to accept csv for non-landslide database

docs/source/index.rst

@@ -10,12 +10,3 @@ Susceptibility and Hazard mappIng fRamEwork SHIRE
    
    example
    example-plain
-
-
-
-Indices and tables
-==================
-
-* :ref:`genindex`
-* :ref:`modindex`
-* :ref:`search`

src/gui_version/create_training_data_gui.py

@@ -265,16 +265,17 @@ class create_training_data:
         """
 
         if self.properties_train['nonls_path'].split('.')[-1] == 'csv':
-            self.absence = pd.read_csv(self.properties_train['nonls_path'])
+            self.df_absence = pd.read_csv(self.properties_train['nonls_path'])
             
-            self.absence = self.absence.rename(
+            self.df_absence = self.df_absence.rename(
             columns={
                 self.properties_train['x_nonls']: self.properties_train['x'],
                 self.properties_train['y_nonls']: self.properties_train['y']})
 
             nonls_id = [
-                'nonls_event_' + str(i) for i in range(len(self.absence))]
-            self.absence.insert(0, self.properties_train['id'], nonls_id)
+                'nonls_event_' + str(i) for i in range(len(self.df_absence))]
+            if self.properties_train['id'] not in self.df_absence.columns.tolist():
+                self.df_absence.insert(0, self.properties_train['id'], nonls_id)
 
             self.logger.info('Absence locations added')
 

src/gui_version/utilities/properties_user_input.csv

 key,type,range,extension,path
 ls_path,str,None,csv,1
-nonls_path,str,None,nc,1
+nonls_path,str,None,"nc,csv",1
 train_path,str,None,csv,1
 geo_path,str,None,csv,1
 feat_path,str,None,csv,1

src/plain_scripts/create_training_data.py

@@ -199,19 +199,37 @@ class create_training_data:
             Supplement presence data with absence data. It needs to be
             pre-generated.
         """
+        
+        if settings.path_nonls_locations.split('.')[-1] == 'csv':
+            self.df_absence = pd.read_csv(settings.path_nonls_locations)
+            
+            self.df_absence = self.df_absence.rename(
+            columns={
+                settings.nonls_database_x: settings.landslide_database_x,
+                settings.nonls_database_y: settings.landslide_database_y})
 
-        ds = nc.Dataset(settings.path_nonls_locations)
+            nonls_id = [
+                'nonls_event_' + str(i) for i in range(len(self.df_absence))]
+            if settings.ID not in self.df_absence.columns.tolist():
+                self.df_absence.insert(0, settings.ID, nonls_id)
 
-        x = ds[settings.nonls_database_x][:].data
-        y = ds[settings.nonls_database_y][:].data
-        
-        self.df_absence = pd.DataFrame(index=range(len(x)),
-                                       columns=list(self.df_train.columns))
+            self.logger.info('Absence locations added')
+
+        elif settings.path_nonls_locations.split('.')[-1] == 'nc':
+            ds = nc.Dataset(settings.path_nonls_locations)
+
+            x = ds[settings.nonls_database_x][:].data
+            y = ds[settings.nonls_database_y][:].data
 
-        self.df_absence[settings.ID] = ['nonls_event_' + str(i)
-                                        for i in range(len(x))]
-        self.df_absence[settings.landslide_database_x] = list(x)
-        self.df_absence[settings.landslide_database_y] = list(y)
+            self.df_absence = pd.DataFrame(index=range(len(x)),
+                                           columns=list(self.df_train.columns))
+
+            self.df_absence[settings.ID] = [
+                'nonls_event_' + str(i) for i in range(len(x))]
+            self.df_absence[settings.landslide_database_x] = list(x)
+            self.df_absence[settings.landslide_database_y] = list(y)
+
+            self.logger.info('Absence locations added')
 
     def label_training_data(self):
 
@@ -576,6 +594,9 @@ class create_training_data:
         """
             Determine if the extent of one or several
             clusters are too large for local interpolation
+            
+            Input:
+                -
 
             Output:
                 num_bb: list, names of clusters that need reclustering

src/plain_scripts/utilities/properties_user_input.csv

 key,type,range,extension,path
 ls_path,str,None,csv,1
-nonls_path,str,None,nc,1
+nonls_path,str,None,"nc,csv",1
 train_path,str,None,csv,1
 geo_path,str,None,csv,1
 feat_path,str,None,csv,1