Trying to make bins and rates_cap more flexible, inserting default values.

mlair/configuration/defaults.py

@@ -56,6 +56,9 @@ DEFAULT_DATA_ORIGIN = {"cloudcover": "REA", "humidity": "REA", "pblheight": "REA
 DEFAULT_USE_MULTIPROCESSING = True
 DEFAULT_USE_MULTIPROCESSING_ON_DEBUG = False
 
+DEFAULT_BINS = 10
+DEFAULT_RATES_CAP = 20
+
 
 def get_defaults():
     """Return all default parameters set in defaults.py"""

mlair/run_modules/experiment_setup.py

@@ -215,7 +215,8 @@ class ExperimentSetup(RunEnvironment):
                  create_new_bootstraps=None, data_path: str = None, batch_path: str = None, login_nodes=None,
                  hpc_hosts=None, model=None, batch_size=None, epochs=None, data_handler=None,
                  data_origin: Dict = None, competitors: list = None, competitor_path: str = None,
-                 use_multiprocessing: bool = None, use_multiprocessing_on_debug: bool = None, **kwargs):
+                 use_multiprocessing: bool = None, use_multiprocessing_on_debug: bool = None,
+                 bins=None, rates_cap=None, **kwargs):
 
         # create run framework
         super().__init__()
@@ -360,6 +361,10 @@ class ExperimentSetup(RunEnvironment):
         # set model architecture class
         self._set_param("model_class", model, VanillaModel)
 
+        # set params for oversampling
+        self._set_param("bins", bins, default=DEFAULT_BINS)
+        self._set_param("rates_cap", rates_cap, default=DEFAULT_RATES_CAP)
+
         # set remaining kwargs
         if len(kwargs) > 0:
             for k, v in kwargs.items():

mlair/run_modules/pre_processing.py

@@ -71,9 +71,11 @@ class PreProcessing(RunEnvironment):
         self.report_pre_processing()
         self.prepare_competitors()
 
-    def apply_oversampling(self, bins=10, rates_cap=20):
+    def apply_oversampling(self):
         #if request for oversampling=True/False
         data = self.data_store.get('data_collection', 'train')
+        bins = self.data_store.get_default('bins')
+        rates_cap = self.data_store.get_default('rates_cap')
         histogram = np.array(bins)
         #get min and max of the whole data
         total_min = 0