[M] fixed remove rural IRIS

predihood/classes/Data.py

@@ -17,7 +17,7 @@ warnings.filterwarnings("ignore", category=RuntimeWarning)
 
 
 class Data:
-    def __init__(self, normalization="density", filtering=True):
+    def __init__(self, normalization="density", filtering=True, add_assessment=False):
         """
         Constructor of the Data class. Initialize attributes.
         Args:
@@ -31,6 +31,7 @@ class Data:
         self.indicators = None
         self.normalization = normalization
         self.filtering = filtering
+        self.add_assessment = add_assessment
 
         # retrieve indicators
         self.get_indicators()

predihood/classes/Dataset.py

@@ -13,7 +13,7 @@ class Dataset:
     """
     This class represents assessed IRIS with their indicators ans EV values. There are options, such as removing outliers or rural IRIS.
     """
-    def __init__(self, data, env, _type, selected_indicators=None, indicators_to_remove=None, train_size=TRAIN_SIZE, test_size=TEST_SIZE, outliers=False):
+    def __init__(self, data, env, _type, selected_indicators=None, indicators_to_remove=None, train_size=TRAIN_SIZE, test_size=TEST_SIZE, outliers=False, remove_rural=False):
         """
         Constructor of the Dataset class. Initialize attributes.
 
@@ -43,6 +43,7 @@ class Dataset:
         else: self.env = "building_type"
         self.train_size, self.test_size = check_train_test_percentages(train_size, test_size)
         self.outliers = outliers
+        self.remove_rural = remove_rural
 
     def init_all_in_one(self):
         """
@@ -50,8 +51,8 @@ class Dataset:
         When the type is "unsupervised", split data into X and Y is not relevant (as there is no train/test sets).
         """
         if self.type == "supervised":
-            if self.outliers:
-                self.remove_outliers()
+            if self.outliers: self.remove_outliers()
+            if self.remove_rural: self.remove_rural_iris()
             self.init_X()
             self.init_Y()
             self.train_test()

predihood/predict.py

@@ -61,9 +61,9 @@ def compute_all_accuracies(data, clf, train_size, test_size, remove_outliers=Fal
             results[env] = OrderedDict()
         log.debug("--- %s ---", env)
 
-        dataset = Dataset(data_not_filtered, env, selected_indicators=data_not_filtered.indicators, train_size=train_size, test_size=test_size, outliers=remove_outliers, _type='supervised')
+        dataset = Dataset(data_not_filtered, env, selected_indicators=data_not_filtered.indicators, train_size=train_size, test_size=test_size, outliers=remove_outliers, remove_rural=remove_rural, _type='supervised')
         dataset.init_all_in_one()
-        if remove_rural: dataset.remove_rural_iris()
+        # if remove_rural: dataset.remove_rural_iris()
 
         mean_classifier = 0.0
         algo = MethodPrediction(name="", dataset=dataset, classifier=clf)
@@ -78,9 +78,9 @@ def compute_all_accuracies(data, clf, train_size, test_size, remove_outliers=Fal
         log.info("accuracy for %s without filtering: %f", env, algo.accuracy)
 
         for top_k, lst in lists.items():
-            dataset = Dataset(data, env, selected_indicators=lst[env], train_size=train_size, test_size=test_size, outliers=remove_outliers, _type='supervised')
+            dataset = Dataset(data, env, selected_indicators=lst[env], train_size=train_size, test_size=test_size, outliers=remove_outliers, remove_rural=remove_rural, _type='supervised')
             dataset.init_all_in_one()
-            if remove_rural: dataset.remove_rural_iris()
+            # if remove_rural: dataset.remove_rural_iris()
             algo2 = MethodPrediction(name='', dataset=dataset, classifier=clf)
             algo2.fit()
             algo2.compute_performance()