Fix normalize error

experimentation/Experiments.py

@@ -2,7 +2,7 @@ import json
 import os
 import time
 import warnings
-import numpy as np
+import statistics
 from sklearn.model_selection import GridSearchCV, cross_validate
 from . import Models
 from .Database import Hyperparameters, MySQL, Outcomes
@@ -82,6 +82,9 @@ class Experiment:
         outcomes = ["fit_time", "score_time", "train_score", "test_score"]
         for item in outcomes:
             total[item] = []
+        nodes_total = []
+        leaves_total = []
+        depths_total = []
         for random_state in [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]:
             kfold = KFold(shuffle=True, random_state=random_state, n_splits=5)
             model.set_params(**{"random_state": random_state})
@@ -101,13 +104,19 @@ class Experiment:
                 )
                 for item in outcomes:
                     total[item].append(results[item])
-        print("end")
+                if type(model).__name__ == "Stree":
+                    for result_item in results["estimator"]:
+                        nodes, leaves = result_item.nodes_leaves()
+                        nodes_total.append(nodes)
+                        leaves_total.append(leaves)
+                        depths_total.append(result_item.depth_)
         if type(model).__name__ == "Stree":
-            best_model = results["estimator"][np.argmax(results["test_score"])]
-            nodes, leaves = best_model.nodes_leaves()
-            depth = best_model.depth_
+            nodes = statistics.mean(nodes_total)
+            leaves = statistics.mean(leaves_total)
+            depth = statistics.mean(depths_total)
         else:
-            nodes = leaves = depth = 0
+            nodes = leaves = depth = 0.0
+        print("end")
         complexity = dict(nodes=nodes, leaves=leaves, depth=depth)
         outcomes = Outcomes(host=self._host, model=self._model_name)
         parameters = json.dumps(parameters, sort_keys=True)

experimentation/Sets.py

@@ -181,7 +181,7 @@ class Datasets_Tanveer(Dataset_Base):
         )
         X = data.drop("clase", axis=1).to_numpy()
         y = data["clase"].to_numpy()
-        return X, y
+        return self.post_process(X, y)  # type: ignore
 
 
 class Datasets_AAAI(Dataset_Base):