Resolve "integration-sota"

Closes #15 (closed)

code/bolsonaro/models/similarity_forest_regressor.py

-from bolsonaro.utils import tqdm_joblib
-
 from sklearn.ensemble import RandomForestRegressor
 from sklearn.metrics import mean_squared_error
 from sklearn.base import BaseEstimator
 from abc import abstractmethod, ABCMeta
 import numpy as np
-from joblib import Parallel, delayed
 from tqdm import tqdm
 
 
@@ -34,35 +31,40 @@ class SimilarityForestRegressor(BaseEstimator, metaclass=ABCMeta):
         selected_trees = list()
         tree_list = list(self._estimator.estimators_)
 
-        for _ in range(self._extracted_forest_size):
-            best_similarity = 100000
-            found_index = 0
-            for i in range(len(tree_list)):
-                lonely_tree = tree_list[i]
-                del tree_list[i]
-                begin_time = time.time()
-                with tqdm_joblib(tqdm(total=len(tree_list), disable=True)) as job_pb:
-                    val_list = Parallel(n_jobs=-1)(delayed(self._tree_predict_job)(
-                        job_pb, tree_list[i], X_val)
-                        for i in range(len(tree_list)))
-                val_list = np.array(val_list)
-                val_mean = np.mean(val_list, axis=0)
-                val_score = self._score_metric(val_mean, y_val)
-                temp_similarity = abs(forest_pred - val_score)
-                if (temp_similarity < best_similarity):
-                    found_index = i
-                    best_similarity = temp_similarity
-                tree_list.insert(i, lonely_tree)
-            selected_trees.append(tree_list[found_index])
-            del tree_list[found_index]
+        val_scores = list()
+        with tqdm(tree_list) as tree_pred_bar:
+            tree_pred_bar.set_description('[Initial tree predictions]')
+            for tree in tree_pred_bar:
+                val_scores.append(tree.predict(X_val))
+            tree_pred_bar.update(1)
+
+        with tqdm(range(self._extracted_forest_size), disable=False) as pruning_forest_bar:
+            pruning_forest_bar.set_description(f'[Pruning forest s={self._extracted_forest_size}]')
+            for i in pruning_forest_bar:
+                best_similarity = 100000
+                found_index = 0
+                with tqdm(range(len(tree_list)), disable=False) as tree_list_bar:
+                    tree_list_bar.set_description(f'[Tree selection s={self._extracted_forest_size} #{i}]')
+                    for j in tree_list_bar:
+                        lonely_tree = tree_list[j]
+                        del tree_list[j]
+                        val_mean = np.mean(np.asarray(val_scores), axis=0)
+                        val_score = self._score_metric(val_mean, y_val)
+                        temp_similarity = abs(forest_pred - val_score)
+                        if (temp_similarity < best_similarity):
+                            found_index = j
+                            best_similarity = temp_similarity
+                        tree_list.insert(j, lonely_tree)
+                        val_scores.insert(j, lonely_tree.predict(X_val))
+                        tree_list_bar.update(1)
+                selected_trees.append(tree_list[found_index])
+                del tree_list[found_index]
+                del val_scores[found_index]
+                pruning_forest_bar.update(1)
 
         pruned_forest = list(set(forest) - set(selected_trees))
         self._estimator.estimators_ = pruned_forest
 
-    def _tree_predict_job(self, job_pb, tree, X_val):
-        val_pred = tree.predict(X_val)
-        return val_pred
-
     def score(self, X, y):
         test_list = list()
         for mod in self._estimator.estimators_: