Now we can create plots!

config/general_values.py

@@ -1,3 +1,15 @@
 
 purposes = ['Train', 'Test']
 dataset_qualities = ['Normal', 'Balanced', 'Augmented']
+
+
+def aveg(given_list):
+    return sum(given_list)/len(given_list)
+
+
+def aveg_not_zero(given_list):
+    return sum(given_list)/max(1, len([1 for elem in given_list
+                                      if elem != 0]))
+
+
+operations = [sum, max, aveg]  # , aveg_not_zero

config/hyperparameters_grid.py

@@ -2,16 +2,10 @@
 
 grid = dict()
 grid['RF'] = {
-    # 'n_estimators': [200, 300, 400, 500],
-    # 'max_features': ['sqrt', 'log2'],
-    # 'max_depth': [4, 5, 6, 7, 8],
-    # 'criterion': ['gini', 'entropy']
-    'n_estimators': [50, 100, 200],
-    'criterion': ['gini', 'entropy'],
-    'max_depth': [None, 10, 20, 30],
-    'min_samples_split': [2, 5, 10],
-    'min_samples_leaf': [1, 2, 4],
-    'class_weight': [None, 'balanced'],
+    'n_estimators': [200, 300, 400, 500],
+    'max_features': ['sqrt', 'log2'],
+    'max_depth': [4, 5, 6, 7, 8],
+    'criterion': ['gini', 'entropy']
 }
 grid['KNN'] = {
     'n_neighbors': [1,3,5,7,12],
@@ -41,18 +35,9 @@
 }
 
 grid['RFR'] = {
-    # 'n_estimators': [200, 300, 400, 500],
-    # 'max_features': ['sqrt', 'log2'],
-    # 'max_depth': [4, 5, 6, 7, 8],
-    # 'criterion': ['squared_error', 'entropy']
-    # # 'criterion': ['squared_error', 'friedman_mse'],
-    # # "max_depth": [1,3,7],
-    # # "min_samples_leaf": [1,5,10],
-    'n_estimators': [50, 100, 200],
-    'criterion': ['mse', 'mae'],
-    'max_depth': [None, 10, 20, 30],
-    'min_samples_split': [2, 5, 10],
-    'min_samples_leaf': [1, 2, 4],
+    'criterion': ['squared_error', 'friedman_mse'],
+    "max_depth": [1,3,7],
+    "min_samples_leaf": [1,5,10],
 }
 grid['KNNR'] = {
     'n_neighbors': [3, 5, 10],
@@ -82,4 +67,4 @@
 grid['SGD'] = {
     'loss':["squared_error", "huber", "epsilon_insensitive"],
     'penalty':["l2", "l1", "elasticnet"]
-}
+}

config/hyperparams/augmented_DT.yaml

@@ -1,3 +1,3 @@
 criterion: gini
-max_depth: 16
-splitter: best
+max_depth: 19
+splitter: random

config/hyperparams/augmented_KNN.yaml

@@ -1,3 +1,3 @@
-algorithm: kd_tree
+algorithm: auto
 n_neighbors: 12
 weights: distance

config/hyperparams/balanced_DT.yaml

@@ -1,3 +1,3 @@
 criterion: gini
-max_depth: 7
+max_depth: 4
 splitter: best

config/hyperparams/balanced_KNN.yaml

@@ -1,3 +1,3 @@
-algorithm: auto
+algorithm: ball_tree
 n_neighbors: 1
 weights: uniform

config/hyperparams/normal_DT.yaml

@@ -1,3 +1,3 @@
 criterion: gini
-max_depth: 13
+max_depth: 10
 splitter: random

config/hyperparams/normal_KNN.yaml

@@ -1,3 +1,3 @@
 algorithm: auto
-n_neighbors: 7
+n_neighbors: 5
 weights: distance

config/ml_models.py

@@ -13,19 +13,19 @@
 from sklearn.neighbors import KNeighborsRegressor
 
 ml_models = [
-            #  'KNN',
-            #  'DT',
-            #  'SVC',
+             'KNN',
+             'DT',
+             'SVC',
              'RF',
-            #  'MLP'
+             'MLP'
              ]
 
 ml_regressors = [
-                #  'DTR',
-                #  'SVR',
+                 'DTR',
+                 'SVR',
                  'RFR',
-                #  'KNNR',
-                #  'MLPR'
+                 'KNNR',
+                 'MLPR'
                  ]
 
 sklearn_models = {