Add nodes, leaves, depth to mysql

Add nodes, leaves, depth, samples, features and classes to analysis

report_score.py

@@ -55,22 +55,30 @@ def parse_arguments():
     return (args.set_of_files, args.model, args.dataset, args.sql, args.param)
 
 
-def nodes_leaves(clf):
-    nodes = 0
-    leaves = 0
-    for node in clf:
-        if node.is_leaf():
-            leaves += 1
-        else:
-            nodes += 1
-    return nodes, leaves
-
-
 def compute_auto_hyperparams(X, y):
-    params = {"max_iter": 1e4, "C": 0.1}
-    classes = len(np.unique(y))
-    if classes > 2:
-        params["split_criteria"] = "max_samples"
+    """Propuesta de auto configuración de hiperparámetros
+    max_it = 10e4
+    (1 valor)
+    split = impurity si clases==2 y split=max_samples si clases > 2
+    (1 valor)
+    kernel=linear o polinómico
+    (2 valores)
+    C = 0.1, 0.5 y 1.0
+    (3 valores)
+    Caso 1: C=1, max_iter=1e4 + condicional split_max kernel lineal
+    Caso 2: C=0.5, max_iter=1e4 + condicional split_max kernel lineal
+    Caso 3: C=0.1, max_iter=1e4 + condicional split_max kernel lineal
+    Caso 4: C=1, max_iter=1e4 + condicional split_max kernel poly
+    Caso 5: C=0.5, max_iter=1e4 + condicional split_max kernel poly
+    Caso 6: C=0.1, max_iter=1e4 + condicional split_max kernel poly
+    Caso 7: C=1, max_iter=1e4 + condicional + kernel rbf
+    Caso 8: kernel rbf
+    """
+    # params = {"max_iter": 1e4, "kernel": "rbf"}
+    # classes = len(np.unique(y))
+    # if classes > 2:
+    #     params["split_criteria"] = "max_samples"
+    params = {"kernel": "rbf"}
     return params
 
 
@@ -97,7 +105,7 @@ def process_dataset(dataset, verbose, model, auto_params):
         clf = Stree(random_state=random_state)
         clf.set_params(**hyperparameters)
         res = cross_validate(clf, X, y, cv=kfold, return_estimator=True)
-        nodes, leaves = nodes_leaves(res["estimator"][0])
+        nodes, leaves = res["estimator"][0].nodes_leaves()
         depth = res["estimator"][0].depth_
         scores.append(res["test_score"])
         times.append(res["fit_time"])
@@ -222,6 +230,9 @@ if dataset == "all":
             parameters = json.loads("{}")
             accuracy_best = 0.0
             acc_best_std = 0.0
+        if auto_params:
+            # show parameters computed
+            parameters = json.loads(hyperparameters)
         accuracy_computed = np.mean(scores)
         diff = accuracy_best - accuracy_computed
         print(
@@ -243,12 +254,12 @@ else:
     accuracy_best = record[5] if record is not None else 0.0
     acc_best_std = record[11] if record is not None else 0.0
     print(
-        f"* Accuracy Computed : {accuracy:6.4f}±{np.std(scores):6.4f} "
+        f"* Accuracy Computed .: {accuracy:6.4f}±{np.std(scores):6.4f} "
         f"{np.mean(times):5.3f}s"
     )
     print(f"* Accuracy Best .....: {accuracy_best:6.4f}±{acc_best_std:6.4f}")
     print(f"* Difference ........: {accuracy_best - accuracy:6.4f}")
-    print(f"* Nodes/Leaves/Depth :{nodes:2d} {leaves:2d} " f"{depth:2d} ")
+    print(f"* Nodes/Leaves/Depth : {nodes:2d} {leaves:2d} " f"{depth:2d} ")
 stop = time.time()
 print(f"- Auto Hyperparams ..: {hyperparameters}")
 hours, rem = divmod(stop - start, 3600)