Merge branch 'main' of github.com:doctorado-ml/benchmark into main

results/grid_input_accuracy_ODTE.json

@@ -1,5 +1,11 @@
 [
     {
+        "n_jobs": [
+            -1
+        ],
+        "n_estimators": [
+            100
+        ],
         "base_estimator__C": [
             1.0
         ],
@@ -11,6 +17,12 @@
         ]
     },
     {
+        "n_jobs": [
+            -1
+        ],
+        "n_estimators": [
+            100
+        ],
         "base_estimator__C": [
             0.001,
             0.0275,
@@ -32,6 +44,12 @@
         ]
     },
     {
+        "n_jobs": [
+            -1
+        ],
+        "n_estimators": [
+            100
+        ],
         "base_estimator__C": [
             0.05,
             1.0,
@@ -60,6 +78,12 @@
         ]
     },
     {
+        "n_jobs": [
+            -1
+        ],
+        "n_estimators": [
+            100
+        ],
         "base_estimator__C": [
             0.05,
             0.2,

src/Experiments.py

@@ -279,6 +279,7 @@ class Experiment:
         output["results"] = self.results
         with open(self.output_file, "w") as f:
             json.dump(output, f)
+            f.flush()
 
     def do_experiment(self):
         now = time.time()
@@ -287,6 +288,7 @@ class Experiment:
             position=0,
             disable=not self.progress_bar,
         )
+        self.duration = 0.0
         for name in loop:
             loop.set_description(f"{name:30s}")
             X, y = self.datasets.load(name)
@@ -296,6 +298,7 @@ class Experiment:
             self._init_experiment()
             self._n_fold_crossval(X, y, hyperparameters)
             self._add_results(name, hyperparameters, samp, feat, n_classes)
+            self._output_results()
         self.duration = time.time() - now
         self._output_results()
         if self.progress_bar:

src/Results.py

@@ -183,18 +183,23 @@ class Report(BaseReport):
 
 
 class ReportBest(BaseReport):
-    header_lengths = [30, 8, 50, 35]
+    header_lengths = [30, 8, 76, 45]
     header_cols = [
         "Dataset",
         "Score",
-        "File",
+        "File/Message",
         "Hyperparameters",
     ]
 
-    def __init__(self, score, model):
-        file_name = os.path.join(
-            Folders.results, Files.best_results(score, model)
+    def __init__(self, score, model, best, grid):
+        name = (
+            Files.best_results(score, model)
+            if best
+            else Files.grid_output(score, model)
         )
+        self.best = best
+        self.grid = grid
+        file_name = os.path.join(Folders.results, name)
         super().__init__(file_name, best_file=True)
         self.compare = False
         self.score_name = score
@@ -222,9 +227,10 @@ class ReportBest(BaseReport):
 
     def header(self):
         self.header_line("*")
+        kind = "Best" if self.best else "Grid"
         self.header_line(
-            f" Report Best {self.score_name} Scores with {self.model} in any "
-            "platform"
+            f" Report {kind} {self.score_name} Scores with {self.model} "
+            "in any platform"
         )
         self.header_line("*")
         print("")

src/build_grid.py

@@ -14,7 +14,8 @@ data = [
     '{"kernel": "rbf"}',
     '{"C": 1.05, "gamma": "auto","kernel": "rbf"}',
     '{"splitter": "random", "max_features": "auto"}',
-    '{"C": 0.05, "max_features": "auto", "kernel": "liblinear", "multiclass_strategy": "ovr"}',
+    '{"C": 0.05, "max_features": "auto", "kernel": "liblinear", '
+    '"multiclass_strategy": "ovr"}',
     '{"kernel": "rbf", "C": 0.05}',
     '{"C": 0.05, "kernel": "liblinear", "multiclass_strategy": "ovr"}',
     '{"C": 7, "gamma": 0.1, "kernel": "rbf"}',
@@ -27,13 +28,15 @@ data = [
     '{"C": 2.8, "kernel": "rbf", "gamma": "auto"}',
     '{"kernel": "rbf"}',
     '{"C": 0.05, "gamma": 0.1, "kernel": "poly"}',
-    '{"C": 8.25, "gamma": 0.1, "kernel": "poly", "multiclass_strategy": "ovr"}',
+    '{"C": 8.25, "gamma": 0.1, "kernel": "poly", "multiclass_strategy": '
+    '"ovr"}',
     '{"kernel": "liblinear", "multiclass_strategy": "ovr"}',
     '{"C": 1.75, "kernel": "liblinear", "multiclass_strategy": "ovr"}',
     '{"C":57, "kernel": "rbf"}',
     '{"C": 7, "gamma": 0.1, "kernel": "rbf", "multiclass_strategy": "ovr"}',
     '{"C": 5, "kernel": "rbf", "gamma": "auto"}',
-    '{"C": 0.05, "max_iter": 10000.0, "kernel": "liblinear", "multiclass_strategy": "ovr"}',
+    '{"C": 0.05, "max_iter": 10000.0, "kernel": "liblinear", '
+    '"multiclass_strategy": "ovr"}',
     '{"C":0.0275, "kernel": "liblinear", "multiclass_strategy": "ovr"}',
     '{"C": 7, "gamma": 10.0, "kernel": "rbf", "multiclass_strategy": "ovr"}',
     '{"kernel": "rbf", "gamma": 0.001}',
@@ -59,16 +62,14 @@ for kernel in kernels:
     for item in hyper:
         results[kernel][item] = []
 # load data
-for item in data:
-    line = json.loads(item)
+for sample in data:
+    line = json.loads(sample)
     if "kernel" not in line:
         line["kernel"] = "linear"
     kernel = line["kernel"]
     for item in hyper:
-        if item in line:
-            results[kernel][item].append(line[item]) if line[
-                item
-            ] not in results[kernel][item] else None
+        if item in line and line[item] not in results[kernel][item]:
+            results[kernel][item].append(line[item])
 
 # Add default values and remove inconsistent values
 results["linear"]["multiclass_strategy"] = ["ovo"]
@@ -81,12 +82,12 @@ for kernel in kernels:
     results[kernel]["C"].append(1.0)
 
 for item in results:
-    results_tmp = {}
+    results_tmp = {"n_jobs": [-1], "n_estimators": [100]}
     for key, value in results[item].items():
         new_key = f"base_estimator__{key}"
         try:
             results_tmp[new_key] = sorted(value)
-        except:
+        except TypeError:
             t1 = sorted(
                 [
                     x

src/report.py

@@ -3,7 +3,8 @@ import argparse
 import numpy as np
 from Experiments import Datasets
 from Results import Report, Excel, SQL, ReportBest
-from Utils import Files, TextColor
+from Utils import Files, TextColor, EnvDefault
+
 
 """Build report on screen of a result file, optionally generate excel and sql
 file, and can compare results of report with best results obtained by model
@@ -49,12 +50,29 @@ def parse_arguments():
         help="best results of models",
     )
     ap.add_argument(
-        "-s",
-        "--score",
+        "-g",
+        "--grid",
         type=str,
         required=False,
-        default="accuracy",
-        help="score used in best results model",
+        help="grid results of model",
+    )
+    ap.add_argument(
+        "-m",
+        "--model",
+        action=EnvDefault,
+        envvar="model",
+        type=str,
+        required=True,
+        help="model name",
+    )
+    ap.add_argument(
+        "-s",
+        "--score",
+        action=EnvDefault,
+        envvar="score",
+        type=str,
+        required=True,
+        help="score name {accuracy, f1_macro, ...}",
     )
     args = ap.parse_args()
 
@@ -64,7 +82,9 @@ def parse_arguments():
         args.sql,
         args.compare,
         args.best,
+        args.grid,
         args.score,
+        args.model,
     )
 
 
@@ -88,13 +108,14 @@ def default_report():
         )
 
 
-(file, excel, sql, compare, best, score) = parse_arguments()
-
+(file, excel, sql, compare, best, grid, score, model) = parse_arguments()
+if grid:
+    best = False
 if file is None and best is None:
     default_report()
 else:
-    if best is not None:
-        report = ReportBest(score, best)
+    if best is not None or grid is not None:
+        report = ReportBest(score, model, best, grid)
         report.report()
     else:
         report = Report(file, compare)