Update README.md

Update README.md

.github/workflows/main.yml

@@ -18,7 +18,7 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python ${{ matrix.python }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python }}
       # Make dot command available in the environment
@@ -53,7 +53,7 @@ jobs:
           coverage run -m unittest -v benchmark.tests
           coverage xml
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v1
+        uses: codecov/codecov-action@v3
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           files: ./coverage.xml

README.md

@@ -1,12 +1,9 @@
-[![CI](https://github.com/Doctorado-ML/benchmark/actions/workflows/main.yml/badge.svg)](https://github.com/Doctorado-ML/benchmark/actions/workflows/main.yml)
 [![codecov](https://codecov.io/gh/Doctorado-ML/benchmark/branch/main/graph/badge.svg?token=ZRP937NDSG)](https://codecov.io/gh/Doctorado-ML/benchmark)
-[![Quality Gate Status](https://haystack.rmontanana.es:25000/api/project_badges/measure?project=benchmark&metric=alert_status&token=336a6e501988888543c3153baa91bad4b9914dd2)](https://haystack.rmontanana.es:25000/dashboard?id=benchmark)
-[![Technical Debt](https://haystack.rmontanana.es:25000/api/project_badges/measure?project=benchmark&metric=sqale_index&token=336a6e501988888543c3153baa91bad4b9914dd2)](https://haystack.rmontanana.es:25000/dashboard?id=benchmark)
 ![https://img.shields.io/badge/python-3.8%2B-blue](https://img.shields.io/badge/python-3.8%2B-brightgreen)
 
 # benchmark
 
-Benchmarking models
+Benchmarking Python models
 
 ## Experimentation
 
@@ -34,7 +31,7 @@ be_report -b STree
 
 ```python
 # Datasets list
-be_report
+be_report datasets
 # Report of given experiment
 be_report -f results/results_STree_iMac27_2021-09-22_17:13:02.json
 # Report of given experiment building excel file and compare with best results

benchmark/Arguments.py

@@ -13,21 +13,27 @@ ALL_METRICS = (
 
 
 class EnvData:
-    @staticmethod
+    def __init__(self):
-    def load():
+        self.args = {}
-        args = {}
+
+    def load(self):
         try:
             with open(Files.dot_env) as f:
                 for line in f.read().splitlines():
                     if line == "" or line.startswith("#"):
                         continue
                     key, value = line.split("=")
-                    args[key] = value
+                    self.args[key] = value
         except FileNotFoundError:
             print(NO_ENV, file=sys.stderr)
             exit(1)
         else:
-            return args
+            return self.args
+
+    def save(self):
+        with open(Files.dot_env, "w") as f:
+            for key, value in self.args.items():
+                f.write(f"{key}={value}\n")
 
 
 class EnvDefault(argparse.Action):
@@ -35,7 +41,7 @@ class EnvDefault(argparse.Action):
     def __init__(
         self, envvar, required=True, default=None, mandatory=False, **kwargs
     ):
-        self._args = EnvData.load()
+        self._args = EnvData().load()
         self._overrides = {}
         if required and not mandatory:
             default = self._args[envvar]
@@ -92,6 +98,17 @@ class Arguments(argparse.ArgumentParser):
                     "help": "dataset to work with",
                 },
             ],
+            "discretize": [
+                ("--discretize",),
+                {
+                    "action": EnvDefault,
+                    "envvar": "discretize",
+                    "required": True,
+                    "help": "Discretize dataset",
+                    "const": "1",
+                    "nargs": "?",
+                },
+            ],
             "excel": [
                 ("-x", "--excel"),
                 {
@@ -101,6 +118,17 @@ class Arguments(argparse.ArgumentParser):
                     "help": "Generate Excel File",
                 },
             ],
+            "fit_features": [
+                ("--fit_features",),
+                {
+                    "action": EnvDefault,
+                    "envvar": "fit_features",
+                    "required": True,
+                    "help": "Include features in fit call",
+                    "const": "1",
+                    "nargs": "?",
+                },
+            ],
             "grid_paramfile": [
                 ("-g", "--grid_paramfile"),
                 {
@@ -123,6 +151,15 @@ class Arguments(argparse.ArgumentParser):
                 ("-p", "--hyperparameters"),
                 {"type": str, "required": False, "default": "{}"},
             ],
+            "ignore_nan": [
+                ("--ignore-nan",),
+                {
+                    "default": False,
+                    "action": "store_true",
+                    "required": False,
+                    "help": "Ignore nan results",
+                },
+            ],
             "key": [
                 ("-k", "--key"),
                 {
@@ -198,6 +235,19 @@ class Arguments(argparse.ArgumentParser):
                     "help": "number of folds",
                 },
             ],
+            "output": [
+                ("-o", "--output"),
+                {
+                    "type": str,
+                    "default": "local",
+                    "choices": ["local", "docker"],
+                    "required": False,
+                    "help": (
+                        "in be_flask tells if it is running in local or "
+                        "in docker {local, docker}"
+                    ),
+                },
+            ],
             "platform": [
                 ("-P", "--platform"),
                 {
@@ -251,6 +301,8 @@ class Arguments(argparse.ArgumentParser):
                     "envvar": "stratified",
                     "required": True,
                     "help": "Stratified",
+                    "const": "1",
+                    "nargs": "?",
                 },
             ],
             "tex_output": [

benchmark/Datasets.py

@@ -2,10 +2,11 @@ import os
 from types import SimpleNamespace
 import pandas as pd
 import numpy as np
+import json
 from scipy.io import arff
 from .Utils import Files
 from .Arguments import EnvData
-from mdlp.discretization import MDLP
+from fimdlp.mdlp import FImdlp
 
 
 class Diterator:
@@ -27,6 +28,14 @@ class DatasetsArff:
     def folder():
         return "datasets"
 
+    @staticmethod
+    def get_range_features(X, c_features):
+        if c_features.strip() == "all":
+            return list(range(X.shape[1]))
+        if c_features.strip() == "none":
+            return []
+        return json.loads(c_features)
+
     def load(self, name, class_name):
         file_name = os.path.join(self.folder(), self.dataset_names(name))
         data = arff.loadarff(file_name)
@@ -34,7 +43,7 @@ class DatasetsArff:
         df.dropna(axis=0, how="any", inplace=True)
         self.dataset = df
         X = df.drop(class_name, axis=1)
-        self.features = X.columns
+        self.features = X.columns.to_list()
         self.class_name = class_name
         y, _ = pd.factorize(df[class_name])
         X = X.to_numpy()
@@ -50,6 +59,10 @@ class DatasetsTanveer:
     def folder():
         return "data"
 
+    @staticmethod
+    def get_range_features(X, name):
+        return []
+
     def load(self, name, *args):
         file_name = os.path.join(self.folder(), self.dataset_names(name))
         data = pd.read_csv(
@@ -75,6 +88,10 @@ class DatasetsSurcov:
     def folder():
         return "datasets"
 
+    @staticmethod
+    def get_range_features(X, name):
+        return []
+
     def load(self, name, *args):
         file_name = os.path.join(self.folder(), self.dataset_names(name))
         data = pd.read_csv(
@@ -93,41 +110,49 @@ class DatasetsSurcov:
 
 
 class Datasets:
-    def __init__(self, dataset_name=None):
+    def __init__(self, dataset_name=None, discretize=None):
-        envData = EnvData.load()
+        env_data = EnvData().load()
         # DatasetsSurcov, DatasetsTanveer, DatasetsArff,...
         source_name = getattr(
             __import__(__name__),
-            f"Datasets{envData['source_data']}",
+            f"Datasets{env_data['source_data']}",
+        )
+        self.discretize = (
+            env_data["discretize"] == "1"
+            if discretize is None
+            else discretize == "1"
         )
-        self.discretize = envData["discretize"] == "1"
         self.dataset = source_name()
-        self.class_names = []
-        self.data_sets = []
         # initialize self.class_names & self.data_sets
         class_names, sets = self._init_names(dataset_name)
         self.class_names = class_names
         self.data_sets = sets
+        self.states = {}  # states of discretized variables
 
     def _init_names(self, dataset_name):
         file_name = os.path.join(self.dataset.folder(), Files.index)
-        default_class = "class"
+        self.continuous_features = {}
         with open(file_name) as f:
             sets = f.read().splitlines()
-            class_names = [default_class] * len(sets)
+            sets = [x for x in sets if not x.startswith("#")]
-        if "," in sets[0]:
+        results = []
-            result = []
+        class_names = []
-            class_names = []
+        for set_name in sets:
-            for data in sets:
+            try:
-                name, class_name = data.split(",")
+                name, class_name, features = set_name.split(";")
-                result.append(name)
+            except ValueError:
-                class_names.append(class_name)
+                class_name = "class"
-            sets = result
+                features = "all"
+                name = set_name
+            results.append(name)
+            class_names.append(class_name)
+            features = features.strip()
+            self.continuous_features[name] = features
         # Set as dataset list the dataset passed as argument
         if dataset_name is None:
-            return class_names, sets
+            return class_names, results
         try:
-            class_name = class_names[sets.index(dataset_name)]
+            class_name = class_names[results.index(dataset_name)]
         except ValueError:
             raise ValueError(f"Unknown dataset: {dataset_name}")
         return [class_name], [dataset_name]
@@ -137,34 +162,54 @@ class Datasets:
         self.discretize = False
         X, y = self.load(name)
         attr = SimpleNamespace()
+        attr.dataset = name
         values, counts = np.unique(y, return_counts=True)
-        comp = ""
+        attr.classes = len(values)
-        sep = ""
-        for count in counts:
-            comp += f"{sep}{count/sum(counts)*100:5.2f}%"
-            sep = "/ "
-        attr.balance = comp
-        attr.classes = len(np.unique(y))
         attr.samples = X.shape[0]
         attr.features = X.shape[1]
+        attr.cont_features = len(self.get_continuous_features())
+        attr.distribution = {}
+        comp = ""
+        sep = ""
+        for value, count in zip(values, counts):
+            comp += f"{sep}{count/sum(counts)*100:5.2f}% ({count}) "
+            sep = "/ "
+            attr.distribution[value.item()] = count / sum(counts)
+        attr.balance = comp
         self.discretize = tmp
         return attr
 
     def get_features(self):
         return self.dataset.features
 
+    def get_states(self, name):
+        return self.states[name] if name in self.states else None
+
+    def get_continuous_features(self):
+        return self.continuous_features_dataset
+
     def get_class_name(self):
         return self.dataset.class_name
 
     def get_dataset(self):
         return self.dataset.dataset
 
+    def build_states(self, name, X):
+        features = self.get_features()
+        self.states[name] = {
+            features[i]: np.unique(X[:, i]).tolist() for i in range(X.shape[1])
+        }
+
     def load(self, name, dataframe=False):
         try:
             class_name = self.class_names[self.data_sets.index(name)]
             X, y = self.dataset.load(name, class_name)
+            self.continuous_features_dataset = self.dataset.get_range_features(
+                X, self.continuous_features[name]
+            )
             if self.discretize:
                 X = self.discretize_dataset(X, y)
+                self.build_states(name, X)
                 dataset = pd.DataFrame(X, columns=self.get_features())
                 dataset[self.get_class_name()] = y
                 self.dataset.dataset = dataset
@@ -188,9 +233,8 @@ class Datasets:
         -------
         tuple (X, y) of numpy.ndarray
         """
-        discretiz = MDLP(random_state=17, dtype=np.int32)
+        discretiz = FImdlp()
-        Xdisc = discretiz.fit_transform(X, y)
+        return discretiz.fit_transform(X, y)
-        return Xdisc
 
     def __iter__(self) -> Diterator:
         return Diterator(self.data_sets)

benchmark/Experiments.py

@@ -22,7 +22,7 @@ from .Arguments import EnvData
 class Randomized:
     @staticmethod
     def seeds():
-        return json.loads(EnvData.load()["seeds"])
+        return json.loads(EnvData().load()["seeds"])
 
 
 class BestResults:
@@ -112,8 +112,12 @@ class Experiment:
         platform,
         title,
         progress_bar=True,
+        ignore_nan=True,
+        fit_features=None,
+        discretize=None,
         folds=5,
     ):
+        env_data = EnvData().load()
         today = datetime.now()
         self.time = today.strftime("%H:%M:%S")
         self.date = today.strftime("%Y-%m-%d")
@@ -131,7 +135,18 @@ class Experiment:
         self.score_name = score_name
         self.model_name = model_name
         self.title = title
+        self.ignore_nan = ignore_nan
         self.stratified = stratified == "1"
+        self.discretize = (
+            env_data["discretize"] == "1"
+            if discretize is None
+            else discretize == "1"
+        )
+        self.fit_features = (
+            env_data["fit_features"] == "1"
+            if fit_features is None
+            else fit_features == "1"
+        )
         self.stratified_class = StratifiedKFold if self.stratified else KFold
         self.datasets = datasets
         dictionary = json.loads(hyperparams_dict)
@@ -184,7 +199,20 @@ class Experiment:
         self.leaves = []
         self.depths = []
 
-    def _n_fold_crossval(self, X, y, hyperparameters):
+    def _build_fit_params(self, name):
+        if not self.fit_features:
+            return None
+        res = dict(
+            features=self.datasets.get_features(),
+            class_name=self.datasets.get_class_name(),
+        )
+        states = self.datasets.get_states(name)
+        if states is None:
+            return res
+        res["state_names"] = states
+        return res
+
+    def _n_fold_crossval(self, name, X, y, hyperparameters):
         if self.scores != []:
             raise ValueError("Must init experiment before!")
         loop = tqdm(
@@ -201,6 +229,7 @@ class Experiment:
                 shuffle=True, random_state=random_state, n_splits=self.folds
             )
             clf = self._build_classifier(random_state, hyperparameters)
+            fit_params = self._build_fit_params(name)
             self.version = Models.get_version(self.model_name, clf)
             with warnings.catch_warnings():
                 warnings.filterwarnings("ignore")
@@ -209,11 +238,19 @@ class Experiment:
                     X,
                     y,
                     cv=kfold,
+                    fit_params=fit_params,
                     return_estimator=True,
-                    scoring=self.score_name,
+                    scoring=self.score_name.replace("-", "_"),
                 )
-            self.scores.append(res["test_score"])
+            if np.isnan(res["test_score"]).any():
-            self.times.append(res["fit_time"])
+                if not self.ignore_nan:
+                    print(res["test_score"])
+                    raise ValueError("NaN in results")
+                results = res["test_score"][~np.isnan(res["test_score"])]
+            else:
+                results = res["test_score"]
+            self.scores.extend(results)
+            self.times.extend(res["fit_time"])
             for result_item in res["estimator"]:
                 nodes_item, leaves_item, depth_item = Models.get_complexity(
                     self.model_name, result_item
@@ -245,6 +282,7 @@ class Experiment:
         output["model"] = self.model_name
         output["version"] = self.version
         output["stratified"] = self.stratified
+        output["discretized"] = self.discretize
         output["folds"] = self.folds
         output["date"] = self.date
         output["time"] = self.time
@@ -273,7 +311,7 @@ class Experiment:
             n_classes = len(np.unique(y))
             hyperparameters = self.hyperparameters_dict[name][1]
             self._init_experiment()
-            self._n_fold_crossval(X, y, hyperparameters)
+            self._n_fold_crossval(name, X, y, hyperparameters)
             self._add_results(name, hyperparameters, samp, feat, n_classes)
             self._output_results()
         self.duration = time.time() - now

benchmark/Manager.py

@@ -0,0 +1,127 @@
+import os
+from types import SimpleNamespace
+
+import xlsxwriter
+
+from benchmark.Results import Report
+from benchmark.ResultsFiles import Excel
+from benchmark.Utils import Files, Folders, TextColor
+
+
+def get_input(message="", is_test=False):
+    return "test" if is_test else input(message)
+
+
+class Manage:
+    def __init__(self, summary):
+        self.summary = summary
+        self.cmd = SimpleNamespace(
+            quit="q", relist="r", delete="d", hide="h", excel="e"
+        )
+
+    def process_file(self, num, command, path):
+        num = int(num)
+        name = self.summary.data_filtered[num]["file"]
+        file_name_result = os.path.join(path, name)
+        verb1, verb2 = (
+            ("delete", "Deleting")
+            if command == self.cmd.delete
+            else (
+                "hide",
+                "Hiding",
+            )
+        )
+        conf_message = (
+            TextColor.RED
+            + f"Are you sure to {verb1} {file_name_result} (y/n)? "
+        )
+        confirm = get_input(message=conf_message)
+        if confirm == "y":
+            print(TextColor.YELLOW + f"{verb2} {file_name_result}")
+            if command == self.cmd.delete:
+                os.unlink(file_name_result)
+            else:
+                os.rename(
+                    os.path.join(Folders.results, name),
+                    os.path.join(Folders.hidden_results, name),
+                )
+            self.summary.data_filtered.pop(num)
+            get_input(message="Press enter to continue")
+            self.summary.list_results()
+
+    def manage_results(self):
+        """Manage results showed in the summary
+        return True if excel file is created False otherwise
+        """
+
+        message = (
+            TextColor.ENDC
+            + f"Choose option {str(self.cmd).replace('namespace', '')}: "
+        )
+        path = (
+            Folders.hidden_results if self.summary.hidden else Folders.results
+        )
+        book = None
+        max_value = len(self.summary.data_filtered)
+        while True:
+            match get_input(message=message).split():
+                case [self.cmd.relist]:
+                    self.summary.list_results()
+                case [self.cmd.quit]:
+                    if book is not None:
+                        book.close()
+                        return True
+                    return False
+                case [self.cmd.hide, num] if num.isdigit() and int(
+                    num
+                ) < max_value:
+                    if self.summary.hidden:
+                        print("Already hidden")
+                    else:
+                        self.process_file(
+                            num, path=path, command=self.cmd.hide
+                        )
+                case [self.cmd.delete, num] if num.isdigit() and int(
+                    num
+                ) < max_value:
+                    self.process_file(
+                        num=num, path=path, command=self.cmd.delete
+                    )
+                case [self.cmd.excel, num] if num.isdigit() and int(
+                    num
+                ) < max_value:
+                    # Add to excel file result #num
+                    book = self.add_to_excel(num, path, book)
+                case [num] if num.isdigit() and int(num) < max_value:
+                    # Report the result #num
+                    self.report(num, path)
+                case _:
+                    print("Invalid option. Try again!")
+
+    def report(self, num, path):
+        num = int(num)
+        file_name_result = os.path.join(
+            path, self.summary.data_filtered[num]["file"]
+        )
+        try:
+            rep = Report(file_name_result, compare=self.summary.compare)
+            rep.report()
+        except ValueError as e:
+            print(e)
+
+    def add_to_excel(self, num, path, book):
+        num = int(num)
+        file_name_result = os.path.join(
+            path, self.summary.data_filtered[num]["file"]
+        )
+        if book is None:
+            file_name = os.path.join(Folders.excel, Files.be_list_excel)
+            book = xlsxwriter.Workbook(file_name, {"nan_inf_to_errors": True})
+        excel = Excel(
+            file_name=file_name_result,
+            book=book,
+            compare=self.summary.compare,
+        )
+        excel.report()
+        print(f"Added {file_name_result} to {Files.be_list_excel}")
+        return book

benchmark/Models.py

@@ -8,41 +8,64 @@ from sklearn.ensemble import (
 )
 from sklearn.svm import SVC
 from stree import Stree
-from bayesclass.clfs import TAN, KDB, AODE
+
+# from bayesclass.clfs import TAN, KDB, AODE, KDBNew, TANNew, AODENew, BoostAODE
 from wodt import Wodt
 from odte import Odte
 from xgboost import XGBClassifier
 import sklearn
 import xgboost
 
+import random
+
+
+class MockModel(SVC):
+    # Only used for testing
+    def predict(self, X):
+        if random.random() < 0.1:
+            return [float("NaN")] * len(X)
+        return super().predict(X)
+
+    def nodes_leaves(self):
+        return 0, 0
+
+    def fit(self, X, y, **kwargs):
+        kwargs.pop("state_names", None)
+        kwargs.pop("features", None)
+        return super().fit(X, y, **kwargs)
+
 
 class Models:
     @staticmethod
     def define_models(random_state):
         return {
             "STree": Stree(random_state=random_state),
-            "TAN": TAN(random_state=random_state),
+            # "TAN": TAN(random_state=random_state),
-            "KDB": KDB(k=3),
+            # "KDB": KDB(k=2),
-            "AODE": AODE(random_state=random_state),
+            # "TANNew": TANNew(random_state=random_state),
+            # "KDBNew": KDBNew(k=2),
+            # "AODENew": AODENew(random_state=random_state),
+            # "AODE": AODE(random_state=random_state),
+            # "BoostAODE": BoostAODE(random_state=random_state),
             "Cart": DecisionTreeClassifier(random_state=random_state),
             "ExtraTree": ExtraTreeClassifier(random_state=random_state),
             "Wodt": Wodt(random_state=random_state),
             "SVC": SVC(random_state=random_state),
             "ODTE": Odte(
-                base_estimator=Stree(random_state=random_state),
+                estimator=Stree(random_state=random_state),
                 random_state=random_state,
             ),
             "BaggingStree": BaggingClassifier(
-                base_estimator=Stree(random_state=random_state),
+                estimator=Stree(random_state=random_state),
                 random_state=random_state,
             ),
             "BaggingWodt": BaggingClassifier(
-                base_estimator=Wodt(random_state=random_state),
+                estimator=Wodt(random_state=random_state),
                 random_state=random_state,
             ),
             "XGBoost": XGBClassifier(random_state=random_state),
             "AdaBoostStree": AdaBoostClassifier(
-                base_estimator=Stree(
+                estimator=Stree(
                     random_state=random_state,
                 ),
                 algorithm="SAMME",
@@ -50,6 +73,7 @@ class Models:
             ),
             "GBC": GradientBoostingClassifier(random_state=random_state),
             "RandomForest": RandomForestClassifier(random_state=random_state),
+            "Mock": MockModel(random_state=random_state),
         }
 
     @staticmethod

benchmark/ResultsBase.py

@@ -0,0 +1,446 @@
+import abc
+import json
+import math
+import os
+from operator import itemgetter
+
+from benchmark.Datasets import Datasets
+from benchmark.Utils import NO_RESULTS, Files, Folders, TextColor
+
+from .Arguments import ALL_METRICS, EnvData
+from .Datasets import Datasets
+from .Experiments import BestResults
+from .Utils import Folders, Symbols
+
+
+class BestResultsEver:
+    def __init__(self):
+        self.data = {}
+        for i in ["Tanveer", "Surcov", "Arff"]:
+            self.data[i] = {}
+            for metric in ALL_METRICS:
+                self.data[i][metric.replace("-", "_")] = ["self", 1.0]
+                self.data[i][metric] = ["self", 1.0]
+        self.data["Tanveer"]["accuracy"] = [
+            "STree_default (liblinear-ovr)",
+            40.282203,
+        ]
+        self.data["Arff"]["accuracy"] = [
+            "STree_default (linear-ovo)",
+            22.109799,
+        ]
+
+    def get_name_value(self, key, score):
+        return self.data[key][score]
+
+
+class BaseReport(abc.ABC):
+    def __init__(self, file_name, best_file=False):
+        self.file_name = file_name
+        if not os.path.isfile(file_name):
+            if not os.path.isfile(os.path.join(Folders.results, file_name)):
+                raise FileNotFoundError(f"{file_name} does not exists!")
+            else:
+                self.file_name = os.path.join(Folders.results, file_name)
+        with open(self.file_name) as f:
+            self.data = json.load(f)
+        self.best_acc_file = best_file
+        if best_file:
+            self.lines = self.data
+        else:
+            self.lines = self.data["results"]
+            self.score_name = self.data["score_name"]
+        self.__load_env_data()
+        self.__compute_best_results_ever()
+        self._compare_totals = {}
+
+    def __load_env_data(self):
+        # Set the labels for nodes, leaves, depth
+        env_data = EnvData().load()
+        self.nodes_label = env_data["nodes"]
+        self.leaves_label = env_data["leaves"]
+        self.depth_label = env_data["depth"]
+        self.key = env_data["source_data"]
+        self.margin = float(env_data["margin"])
+
+    def __compute_best_results_ever(self):
+        best = BestResultsEver()
+        self.best_score_name, self.best_score_value = best.get_name_value(
+            self.key, self.score_name
+        )
+
+    def _get_accuracy(self, item):
+        return self.data[item][0] if self.best_acc_file else item["score"]
+
+    def report(self):
+        self.header()
+        accuracy_total = 0.0
+        for result in self.lines:
+            self.print_line(result)
+            accuracy_total += self._get_accuracy(result)
+        self.footer(accuracy_total)
+
+    def _load_best_results(self, score, model):
+        best = BestResults(score, model, Datasets())
+        self.best_results = best.load({})
+
+    def _compute_status(self, dataset, accuracy: float):
+        status = " "
+        if self.compare:
+            # Compare with best results
+            best = self.best_results[dataset][0]
+            if accuracy == best:
+                status = Symbols.equal_best
+            elif accuracy > best:
+                status = Symbols.better_best
+        else:
+            # compare with dataset label distribution only if its a binary one
+            # down_arrow if accuracy is less than the ZeroR
+            # black_star if accuracy is greater than the ZeroR + margin%
+            if self.score_name == "accuracy":
+                dt = Datasets()
+                attr = dt.get_attributes(dataset)
+                if attr.classes == 2:
+                    max_category = max(attr.distribution.values())
+                    max_value = max_category * (1 + self.margin)
+                    if max_value > 1:
+                        max_value = 0.9995
+                    status = (
+                        Symbols.cross
+                        if accuracy <= max_value
+                        else (
+                            Symbols.upward_arrow
+                            if accuracy > max_value
+                            else " "
+                        )
+                    )
+        if status != " ":
+            if status not in self._compare_totals:
+                self._compare_totals[status] = 1
+            else:
+                self._compare_totals[status] += 1
+        return status
+
+    def _status_meaning(self, status):
+        meaning = {
+            Symbols.equal_best: "Equal to best",
+            Symbols.better_best: "Better than best",
+            Symbols.cross: "Less than or equal to ZeroR",
+            Symbols.upward_arrow: f"Better than ZeroR + "
+            f"{self.margin*100:3.1f}%",
+        }
+        return meaning[status]
+
+    def _get_best_accuracy(self):
+        return self.best_score_value
+
+    def _get_message_best_accuracy(self):
+        return f"{self.score_name} compared to {self.best_score_name} .:"
+
+    @abc.abstractmethod
+    def header(self) -> None:
+        pass
+
+    @abc.abstractmethod
+    def print_line(self, result) -> None:
+        pass
+
+    @abc.abstractmethod
+    def footer(self, accuracy: float) -> None:
+        pass
+
+
+class StubReport(BaseReport):
+    def __init__(self, file_name, compare=False):
+        self.compare = compare
+        super().__init__(file_name=file_name, best_file=False)
+        if self.compare:
+            self._load_best_results(self.score_name, self.data["model"])
+
+    def print_line(self, line) -> None:
+        pass
+
+    def header(self) -> None:
+        self.title = self.data["title"]
+        self.duration = self.data["duration"]
+        self.model = self.data["model"]
+        self.date = self.data["date"]
+        self.time = self.data["time"]
+        self.metric = self.data["score_name"]
+        self.platform = self.data["platform"]
+
+    def footer(self, accuracy: float) -> None:
+        self.accuracy = accuracy
+        self.score = accuracy / self._get_best_accuracy()
+
+
+class Summary:
+    def __init__(self, hidden=False, compare=False) -> None:
+        self.results = Files.get_all_results(hidden=hidden)
+        self.data = []
+        self.data_filtered = []
+        self.datasets = {}
+        self.models = set()
+        self.hidden = hidden
+        self.compare = compare
+
+    def get_models(self):
+        return sorted(self.models)
+
+    def acquire(self, given_score="any") -> None:
+        """Get all results"""
+        for result in self.results:
+            (
+                score,
+                model,
+                platform,
+                date,
+                time,
+                stratified,
+            ) = Files().split_file_name(result)
+            if given_score in ("any", score):
+                self.models.add(model)
+                report = StubReport(
+                    os.path.join(
+                        (
+                            Folders.hidden_results
+                            if self.hidden
+                            else Folders.results
+                        ),
+                        result,
+                    )
+                )
+                report.report()
+                entry = dict(
+                    score=score,
+                    model=model,
+                    title=report.title,
+                    platform=platform,
+                    date=date,
+                    time=time,
+                    stratified=stratified,
+                    file=result,
+                    metric=report.score,
+                    duration=report.duration,
+                )
+                self.datasets[result] = report.lines
+                self.data.append(entry)
+
+    def get_results_criteria(
+        self, score, model, input_data, sort_key, number, nan=False
+    ):
+        data = self.data.copy() if input_data is None else input_data
+        if score:
+            data = [x for x in data if x["score"] == score]
+        if model:
+            data = [x for x in data if x["model"] == model]
+        if nan:
+            data = [x for x in data if x["metric"] != x["metric"]]
+        keys = (
+            itemgetter(sort_key, "time")
+            if sort_key == "date"
+            else itemgetter(sort_key, "date", "time")
+        )
+        data = sorted(data, key=keys, reverse=True)
+        if number > 0:
+            data = data[:number]
+        return data
+
+    def list_results(
+        self,
+        score=None,
+        model=None,
+        input_data=None,
+        sort_key="date",
+        number=0,
+        nan=False,
+    ) -> None:
+        """Print the list of results"""
+        if self.data_filtered == []:
+            self.data_filtered = self.get_results_criteria(
+                score, model, input_data, sort_key, number, nan=nan
+            )
+        if self.data_filtered == []:
+            raise ValueError(NO_RESULTS)
+        max_file = max(len(x["file"]) for x in self.data_filtered)
+        max_title = max(len(x["title"]) for x in self.data_filtered)
+        if self.hidden:
+            color1 = TextColor.GREEN
+            color2 = TextColor.YELLOW
+        else:
+            color1 = TextColor.LINE1
+            color2 = TextColor.LINE2
+        print(color1, end="")
+        print(
+            f" #  {'Date':10s} {'File':{max_file}s} {'Score':8s} "
+            f"{'Time(h)':7s} {'Title':s}"
+        )
+        print(
+            "===",
+            "=" * 10
+            + " "
+            + "=" * max_file
+            + " "
+            + "=" * 8
+            + " "
+            + "=" * 7
+            + " "
+            + "=" * max_title,
+        )
+        print(
+            "\n".join(
+                [
+                    (color2 if n % 2 == 0 else color1) + f"{n:3d} "
+                    f"{x['date']} {x['file']:{max_file}s} "
+                    f"{x['metric']:8.5f} "
+                    f"{x['duration']/3600:7.3f} "
+                    f"{x['title']}"
+                    for n, x in enumerate(self.data_filtered)
+                ]
+            )
+        )
+
+    def show_result(self, data: dict, title: str = "") -> None:
+        def whites(n: int) -> str:
+            return " " * n + color1 + "*"
+
+        if data == {}:
+            print(f"** {title} has No data **")
+            return
+        color1 = TextColor.CYAN
+        color2 = TextColor.YELLOW
+        file_name = data["file"]
+        metric = data["metric"]
+        result = StubReport(os.path.join(Folders.results, file_name))
+        length = 81
+        print(color1 + "*" * length)
+        if title != "":
+            print(
+                "*"
+                + color2
+                + TextColor.BOLD
+                + f"{title:^{length - 2}s}"
+                + TextColor.ENDC
+                + color1
+                + "*"
+            )
+            print("*" + "-" * (length - 2) + "*")
+        print("*" + whites(length - 2))
+        print(
+            "* "
+            + color2
+            + f"{result.data['title']:^{length - 4}}"
+            + color1
+            + " *"
+        )
+        print("*" + whites(length - 2))
+        print(
+            "* Model: "
+            + color2
+            + f"{result.data['model']:15s} "
+            + color1
+            + "Ver. "
+            + color2
+            + f"{result.data['version']:10s} "
+            + color1
+            + "Score: "
+            + color2
+            + f"{result.data['score_name']:10s} "
+            + color1
+            + "Metric: "
+            + color2
+            + f"{metric:10.7f}"
+            + whites(length - 78)
+        )
+        print(color1 + "*" + whites(length - 2))
+        print(
+            "* Date : "
+            + color2
+            + f"{result.data['date']:15s}"
+            + color1
+            + " Time: "
+            + color2
+            + f"{result.data['time']:18s} "
+            + color1
+            + "Time Spent: "
+            + color2
+            + f"{result.data['duration']:9,.2f}"
+            + color1
+            + " secs."
+            + whites(length - 78)
+        )
+        seeds = str(result.data["seeds"])
+        seeds_len = len(seeds)
+        print(
+            "* Seeds: "
+            + color2
+            + f"{seeds:{seeds_len}s} "
+            + color1
+            + "Platform: "
+            + color2
+            + f"{result.data['platform']:17s} "
+            + whites(length - 79)
+        )
+        print(
+            "* Stratified: "
+            + color2
+            + f"{str(result.data['stratified']):15s}"
+            + whites(length - 30)
+        )
+        print("* " + color2 + f"{file_name:60s}" + whites(length - 63))
+        print(color1 + "*" + whites(length - 2))
+        print(color1 + "*" * length)
+
+    def best_results(self, criterion=None, value=None, score="accuracy", n=10):
+        # First filter the same score results (accuracy, f1, ...)
+        haystack = [x for x in self.data if x["score"] == score]
+        haystack = (
+            haystack
+            if criterion is None or value is None
+            else [x for x in haystack if x[criterion] == value]
+        )
+        if haystack == []:
+            raise ValueError(NO_RESULTS)
+        return (
+            sorted(
+                haystack,
+                key=lambda x: -1.0 if math.isnan(x["metric"]) else x["metric"],
+                reverse=True,
+            )[:n]
+            if len(haystack) > 0
+            else {}
+        )
+
+    def best_result(
+        self, criterion=None, value=None, score="accuracy"
+    ) -> dict:
+        return self.best_results(criterion, value, score)[0]
+
+    def best_results_datasets(self, score="accuracy") -> dict:
+        """Get the best results for each dataset"""
+        dt = Datasets()
+        best_results = {}
+        for dataset in dt:
+            best_results[dataset] = (1, "", "", "")
+        haystack = [x for x in self.data if x["score"] == score]
+        # Search for the best results for each dataset
+        for entry in haystack:
+            for dataset in self.datasets[entry["file"]]:
+                if dataset["score"] < best_results[dataset["dataset"]][0]:
+                    best_results[dataset["dataset"]] = (
+                        dataset["score"],
+                        dataset["hyperparameters"],
+                        entry["file"],
+                        entry["title"],
+                    )
+        return best_results
+
+    def show_top(self, score="accuracy", n=10):
+        try:
+            self.list_results(
+                score=score,
+                input_data=self.best_results(score=score, n=n),
+                sort_key="metric",
+            )
+        except ValueError as e:
+            print(e)

benchmark/Utils.py

@@ -13,6 +13,9 @@ class Folders:
     exreport = "exreport"
     report = os.path.join(exreport, "exreport_output")
     img = "img"
+    excel = "excel"
+    sql = "sql"
+    current = os.getcwd()
 
     @staticmethod
     def src():
@@ -106,7 +109,8 @@ class Files:
             )
         return None
 
-    def get_all_results(self, hidden) -> list[str]:
+    @staticmethod
+    def get_all_results(hidden) -> list[str]:
         result_path = os.path.join(
             ".", Folders.hidden_results if hidden else Folders.results
         )
@@ -115,7 +119,7 @@ class Files:
         else:
             raise ValueError(f"{result_path} does not exist")
         result = []
-        prefix, suffix = self.results_suffixes()
+        prefix, suffix = Files.results_suffixes()
         for result_file in files_list:
             if result_file.startswith(prefix) and result_file.endswith(suffix):
                 result.append(result_file)
@@ -126,6 +130,9 @@ class Symbols:
     check_mark = "\N{heavy check mark}"
     exclamation = "\N{heavy exclamation mark symbol}"
     black_star = "\N{black star}"
+    cross = "\N{Ballot X}"
+    upward_arrow = "\N{Black-feathered north east arrow}"
+    down_arrow = "\N{downwards black arrow}"
     equal_best = check_mark
     better_best = black_star
 

benchmark/__init__.py

@@ -1,3 +1,4 @@
+from .ResultsBase import Summary
 from .Datasets import (
     Datasets,
     DatasetsSurcov,
@@ -5,11 +6,11 @@ from .Datasets import (
     DatasetsArff,
 )
 from .Experiments import Experiment
-from .Results import Report, Summary
+from .Results import Report
 from ._version import __version__
 
 __author__ = "Ricardo Montañana Gómez"
-__copyright__ = "Copyright 2020-2023, Ricardo Montañana Gómez"
+__copyright__ = "Copyright 2020-2024, Ricardo Montañana Gómez"
 __license__ = "MIT License"
 __author_email__ = "ricardo.montanana@alu.uclm.es"
 

benchmark/_version.py

@@ -1 +1 @@
-__version__ = "0.4.0"
+__version__ = "1.0.1"

benchmark/scripts/app/app.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python
+from benchmark.Arguments import EnvData
+from flask import Flask
+from .main import main, OUTPUT
+
+FRAMEWORK = "framework"
+FRAMEWORKS = "frameworks"
+TEST = "test"
+
+
+def create_app(output="local"):
+    app = Flask(__name__)
+    config = EnvData().load()
+    app.register_blueprint(main)
+    app.config[FRAMEWORK] = config[FRAMEWORK]
+    app.config[FRAMEWORKS] = ["bootstrap", "bulma"]
+    app.config[OUTPUT] = output
+    app.jinja_env.auto_reload = True
+    app.config["TEMPLATES_AUTO_RELOAD"] = True
+    return app

benchmark/scripts/app/main.py

@@ -0,0 +1,210 @@
+#!/usr/bin/env python
+import os
+import json
+import shutil
+import xlsxwriter
+from dotenv import dotenv_values
+from benchmark.Utils import Files, Folders
+from benchmark.Arguments import EnvData
+from benchmark.ResultsBase import StubReport
+from benchmark.ResultsFiles import Excel, ReportDatasets
+from benchmark.Datasets import Datasets
+from flask import Blueprint, current_app, send_file
+from flask import render_template, request, redirect, url_for
+
+
+main = Blueprint("main", __name__)
+FRAMEWORK = "framework"
+FRAMEWORKS = "frameworks"
+OUTPUT = "output"
+TEST = "test"
+
+
+class AjaxResponse:
+    def __init__(self, success, file_name, code=200):
+        self.success = success
+        self.file_name = file_name
+        self.code = code
+
+    def to_string(self):
+        return (
+            json.dumps(
+                {
+                    "success": self.success,
+                    "file": self.file_name,
+                    "output": current_app.config[OUTPUT],
+                }
+            ),
+            self.code,
+            {"ContentType": "application/json"},
+        )
+
+
+def process_data(file_name, compare, data):
+    report = StubReport(
+        os.path.join(Folders.results, file_name), compare=compare
+    )
+    new_list = []
+    for result in data["results"]:
+        symbol = report._compute_status(result["dataset"], result["score"])
+        result["symbol"] = symbol if symbol != " " else " "
+        new_list.append(result)
+    data["results"] = new_list
+    # Compute summary with explanation of symbols
+    summary = {}
+    for key, value in report._compare_totals.items():
+        summary[key] = (report._status_meaning(key), value)
+    return summary
+
+
+@main.route("/index/<compare>")
+@main.route("/")
+def index(compare="False"):
+    # Get a list of files in a directory
+    files = {}
+    names = Files.get_all_results(hidden=False)
+    for name in names:
+        report = StubReport(os.path.join(Folders.results, name))
+        report.report()
+        files[name] = {
+            "duration": report.duration,
+            "score": report.score,
+            "title": report.title,
+        }
+    candidate = current_app.config[FRAMEWORKS].copy()
+    candidate.remove(current_app.config[FRAMEWORK])
+    return render_template(
+        "select.html",
+        files=files,
+        candidate=candidate[0],
+        framework=current_app.config[FRAMEWORK],
+        compare=compare.capitalize() == "True",
+    )
+
+
+@main.route("/datasets/<compare>")
+def datasets(compare):
+    dt = Datasets()
+    datos = []
+    for dataset in dt:
+        datos.append(dt.get_attributes(dataset))
+    return render_template(
+        "datasets.html",
+        datasets=datos,
+        compare=compare,
+        framework=current_app.config[FRAMEWORK],
+    )
+
+
+@main.route("/showfile/<file_name>/<compare>")
+def showfile(file_name, compare, back=None):
+    compare = compare.capitalize() == "True"
+    back = request.args["url"] if back is None else back
+    app_config = dotenv_values(".env")
+    with open(os.path.join(Folders.results, file_name)) as f:
+        data = json.load(f)
+    try:
+        summary = process_data(file_name, compare, data)
+    except Exception as e:
+        return render_template("error.html", message=str(e), compare=compare)
+    return render_template(
+        "report.html",
+        data=data,
+        file=file_name,
+        summary=summary,
+        framework=current_app.config[FRAMEWORK],
+        back=back,
+        app_config=app_config,
+    )
+
+
+@main.route("/show", methods=["post"])
+def show():
+    selected_file = request.form["selected-file"]
+    compare = request.form["compare"]
+    return showfile(
+        file_name=selected_file,
+        compare=compare,
+        back=url_for(
+            "main.index", compare=compare, output=current_app.config[OUTPUT]
+        ),
+    )
+
+
+@main.route("/excel", methods=["post"])
+def excel():
+    selected_files = request.json["selectedFiles"]
+    compare = request.json["compare"]
+    book = None
+    if selected_files[0] == "datasets":
+        # Create a list of datasets
+        report = ReportDatasets(excel=True, output=False)
+        report.report()
+        excel_name = os.path.join(Folders.excel, Files.datasets_report_excel)
+        if current_app.config[OUTPUT] == "local":
+            Files.open(excel_name, test=current_app.config[TEST])
+        return AjaxResponse(True, Files.datasets_report_excel).to_string()
+    try:
+        for file_name in selected_files:
+            file_name_result = os.path.join(Folders.results, file_name)
+            if book is None:
+                file_excel = os.path.join(Folders.excel, Files.be_list_excel)
+                book = xlsxwriter.Workbook(
+                    file_excel, {"nan_inf_to_errors": True}
+                )
+            excel = Excel(
+                file_name=file_name_result,
+                book=book,
+                compare=compare,
+            )
+            excel.report()
+    except Exception as e:
+        if book is not None:
+            book.close()
+        return AjaxResponse(
+            False, "Could not create excel file, " + str(e)
+        ).to_string()
+    if book is not None:
+        book.close()
+    if current_app.config[OUTPUT] == "local":
+        Files.open(file_excel, test=current_app.config[TEST])
+    return AjaxResponse(True, Files.be_list_excel).to_string()
+
+
+@main.route("/download/<file_name>")
+def download(file_name):
+    src = os.path.join(Folders.current, Folders.excel, file_name)
+    dest = os.path.join(
+        Folders.src(), "scripts", "app", "static", "excel", file_name
+    )
+    shutil.copyfile(src, dest)
+    return send_file(dest, as_attachment=True)
+
+
+@main.route("/config/<framework>/<compare>")
+def config(framework, compare):
+    if framework not in current_app.config[FRAMEWORKS]:
+        message = f"framework {framework} not supported"
+        return render_template("error.html", message=message)
+    env = EnvData()
+    env.load()
+    env.args[FRAMEWORK] = framework
+    env.save()
+    current_app.config[FRAMEWORK] = framework
+    return redirect(url_for("main.index", compare=compare))
+
+
+@main.route("/best_results/<file>/<compare>")
+def best_results(file, compare):
+    compare = compare.capitalize() == "True"
+    try:
+        with open(os.path.join(Folders.results, file)) as f:
+            data = json.load(f)
+    except Exception as e:
+        return render_template("error.html", message=str(e), compare=compare)
+    return render_template(
+        "report_best.html",
+        data=data,
+        compare=compare,
+        framework=current_app.config[FRAMEWORK],
+    )

benchmark/scripts/app/static/css/main.css

@@ -0,0 +1,30 @@
+.alternate-font {
+  font-family: Arial;
+}
+
+tbody {
+  font-family: Courier;
+}
+
+.tag {
+  cursor: pointer;
+}
+
+.ajaxLoading {
+  cursor: progress !important;
+}
+
+#file-table tbody tr.selected td {
+  background-color: #0dcaf0;
+  color: white;
+}
+
+#report-table tbody tr.selected td {
+  background-color: #0dcaf0;
+  color: white;
+}
+
+.btn-small {
+  padding: 0.25rem 0.5rem;
+  font-size: 0.75rem;
+}

benchmark/scripts/app/static/excel/.gitignore

@@ -0,0 +1 @@
+*.xlsx

benchmark/scripts/app/static/js/excelFiles.js

@@ -0,0 +1,29 @@
+function excelFiles(selectedFiles, compare) {
+    var data = {
+        "selectedFiles": selectedFiles,
+        "compare": compare
+    };
+    // send data to server with ajax post
+    $.ajax({
+        type:'POST',
+        url:'/excel',
+        data: JSON.stringify(data),
+        contentType: "application/json",
+        dataType: 'json',
+        success: function(data){
+            if (data.success) {
+                if (data.output == "local") {
+                    alert("Se ha generado el archivo " + data.file);
+                } else {
+                    window.open('/download/' + data.file, "_blank");
+                }
+            } else {
+                alert(data.file);
+            }
+        },
+        error: function (xhr, ajaxOptions, thrownError) {
+            var mensaje = JSON.parse(xhr.responseText || '{\"mensaje\": \"Error indeterminado\"}');
+            alert(mensaje.mensaje);
+        }
+    });
+}

benchmark/scripts/app/templates/base_bootstrap.html

@@ -0,0 +1,20 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>{{ title }}</title>
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0-alpha3/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-KK94CHFLLe+nY2dmCWGMq91rCGa5gtU4mk92HdvYe+M/SXH301p5ILy+dN9+nJOZ" crossorigin="anonymous" />
+    <link href="https://fonts.googleapis.com/css?family=Montserrat:300,400,500,600" rel="stylesheet" />
+    <link rel="stylesheet" href="https://cdn.datatables.net/1.10.25/css/jquery.dataTables.min.css" />
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/MaterialDesign-Webfont/7.1.96/css/materialdesignicons.css" integrity="sha512-lD1LHcZ8tFHvMFNeo6qOLY/HjzSPCasPJOAoir22byDxlZI1R71S5lZel8zRL2TZ+Dut1wOHfYgSU2lHXuL00w==" crossorigin="anonymous" referrerpolicy="no-referrer" />
+     <link rel="stylesheet" href="{{ url_for('static', filename='css/main.css') }}" />
+  </head>
+  <body>
+    {% block content %}
+
+    {% endblock %}
+  </body>
+  <script src="https://code.jquery.com/jquery-3.6.0.min.js"></script>
+  {% block jscript %}
+
+  {% endblock %}
+</html>

benchmark/scripts/app/templates/base_bulma.html

@@ -0,0 +1,19 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>{{ title }}</title>
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/bulma/0.9.3/css/bulma.min.css" />
+    <link rel="stylesheet" href="https://cdn.datatables.net/1.10.25/css/jquery.dataTables.min.css" />
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/MaterialDesign-Webfont/7.1.96/css/materialdesignicons.css" integrity="sha512-lD1LHcZ8tFHvMFNeo6qOLY/HjzSPCasPJOAoir22byDxlZI1R71S5lZel8zRL2TZ+Dut1wOHfYgSU2lHXuL00w==" crossorigin="anonymous" referrerpolicy="no-referrer" />
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/main.css') }}" />
+  </head>
+  <body>
+    {% block content %}
+
+    {% endblock %}
+  </body>
+  <script src="https://code.jquery.com/jquery-3.6.0.min.js"></script>
+  {% block jscript %}
+
+  {% endblock %}
+</html>

benchmark/scripts/app/templates/datasets.html

@@ -0,0 +1,68 @@
+{% extends 'base_' ~ framework ~ '.html' %}
+{% macro javascript(file) %}
+  <script src="{{ url_for('static', filename=file) }}"></script>
+{% endmacro %}
+{% if framework == 'bootstrap' %}
+  {% set button_class = 'btn btn-primary btn-small' %}
+  {% set h1_class = 'text-center' %}
+  {% set table_class = 'table table-striped table-hover table-bordered' %}
+  {% set head_class = 'bg-primary text-white' %}
+  {% set text_right = 'text-end' %}
+  {% set container = 'container' %}
+  {% set selected = 'selected' %}
+  {%- macro header(title, close, url) -%}
+    <div class="p-4 bg-primary text-white">
+      {%- if close -%}
+        <button type="button" class="btn-close" aria-label="Close" onclick="location.href = '{{ url }}'"></button>
+      {%- endif -%}
+      <h1 class="alternate-font">{{ title }}</h1>
+    </div>
+  {%- endmacro -%}
+{% else %}
+  {% set button_class = 'button is-primary is-small' %}
+  {% set h1_class = 'title is-1 has-text-centered' %}
+  {% set table_class = 'table is-striped is-hoverable cell-border is-bordered' %}
+  {% set head_class = 'is-selected' %}
+  {% set text_right = 'has-text-right' %}
+  {% set container = 'container' %}
+  {% set selected = 'is-selected' %}
+  {%- macro header(title, close, url) -%}
+    <div class="hero is-info is-bold">
+      <div class="hero-body">
+        {%- if close -%}
+          <button class="delete is-large" onclick="location.href = '{{ url }}'"></button>
+        {%- endif -%}
+        <h1 class="is-size-3 alternate-font">{{ title }}</h1>
+      </div>
+    </div>
+  {%- endmacro -%}
+{% endif %}
+{% block content %}
+  <div class="{{ container }}">
+    {{ header('Benchmark Datasets Report', True, url_for('main.index', compare = compare)) }}
+    <button class="{{ button_class }}" onclick="excelFiles(['datasets'], false)"><i class="mdi mdi-file-excel"></i> Excel</button>
+    {% include 'partials/datasets_table.html' %}
+  </div>
+{% endblock %}
+{% block jscript %}
+{{ javascript("js/excelFiles.js") }}
+  <script>
+    $(document).ready(function () {
+      $(document).ajaxStart(function(){ 
+          $("body").addClass('ajaxLoading');
+      });
+      $(document).ajaxStop(function(){ 
+          $("body").removeClass('ajaxLoading');
+      });
+    });
+    // Check if row is selected
+    $('#file-table tbody').on('click', 'tr', function () {
+      if ($(this).hasClass('{{ selected }}')) {
+          $(this).removeClass('{{ selected }}');
+      } else {
+          $('#file-table tbody tr.{{ selected }}').removeClass("{{ selected }}")
+          $(this).addClass('{{ selected }}');
+      }
+    });
+  </script>
+{% endblock %}

benchmark/scripts/app/templates/error.html

@@ -0,0 +1,20 @@
+<!DOCTYPE html>
+<html>
+    <head>
+        <title>Error</title>
+        <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0-alpha3/dist/css/bootstrap.min.css" rel="stylesheet"
+            integrity="sha384-KK94CHFLLe+nY2dmCWGMq91rCGa5gtU4mk92HdvYe+M/SXH301p5ILy+dN9+nJOZ" crossorigin="anonymous">
+    </head>
+    <body>
+        <div class="container">
+            <div class="alert alert-danger my-5" role="alert">
+
+                <h4 class="alert-heading"><button class="btn-close btn-sm" type="button"
+                        onclick="location.href='/index/{{ compare }}';"></button>Error</h4>
+                <p>There was an error processing action, {{ message }}. Please try again later.</p>
+                <hr>
+                <p class="mb-0">If the problem persists, please contact support.</p>
+            </div>
+        </div>
+    </body>
+</html>

benchmark/scripts/app/templates/js/report.js

@@ -0,0 +1,22 @@
+$(document).ready(function () {
+    // Check if row is selected
+    $('#report-table tbody').on('click', 'tr', function () {
+        if ($(this).hasClass('{{ selected }}')) {
+            $(this).removeClass('{{ selected }}');
+        } else {
+            $('#report-table tbody tr.{{ selected }}').removeClass("{{ selected }}")
+            $(this).addClass('{{ selected }}');
+        }
+    });
+    $(document).ajaxStart(function(){ 
+        $("body").addClass('ajaxLoading');
+    });
+    $(document).ajaxStop(function(){ 
+        $("body").removeClass('ajaxLoading');
+    });
+  });
+  function excelFile() {
+    var selectedFiles = ["{{ file }}"];
+    var compare = "{{ compare }}" == "True";
+    excelFiles(selectedFiles, compare)
+}

benchmark/scripts/app/templates/js/select.js

@@ -0,0 +1,97 @@
+$(document).ready(function () {
+  var table = $("#file-table").DataTable({
+    paging: true,
+    searching: true,
+    ordering: true,
+    info: true,
+    "select.items": "row",
+    pageLength: 25,
+    columnDefs: [
+      {
+        targets: 8,
+        orderable: false,
+      },
+    ],
+    //"language": {
+    //    "lengthMenu": "_MENU_"
+    //}
+  });
+  $('#file-table').on( 'draw.dt', function () {
+    enable_disable_best_buttons();
+  } );
+  // Check if row is selected
+  $("#file-table tbody").on("click", "tr", function () {
+    if ($(this).hasClass("{{ select.selected() }}")) {
+      $(this).removeClass("{{ select.selected() }}");
+    } else {
+      table
+        .$("tr.{{ select.selected() }}")
+        .removeClass("{{ select.selected() }}");
+      $(this).addClass("{{ select.selected() }}");
+    }
+  });
+  // Show file with doubleclick
+  $("#file-table tbody").on("dblclick", "tr", function () {
+    showFile($(this).attr("id"));
+  });
+  $(document).ajaxStart(function () {
+    $("body").addClass("ajaxLoading");
+  });
+  $(document).ajaxStop(function () {
+    $("body").removeClass("ajaxLoading");
+  });
+  $('#compare').change(function() {
+    enable_disable_best_buttons();
+  });
+  enable_disable_best_buttons();
+});
+function enable_disable_best_buttons(){
+  if ($('#compare').is(':checked')) {
+    $("[name='best_buttons']").addClass("tag is-link is-normal");
+      $("[name='best_buttons']").removeAttr("hidden");
+    } else {
+      $("[name='best_buttons']").removeClass("tag is-link is-normal");
+      $("[name='best_buttons']").attr("hidden", true);
+    }
+}
+function showFile(selectedFile) {
+  var form = $(
+    '<form action="/show" method="post">' +
+      '<input type="hidden" name="selected-file" value="' +
+      selectedFile +
+      '" />' +
+      '<input type="hidden" name="compare" value=' +
+      $("#compare").is(":checked") +
+      " />" +
+      "</form>"
+  );
+  $("body").append(form);
+  form.submit();
+}
+function excel() {
+  var checkbox = document.getElementsByName("selected_files");
+  var selectedFiles = [];
+  for (var i = 0; i < checkbox.length; i++) {
+    if (checkbox[i].checked) {
+      selectedFiles.push(checkbox[i].value);
+    }
+  }
+  if (selectedFiles.length == 0) {
+    alert("Select at least one file");
+    return;
+  }
+  var compare = $("#compare").is(":checked");
+  excelFiles(selectedFiles, compare);
+}
+function setCheckBoxes(value) {
+  var checkbox = document.getElementsByName("selected_files");
+  for (i = 0; i < checkbox.length; i++) {
+    checkbox[i].checked = value;
+  }
+}
+function redirectDouble(route, parameter) {
+  location.href = "/"+ route + "/" + parameter + "/" + $("#compare").is(":checked");
+}
+function redirectSimple(route) {
+  location.href = "/" + route + "/" + $("#compare").is(":checked");
+}

benchmark/scripts/app/templates/partials/cfg_select_bootstrap.jinja

@@ -0,0 +1,56 @@
+{%- macro header(title, close=False, url="") -%}
+<div class="p-4 bg-primary text-white">
+{%- if close -%}
+    <button type="button" class="btn-close" aria-label="Close" onclick="location.href = '{{url}}'"></button>
+{%- endif -%}
+<h1 class="alternate-font">{{ title }}</h1>
+</div>
+{%- endmacro -%}
+{%- macro get_table_class() -%}
+table table-striped table-hover table-bordered
+{%- endmacro -%}
+{%- macro icon(icon_name) -%}
+<i class="mdi mdi-{{icon_name}}"></i>
+{%- endmacro -%}
+{%- macro get_button(text, action) -%}
+    <button class="btn btn-primary btn-small" onclick="{{ action }}">{{ text|safe }}</button>
+{%- endmacro -%}
+{%- macro get_button_class() -%}
+    button btn-primary btn-small
+{%- endmacro %}
+{%- macro get_button_tag(icon_name, method, visible=True, name="") -%}
+    <button class="btn btn-primary btn-small" onclick="{{ method }}" {{ "" if visible else "hidden='true'" }} {{ "" if name=="" else "name='" + name +"'"}}><i class="mdi mdi-{{ icon_name }}"></i></button>
+{%- endmacro -%}
+{%- macro get_button_reset() -%}
+<button class="btn btn-primary btn-small btn-danger" onclick="setCheckBoxes(false)"><i class="mdi mdi-checkbox-multiple-blank"></i></button>
+{%- endmacro -%}
+{%- macro get_button_all() -%}
+<button class="btn btn-primary btn-small btn-success" onclick="setCheckBoxes(true)"><i class="mdi mdi-checkbox-multiple-marked"></i></button>
+{%- endmacro -%}
+{%- macro get_tag_class() -%}
+badge bg-info bg-small
+{%- endmacro -%}
+{%- macro get_container_class() -%}
+container-fluid
+{%- endmacro -%}
+{%- macro selected() -%}
+selected
+{%- endmacro -%}
+{%- macro get_level_class() -%}
+navbar
+{%- endmacro -%}
+{%- macro get_align_right() -%}
+text-end
+{%- endmacro -%}
+{%- macro get_left_position() -%}
+float-left
+{%- endmacro -%}
+{%- macro get_right_position() -%}
+float-right
+{%- endmacro -%}
+{%- macro get_row_head_class() -%}
+bg-primary text-white
+{%- endmacro -%}
+{%- macro get_align_center() -%}
+text-center
+{%- endmacro -%}

benchmark/scripts/app/templates/partials/cfg_select_bulma.jinja

@@ -0,0 +1,58 @@
+{%- macro header(title, close=False, url="") -%}
+<div class="hero is-info is-bold">
+<div class="hero-body">
+    {%- if close -%}
+    <button class="delete is-large" onclick="location.href = '{{ url }}'"></button>
+    {%- endif -%}
+    <h1 class="is-size-3 alternate-font">{{ title }}</h1>
+</div>
+</div>
+{%- endmacro -%}
+{%- macro get_table_class() -%}
+table is-striped is-hoverable cell-border is-bordered
+{%- endmacro -%}
+{%- macro icon(icon_name) -%}
+<i class="mdi mdi-{{icon_name}}"></i>
+{%- endmacro -%}
+{%- macro get_button(text, action) -%}
+    <button class="button is-primary is-small" onclick="{{ action }}">{{ text|safe }}</button>
+{%- endmacro -%}
+{%- macro get_button_tag(icon_name, method, visible=True, name="") -%}
+    <span class="{{ "tag is-link is-normal" if visible else "" }}" type="button" onclick="{{ method }}" {{ "" if visible else "hidden='true'" }} {{ "" if name=="" else "name='" + name +"'"}}>{{icon(icon_name)}}</span>
+{%- endmacro -%}
+{%- macro get_button_reset() -%}
+    <span class="tag is-link is-danger" type="button" onclick="setCheckBoxes(false)"><i class="mdi mdi-checkbox-multiple-blank"></i></span>
+{%- endmacro -%}
+{%- macro get_button_all() -%}
+    <span class="tag is-link is-success" type="button" onclick="setCheckBoxes(true)"><i class="mdi mdi-checkbox-multiple-marked"></i></span>
+{%- endmacro -%}
+{%- macro get_tag_class() -%}
+tag is-info is-small
+{%- endmacro -%}
+{%- macro get_container_class() -%}
+container is-fluid
+{%- endmacro -%}
+{%- macro selected() -%}
+is-selected
+{%- endmacro -%}
+{%- macro get_level_class() -%}
+level
+{%- endmacro -%}
+{%- macro get_align_right() -%}
+has-text-right
+{%- endmacro -%}
+{%- macro get_align_center() -%}
+has-text-center
+{%- endmacro -%}
+{%- macro get_left_position() -%}
+float-left
+{%- endmacro -%}
+{%- macro get_right_position() -%}
+float-right
+{%- endmacro -%}
+{%- macro get_row_head_class() -%}
+is-selected
+{%- endmacro -%}
+{%- macro get_align_center() -%}
+has-text-center
+{%- endmacro -%}

benchmark/scripts/app/templates/partials/datasets_table.html

@@ -0,0 +1,27 @@
+{% extends "base_" ~ framework ~ ".html" %}
+{% block content %}
+  <table id="file-table" class="{{ table_class }}">
+    <thead>
+      <tr class="{{ head_class }}">
+        <th class="{{ text_center }}">Dataset</th>
+        <th class="{{ text_center }}">Samples</th>
+        <th class="{{ text_center }}">Features</th>
+        <th class="{{ text_center }}">Cont. Feat.</th>
+        <th class="{{ text_center }}">Classes</th>
+        <th class="{{ text_center }}">Balance</th>
+      </tr>
+    </thead>
+    <tbody>
+      {% for dataset in datasets %}
+        <tr>
+          <td>{{ dataset.dataset }}</td>
+          <td class="{{ text_right }}">{{ "{:,}".format(dataset.samples) }}</td>
+          <td class="{{ text_right }}">{{ "{:,}".format(dataset.features) }}</td>
+          <td class="{{ text_right }}">{{ dataset.cont_features }}</td>
+          <td class="{{ text_right }}">{{ dataset.classes }}</td>
+          <td>{{ dataset.balance }}</td>
+        </tr>
+      {% endfor %}
+    </tbody>
+  </table>
+{% endblock %}

benchmark/scripts/app/templates/partials/table_report.html

@@ -0,0 +1,14 @@
+{% for item in data.results %}
+  <tr>
+    <td>{{ item.dataset }}</td>
+    <td class="{{ right }}">{{ '{:,}'.format(item.samples) }}</td>
+    <td class="{{ right }}">{{"%d" % item.features}}</td>
+    <td class="{{ right }}">{{"%d" % item.classes}}</td>
+    <td class="{{ right }}">{{ '{:,.2f}'.format(item.nodes|float) }}</td>
+    <td class="{{ right }}">{{ '{:,.2f}'.format(item.leaves|float) }}</td>
+    <td class="{{ right }}">{{ '{:,.2f}'.format(item.depth|float) }}</td>
+    <td class="{{ right }}">{{"%.6f±%.4f" % (item.score, item.score_std)}} {{ item.symbol|safe }}</td>
+    <td class="{{ right }}">{{"%.6f±%.4f" % (item.time, item.time_std)}}</td>
+    <td class="{{ center }}">{{ item.hyperparameters }}</td>
+  </tr>
+{% endfor %}

benchmark/scripts/app/templates/partials/table_report_bootstrap.html

@@ -0,0 +1,102 @@
+<div id="app">
+  <section class="section">
+    <div class="container-fluid">
+      <div class="p-4 bg-primary text-white">
+        <button type="button"
+                class="btn-close"
+                aria-label="Close"
+                onclick="location.href = '{{ back }}'"></button>
+        <h1>{{ data.title }}</h1>
+      </div>
+      <div>
+        <table class="table table-bordered">
+          <thead>
+            <tr class="bg-info text-white">
+              <th class="text-center">Platform</th>
+              <th class="text-center">Model</th>
+              <th class="text-center">Date</th>
+              <th class="text-center">Time</th>
+              {% if data.duration > 7200 %}
+                {% set unit = "h" %}
+                {% set divider = 3600 %}
+              {% else %}
+                {% set unit = "min" %}
+                {% set divider = 60 %}
+              {% endif %}
+              <th class="text-center">Duration ({{ unit }})</th>
+              <th class="text-center">Stratified</th>
+              <th class="text-center">Discretized</th>
+              <th class="text-center"># Folds</th>
+            </tr>
+            <tr>
+              <th class="text-center">{{ data.platform }}</th>
+              <th class="text-center">{{ data.model }} {{ data.version }}</th>
+              <th class="text-center">{{ data.date }}</th>
+              <th class="text-center">{{ data.time }}</th>
+              <th class="text-center">{{ "%.2f" % (data.duration/divider) }}</th>
+              <th class="text-center">{{ data.stratified }}</th>
+              <th class="text-center">{{ data.discretized }}</th>
+              <th class="text-center">{{ data.folds }}</th>
+            </tr>
+            <tr>
+              <th class="text-center bg-info text-white">Language</th>
+              <th class="text-center" colspan=3>{{ data.language }} {{ data.language_version }}</th>
+              <th class="text-center bg-info text-white">Seeds</th>
+              <th class="text-center" colspan=6>{{ data.seeds }}</th>
+            </tr>
+          </thead>
+        </table>
+        <div>
+          <button class="{{ button }}" onclick="excelFile()">
+            <i class="mdi mdi-file-excel"></i> Excel
+          </button>
+        </div>
+        <table id="report-table"
+               class="table table-striped table-hover table-bordered">
+          <thead>
+            <tr class="bg-primary text-white">
+              <th class="text-center">Dataset</th>
+              <th class="text-center">Samples</th>
+              <th class="text-center">Features</th>
+              <th class="text-center">Classes</th>
+              <th class="text-center">{{ app_config.nodes }}</th>
+              <th class="text-center">{{ app_config.leaves }}</th>
+              <th class="text-center">{{ app_config.depth }}</th>
+              <th class="text-center">{{ data.score_name|capitalize }}</th>
+              <th class="text-center">Time</th>
+              <th class="text-center">hyperparameters</th>
+            </tr>
+          </thead>
+          <tbody>
+            {% include "partials/table_report.html" %}
+          </tbody>
+        </table>
+        {% if summary|length > 0 %}
+          <div class="col-4 col-lg-4">
+            <table class="table table-bordered">
+              <thead>
+                <tr>
+                  <th class="text-center bg-primary text-white">Symbol</th>
+                  <th class="text-center bg-primary text-white">Meaning</th>
+                  <th class="text-center bg-primary text-white">Count</th>
+                </tr>
+              </thead>
+              {% include "partials/table_summary.html" %}
+            </table>
+          </div>
+        {% endif %}
+        <button type="button"
+                class="btn-close"
+                aria-label="Close"
+                onclick="location.href = '{{ back }}'"></button>
+        <h7>
+        <b>
+          Total score: {{ "%.6f" % (data.results | sum(attribute="score") ) }}
+        </b>
+        </h7>
+        <h7>
+        Number of files: {{ data.results | length }}
+        </h7>
+      </div>
+    </section>
+  </div>

benchmark/scripts/app/templates/partials/table_report_bulma.html

@@ -0,0 +1,100 @@
+<div id="app">
+  <header>
+    <div class="container is-fluid">
+      <div class="hero is-info is-bold">
+        <div class="hero-body">
+          <button class="delete is-large" onclick="location.href = '{{ back }}'"></button>
+          <h1 class="is-size-3">{{ data.title }}</h1>
+        </div>
+      </div>
+    </div>
+  </header>
+  <section class="section">
+    <div class="container is-fluid">
+      <div>
+        <table class="table is-fullwidth is-striped is-bordered">
+          <thead>
+            <tr class="is-selected">
+              <th class="has-text-centered">Platform</th>
+              <th class="has-text-centered">Model</th>
+              <th class="has-text-centered">Date</th>
+              <th class="has-text-centered">Time</th>
+              {% if data.duration > 7200 %}
+                {% set unit = "h" %}
+                {% set divider = 3600 %}
+              {% else %}
+                {% set unit = "min" %}
+                {% set divider = 60 %}
+              {% endif %}
+              <th class="has-text-centered">Duration ({{ unit }})</th>
+              <th class="has-text-centered">Stratified</th>
+              <th class="has-text-centered">Discretized</th>
+              <th class="has-text-centered"># Folds</th>
+            </tr>
+            <tr>
+              <th class="has-text-centered">{{ data.platform }}</th>
+              <th class="has-text-centered">{{ data.model }} {{ data.version }}</th>
+              <th class="has-text-centered">{{ data.date }}</th>
+              <th class="has-text-centered">{{ data.time }}</th>
+              <th class="has-text-centered">{{ "%.2f" % (data.duration/divider) }}</th>
+              <th class="has-text-centered">{{ data.stratified }}</th>
+              <th class="has-text-centered">{{ data.discretized }}</th>
+              <th class="has-text-centered">{{ data.folds }}</th>
+            </tr>
+            <tr>
+              <th class="has-text-center is-selected">Language</th>
+              <th class="has-text-centered" colspan=3>{{ data.language }} {{ data.language_version }}</th>
+              <th class="has-text-centered is-selected">Seeds</th>
+              <th class="has-text-centered" colspan=6>{{ data.seeds }}</th>
+            </tr>
+          </thead>
+        </table>
+        <div>
+          <button class="{{ button }}" onclick="excelFile()">
+            <i class="mdi mdi-file-excel"></i> Excel
+          </button>
+        </div>
+        <table id="report-table"
+               class="table is-fullwidth is-striped is-hoverable is-bordered">
+          <thead>
+            <tr class="is-selected">
+              <th class="has-text-centered">Dataset</th>
+              <th class="has-text-centered">Samples</th>
+              <th class="has-text-centered">Features</th>
+              <th class="has-text-centered">Classes</th>
+              <th class="has-text-centered">{{ app_config.nodes }}</th>
+              <th class="has-text-centered">{{ app_config.leaves }}</th>
+              <th class="has-text-centered">{{ app_config.depth }}</th>
+              <th class="has-text-centered">{{ data.score_name|capitalize }}</th>
+              <th class="has-text-centered">Time</th>
+              <th class="has-text-centered">hyperparameters</th>
+            </tr>
+          </thead>
+          <tbody>
+            {% include "partials/table_report.html" %}
+          </tbody>
+        </table>
+        {% if summary|length > 0 %}
+          <div class="col-2 col-lg-2">
+            <table class="table is-bordered">
+              <thead>
+                <tr class="is-selected">
+                  <th class="has-text-centered">Symbol</th>
+                  <th class="has-text-centered">Meaning</th>
+                  <th class="has-text-centered">Count</th>
+                </tr>
+              </thead>
+              {% include "partials/table_summary.html" %}
+            </table>
+          </div>
+        {% endif %}
+        <h2 class="has-text-white has-background-primary">
+          <b>
+            <button class="delete" onclick="location.href = '{{ back }}'"></button>
+            Total score: {{ "%.6f" % (data.results | sum(attribute="score") ) }}
+          </b>
+        </h2>
+        <h2>Number of files: {{ data.results | length }}</h2>
+      </div>
+    </section>
+  </div>

benchmark/scripts/app/templates/partials/table_select.html

@@ -0,0 +1,41 @@
+<table id="file-table" class="{{ select.get_table_class() }}">
+  <thead>
+    <tr>
+      <th>Model</th>
+      <th>Metric</th>
+      <th>Platform</th>
+      <th>Date</th>
+      <th>Time</th>
+      <th>Stratified</th>
+      <th>Title</th>
+      <th>Score</th>
+      <th>{{ select.get_button_reset()|safe }} {{ select.get_button_all()|safe }}</th>
+    </tr>
+  </thead>
+  <tbody>
+    {% for file, data in files.items() %} 
+      {% set parts = file.split('_') %} 
+      {% set stratified = parts[6].split('.')[0] %}
+      <tr id="{{ file }}">
+        <td>{{ parts[2] }}</td>
+        <td>{{ parts[1] }}</td>
+        <td>{{ parts[3] }}</td>
+        <td>{{ parts[4] }}</td>
+        <td>{{ parts[5] }}</td>
+        <td>{{ 'True' if stratified =='1' else 'False' }}</td>
+        <td>{{ "%s" % data["title"] }}</td>
+        <td class="{{ select.get_align_right() }}">{{ "%.6f" % data["score"] }}</td>
+        <td>
+          {{ select.get_button_tag("table-eye", "showFile('" ~ file ~ "')") | safe }}
+          {% set file_best = "best_results_" ~ parts[1] ~ "_" ~ parts[2] ~ ".json" %}
+          {{ select.get_button_tag("star-circle-outline", "redirectDouble('best_results', '" ~ file_best ~ "')", visible=False, name="best_buttons") | safe }}
+          <input
+            type="checkbox"
+            name="selected_files"
+            value="{{ file }}"
+          />
+        </td>
+      </tr>
+    {% endfor %}
+  </tbody>
+</table>

benchmark/scripts/app/templates/partials/table_select_design.html

@@ -0,0 +1,15 @@
+<div class="{{ select.get_container_class() }}">
+    {{ select.header("Benchmark Results") }}
+    <div class="{{ select.get_level_class() }}">
+        <div class="{{ select.get_left_position() }}">
+            {{ select.get_button("Use " ~ candidate, "redirectDouble('config', '" ~ candidate ~ "')")|safe }}
+            {{ select.get_button(select.icon("excel") ~ " Excel", "excel()")|safe }}
+            {{ select.get_button(select.icon("database-eye") ~ " Datasets", "redirectSimple('datasets')")|safe }}
+        </div>
+        <div class="{{ select.get_right_position() }}">
+            <input type="checkbox" id="compare" name="compare" {% if compare %} {{ "checked" }} {% endif %}>
+            <span class="{{ select.get_tag_class() }}">Comparing with best results</span>
+        </div>
+    </div>
+    {% include "partials/table_select.html" %}
+</div>

benchmark/scripts/app/templates/partials/table_summary.html

@@ -0,0 +1,13 @@
+{% for key, value in summary.items() %}
+    <tr>
+        <td class="{{ center }}">
+            {{key}}
+        </td>
+        <td >
+            {{value[0]}}
+        </td>
+        <td class={{ right }}>
+            {{'{:,}'.format(value[1])}}
+        </td>
+    </tr>
+{% endfor %}

benchmark/scripts/app/templates/report.html

@@ -0,0 +1,29 @@
+{% macro javascript(file) %}
+  <script src="{{ url_for('static', filename=file) }}"></script>
+{% endmacro %}
+{% set title = 'Report Viewer' %}
+{% extends 'base_' ~ framework ~ '.html' %}
+{% block content %}
+  {% if framework == 'bootstrap' %}
+    {% set center = 'text-center' %}
+    {% set right = 'text-end' %}
+    {% set button = 'btn btn-primary' %}
+    {% include 'partials/table_report_bootstrap.html' %}
+  {% else %}
+    {% set center = 'has-text-centered' %}
+    {% set right = 'has-text-right' %}
+    {% set button = 'button is-primary' %}
+    {% include 'partials/table_report_bulma.html' %}
+  {% endif %}
+{% endblock %}
+{% block jscript %}
+  {% if framework == 'bootstrap' %}
+    {% set selected = 'selected' %}
+  {% else %}
+    {% set selected = 'is-selected' %}
+  {% endif %}
+  <script>
+    {% include "js/report.js" %}
+  </script>
+  {{ javascript("js/excelFiles.js") }}
+{% endblock %}

benchmark/scripts/app/templates/report_best.html

@@ -0,0 +1,47 @@
+{% set title = "Best Results" %}
+{% extends "base_" ~ framework ~ ".html" %}
+{% import "partials/cfg_select_" ~ framework ~ ".jinja" as select %}
+{% block content %}
+    <div class="container">
+        {{ select.header(title, True, url_for("main.index", compare=compare)) }}
+        <table id="file-table" class="{{ select.get_table_class() }}">
+            <thead>
+                <tr class="{{ select.get_row_head_class() }}">
+                <th class="{{ select.get_align_center() }}">Dataset</th>
+                <th class="{{ select.get_align_center() }}">Score</th>
+                <th class="{{ select.get_align_center() }}">Hyperparameters</th>
+                <th class="{{ select.get_align_center() }}">File</th>
+                </tr>
+            </thead>
+            <tbody>
+                {% for dataset, info in data.items() %}
+                <tr>
+                    <td>{{ dataset }}</td>
+                    <td class="{{ select.get_align_right() }}">{{ '%9.7f' % info[0] }}</td>
+                    <td class="{{ select.get_align_center() }}">{{ info[1] }}</td>
+                    <td>
+                    {% set url = url_for(request.endpoint, **request.view_args)|urlencode %}
+                    <a href="{{ url_for('main.showfile', file_name = info[2], compare = compare) }}?url={{ url }}">{{ info[2] }}</a>
+                    </td>
+                </tr>
+                {% endfor %}
+            </tbody>
+        </table>
+    </div>
+{% endblock %}
+{% block jscript %}
+<script>
+    $(document).ready(function () {
+        // Check if row is selected
+        $('#file-table tbody').on('click', 'tr', function () {
+            if ($(this).hasClass('{{ select.selected() }}')) {
+                $(this).removeClass('{{ select.selected() }}');
+            } else {
+                $('#file-table tbody tr.{{ select.selected() }}').removeClass("{{ select.selected() }}")
+                $(this).addClass('{{ select.selected() }}');
+            }
+        });
+  });
+</script>
+{% endblock %}
+

benchmark/scripts/app/templates/select.html

@@ -0,0 +1,20 @@
+{% macro javascript(file) %}
+  <script src="{{ url_for('static', filename=file) }}"></script>
+{% endmacro %}
+{% set title = 'Benchmark Results' %}
+{% extends 'base_' ~ framework ~ '.html' %}
+{% import 'partials/cfg_select_' ~ framework ~ '.jinja' as select %}
+{% block content %}
+  {% include 'partials/table_select_design.html' %}
+{% endblock %}
+
+{% block jscript %}
+  <script src="https://cdn.datatables.net/1.10.25/js/jquery.dataTables.min.js"></script>
+  {% if framework == 'bootstrap' %}
+    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.2.3/dist/js/bootstrap.min.js" integrity="sha384-cuYeSxntonz0PPNlHhBs68uyIAVpIIOZZ5JqeqvYYIcEL727kskC66kF92t6Xl2V" crossorigin="anonymous"></script>
+  {% endif %}
+  <script>
+    {% include'/js/select.js' %}
+  </script>
+  {{ javascript('js/excelFiles.js') }}
+{% endblock %}

benchmark/scripts/be_benchmark.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-from benchmark.Results import Benchmark
+from benchmark.ResultsFiles import Benchmark
 from benchmark.Utils import Files
 from benchmark.Arguments import Arguments
 

benchmark/scripts/be_best.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 import json
-from benchmark.Results import Summary
+from benchmark.ResultsBase import Summary
 from benchmark.Arguments import ALL_METRICS, Arguments
 
 

benchmark/scripts/be_build_grid.py

@@ -46,7 +46,7 @@ def main(args_test=None):
         '{"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", '
+        '{"C": 0.05, "max_iter": 10000, "kernel": "liblinear", '
         '"multiclass_strategy": "ovr"}',
         '{"C":0.0275, "kernel": "liblinear", "multiclass_strategy": "ovr"}',
         '{"C": 7, "gamma": 10.0, "kernel": "rbf", "multiclass_strategy": '
@@ -97,7 +97,7 @@ def main(args_test=None):
     for item in results:
         results_tmp = {"n_jobs": [-1], "n_estimators": [100]}
         for key, value in results[item].items():
-            new_key = f"base_estimator__{key}"
+            new_key = f"estimator__{key}"
             try:
                 results_tmp[new_key] = sorted(value)
             except TypeError:
@@ -111,6 +111,7 @@ def main(args_test=None):
                 t2 = sorted([x for x in value if isinstance(x, str)])
                 results_tmp[new_key] = t1 + t2
         output.append(results_tmp)
+
     # save results
     file_name = Files.grid_input(args.score, args.model)
     file_output = os.path.join(Folders.results, file_name)

benchmark/scripts/be_flask.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python
+import webbrowser
+from benchmark.Arguments import Arguments
+from benchmark.scripts.app.app import create_app, TEST, OUTPUT
+
+# Launch a flask server to serve the results
+
+def main(args_test=None):
+    arguments = Arguments(prog="be_flask")
+    arguments.xset("output")
+    args = arguments.parse(args_test)
+    app = create_app()
+    app.config[TEST] = args_test is not None
+    app.config[OUTPUT] = args.output
+    print("Output is ", args.output)
+    if args.output == "local":
+        webbrowser.open_new("http://127.0.0.1:1234/")
+    app.run(port=1234, host="0.0.0.0")

benchmark/scripts/be_init_project.py

@@ -15,6 +15,9 @@ def main(args_test=None):
     folders.append(os.path.join(args.project_name, Folders.exreport))
     folders.append(os.path.join(args.project_name, Folders.report))
     folders.append(os.path.join(args.project_name, Folders.img))
+    folders.append(os.path.join(args.project_name, Folders.excel))
+    folders.append(os.path.join(args.project_name, Folders.sql))
+
     try:
         for folder in folders:
             print(f"Creating folder {folder}")

benchmark/scripts/be_list.py

@@ -1,7 +1,9 @@
 #! /usr/bin/env python
-from benchmark.Results import Summary
+import os
-from benchmark.Utils import Files
+from benchmark.ResultsBase import Summary
+from benchmark.Utils import Files, Folders
 from benchmark.Arguments import Arguments
+from benchmark.Manager import Manage
 
 """List experiments of a model
 """
@@ -26,7 +28,9 @@ def main(args_test=None):
     except ValueError as e:
         print(e)
         return
-    excel_generated = data.manage_results()
+    manager = Manage(data)
+    excel_generated = manager.manage_results()
     if excel_generated:
-        print(f"Generated file: {Files.be_list_excel}")
+        name = os.path.join(Folders.excel, Files.be_list_excel)
-        Files.open(Files.be_list_excel, test=args_test is not None)
+        print(f"Generated file: {name}")
+        Files.open(name, test=args_test is not None)

benchmark/scripts/be_main.py

@@ -13,7 +13,8 @@ def main(args_test=None):
     arguments = Arguments(prog="be_main")
     arguments.xset("stratified").xset("score").xset("model", mandatory=True)
     arguments.xset("n_folds").xset("platform").xset("quiet").xset("title")
-    arguments.xset("report")
+    arguments.xset("report").xset("ignore_nan").xset("discretize")
+    arguments.xset("fit_features")
     arguments.add_exclusive(
         ["grid_paramfile", "best_paramfile", "hyperparameters"]
     )
@@ -29,14 +30,19 @@ def main(args_test=None):
             score_name=args.score,
             model_name=args.model,
             stratified=args.stratified,
-            datasets=Datasets(dataset_name=args.dataset),
+            datasets=Datasets(
+                dataset_name=args.dataset, discretize=args.discretize
+            ),
             hyperparams_dict=args.hyperparameters,
             hyperparams_file=args.best_paramfile,
             grid_paramfile=args.grid_paramfile,
             progress_bar=not args.quiet,
             platform=args.platform,
+            ignore_nan=args.ignore_nan,
             title=args.title,
             folds=args.n_folds,
+            fit_features=args.fit_features,
+            discretize=args.discretize,
         )
         job.do_experiment()
     except ValueError as e:

benchmark/scripts/be_report.py

@@ -1,7 +1,10 @@
 #!/usr/bin/env python
-from benchmark.Results import Report, Excel, SQL, ReportBest, ReportDatasets
+import os
-from benchmark.Utils import Files
+from benchmark.Results import Report, ReportBest
+from benchmark.ResultsFiles import Excel, SQLFile, ReportDatasets
+from benchmark.Utils import Files, Folders
 from benchmark.Arguments import Arguments
+from pathlib import Path
 
 
 """Build report on screen of a result file, optionally generate excel and sql
@@ -65,15 +68,17 @@ def main(args_test=None):
                 print(e)
                 return
             if args.sql:
-                sql = SQL(args.file_name)
+                sql = SQLFile(args.file_name)
                 sql.report()
             if args.excel:
                 excel = Excel(
-                    file_name=args.file_name,
+                    file_name=Path(args.file_name).name,
                     compare=args.compare,
                 )
                 excel.report()
-                Files.open(excel.get_file_name(), is_test)
+                Files.open(
+                    os.path.join(Folders.excel, excel.get_file_name()), is_test
+                )
         case "datasets":
             report = ReportDatasets(args.excel)
             report.report()

benchmark/scripts/be_summary.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-from benchmark.Results import Summary
+from benchmark.ResultsBase import Summary
 from benchmark.Arguments import ALL_METRICS, Arguments
 
 

benchmark/tests/.env

@@ -7,3 +7,8 @@ stratified=0
 source_data=Tanveer
 seeds=[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]
 discretize=0
+nodes=Nodes
+leaves=Leaves
+depth=Depth
+fit_features=0
+margin=0.1

benchmark/tests/.env.arff

@@ -6,3 +6,8 @@ stratified=0
 source_data=Arff
 seeds=[271, 314, 171]
 discretize=1
+nodes=Nodes
+leaves=Leaves
+depth=Depth
+fit_features=1
+margin=0.1

benchmark/tests/.env.dist

@@ -7,3 +7,8 @@ stratified=0
 source_data=Tanveer
 seeds=[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]
 discretize=0
+nodes=Nodes
+leaves=Leaves
+depth=Depth
+fit_features=0
+margin=0.1

benchmark/tests/.env.surcov

@@ -7,3 +7,8 @@ stratified=0
 source_data=Surcov
 seeds=[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]
 discretize=0
+nodes=Nodes
+leaves=Leaves
+depth=Depth
+fit_features=0
+margin=0.1

benchmark/tests/Arguments_test.py

@@ -68,7 +68,7 @@ class ArgumentsTest(TestBase):
         test_args = ["-n", "3", "-k", "date"]
         with self.assertRaises(SystemExit):
             arguments.parse(test_args)
-        self.assertRegexpMatches(
+        self.assertRegex(
             stderr.getvalue(),
             r"error: the following arguments are required: -m/--model",
         )
@@ -79,7 +79,7 @@ class ArgumentsTest(TestBase):
         test_args = ["-n", "3", "-m", "SVC"]
         with self.assertRaises(SystemExit):
             arguments.parse(test_args)
-        self.assertRegexpMatches(
+        self.assertRegex(
             stderr.getvalue(),
             r"error: the following arguments are required: -k/--key",
         )
@@ -114,7 +114,7 @@ class ArgumentsTest(TestBase):
         test_args = None
         with self.assertRaises(SystemExit):
             arguments.parse(test_args)
-        self.assertRegexpMatches(
+        self.assertRegex(
             stderr.getvalue(),
             r"error: the following arguments are required: -m/--model, "
             "-k/--key, --title",

benchmark/tests/Benchmark_test.py

@@ -4,7 +4,7 @@ from unittest.mock import patch
 from openpyxl import load_workbook
 from .TestBase import TestBase
 from ..Utils import Folders, Files, NO_RESULTS
-from ..Results import Benchmark
+from ..ResultsFiles import Benchmark
 from .._version import __version__
 
 
@@ -15,10 +15,10 @@ class BenchmarkTest(TestBase):
             files.append(Files.exreport(score))
             files.append(Files.exreport_output(score))
             files.append(Files.exreport_err(score))
-        files.append(Files.exreport_excel(score))
         files.append(Files.exreport_pdf)
         files.append(Files.tex_output("accuracy"))
         self.remove_files(files, Folders.exreport)
+        self.remove_files([Files.exreport_excel("accuracy")], Folders.excel)
         self.remove_files(files, ".")
         return super().tearDown()
 
@@ -90,15 +90,6 @@ class BenchmarkTest(TestBase):
         self.assertTrue(os.path.exists(benchmark.get_tex_file()))
         self.check_file_file(benchmark.get_tex_file(), "exreport_tex")
 
-    @staticmethod
-    def generate_excel_sheet(test, sheet, file_name):
-        with open(os.path.join("test_files", file_name), "w") as f:
-            for row in range(1, sheet.max_row + 1):
-                for col in range(1, sheet.max_column + 1):
-                    value = sheet.cell(row=row, column=col).value
-                    if value is not None:
-                        print(f'{row};{col};"{value}"', file=f)
-
     def test_excel_output(self):
         benchmark = Benchmark("accuracy", visualize=False)
         benchmark.compile_results()

benchmark/tests/BestResults_test.py

@@ -18,7 +18,7 @@ class BestResultTest(TestBase):
                     "C": 7,
                     "gamma": 0.1,
                     "kernel": "rbf",
-                    "max_iter": 10000.0,
+                    "max_iter": 10000,
                     "multiclass_strategy": "ovr",
                 },
                 "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json",

benchmark/tests/Dataset_test.py

@@ -1,4 +1,3 @@
-import shutil
 from .TestBase import TestBase
 from ..Experiments import Randomized
 from ..Datasets import Datasets
@@ -17,10 +16,6 @@ class DatasetTest(TestBase):
         self.set_env(".env.dist")
         return super().tearDown()
 
-    @staticmethod
-    def set_env(env):
-        shutil.copy(env, ".env")
-
     def test_Randomized(self):
         expected = [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]
         self.assertSequenceEqual(Randomized.seeds(), expected)

benchmark/tests/Excel_test.py

@@ -2,8 +2,8 @@ import os
 from openpyxl import load_workbook
 from xlsxwriter import Workbook
 from .TestBase import TestBase
-from ..Results import Excel
+from ..ResultsFiles import Excel
-from ..Utils import Folders
+from ..Utils import Folders, Files
 
 
 class ExcelTest(TestBase):
@@ -13,7 +13,7 @@ class ExcelTest(TestBase):
             "results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.xlsx",
             "results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.xlsx",
         ]
-        self.remove_files(files, Folders.results)
+        self.remove_files(files, Folders.excel)
         return super().tearDown()
 
     def test_report_excel_compared(self):
@@ -21,7 +21,7 @@ class ExcelTest(TestBase):
         report = Excel(file_name, compare=True)
         report.report()
         file_output = report.get_file_name()
-        book = load_workbook(file_output)
+        book = load_workbook(os.path.join(Folders.excel, file_output))
         sheet = book["STree"]
         self.check_excel_sheet(sheet, "excel_compared")
 
@@ -30,14 +30,14 @@ class ExcelTest(TestBase):
         report = Excel(file_name, compare=False)
         report.report()
         file_output = report.get_file_name()
-        book = load_workbook(file_output)
+        book = load_workbook(os.path.join(Folders.excel, file_output))
         sheet = book["STree"]
         self.check_excel_sheet(sheet, "excel")
 
     def test_Excel_Add_sheet(self):
         file_name = "results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json"
-        excel_file_name = file_name.replace(".json", ".xlsx")
+        excel_file_name = file_name.replace(Files.report_ext, ".xlsx")
-        book = Workbook(os.path.join(Folders.results, excel_file_name))
+        book = Workbook(os.path.join(Folders.excel, excel_file_name))
         excel = Excel(file_name=file_name, book=book)
         excel.report()
         report = Excel(
@@ -46,7 +46,7 @@ class ExcelTest(TestBase):
         )
         report.report()
         book.close()
-        book = load_workbook(os.path.join(Folders.results, excel_file_name))
+        book = load_workbook(os.path.join(Folders.excel, excel_file_name))
         sheet = book["STree"]
         self.check_excel_sheet(sheet, "excel_add_STree")
         sheet = book["ODTE"]

benchmark/tests/Experiment_test.py

@@ -1,4 +1,6 @@
 import json
+from io import StringIO
+from unittest.mock import patch
 from .TestBase import TestBase
 from ..Experiments import Experiment
 from ..Datasets import Datasets
@@ -8,10 +10,12 @@ class ExperimentTest(TestBase):
     def setUp(self):
         self.exp = self.build_exp()
 
-    def build_exp(self, hyperparams=False, grid=False):
+    def build_exp(
+        self, hyperparams=False, grid=False, model="STree", ignore_nan=False
+    ):
         params = {
             "score_name": "accuracy",
-            "model_name": "STree",
+            "model_name": model,
             "stratified": "0",
             "datasets": Datasets(),
             "hyperparams_dict": "{}",
@@ -21,6 +25,7 @@ class ExperimentTest(TestBase):
             "title": "Test",
             "progress_bar": False,
             "folds": 2,
+            "ignore_nan": ignore_nan,
         }
         return Experiment(**params)
 
@@ -31,6 +36,7 @@ class ExperimentTest(TestBase):
             ],
             ".",
         )
+        self.set_env(".env.dist")
         return super().tearDown()
 
     def test_build_hyperparams_file(self):
@@ -46,7 +52,7 @@ class ExperimentTest(TestBase):
                     "C": 7,
                     "gamma": 0.1,
                     "kernel": "rbf",
-                    "max_iter": 10000.0,
+                    "max_iter": 10000,
                     "multiclass_strategy": "ovr",
                 },
                 "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json",
@@ -89,7 +95,7 @@ class ExperimentTest(TestBase):
     def test_exception_n_fold_crossval(self):
         self.exp.do_experiment()
         with self.assertRaises(ValueError):
-            self.exp._n_fold_crossval([], [], {})
+            self.exp._n_fold_crossval("", [], [], {})
 
     def test_do_experiment(self):
         self.exp.do_experiment()
@@ -131,3 +137,42 @@ class ExperimentTest(TestBase):
         ):
             for key, value in expected_result.items():
                 self.assertEqual(computed_result[key], value)
+
+    def test_build_fit_parameters(self):
+        self.set_env(".env.arff")
+        expected = {
+            "state_names": {
+                "sepallength": [0, 1, 2],
+                "sepalwidth": [0, 1, 2, 3, 4, 5],
+                "petallength": [0, 1, 2, 3],
+                "petalwidth": [0, 1, 2],
+            },
+            "features": [
+                "sepallength",
+                "sepalwidth",
+                "petallength",
+                "petalwidth",
+            ],
+        }
+        exp = self.build_exp(model="TAN")
+        X, y = exp.datasets.load("iris")
+        computed = exp._build_fit_params("iris")
+        for key, value in expected["state_names"].items():
+            self.assertEqual(computed["state_names"][key], value)
+        for feature in expected["features"]:
+            self.assertIn(feature, computed["features"])
+        # Ask for states of a dataset that does not exist
+        computed = exp._build_fit_params("not_existing")
+        self.assertTrue("states" not in computed)
+
+    @patch("sys.stdout", new_callable=StringIO)
+    def test_experiment_with_nan_not_ignored(self, mock_output):
+        exp = self.build_exp(model="Mock")
+        self.assertRaises(ValueError, exp.do_experiment)
+        output_text = mock_output.getvalue().splitlines()
+        expected = "[      nan 0.8974359]"
+        self.assertEqual(expected, output_text[0])
+
+    def test_experiment_with_nan_ignored(self):
+        self.exp = self.build_exp(model="Mock", ignore_nan=True)
+        self.exp.do_experiment()

benchmark/tests/Models_test.py

@@ -70,19 +70,19 @@ class ModelTest(TestBase):
     def test_BaggingStree(self):
         clf = Models.get_model("BaggingStree")
         self.assertIsInstance(clf, BaggingClassifier)
-        clf_base = clf.base_estimator
+        clf_base = clf.estimator
         self.assertIsInstance(clf_base, Stree)
 
     def test_BaggingWodt(self):
         clf = Models.get_model("BaggingWodt")
         self.assertIsInstance(clf, BaggingClassifier)
-        clf_base = clf.base_estimator
+        clf_base = clf.estimator
         self.assertIsInstance(clf_base, Wodt)
 
     def test_AdaBoostStree(self):
         clf = Models.get_model("AdaBoostStree")
         self.assertIsInstance(clf, AdaBoostClassifier)
-        clf_base = clf.base_estimator
+        clf_base = clf.estimator
         self.assertIsInstance(clf_base, Stree)
 
     def test_unknown_classifier(self):
@@ -102,7 +102,7 @@ class ModelTest(TestBase):
         test = {
             "STree": ((11, 6, 4), 1.0),
             "Wodt": ((303, 152, 50), 0.9382022471910112),
-            "ODTE": ((7.86, 4.43, 3.37), 1.0),
+            "ODTE": ((786, 443, 337), 1.0),
             "Cart": ((23, 12, 5), 1.0),
             "SVC": ((0, 0, 0), 0.7078651685393258),
             "RandomForest": ((21.3, 11, 5.26), 1.0),

benchmark/tests/Report_test.py

@@ -2,7 +2,10 @@ import os
 from io import StringIO
 from unittest.mock import patch
 from .TestBase import TestBase
-from ..Results import Report, BaseReport, ReportBest, ReportDatasets, get_input
+from ..Results import Report, ReportBest
+from ..ResultsFiles import ReportDatasets
+from ..ResultsBase import BaseReport
+from ..Manager import get_input
 from ..Utils import Symbols
 
 
@@ -63,6 +66,27 @@ class ReportTest(TestBase):
         self.assertEqual(res, Symbols.better_best)
         res = report._compute_status("balloons", 1.0)
         self.assertEqual(res, Symbols.better_best)
+        report = Report(file_name=file_name)
+        with patch(self.output, new=StringIO()):
+            report.report()
+        res = report._compute_status("balloons", 0.99)
+        self.assertEqual(res, Symbols.upward_arrow)
+        report.margin = 0.9
+        res = report._compute_status("balloons", 0.99)
+        self.assertEqual(res, Symbols.cross)
+
+    def test_reportbase_compute_status(self):
+        with patch.multiple(BaseReport, __abstractmethods__=set()):
+            file_name = os.path.join(
+                "results",
+                "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json",
+            )
+            temp = BaseReport(file_name)
+            temp.compare = False
+            temp._compare_totals = {}
+            temp.score_name = "f1"
+            res = temp._compute_status("balloons", 0.99)
+            self.assertEqual(res, " ")
 
     def test_report_file_not_found(self):
         with self.assertRaises(FileNotFoundError):
@@ -87,7 +111,6 @@ class ReportTest(TestBase):
             if self.stree_version in line:
                 # replace STree version
                 line = self.replace_STree_version(line, output_text, index)
-
             self.assertEqual(line, output_text[index])
 
     @patch("sys.stdout", new_callable=StringIO)

benchmark/tests/SQL_test.py

@@ -1,7 +1,7 @@
 import os
 from .TestBase import TestBase
-from ..Results import SQL
+from ..ResultsFiles import SQLFile
-from ..Utils import Folders
+from ..Utils import Folders, Files
 
 
 class SQLTest(TestBase):
@@ -9,14 +9,14 @@ class SQLTest(TestBase):
         files = [
             "results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.sql",
         ]
-        self.remove_files(files, Folders.results)
+        self.remove_files(files, Folders.sql)
         return super().tearDown()
 
     def test_report_SQL(self):
         file_name = "results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.json"
-        report = SQL(file_name)
+        report = SQLFile(file_name)
         report.report()
         file_name = os.path.join(
-            Folders.results, file_name.replace(".json", ".sql")
+            Folders.sql, file_name.replace(Files.report_ext, ".sql")
         )
         self.check_file_file(file_name, "sql")

benchmark/tests/Summary_test.py

@@ -1,7 +1,7 @@
 from io import StringIO
 from unittest.mock import patch
 from .TestBase import TestBase
-from ..Results import Summary
+from ..ResultsBase import Summary
 from ..Utils import NO_RESULTS
 
 

benchmark/tests/TestBase.py

@@ -4,6 +4,7 @@ import pathlib
 import sys
 import csv
 import unittest
+import shutil
 from importlib import import_module
 from io import StringIO
 from unittest.mock import patch
@@ -19,6 +20,10 @@ class TestBase(unittest.TestCase):
         self.stree_version = "1.2.4"
         super().__init__(*args, **kwargs)
 
+    @staticmethod
+    def set_env(env):
+        shutil.copy(env, ".env")
+
     def remove_files(self, files, folder):
         for file_name in files:
             file_name = os.path.join(folder, file_name)
@@ -26,6 +31,7 @@ class TestBase(unittest.TestCase):
                 os.remove(file_name)
 
     def generate_excel_sheet(self, sheet, file_name):
+        file_name += self.ext
         with open(os.path.join(self.test_files, file_name), "w") as f:
             for row in range(1, sheet.max_row + 1):
                 for col in range(1, sheet.max_column + 1):

benchmark/tests/Util_test.py

@@ -11,6 +11,8 @@ class UtilTest(TestBase):
         self.assertEqual("results", Folders.results)
         self.assertEqual("hidden_results", Folders.hidden_results)
         self.assertEqual("exreport", Folders.exreport)
+        self.assertEqual("excel", Folders.excel)
+        self.assertEqual("img", Folders.img)
         self.assertEqual(
             os.path.join(Folders.exreport, "exreport_output"), Folders.report
         )
@@ -116,7 +118,7 @@ class UtilTest(TestBase):
     def test_Files_get_results(self):
         os.chdir(os.path.dirname(os.path.abspath(__file__)))
         self.assertCountEqual(
-            Files().get_all_results(hidden=False),
+            Files.get_all_results(hidden=False),
             [
                 "results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json",
                 "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json",
@@ -128,7 +130,7 @@ class UtilTest(TestBase):
             ],
         )
         self.assertCountEqual(
-            Files().get_all_results(hidden=True),
+            Files.get_all_results(hidden=True),
             [
                 "results_accuracy_STree_iMac27_2021-11-01_23:55:16_0.json",
                 "results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_"
@@ -141,7 +143,7 @@ class UtilTest(TestBase):
         # check with results
         os.rename(Folders.results, f"{Folders.results}.test")
         try:
-            Files().get_all_results(hidden=False)
+            Files.get_all_results(hidden=False)
         except ValueError:
             pass
         else:
@@ -151,7 +153,7 @@ class UtilTest(TestBase):
         # check with hidden_results
         os.rename(Folders.hidden_results, f"{Folders.hidden_results}.test")
         try:
-            Files().get_all_results(hidden=True)
+            Files.get_all_results(hidden=True)
         except ValueError:
             pass
         else:
@@ -180,6 +182,11 @@ class UtilTest(TestBase):
             "source_data": "Tanveer",
             "seeds": "[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]",
             "discretize": "0",
+            "nodes": "Nodes",
+            "leaves": "Leaves",
+            "depth": "Depth",
+            "fit_features": "0",
+            "margin": "0.1",
         }
         computed = EnvData().load()
         self.assertDictEqual(computed, expected)

benchmark/tests/datasets/all.txt

@@ -1,2 +1,2 @@
-iris,class
+iris;class;all
-wine,class
+wine;class;[0, 1]

benchmark/tests/excel/.gitignore

@@ -0,0 +1 @@
+#

benchmark/tests/results/best_results_accuracy_STree.json

@@ -1 +1 @@
-{"balance-scale": [0.98, {"splitter": "best", "max_features": "auto"}, "results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json"], "balloons": [0.86, {"C": 7, "gamma": 0.1, "kernel": "rbf", "max_iter": 10000.0, "multiclass_strategy": "ovr"}, "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json"]}
+{"balance-scale": [0.98, {"splitter": "best", "max_features": "auto"}, "results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json"], "balloons": [0.86, {"C": 7, "gamma": 0.1, "kernel": "rbf", "max_iter": 10000, "multiclass_strategy": "ovr"}, "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json"]}

benchmark/tests/results/grid_output_accuracy_STree.json

@@ -6,7 +6,7 @@
             "kernel": "liblinear",
             "multiclass_strategy": "ovr"
         },
-        "v. 1.3.0, Computed on Test on 2022-02-22 at 12:00:00 took 1s"
+        "v. 1.4.0, Computed on Test on 2022-02-22 at 12:00:00 took 1s"
     ],
     "balloons": [
         0.625,
@@ -15,6 +15,6 @@
             "kernel": "linear",
             "multiclass_strategy": "ovr"
         },
-        "v. 1.3.0, Computed on Test on 2022-02-22 at 12:00:00 took 1s"
+        "v. 1.4.0, Computed on Test on 2022-02-22 at 12:00:00 took 1s"
     ]
 }

benchmark/tests/results/results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.json

@@ -1,59 +1 @@
-{
+{"score_name": "accuracy", "title": "Gridsearched hyperparams v022.1b random_init", "model": "ODTE", "version": "0.3.2", "language_version": "3.11x", "language": "Python", "stratified": false, "folds": 5, "date": "2022-04-20", "time": "10:52:20", "duration": 22591.471411943436, "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1], "platform": "Galgo", "results": [{"dataset": "balance-scale", "samples": 625, "features": 4, "classes": 3, "hyperparameters": {"base_estimator__C": 57, "base_estimator__gamma": 0.1, "base_estimator__kernel": "rbf", "base_estimator__multiclass_strategy": "ovr", "n_estimators": 100, "n_jobs": -1}, "nodes": 7.361199999999999, "leaves": 4.180599999999999, "depth": 3.536, "score": 0.96352, "score_std": 0.024949741481626608, "time": 0.31663217544555666, "time_std": 0.19918813895255585}, {"dataset": "balloons", "samples": 16, "features": 4, "classes": 2, "hyperparameters": {"base_estimator__C": 5, "base_estimator__gamma": 0.14, "base_estimator__kernel": "rbf", "base_estimator__multiclass_strategy": "ovr", "n_estimators": 100, "n_jobs": -1}, "nodes": 2.9951999999999996, "leaves": 1.9975999999999998, "depth": 1.9975999999999998, "score": 0.785, "score_std": 0.2461311755051675, "time": 0.11560620784759522, "time_std": 0.012784241828599895}], "discretized": false}
-  "score_name": "accuracy",
-  "title": "Gridsearched hyperparams v022.1b random_init",
-  "model": "ODTE",
-  "version": "0.3.2",
-  "language_version": "3.11x",
-  "language": "Python",
-  "stratified": false,
-  "folds": 5,
-  "date": "2022-04-20",
-  "time": "10:52:20",
-  "duration": 22591.471411943436,
-  "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1],
-  "platform": "Galgo",
-  "results": [
-    {
-      "dataset": "balance-scale",
-      "samples": 625,
-      "features": 4,
-      "classes": 3,
-      "hyperparameters": {
-        "base_estimator__C": 57,
-        "base_estimator__gamma": 0.1,
-        "base_estimator__kernel": "rbf",
-        "base_estimator__multiclass_strategy": "ovr",
-        "n_estimators": 100,
-        "n_jobs": -1
-      },
-      "nodes": 7.361199999999999,
-      "leaves": 4.180599999999999,
-      "depth": 3.536,
-      "score": 0.96352,
-      "score_std": 0.024949741481626608,
-      "time": 0.31663217544555666,
-      "time_std": 0.19918813895255585
-    },
-    {
-      "dataset": "balloons",
-      "samples": 16,
-      "features": 4,
-      "classes": 2,
-      "hyperparameters": {
-        "base_estimator__C": 5,
-        "base_estimator__gamma": 0.14,
-        "base_estimator__kernel": "rbf",
-        "base_estimator__multiclass_strategy": "ovr",
-        "n_estimators": 100,
-        "n_jobs": -1
-      },
-      "nodes": 2.9951999999999996,
-      "leaves": 1.9975999999999998,
-      "depth": 1.9975999999999998,
-      "score": 0.785,
-      "score_std": 0.2461311755051675,
-      "time": 0.11560620784759522,
-      "time_std": 0.012784241828599895
-    }
-  ]
-}

benchmark/tests/results/results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json

@@ -1,45 +1 @@
-{
+{"score_name": "accuracy", "title": "Test default paramters with RandomForest", "model": "RandomForest", "version": "-", "language_version": "3.11x", "language": "Python", "stratified": false, "folds": 5, "date": "2022-01-14", "time": "12:39:30", "duration": 272.7363500595093, "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1], "platform": "iMac27", "results": [{"dataset": "balance-scale", "samples": 625, "features": 4, "classes": 3, "hyperparameters": {}, "nodes": 196.91440000000003, "leaves": 98.42, "depth": 10.681399999999998, "score": 0.83616, "score_std": 0.02649630917694009, "time": 0.08222018241882324, "time_std": 0.0013026326815120633}, {"dataset": "balloons", "samples": 16, "features": 4, "classes": 2, "hyperparameters": {}, "nodes": 9.110800000000001, "leaves": 4.58, "depth": 3.0982, "score": 0.625, "score_std": 0.24958298553119898, "time": 0.07016648769378662, "time_std": 0.002460508923990468}], "discretized": false}
-  "score_name": "accuracy",
-  "title": "Test default paramters with RandomForest",
-  "model": "RandomForest",
-  "version": "-",
-  "language_version": "3.11x",
-  "language": "Python",
-  "stratified": false,
-  "folds": 5,
-  "date": "2022-01-14",
-  "time": "12:39:30",
-  "duration": 272.7363500595093,
-  "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1],
-  "platform": "iMac27",
-  "results": [
-    {
-      "dataset": "balance-scale",
-      "samples": 625,
-      "features": 4,
-      "classes": 3,
-      "hyperparameters": {},
-      "nodes": 196.91440000000003,
-      "leaves": 98.42,
-      "depth": 10.681399999999998,
-      "score": 0.83616,
-      "score_std": 0.02649630917694009,
-      "time": 0.08222018241882324,
-      "time_std": 0.0013026326815120633
-    },
-    {
-      "dataset": "balloons",
-      "samples": 16,
-      "features": 4,
-      "classes": 2,
-      "hyperparameters": {},
-      "nodes": 9.110800000000001,
-      "leaves": 4.58,
-      "depth": 3.0982,
-      "score": 0.625,
-      "score_std": 0.24958298553119898,
-      "time": 0.07016648769378662,
-      "time_std": 0.002460508923990468
-    }
-  ]
-}

benchmark/tests/results/results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json

@@ -1,57 +1 @@
-{
+{"score_name": "accuracy", "model": "STree", "stratified": false, "folds": 5, "language_version": "3.11x", "language": "Python", "date": "2021-09-30", "time": "11:42:07", "duration": 624.2505249977112, "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1], "platform": "iMac27", "results": [{"dataset": "balance-scale", "samples": 625, "features": 4, "classes": 3, "hyperparameters": {"C": 10000, "gamma": 0.1, "kernel": "rbf", "max_iter": 10000, "multiclass_strategy": "ovr"}, "nodes": 7.0, "leaves": 4.0, "depth": 3.0, "score": 0.97056, "score_std": 0.015046806970251203, "time": 0.01404867172241211, "time_std": 0.002026269126958884}, {"dataset": "balloons", "samples": 16, "features": 4, "classes": 2, "hyperparameters": {"C": 7, "gamma": 0.1, "kernel": "rbf", "max_iter": 10000, "multiclass_strategy": "ovr"}, "nodes": 3.0, "leaves": 2.0, "depth": 2.0, "score": 0.86, "score_std": 0.28501461950807594, "time": 0.0008541679382324218, "time_std": 3.629469326417878e-05}], "title": "With gridsearched hyperparameters", "version": "1.2.3", "discretized": false}
-  "score_name": "accuracy",
-  "model": "STree",
-  "stratified": false,
-  "folds": 5,
-  "language_version": "3.11x",
-  "language": "Python",
-  "date": "2021-09-30",
-  "time": "11:42:07",
-  "duration": 624.2505249977112,
-  "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1],
-  "platform": "iMac27",
-  "results": [
-    {
-      "dataset": "balance-scale",
-      "samples": 625,
-      "features": 4,
-      "classes": 3,
-      "hyperparameters": {
-        "C": 10000.0,
-        "gamma": 0.1,
-        "kernel": "rbf",
-        "max_iter": 10000.0,
-        "multiclass_strategy": "ovr"
-      },
-      "nodes": 7.0,
-      "leaves": 4.0,
-      "depth": 3.0,
-      "score": 0.97056,
-      "score_std": 0.015046806970251203,
-      "time": 0.01404867172241211,
-      "time_std": 0.002026269126958884
-    },
-    {
-      "dataset": "balloons",
-      "samples": 16,
-      "features": 4,
-      "classes": 2,
-      "hyperparameters": {
-        "C": 7,
-        "gamma": 0.1,
-        "kernel": "rbf",
-        "max_iter": 10000.0,
-        "multiclass_strategy": "ovr"
-      },
-      "nodes": 3.0,
-      "leaves": 2.0,
-      "depth": 2.0,
-      "score": 0.86,
-      "score_std": 0.28501461950807594,
-      "time": 0.0008541679382324218,
-      "time_std": 3.629469326417878e-5
-    }
-  ],
-  "title": "With gridsearched hyperparameters",
-  "version": "1.2.3"
-}

benchmark/tests/results/results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json

@@ -1,51 +1 @@
-{
+{"score_name": "accuracy", "model": "STree", "language": "Python", "language_version": "3.11x", "stratified": false, "folds": 5, "date": "2021-10-27", "time": "09:40:40", "duration": 3395.009148836136, "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1], "platform": "iMac27", "results": [{"dataset": "balance-scale", "samples": 625, "features": 4, "classes": 3, "hyperparameters": {"splitter": "best", "max_features": "auto"}, "nodes": 11.08, "leaves": 5.9, "depth": 5.9, "score": 0.98, "score_std": 0.001, "time": 0.28520655155181884, "time_std": 0.06031593282605064}, {"dataset": "balloons", "samples": 16, "features": 4, "classes": 2, "hyperparameters": {"splitter": "best", "max_features": "auto"}, "nodes": 4.12, "leaves": 2.56, "depth": 2.56, "score": 0.695, "score_std": 0.2756860130252853, "time": 0.021201000213623047, "time_std": 0.003526023309468471}], "title": "default A", "version": "1.2.3", "discretized": false}
-  "score_name": "accuracy",
-  "model": "STree",
-  "language": "Python",
-  "language_version": "3.11x",
-  "stratified": false,
-  "folds": 5,
-  "date": "2021-10-27",
-  "time": "09:40:40",
-  "duration": 3395.009148836136,
-  "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1],
-  "platform": "iMac27",
-  "results": [
-    {
-      "dataset": "balance-scale",
-      "samples": 625,
-      "features": 4,
-      "classes": 3,
-      "hyperparameters": {
-        "splitter": "best",
-        "max_features": "auto"
-      },
-      "nodes": 11.08,
-      "leaves": 5.9,
-      "depth": 5.9,
-      "score": 0.98,
-      "score_std": 0.001,
-      "time": 0.28520655155181884,
-      "time_std": 0.06031593282605064
-    },
-    {
-      "dataset": "balloons",
-      "samples": 16,
-      "features": 4,
-      "classes": 2,
-      "hyperparameters": {
-        "splitter": "best",
-        "max_features": "auto"
-      },
-      "nodes": 4.12,
-      "leaves": 2.56,
-      "depth": 2.56,
-      "score": 0.695,
-      "score_std": 0.2756860130252853,
-      "time": 0.021201000213623047,
-      "time_std": 0.003526023309468471
-    }
-  ],
-  "title": "default A",
-  "version": "1.2.3"
-}

benchmark/tests/results/results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json

@@ -1,51 +1 @@
-{
+{"score_name": "accuracy", "model": "STree", "language_version": "3.11x", "language": "Python", "stratified": false, "folds": 5, "date": "2021-11-01", "time": "19:17:07", "duration": 4115.042420864105, "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1], "platform": "macbook-pro", "results": [{"dataset": "balance-scale", "samples": 625, "features": 4, "classes": 3, "hyperparameters": {"max_features": "auto", "splitter": "mutual"}, "nodes": 18.78, "leaves": 9.88, "depth": 5.9, "score": 0.97, "score_std": 0.002, "time": 0.23330417156219482, "time_std": 0.048087665954193885}, {"dataset": "balloons", "samples": 16, "features": 4, "classes": 2, "hyperparameters": {"max_features": "auto", "splitter": "mutual"}, "nodes": 4.72, "leaves": 2.86, "depth": 2.78, "score": 0.5566666666666668, "score_std": 0.2941277122460771, "time": 0.021352062225341795, "time_std": 0.005808742398555902}], "title": "default B", "version": "1.2.3", "discretized": false}
-  "score_name": "accuracy",
-  "model": "STree",
-  "language_version": "3.11x",
-  "language": "Python",
-  "stratified": false,
-  "folds": 5,
-  "date": "2021-11-01",
-  "time": "19:17:07",
-  "duration": 4115.042420864105,
-  "seeds": [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1],
-  "platform": "macbook-pro",
-  "results": [
-    {
-      "dataset": "balance-scale",
-      "samples": 625,
-      "features": 4,
-      "classes": 3,
-      "hyperparameters": {
-        "max_features": "auto",
-        "splitter": "mutual"
-      },
-      "nodes": 18.78,
-      "leaves": 9.88,
-      "depth": 5.9,
-      "score": 0.97,
-      "score_std": 0.002,
-      "time": 0.23330417156219482,
-      "time_std": 0.048087665954193885
-    },
-    {
-      "dataset": "balloons",
-      "samples": 16,
-      "features": 4,
-      "classes": 2,
-      "hyperparameters": {
-        "max_features": "auto",
-        "splitter": "mutual"
-      },
-      "nodes": 4.72,
-      "leaves": 2.86,
-      "depth": 2.78,
-      "score": 0.5566666666666668,
-      "score_std": 0.2941277122460771,
-      "time": 0.021352062225341795,
-      "time_std": 0.005808742398555902
-    }
-  ],
-  "title": "default B",
-  "version": "1.2.3"
-}

benchmark/tests/scripts/Be_Benchmark_test.py

@@ -16,10 +16,10 @@ class BeBenchmarkTest(TestBase):
             files.append(Files.exreport(score))
             files.append(Files.exreport_output(score))
             files.append(Files.exreport_err(score))
-        files.append(Files.exreport_excel(self.score))
         files.append(Files.exreport_pdf)
         files.append(Files.tex_output(self.score))
         self.remove_files(files, Folders.exreport)
+        self.remove_files([Files.exreport_excel(self.score)], Folders.excel)
         self.remove_files(files, ".")
         return super().tearDown()
 
@@ -41,7 +41,7 @@ class BeBenchmarkTest(TestBase):
         self.check_file_file(file_name, "exreport_tex")
         # Check excel file
         file_name = os.path.join(
-            Folders.exreport, Files.exreport_excel(self.score)
+            Folders.excel, Files.exreport_excel(self.score)
         )
         book = load_workbook(file_name)
         replace = None

benchmark/tests/scripts/Be_Init_Project_test.py

@@ -33,6 +33,7 @@ class BeInitProjectTest(TestBase):
             Folders.exreport,
             Folders.report,
             Folders.img,
+            Folders.excel,
         ]
         for folder in expected:
             self.assertIsFolder(os.path.join(test_project, folder))

benchmark/tests/scripts/Be_List_test.py

@@ -10,53 +10,55 @@ class BeListTest(TestBase):
     def setUp(self):
         self.prepare_scripts_env()
 
-    @patch("benchmark.Results.get_input", return_value="q")
+    @patch("benchmark.Manager.get_input", return_value="q")
     def test_be_list(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["-m", "STree"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_model")
 
-    @patch("benchmark.Results.get_input", side_effect=iter(["x", "q"]))
+    @patch("benchmark.Manager.get_input", side_effect=iter(["x", "q"]))
     def test_be_list_invalid_option(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["-m", "STree"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_model_invalid")
 
-    @patch("benchmark.Results.get_input", side_effect=iter(["0", "q"]))
+    @patch("benchmark.Manager.get_input", side_effect=iter(["0", "q"]))
     def test_be_list_report(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["-m", "STree"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_report")
 
-    @patch("benchmark.Results.get_input", side_effect=iter(["r", "q"]))
+    @patch("benchmark.Manager.get_input", side_effect=iter(["r", "q"]))
     def test_be_list_twice(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["-m", "STree"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_model_2")
 
-    @patch("benchmark.Results.get_input", side_effect=iter(["e 2", "q"]))
+    @patch("benchmark.Manager.get_input", side_effect=iter(["e 2", "q"]))
     def test_be_list_report_excel(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["-m", "STree"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_report_excel")
-        book = load_workbook(Files.be_list_excel)
+
+        book = load_workbook(os.path.join(Folders.excel, Files.be_list_excel))
         sheet = book["STree"]
         self.check_excel_sheet(sheet, "excel")
 
     @patch(
-        "benchmark.Results.get_input", side_effect=iter(["e 2", "e 1", "q"])
+        "benchmark.Manager.get_input",
+        side_effect=iter(["e 2", "e 1", "q"]),
     )
     def test_be_list_report_excel_twice(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["-m", "STree"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_report_excel_2")
-        book = load_workbook(Files.be_list_excel)
+        book = load_workbook(os.path.join(Folders.excel, Files.be_list_excel))
         sheet = book["STree"]
         self.check_excel_sheet(sheet, "excel")
         sheet = book["STree2"]
         self.check_excel_sheet(sheet, "excel2")
 
-    @patch("benchmark.Results.get_input", return_value="q")
+    @patch("benchmark.Manager.get_input", return_value="q")
     def test_be_list_no_data(self, input_data):
         stdout, stderr = self.execute_script(
             "be_list", ["-m", "Wodt", "-s", "f1-macro"]
@@ -65,9 +67,10 @@ class BeListTest(TestBase):
         self.assertEqual(stdout.getvalue(), f"{NO_RESULTS}\n")
 
     @patch(
-        "benchmark.Results.get_input", side_effect=iter(["d 0", "y", "", "q"])
+        "benchmark.Manager.get_input",
+        side_effect=iter(["d 0", "y", "", "q"]),
     )
-    # @patch("benchmark.Results.get_input", side_effect=iter(["q"]))
+    # @patch("benchmark.ResultsBase.get_input", side_effect=iter(["q"]))
     def test_be_list_delete(self, input_data):
         def copy_files(source_folder, target_folder, file_name):
             source = os.path.join(source_folder, file_name)
@@ -91,7 +94,8 @@ class BeListTest(TestBase):
             self.fail("test_be_list_delete() should not raise exception")
 
     @patch(
-        "benchmark.Results.get_input", side_effect=iter(["h 0", "y", "", "q"])
+        "benchmark.Manager.get_input",
+        side_effect=iter(["h 0", "y", "", "q"]),
     )
     def test_be_list_hide(self, input_data):
         def swap_files(source_folder, target_folder, file_name):
@@ -115,30 +119,36 @@ class BeListTest(TestBase):
             swap_files(Folders.results, Folders.hidden_results, file_name)
             self.fail("test_be_list_hide() should not raise exception")
 
-    @patch("benchmark.Results.get_input", side_effect=iter(["h 0", "q"]))
+    @patch("benchmark.Manager.get_input", side_effect=iter(["h 0", "q"]))
     def test_be_list_already_hidden(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["--hidden"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_already_hidden")
 
-    @patch("benchmark.Results.get_input", side_effect=iter(["h 0", "n", "q"]))
+    @patch("benchmark.Manager.get_input", side_effect=iter(["h 0", "n", "q"]))
     def test_be_list_dont_hide(self, input_data):
         stdout, stderr = self.execute_script("be_list", "")
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_default")
 
-    @patch("benchmark.Results.get_input", side_effect=iter(["q"]))
+    @patch("benchmark.Manager.get_input", side_effect=iter(["q"]))
     def test_be_list_hidden_nan(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["--hidden", "--nan"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_hidden_nan")
 
-    @patch("benchmark.Results.get_input", side_effect=iter(["q"]))
+    @patch("benchmark.Manager.get_input", side_effect=iter(["q"]))
     def test_be_list_hidden(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["--hidden"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_hidden")
 
+    @patch("benchmark.Manager.get_input", side_effect=iter(["0", "q"]))
+    def test_be_list_compare(self, input_data):
+        stdout, stderr = self.execute_script("be_list", ["--compare"])
+        self.assertEqual(stderr.getvalue(), "")
+        self.check_output_file(stdout, "be_list_compare_fault")
+
     def test_be_no_env(self):
         path = os.getcwd()
         os.chdir("..")

benchmark/tests/scripts/Be_Main_test.py

@@ -25,7 +25,7 @@ class BeMainTest(TestBase):
         self.check_output_lines(
             stdout=stdout,
             file_name="be_main_dataset",
-            lines_to_compare=[0, 2, 3, 5, 6, 7, 8, 9, 11, 12, 13],
+            lines_to_compare=[0, 2, 3, 5, 6, 7, 8, 9, 11, 12, 13, 14],
         )
 
     def test_be_main_complete(self):
@@ -37,7 +37,9 @@ class BeMainTest(TestBase):
         report_name = stdout.getvalue().splitlines()[-1].split("in ")[1]
         self.files.append(report_name)
         self.check_output_lines(
-            stdout, "be_main_complete", [0, 2, 3, 5, 6, 7, 8, 9, 12, 13, 14]
+            stdout,
+            "be_main_complete",
+            [0, 2, 3, 5, 6, 7, 8, 9, 12, 13, 14, 15],
         )
 
     def test_be_main_no_report(self):
@@ -118,7 +120,7 @@ class BeMainTest(TestBase):
                 module.main(parameter)
             self.assertEqual(msg.exception.code, 2)
             self.assertEqual(stderr.getvalue(), "")
-            self.assertRegexpMatches(stdout.getvalue(), message)
+            self.assertRegex(stdout.getvalue(), message)
 
     def test_be_main_best_params_non_existent(self):
         model = "GBC"

benchmark/tests/scripts/Be_Print_Strees_test.py

@@ -27,7 +27,7 @@ class BePrintStrees(TestBase):
                 stdout.getvalue(), f"File {file_name} generated\n"
             )
             computed_size = os.path.getsize(file_name)
-            self.assertGreater(computed_size, 25000)
+            self.assertGreater(computed_size, 24500)
 
     def test_be_print_strees_dataset_color(self):
         for name in self.datasets:

benchmark/tests/scripts/Be_Report_test.py

@@ -13,11 +13,17 @@ class BeReportTest(TestBase):
 
     def tearDown(self) -> None:
         files = [
-            "results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.sql",
             "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.xlsx",
         ]
         self.remove_files(files, Folders.results)
-        self.remove_files([Files.datasets_report_excel], os.getcwd())
+        self.remove_files(
+            [Files.datasets_report_excel],
+            os.path.join(os.getcwd(), Folders.excel),
+        )
+        files = [
+            "results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.sql",
+        ]
+        self.remove_files(files, Folders.sql)
         return super().tearDown()
 
     def test_be_report(self):
@@ -34,7 +40,7 @@ class BeReportTest(TestBase):
         self.assertEqual(stderr.getvalue(), "")
         self.assertEqual(stdout.getvalue(), "unknown does not exists!\n")
 
-    def test_be_report_compare(self):
+    def test_be_report_compared(self):
         file_name = "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json"
         stdout, stderr = self.execute_script(
             "be_report", ["file", file_name, "-c"]
@@ -67,7 +73,9 @@ class BeReportTest(TestBase):
                 # replace benchmark version
                 line = self.replace_benchmark_version(line, output_text, index)
             self.assertEqual(line, output_text[index])
-        file_name = os.path.join(os.getcwd(), Files.datasets_report_excel)
+        file_name = os.path.join(
+            os.getcwd(), Folders.excel, Files.datasets_report_excel
+        )
         book = load_workbook(file_name)
         sheet = book["Datasets"]
         self.check_excel_sheet(
@@ -111,7 +119,16 @@ class BeReportTest(TestBase):
     def test_be_report_without_subcommand(self):
         stdout, stderr = self.execute_script("be_report", "")
         self.assertEqual(stderr.getvalue(), "")
-        self.check_output_file(stdout, "report_without_subcommand")
+        self.maxDiff = None
+        # Can't use check_output_file because of the width of the console
+        # output is different in different environments
+        file_name = "report_without_subcommand" + self.ext
+        with open(os.path.join(self.test_files, file_name)) as f:
+            expected = f.read()
+        if expected == stdout.getvalue():
+            self.assertEqual(stdout.getvalue(), expected)
+        else:
+            self.check_output_file(stdout, "report_without_subcommand2")
 
     def test_be_report_excel_compared(self):
         file_name = "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json"
@@ -120,7 +137,7 @@ class BeReportTest(TestBase):
             ["file", file_name, "-x", "-c"],
         )
         file_name = os.path.join(
-            Folders.results, file_name.replace(".json", ".xlsx")
+            Folders.excel, file_name.replace(Files.report_ext, ".xlsx")
         )
         book = load_workbook(file_name)
         sheet = book["STree"]
@@ -135,7 +152,7 @@ class BeReportTest(TestBase):
             ["file", file_name, "-x"],
         )
         file_name = os.path.join(
-            Folders.results, file_name.replace(".json", ".xlsx")
+            Folders.excel, file_name.replace(Files.report_ext, ".xlsx")
         )
         book = load_workbook(file_name)
         sheet = book["STree"]
@@ -150,7 +167,7 @@ class BeReportTest(TestBase):
             ["file", file_name, "-q"],
         )
         file_name = os.path.join(
-            Folders.results, file_name.replace(".json", ".sql")
+            Folders.sql, file_name.replace(Files.report_ext, ".sql")
         )
         self.check_file_file(file_name, "sql")
         self.assertEqual(stderr.getvalue(), "")

benchmark/tests/sql/.gitignore

@@ -0,0 +1 @@
+#

benchmark/tests/test_files/be_build_grid.test

@@ -6,13 +6,13 @@
         "n_estimators": [
             100
         ],
-        "base_estimator__C": [
+        "estimator__C": [
             1.0
         ],
-        "base_estimator__kernel": [
+        "estimator__kernel": [
             "linear"
         ],
-        "base_estimator__multiclass_strategy": [
+        "estimator__multiclass_strategy": [
             "ovo"
         ]
     },
@@ -23,7 +23,7 @@
         "n_estimators": [
             100
         ],
-        "base_estimator__C": [
+        "estimator__C": [
             0.001,
             0.0275,
             0.05,
@@ -36,10 +36,10 @@
             7,
             10000.0
         ],
-        "base_estimator__kernel": [
+        "estimator__kernel": [
             "liblinear"
         ],
-        "base_estimator__multiclass_strategy": [
+        "estimator__multiclass_strategy": [
             "ovr"
         ]
     },
@@ -50,7 +50,7 @@
         "n_estimators": [
             100
         ],
-        "base_estimator__C": [
+        "estimator__C": [
             0.05,
             1.0,
             1.05,
@@ -62,7 +62,7 @@
             57,
             10000.0
         ],
-        "base_estimator__gamma": [
+        "estimator__gamma": [
             0.001,
             0.1,
             0.14,
@@ -70,10 +70,10 @@
             "auto",
             "scale"
         ],
-        "base_estimator__kernel": [
+        "estimator__kernel": [
             "rbf"
         ],
-        "base_estimator__multiclass_strategy": [
+        "estimator__multiclass_strategy": [
             "ovr"
         ]
     },
@@ -84,20 +84,20 @@
         "n_estimators": [
             100
         ],
-        "base_estimator__C": [
+        "estimator__C": [
             0.05,
             0.2,
             1.0,
             8.25
         ],
-        "base_estimator__gamma": [
+        "estimator__gamma": [
             0.1,
             "scale"
         ],
-        "base_estimator__kernel": [
+        "estimator__kernel": [
             "poly"
         ],
-        "base_estimator__multiclass_strategy": [
+        "estimator__multiclass_strategy": [
             "ovo",
             "ovr"
         ]

benchmark/tests/test_files/be_init_project.test

@@ -4,6 +4,8 @@ Creating folder test_project/hidden_results
 Creating folder test_project/exreport
 Creating folder test_project/exreport/exreport_output
 Creating folder test_project/img
+Creating folder test_project/excel
+Creating folder test_project/sql
 Done!
 Please, edit .env file with your settings and add a datasets folder
 with an all.txt file with the datasets you want to use.

benchmark/tests/test_files/be_list_compare_fault.test

@@ -0,0 +1,8 @@
+ #  Date       File                                                            Score    Time(h) Title
+=== ========== =============================================================== ======== ======= ============================================
+  0 2022-04-20 results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.json           0.04341   6.275 Gridsearched hyperparams v022.1b random_init
+  1 2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest
+  2 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
+  3 2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
+  4 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched hyperparameters
+results/best_results_accuracy_ODTE.json does not exist

benchmark/tests/test_files/be_list_report.test

@@ -6,7 +6,7 @@
 *************************************************************************************************************************
 * STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-11-01 19:17:07             *
 * default B                                                                                                             *
-* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False  Discretized: False                          *
 * Execution took 4115.04 seconds,   1.14 hours, on macbook-pro                                                          *
 * Score is accuracy                                                                                                     *
 *************************************************************************************************************************
@@ -14,7 +14,8 @@
 Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score           Time              Hyperparameters 
 ============================== ====== ===== === ======= ======= ======= =============== ================= =============== 
 balance-scale                     625     4   3   18.78    9.88    5.90 0.970000±0.0020   0.233304±0.0481 {'max_features': 'auto', 'splitter': 'mutual'} 
-balloons                           16     4   2    4.72    2.86    2.78 0.556667±0.2941   0.021352±0.0058 {'max_features': 'auto', 'splitter': 'mutual'} 
+balloons                           16     4   2    4.72    2.86    2.78 0.556667±0.2941✗  0.021352±0.0058 {'max_features': 'auto', 'splitter': 'mutual'} 
 *************************************************************************************************************************
+* ✗ Less than or equal to ZeroR...:  1                                                                                  *
 * accuracy compared to STree_default (liblinear-ovr) .:  0.0379                                                         *
 *************************************************************************************************************************

benchmark/tests/test_files/be_list_report_excel.test

@@ -4,4 +4,4 @@
   1 2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json       0.04158   0.943 default A
   2 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json       0.04544   0.173 With gridsearched hyperparameters
 Added results/results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json to some_results.xlsx
-Generated file: some_results.xlsx
+Generated file: excel/some_results.xlsx

benchmark/tests/test_files/be_list_report_excel_2.test

@@ -5,4 +5,4 @@
   2 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json       0.04544   0.173 With gridsearched hyperparameters
 Added results/results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json to some_results.xlsx
 Added results/results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json to some_results.xlsx
-Generated file: some_results.xlsx
+Generated file: excel/some_results.xlsx

benchmark/tests/test_files/be_main_best.test

@@ -1,7 +1,7 @@
 *************************************************************************************************************************
 * STree ver. 1.2.4 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2022-05-09 00:15:25             *
 * test                                                                                                                  *
-* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False  Discretized: False                          *
 * Execution took    0.80 seconds,   0.00 hours, on iMac27                                                               *
 * Score is accuracy                                                                                                     *
 *************************************************************************************************************************
@@ -9,8 +9,9 @@
 Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score           Time              Hyperparameters 
 ============================== ====== ===== === ======= ======= ======= =============== ================= =============== 
 balance-scale                      625     4   3   23.32   12.16    6.44 0.840160±0.0304   0.013745±0.0019 {'splitter': 'best', 'max_features': 'auto'} 
-balloons                            16     4   2    3.00    2.00    2.00 0.860000±0.2850   0.000388±0.0000 {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+balloons                            16     4   2    3.00    2.00    2.00 0.860000±0.2850   0.000388±0.0000 {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'} 
 *************************************************************************************************************************
+* ➶ Better than ZeroR + 10.0%.....:  1                                                                                  *
 * accuracy compared to STree_default (liblinear-ovr) .:  0.0422                                                         *
 *************************************************************************************************************************
 Results in results/results_accuracy_STree_iMac27_2022-05-09_00:15:25_0.json

benchmark/tests/test_files/be_main_complete.test

@@ -1,7 +1,7 @@
 *************************************************************************************************************************
 * STree ver. 1.2.4 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2022-05-08 20:14:43             *
 * test                                                                                                                  *
-* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False  Discretized: False                          *
 * Execution took    0.48 seconds,   0.00 hours, on iMac27                                                               *
 * Score is accuracy                                                                                                     *
 *************************************************************************************************************************
@@ -11,6 +11,7 @@ Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score
 balance-scale                     625     4   3   17.36    9.18    6.18 0.908480±0.0247   0.007388±0.0013 {}              
 balloons                           16     4   2    4.64    2.82    2.66 0.663333±0.3009   0.000664±0.0002 {}              
 *************************************************************************************************************************
+* ➶ Better than ZeroR + 10.0%.....:  1                                                                                  *
 * accuracy compared to STree_default (liblinear-ovr) .:  0.0390                                                         *
 *************************************************************************************************************************
 Results in results/results_accuracy_STree_iMac27_2022-05-08_20:14:43_0.json

benchmark/tests/test_files/be_main_dataset.test

@@ -1,15 +1,16 @@
 *************************************************************************************************************************
 * STree ver. 1.2.4 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2022-05-08 19:38:28             *
 * Test with only one dataset                                                                                            *
-* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False  Discretized: False                          *
 * Execution took    0.06 seconds,   0.00 hours, on iMac27                                                               *
 * Score is accuracy                                                                                                     *
 *************************************************************************************************************************
 
 Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score           Time              Hyperparameters 
 ============================== ====== ===== === ======= ======= ======= =============== ================= =============== 
-balloons                           16     4   2    4.64    2.82    2.66 0.663333±0.3009   0.000671±0.0001 {}              
+balloons                           16     4   2    4.64    2.82    2.66 0.663333±0.3009➶  0.000671±0.0001 {}              
 *************************************************************************************************************************
+* ➶ Better than ZeroR + 10.0%.....:  1                                                                                  *
 * accuracy compared to STree_default (liblinear-ovr) .:  0.0165                                                         *
 *************************************************************************************************************************
 Partial result file removed: results/results_accuracy_STree_iMac27_2022-05-08_19:38:28_0.json

benchmark/tests/test_files/be_main_grid.test

@@ -1,7 +1,7 @@
 *************************************************************************************************************************
 * STree ver. 1.2.4 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2022-05-09 00:21:06             *
 * test                                                                                                                  *
-* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False  Discretized: False                          *
 * Execution took    0.89 seconds,   0.00 hours, on iMac27                                                               *
 * Score is accuracy                                                                                                     *
 *************************************************************************************************************************
@@ -11,6 +11,7 @@ Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score
 balance-scale                     625     4   3   26.12   13.56    7.94 0.910720±0.0249   0.015852±0.0027 {'C': 1.0, 'kernel': 'liblinear', 'multiclass_strategy': 'ovr'} 
 balloons                           16     4   2    4.64    2.82    2.66 0.663333±0.3009   0.000640±0.0001 {'C': 1.0, 'kernel': 'linear', 'multiclass_strategy': 'ovr'} 
 *************************************************************************************************************************
+* ➶ Better than ZeroR + 10.0%.....:  1                                                                                  *
 * accuracy compared to STree_default (liblinear-ovr) .:  0.0391                                                         *
 *************************************************************************************************************************
 Results in results/results_accuracy_STree_iMac27_2022-05-09_00:21:06_0.json

benchmark/tests/test_files/excel.test

@@ -3,12 +3,12 @@
 3;1;" Score is accuracy"
 3;2;" Execution time"
 3;5;" 624.25 s"
-3;7;" "
+3;7;"Platform"
-3;8;"Platform"
 3;9;"iMac27"
-3;10;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+3;11;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
 4;5;"  0.17 h"
-4;10;"Stratified: False"
+4;11;"Stratified: False"
+4;13;"Discretized: False"
 6;1;"Dataset"
 6;2;"Samples"
 6;3;"Features"
@@ -17,10 +17,11 @@
 6;6;"Leaves"
 6;7;"Depth"
 6;8;"Score"
-6;9;"Score Std."
+6;9;"Stat"
-6;10;"Time"
+6;10;"Score Std."
-6;11;"Time Std."
+6;11;"Time"
-6;12;"Hyperparameters"
+6;12;"Time Std."
+6;13;"Hyperparameters"
 7;1;"balance-scale"
 7;2;"625"
 7;3;"4"
@@ -29,10 +30,11 @@
 7;6;"4"
 7;7;"3"
 7;8;"0.97056"
-7;9;"0.0150468069702512"
+7;9;" "
-7;10;"0.01404867172241211"
+7;10;"0.0150468069702512"
-7;11;"0.002026269126958884"
+7;11;"0.01404867172241211"
-7;12;"{'C': 10000.0, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'}"
+7;12;"0.002026269126958884"
+7;13;"{'C': 10000, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'}"
 8;1;"balloons"
 8;2;"16"
 8;3;"4"
@@ -41,8 +43,12 @@
 8;6;"2"
 8;7;"2"
 8;8;"0.86"
-8;9;"0.2850146195080759"
+8;9;"➶"
-8;10;"0.0008541679382324218"
+8;10;"0.2850146195080759"
-8;11;"3.629469326417878e-05"
+8;11;"0.0008541679382324218"
-8;12;"{'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'}"
+8;12;"3.629469326417878e-05"
-10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0454"
+8;13;"{'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'}"
+11;2;"➶"
+11;3;"1"
+11;4;"Better than ZeroR + 10.0%"
+13;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0454"

benchmark/tests/test_files/excel2.test

@@ -3,12 +3,12 @@
 3;1;" Score is accuracy"
 3;2;" Execution time"
 3;5;"3,395.01 s"
-3;7;" "
+3;7;"Platform"
-3;8;"Platform"
 3;9;"iMac27"
-3;10;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+3;11;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
 4;5;"  0.94 h"
-4;10;"Stratified: False"
+4;11;"Stratified: False"
+4;13;"Discretized: False"
 6;1;"Dataset"
 6;2;"Samples"
 6;3;"Features"
@@ -17,10 +17,11 @@
 6;6;"Leaves"
 6;7;"Depth"
 6;8;"Score"
-6;9;"Score Std."
+6;9;"Stat"
-6;10;"Time"
+6;10;"Score Std."
-6;11;"Time Std."
+6;11;"Time"
-6;12;"Hyperparameters"
+6;12;"Time Std."
+6;13;"Hyperparameters"
 7;1;"balance-scale"
 7;2;"625"
 7;3;"4"
@@ -29,10 +30,11 @@
 7;6;"5.9"
 7;7;"5.9"
 7;8;"0.98"
-7;9;"0.001"
+7;9;" "
-7;10;"0.2852065515518188"
+7;10;"0.001"
-7;11;"0.06031593282605064"
+7;11;"0.2852065515518188"
-7;12;"{'splitter': 'best', 'max_features': 'auto'}"
+7;12;"0.06031593282605064"
+7;13;"{'splitter': 'best', 'max_features': 'auto'}"
 8;1;"balloons"
 8;2;"16"
 8;3;"4"
@@ -41,8 +43,12 @@
 8;6;"2.56"
 8;7;"2.56"
 8;8;"0.695"
-8;9;"0.2756860130252853"
+8;9;"➶"
-8;10;"0.02120100021362305"
+8;10;"0.2756860130252853"
-8;11;"0.003526023309468471"
+8;11;"0.02120100021362305"
-8;12;"{'splitter': 'best', 'max_features': 'auto'}"
+8;12;"0.003526023309468471"
-10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0416"
+8;13;"{'splitter': 'best', 'max_features': 'auto'}"
+11;2;"➶"
+11;3;"1"
+11;4;"Better than ZeroR + 10.0%"
+13;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0416"

benchmark/tests/test_files/excel_add_ODTE.test

@@ -3,12 +3,12 @@
 3;1;" Score is accuracy"
 3;2;" Execution time"
 3;5;"22,591.47 s"
-3;7;" "
+3;7;"Platform"
-3;8;"Platform"
 3;9;"Galgo"
-3;10;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+3;11;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
 4;5;"  6.28 h"
-4;10;"Stratified: False"
+4;11;"Stratified: False"
+4;13;"Discretized: False"
 6;1;"Dataset"
 6;2;"Samples"
 6;3;"Features"
@@ -17,10 +17,11 @@
 6;6;"Leaves"
 6;7;"Depth"
 6;8;"Score"
-6;9;"Score Std."
+6;9;"Stat"
-6;10;"Time"
+6;10;"Score Std."
-6;11;"Time Std."
+6;11;"Time"
-6;12;"Hyperparameters"
+6;12;"Time Std."
+6;13;"Hyperparameters"
 7;1;"balance-scale"
 7;2;"625"
 7;3;"4"
@@ -29,10 +30,11 @@
 7;6;"4.180599999999999"
 7;7;"3.536"
 7;8;"0.96352"
-7;9;"0.02494974148162661"
+7;9;" "
-7;10;"0.3166321754455567"
+7;10;"0.02494974148162661"
-7;11;"0.1991881389525559"
+7;11;"0.3166321754455567"
-7;12;"{'base_estimator__C': 57, 'base_estimator__gamma': 0.1, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
+7;12;"0.1991881389525559"
+7;13;"{'base_estimator__C': 57, 'base_estimator__gamma': 0.1, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
 8;1;"balloons"
 8;2;"16"
 8;3;"4"
@@ -41,8 +43,12 @@
 8;6;"1.9976"
 8;7;"1.9976"
 8;8;"0.785"
-8;9;"0.2461311755051675"
+8;9;"➶"
-8;10;"0.1156062078475952"
+8;10;"0.2461311755051675"
-8;11;"0.0127842418285999"
+8;11;"0.1156062078475952"
-8;12;"{'base_estimator__C': 5, 'base_estimator__gamma': 0.14, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
+8;12;"0.0127842418285999"
-10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0434"
+8;13;"{'base_estimator__C': 5, 'base_estimator__gamma': 0.14, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
+11;2;"➶"
+11;3;"1"
+11;4;"Better than ZeroR + 10.0%"
+13;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0434"

benchmark/tests/test_files/excel_add_STree.test

@@ -3,12 +3,12 @@
 3;1;" Score is accuracy"
 3;2;" Execution time"
 3;5;"3,395.01 s"
-3;7;" "
+3;7;"Platform"
-3;8;"Platform"
 3;9;"iMac27"
-3;10;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+3;11;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
 4;5;"  0.94 h"
-4;10;"Stratified: False"
+4;11;"Stratified: False"
+4;13;"Discretized: False"
 6;1;"Dataset"
 6;2;"Samples"
 6;3;"Features"
@@ -17,9 +17,11 @@
 6;6;"Leaves"
 6;7;"Depth"
 6;8;"Score"
-6;9;"Score Std."
+6;9;"Stat"
-6;10;"Time"
+6;10;"Score Std."
-6;11;"Time Std."
+6;11;"Time"
+6;12;"Time Std."
+6;13;"Hyperparameters"
 7;1;"balance-scale"
 7;2;"625"
 7;3;"4"
@@ -28,9 +30,11 @@
 7;6;"5.9"
 7;7;"5.9"
 7;8;"0.98"
-7;9;"0.001"
+7;9;" "
-7;10;"0.2852065515518188"
+7;10;"0.001"
-7;11;"0.06031593282605064"
+7;11;"0.2852065515518188"
+7;12;"0.06031593282605064"
+7;13;"{'splitter': 'best', 'max_features': 'auto'}"
 8;1;"balloons"
 8;2;"16"
 8;3;"4"
@@ -39,8 +43,12 @@
 8;6;"2.56"
 8;7;"2.56"
 8;8;"0.695"
-8;9;"0.2756860130252853"
+8;9;"➶"
-8;10;"0.02120100021362305"
+8;10;"0.2756860130252853"
-8;11;"0.003526023309468471"
+8;11;"0.02120100021362305"
-8;12;"{'splitter': 'best', 'max_features': 'auto'}"
+8;12;"0.003526023309468471"
-10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0416"
+8;13;"{'splitter': 'best', 'max_features': 'auto'}"
+11;2;"➶"
+11;3;"1"
+11;4;"Better than ZeroR + 10.0%"
+13;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0416"

benchmark/tests/test_files/excel_compared.test

@@ -3,10 +3,12 @@
 3;1;" Score is accuracy"
 3;2;" Execution time"
 3;5;" 624.25 s"
-3;8;"Platform"
+3;7;"Platform"
 3;9;"iMac27"
-3;10;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+3;11;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
-4;10;"Stratified: False"
+4;5;"  0.17 h"
+4;11;"Stratified: False"
+4;13;"Discretized: False"
 6;1;"Dataset"
 6;2;"Samples"
 6;3;"Features"
@@ -21,32 +23,32 @@
 6;12;"Time Std."
 6;13;"Hyperparameters"
 7;1;"balance-scale"
-7;2;625
+7;2;"625"
-7;3;4
+7;3;"4"
-7;4;3
+7;4;"3"
-7;5;7
+7;5;"7"
-7;6;4
+7;6;"4"
-7;7;3
+7;7;"3"
-7;8;0.97056
+7;8;"0.97056"
 7;9;" "
-7;10;0.0150468069702512
+7;10;"0.0150468069702512"
-7;11;0.01404867172241211
+7;11;"0.01404867172241211"
-7;12;0.002026269126958884
+7;12;"0.002026269126958884"
-7;13;"{'C': 10000.0, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'}"
+7;13;"{'C': 10000, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'}"
 8;1;"balloons"
-8;2;16
+8;2;"16"
-8;3;4
+8;3;"4"
-8;4;2
+8;4;"2"
-8;5;3
+8;5;"3"
-8;6;2
+8;6;"2"
-8;7;2
+8;7;"2"
-8;8;0.86
+8;8;"0.86"
 8;9;"✔"
-8;10;0.2850146195080759
+8;10;"0.2850146195080759"
-8;11;0.0008541679382324218
+8;11;"0.0008541679382324218"
-8;12;3.629469326417878e-05
+8;12;"3.629469326417878e-05"
-8;13;"{'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'}"
+8;13;"{'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'}"
 11;2;"✔"
-11;3;1
+11;3;"1"
 11;4;"Equal to best"
 13;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0454"

benchmark/tests/test_files/exreport_excel_Datasets.test

@@ -1,25 +1,28 @@
-1;1;"Datasets used in benchmark ver. 0.2.0"
+1;1;"Datasets used in benchmark ver. 1.0.1"
 2;1;" Default score accuracy"
 2;2;"Cross validation"
-2;5;"5 Folds"
+2;6;"5 Folds"
 3;2;"Stratified"
-3;5;"False"
+3;6;"False"
 4;2;"Discretized"
-4;5;"False"
+4;6;"False"
 5;2;"Seeds"
-5;5;"[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+5;6;"[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
 6;1;"Dataset"
 6;2;"Samples"
 6;3;"Features"
-6;4;"Classes"
+6;4;"Continuous"
-6;5;"Balance"
+6;5;"Classes"
+6;6;"Balance"
 7;1;"balance-scale"
 7;2;"625"
 7;3;"4"
-7;4;"3"
+7;4;"0"
-7;5;" 7.84%/ 46.08%/ 46.08%"
+7;5;"3"
+7;6;" 7.84% (49) / 46.08% (288) / 46.08% (288) "
 8;1;"balloons"
 8;2;"16"
 8;3;"4"
-8;4;"2"
+8;4;"0"
-8;5;"56.25%/ 43.75%"
+8;5;"2"
+8;6;"56.25% (9) / 43.75% (7) "

benchmark/tests/test_files/exreport_excel_ODTE.test

@@ -3,12 +3,12 @@
 3;1;" Score is accuracy"
 3;2;" Execution time"
 3;5;"22,591.47 s"
-3;7;" "
+3;7;"Platform"
-3;8;"Platform"
 3;9;"Galgo"
-3;10;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+3;11;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
 4;5;"  6.28 h"
-4;10;"Stratified: False"
+4;11;"Stratified: False"
+4;13;"Discretized: False"
 6;1;"Dataset"
 6;2;"Samples"
 6;3;"Features"
@@ -17,10 +17,11 @@
 6;6;"Leaves"
 6;7;"Depth"
 6;8;"Score"
-6;9;"Score Std."
+6;9;"Stat"
-6;10;"Time"
+6;10;"Score Std."
-6;11;"Time Std."
+6;11;"Time"
-6;12;"Hyperparameters"
+6;12;"Time Std."
+6;13;"Hyperparameters"
 7;1;"balance-scale"
 7;2;"625"
 7;3;"4"
@@ -29,10 +30,11 @@
 7;6;"4.180599999999999"
 7;7;"3.536"
 7;8;"0.96352"
-7;9;"0.02494974148162661"
+7;9;" "
-7;10;"0.3166321754455567"
+7;10;"0.02494974148162661"
-7;11;"0.1991881389525559"
+7;11;"0.3166321754455567"
-7;12;"{'base_estimator__C': 57, 'base_estimator__gamma': 0.1, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
+7;12;"0.1991881389525559"
+7;13;"{'base_estimator__C': 57, 'base_estimator__gamma': 0.1, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
 8;1;"balloons"
 8;2;"16"
 8;3;"4"
@@ -41,8 +43,12 @@
 8;6;"1.9976"
 8;7;"1.9976"
 8;8;"0.785"
-8;9;"0.2461311755051675"
+8;9;"➶"
-8;10;"0.1156062078475952"
+8;10;"0.2461311755051675"
-8;11;"0.0127842418285999"
+8;11;"0.1156062078475952"
-8;12;"{'base_estimator__C': 5, 'base_estimator__gamma': 0.14, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
+8;12;"0.0127842418285999"
-10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0434"
+8;13;"{'base_estimator__C': 5, 'base_estimator__gamma': 0.14, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
+11;2;"➶"
+11;3;"1"
+11;4;"Better than ZeroR + 10.0%"
+13;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0434"

benchmark/tests/test_files/exreport_excel_RandomForest.test

@@ -3,12 +3,12 @@
 3;1;" Score is accuracy"
 3;2;" Execution time"
 3;5;" 272.74 s"
-3;7;" "
+3;7;"Platform"
-3;8;"Platform"
 3;9;"iMac27"
-3;10;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+3;11;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
 4;5;"  0.08 h"
-4;10;"Stratified: False"
+4;11;"Stratified: False"
+4;13;"Discretized: False"
 6;1;"Dataset"
 6;2;"Samples"
 6;3;"Features"
@@ -17,10 +17,11 @@
 6;6;"Leaves"
 6;7;"Depth"
 6;8;"Score"
-6;9;"Score Std."
+6;9;"Stat"
-6;10;"Time"
+6;10;"Score Std."
-6;11;"Time Std."
+6;11;"Time"
-6;12;"Hyperparameters"
+6;12;"Time Std."
+6;13;"Hyperparameters"
 7;1;"balance-scale"
 7;2;"625"
 7;3;"4"
@@ -29,10 +30,11 @@
 7;6;"98.42"
 7;7;"10.6814"
 7;8;"0.83616"
-7;9;"0.02649630917694009"
+7;9;" "
-7;10;"0.08222018241882324"
+7;10;"0.02649630917694009"
-7;11;"0.001302632681512063"
+7;11;"0.08222018241882324"
-7;12;"{}"
+7;12;"0.001302632681512063"
+7;13;"{}"
 8;1;"balloons"
 8;2;"16"
 8;3;"4"
@@ -41,8 +43,12 @@
 8;6;"4.58"
 8;7;"3.0982"
 8;8;"0.625"
-8;9;"0.249582985531199"
+8;9;"➶"
-8;10;"0.07016648769378662"
+8;10;"0.249582985531199"
-8;11;"0.002460508923990468"
+8;11;"0.07016648769378662"
-8;12;"{}"
+8;12;"0.002460508923990468"
-10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0363"
+8;13;"{}"
+11;2;"➶"
+11;3;"1"
+11;4;"Better than ZeroR + 10.0%"
+13;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0363"

benchmark/tests/test_files/exreport_excel_STree.test

@@ -3,12 +3,12 @@
 3;1;" Score is accuracy"
 3;2;" Execution time"
 3;5;" 624.25 s"
-3;7;" "
+3;7;"Platform"
-3;8;"Platform"
 3;9;"iMac27"
-3;10;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+3;11;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
 4;5;"  0.17 h"
-4;10;"Stratified: False"
+4;11;"Stratified: False"
+4;13;"Discretized: False"
 6;1;"Dataset"
 6;2;"Samples"
 6;3;"Features"
@@ -17,10 +17,11 @@
 6;6;"Leaves"
 6;7;"Depth"
 6;8;"Score"
-6;9;"Score Std."
+6;9;"Stat"
-6;10;"Time"
+6;10;"Score Std."
-6;11;"Time Std."
+6;11;"Time"
-6;12;"Hyperparameters"
+6;12;"Time Std."
+6;13;"Hyperparameters"
 7;1;"balance-scale"
 7;2;"625"
 7;3;"4"
@@ -29,10 +30,11 @@
 7;6;"4"
 7;7;"3"
 7;8;"0.97056"
-7;9;"0.0150468069702512"
+7;9;" "
-7;10;"0.01404867172241211"
+7;10;"0.0150468069702512"
-7;11;"0.002026269126958884"
+7;11;"0.01404867172241211"
-7;12;"{'C': 10000.0, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'}"
+7;12;"0.002026269126958884"
+7;13;"{'C': 10000, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'}"
 8;1;"balloons"
 8;2;"16"
 8;3;"4"
@@ -41,8 +43,12 @@
 8;6;"2"
 8;7;"2"
 8;8;"0.86"
-8;9;"0.2850146195080759"
+8;9;"➶"
-8;10;"0.0008541679382324218"
+8;10;"0.2850146195080759"
-8;11;"3.629469326417878e-05"
+8;11;"0.0008541679382324218"
-8;12;"{'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'}"
+8;12;"3.629469326417878e-05"
-10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0454"
+8;13;"{'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'}"
+11;2;"➶"
+11;3;"1"
+11;4;"Better than ZeroR + 10.0%"
+13;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0454"

benchmark/tests/test_files/report.test

@@ -1,15 +1,16 @@
 *************************************************************************************************************************
 * STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07             *
 * With gridsearched hyperparameters                                                                                     *
-* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False  Discretized: False                          *
 * Execution took  624.25 seconds,   0.17 hours, on iMac27                                                               *
 * Score is accuracy                                                                                                     *
 *************************************************************************************************************************
 
 Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score           Time              Hyperparameters 
 ============================== ====== ===== === ======= ======= ======= =============== ================= =============== 
-balance-scale                     625     4   3    7.00    4.00    3.00 0.970560±0.0150   0.014049±0.0020 {'C': 10000.0, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+balance-scale                     625     4   3    7.00    4.00    3.00 0.970560±0.0150   0.014049±0.0020 {'C': 10000, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'} 
-balloons                           16     4   2    3.00    2.00    2.00 0.860000±0.2850   0.000854±0.0000 {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+balloons                           16     4   2    3.00    2.00    2.00 0.860000±0.2850➶  0.000854±0.0000 {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'} 
 *************************************************************************************************************************
+* ➶ Better than ZeroR + 10.0%.....:  1                                                                                  *
 * accuracy compared to STree_default (liblinear-ovr) .:  0.0454                                                         *
 *************************************************************************************************************************

benchmark/tests/test_files/report_best.test

@@ -5,7 +5,7 @@
 Dataset                        Score    File/Message                                                                 Hyperparameters                               
 ============================== ======== ============================================================================ ============================================= 
 balance-scale                  0.980000 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json                     {'splitter': 'best', 'max_features': 'auto'} 
-balloons                       0.860000 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json                     {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+balloons                       0.860000 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json                     {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'} 
 ******************************************************************************************************************************************************************
 * accuracy compared to STree_default (liblinear-ovr) .:  0.0457                                                                                                  *
 ******************************************************************************************************************************************************************

benchmark/tests/test_files/report_compared.test

@@ -1,16 +1,16 @@
 *************************************************************************************************************************
 * STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07             *
 * With gridsearched hyperparameters                                                                                     *
-* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False  Discretized: False                          *
 * Execution took  624.25 seconds,   0.17 hours, on iMac27                                                               *
 * Score is accuracy                                                                                                     *
 *************************************************************************************************************************
 
 Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score           Time              Hyperparameters 
 ============================== ====== ===== === ======= ======= ======= =============== ================= =============== 
-balance-scale                     625     4   3    7.00    4.00    3.00 0.970560±0.0150   0.014049±0.0020 {'C': 10000.0, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+balance-scale                     625     4   3    7.00    4.00    3.00 0.970560±0.0150   0.014049±0.0020 {'C': 10000, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'} 
-balloons                           16     4   2    3.00    2.00    2.00 0.860000±0.2850✔  0.000854±0.0000 {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+balloons                           16     4   2    3.00    2.00    2.00 0.860000±0.2850✔  0.000854±0.0000 {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000, 'multiclass_strategy': 'ovr'} 
 *************************************************************************************************************************
-* ✔ Equal to best .....:  1                                                                                             *
+* ✔ Equal to best.................:  1                                                                                  *
 * accuracy compared to STree_default (liblinear-ovr) .:  0.0454                                                         *
 *************************************************************************************************************************