Add first select table with data

Continuous features

.env.dist

@@ -4,3 +4,5 @@ n_folds=5
 model=ODTE
 stratified=0
 source_data=Tanveer
+seeds=[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]
+discretize=0

.flake8

@@ -1,2 +1,3 @@
 [flake8]
 exclude = .git,__init__.py
+ignore = E203, W503

.github/workflows/build.yml

@@ -8,7 +8,7 @@ jobs:
     name: Build
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         with:
           fetch-depth: 0
       - run: echo "project_version=$(git describe --tags --abbrev=0)" >> $GITHUB_ENV
@@ -22,7 +22,8 @@ jobs:
             -Dsonar.python.version=3.10
         # If you wish to fail your job when the Quality Gate is red, uncomment the
         # following lines. This would typically be used to fail a deployment.
-      - uses: sonarsource/sonarqube-quality-gate-action@master
+      #- uses: sonarsource/sonarqube-quality-gate-action@master
-        timeout-minutes: 5
+      #  timeout-minutes: 5
-        env:
+      #  env:
-          SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
+      #    SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
+      #    SONAR_HOST_URL: ${{ secrets.SONAR_HOST_URL }}

.github/workflows/main.yml

@@ -12,13 +12,13 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-latest, ubuntu-latest]
+        os: [ubuntu-latest]
         python: ["3.10"]
 
     steps:
-      - uses: actions/checkout@v2
+      - 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
@@ -43,6 +43,7 @@ jobs:
           pip install -q --upgrade pip
           pip install -q -r requirements.txt
           pip install -q --upgrade codecov coverage black flake8
+          git clone https://github.com/Doctorado-ML/bayesclass.git
       - name: Lint
         run: |
           black --check --diff benchmark
@@ -52,7 +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

@@ -1,7 +1,7 @@
 [![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)](http://haystack.local:25000/dashboard?id=benchmark)
+[![Quality Gate Status](https://sonar.rmontanana.es/api/project_badges/measure?project=benchmark&metric=alert_status&token=336a6e501988888543c3153baa91bad4b9914dd2)](https://sonar.rmontanana.es/dashboard?id=benchmark)
-[![Technical Debt](https://haystack.rmontanana.es:25000/api/project_badges/measure?project=benchmark&metric=sqale_index&token=336a6e501988888543c3153baa91bad4b9914dd2)](http://haystack.local:25000/dashboard?id=benchmark)
+[![Technical Debt](https://sonar.rmontanana.es/api/project_badges/measure?project=benchmark&metric=sqale_index&token=336a6e501988888543c3153baa91bad4b9914dd2)](https://sonar.rmontanana.es/dashboard?id=benchmark)
 ![https://img.shields.io/badge/python-3.8%2B-blue](https://img.shields.io/badge/python-3.8%2B-brightgreen)
 
 # benchmark
@@ -34,7 +34,7 @@ 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

@@ -36,6 +36,7 @@ class EnvDefault(argparse.Action):
         self, envvar, required=True, default=None, mandatory=False, **kwargs
     ):
         self._args = EnvData.load()
+        self._overrides = {}
         if required and not mandatory:
             default = self._args[envvar]
             required = False
@@ -47,24 +48,27 @@ class EnvDefault(argparse.Action):
         setattr(namespace, self.dest, values)
 
 
-class Arguments:
+class Arguments(argparse.ArgumentParser):
-    def __init__(self):
+    def __init__(self, *args, **kwargs):
-        self.ap = argparse.ArgumentParser()
+        super().__init__(*args, **kwargs)
         models_data = Models.define_models(random_state=0)
+        self._overrides = {}
+        self._subparser = None
         self.parameters = {
-            "best": [
+            "best_paramfile": [
-                ("-b", "--best"),
+                ("-b", "--best_paramfile"),
                 {
-                    "type": str,
+                    "action": "store_true",
                     "required": False,
-                    "help": "best results of models",
+                    "default": False,
+                    "help": "Use best hyperparams file?",
                 },
             ],
             "color": [
                 ("-c", "--color"),
                 {
-                    "type": bool,
                     "required": False,
+                    "action": "store_true",
                     "default": False,
                     "help": "use colors for the tree",
                 },
@@ -72,8 +76,9 @@ class Arguments:
             "compare": [
                 ("-c", "--compare"),
                 {
-                    "type": bool,
+                    "action": "store_true",
                     "required": False,
+                    "default": False,
                     "help": "Compare accuracy with best results",
                 },
             ],
@@ -81,45 +86,57 @@ class Arguments:
                 ("-d", "--dataset"),
                 {
                     "type": str,
+                    "envvar": "dataset",  # for compatiblity with EnvDefault
+                    "action": EnvDefault,
                     "required": False,
                     "help": "dataset to work with",
                 },
             ],
+            "discretize": [
+                ("--discretize",),
+                {
+                    "action": EnvDefault,
+                    "envvar": "discretize",
+                    "required": True,
+                    "help": "Discretize dataset",
+                    "const": "1",
+                    "nargs": "?",
+                },
+            ],
             "excel": [
                 ("-x", "--excel"),
                 {
-                    "type": bool,
                     "required": False,
+                    "action": "store_true",
                     "default": False,
                     "help": "Generate Excel File",
                 },
             ],
-            "file": [
+            "fit_features": [
-                ("-f", "--file"),
+                ("--fit_features",),
-                {"type": str, "required": False, "help": "Result file"},
-            ],
-            "grid": [
-                ("-g", "--grid"),
                 {
-                    "type": str,
+                    "action": EnvDefault,
-                    "required": False,
+                    "envvar": "fit_features",
-                    "help": "grid results of model",
+                    "required": True,
+                    "help": "Include features in fit call",
+                    "const": "1",
+                    "nargs": "?",
                 },
             ],
             "grid_paramfile": [
                 ("-g", "--grid_paramfile"),
                 {
-                    "type": bool,
                     "required": False,
+                    "action": "store_true",
                     "default": False,
-                    "help": "Use best hyperparams file?",
+                    "help": "Use grid output hyperparams file?",
                 },
             ],
             "hidden": [
                 ("--hidden",),
                 {
-                    "type": str,
                     "required": False,
+                    "action": "store_true",
                     "default": False,
                     "help": "Show hidden results",
                 },
@@ -128,6 +145,15 @@ class Arguments:
                 ("-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"),
                 {
@@ -140,8 +166,8 @@ class Arguments:
             "lose": [
                 ("-l", "--lose"),
                 {
-                    "type": bool,
                     "default": False,
+                    "action": "store_true",
                     "required": False,
                     "help": "show lose results",
                 },
@@ -178,9 +204,10 @@ class Arguments:
             "nan": [
                 ("--nan",),
                 {
-                    "type": bool,
+                    "action": "store_true",
                     "required": False,
-                    "help": "Move nan results to hidden folder",
+                    "default": False,
+                    "help": "List nan results to hidden folder",
                 },
             ],
             "number": [
@@ -202,15 +229,6 @@ class Arguments:
                     "help": "number of folds",
                 },
             ],
-            "paramfile": [
-                ("-f", "--paramfile"),
-                {
-                    "type": bool,
-                    "required": False,
-                    "default": False,
-                    "help": "Use best hyperparams file?",
-                },
-            ],
             "platform": [
                 ("-P", "--platform"),
                 {
@@ -224,7 +242,7 @@ class Arguments:
             "quiet": [
                 ("-q", "--quiet"),
                 {
-                    "type": bool,
+                    "action": "store_true",
                     "required": False,
                     "default": False,
                 },
@@ -232,7 +250,7 @@ class Arguments:
             "report": [
                 ("-r", "--report"),
                 {
-                    "type": bool,
+                    "action": "store_true",
                     "default": False,
                     "required": False,
                     "help": "Report results",
@@ -250,23 +268,29 @@ class Arguments:
             ],
             "sql": [
                 ("-q", "--sql"),
-                {"type": bool, "required": False, "help": "Generate SQL File"},
+                {
+                    "required": False,
+                    "action": "store_true",
+                    "default": False,
+                    "help": "Generate SQL File",
+                },
             ],
             "stratified": [
                 ("-t", "--stratified"),
                 {
                     "action": EnvDefault,
                     "envvar": "stratified",
-                    "type": str,
                     "required": True,
                     "help": "Stratified",
+                    "const": "1",
+                    "nargs": "?",
                 },
             ],
             "tex_output": [
                 ("-t", "--tex-output"),
                 {
-                    "type": bool,
                     "required": False,
+                    "action": "store_true",
                     "default": False,
                     "help": "Generate Tex file with the table",
                 },
@@ -278,8 +302,8 @@ class Arguments:
             "win": [
                 ("-w", "--win"),
                 {
-                    "type": bool,
                     "default": False,
+                    "action": "store_true",
                     "required": False,
                     "help": "show win results",
                 },
@@ -287,12 +311,43 @@ class Arguments:
         }
 
     def xset(self, *arg_name, **kwargs):
-        names, default = self.parameters[arg_name[0]]
+        names, parameters = self.parameters[arg_name[0]]
-        self.ap.add_argument(
+        if "overrides" in kwargs:
+            self._overrides[names[0]] = (kwargs["overrides"], kwargs["const"])
+            del kwargs["overrides"]
+        self.add_argument(
             *names,
-            **{**default, **kwargs},
+            **{**parameters, **kwargs},
         )
         return self
 
+    def add_subparser(
+        self, dest="subcommand", help_text="help for subcommand"
+    ):
+        self._subparser = self.add_subparsers(dest=dest, help=help_text)
+
+    def add_subparsers_options(self, subparser, arguments):
+        command, help_text = subparser
+        parser = self._subparser.add_parser(command, help=help_text)
+        for name, args in arguments:
+            try:
+                names, parameters = self.parameters[name]
+            except KeyError:
+                names = (name,)
+                parameters = {}
+            # Order of args is important
+            parser.add_argument(*names, **{**args, **parameters})
+
+    def add_exclusive(self, hyperparameters, required=False):
+        group = self.add_mutually_exclusive_group(required=required)
+        for name in hyperparameters:
+            names, parameters = self.parameters[name]
+            group.add_argument(*names, **parameters)
+
     def parse(self, args=None):
-        return self.ap.parse_args(args)
+        for key, (dest_key, value) in self._overrides.items():
+            if args is None:
+                args = sys.argv[1:]
+            if key in args:
+                args.extend((f"--{dest_key}", value))
+        return super().parse_args(args)

benchmark/Datasets.py

@@ -1,8 +1,12 @@
 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 fimdlp.mdlp import FImdlp
 
 
 class Diterator:
@@ -24,13 +28,23 @@ 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]))
+        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)
         df = pd.DataFrame(data[0])
-        df = df.dropna()
+        df.dropna(axis=0, how="any", inplace=True)
-        X = df.drop(class_name, axis=1).to_numpy()
+        self.dataset = df
+        X = df.drop(class_name, axis=1)
+        self.features = X.columns.to_list()
+        self.class_name = class_name
         y, _ = pd.factorize(df[class_name])
+        X = X.to_numpy()
         return X, y
 
 
@@ -43,15 +57,23 @@ class DatasetsTanveer:
     def folder():
         return "data"
 
-    def load(self, name, _):
+    @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(
             file_name,
             sep="\t",
             index_col=0,
         )
-        X = data.drop("clase", axis=1).to_numpy()
+        X = data.drop("clase", axis=1)
+        self.features = X.columns
+        X = X.to_numpy()
         y = data["clase"].to_numpy()
+        self.dataset = data
+        self.class_name = "clase"
         return X, y
 
 
@@ -64,7 +86,11 @@ class DatasetsSurcov:
     def folder():
         return "datasets"
 
-    def load(self, name, _):
+    @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(
             file_name,
@@ -72,55 +98,142 @@ class DatasetsSurcov:
         )
         data.dropna(axis=0, how="any", inplace=True)
         self.columns = data.columns
-        col_list = ["class"]
+        X = data.drop(["class"], axis=1)
-        X = data.drop(col_list, axis=1).to_numpy()
+        self.features = X.columns
+        self.class_name = "class"
+        self.dataset = data
+        X = X.to_numpy()
         y = data["class"].to_numpy()
         return X, y
 
 
 class Datasets:
-    def __init__(self, dataset_name=None):
+    def __init__(self, dataset_name=None, discretize=None):
-
+        env_data = EnvData.load()
-        envData = EnvData.load()
+        # DatasetsSurcov, DatasetsTanveer, DatasetsArff,...
-        class_name = getattr(
+        source_name = getattr(
             __import__(__name__),
-            f"Datasets{envData['source_data']}",
+            f"Datasets{env_data['source_data']}",
         )
-        self.dataset = class_name()
+        self.discretize = (
-        self.class_names = []
+            env_data["discretize"] == "1"
-        self.load_names()
+            if discretize is None
-        if dataset_name is not None:
+            else discretize == "1"
-            try:
+        )
-                class_name = self.class_names[
+        self.dataset = source_name()
-                    self.data_sets.index(dataset_name)
+        # initialize self.class_names & self.data_sets
-                ]
+        class_names, sets = self._init_names(dataset_name)
-                self.class_names = [class_name]
+        self.class_names = class_names
-            except ValueError:
+        self.data_sets = sets
-                raise ValueError(f"Unknown dataset: {dataset_name}")
+        self.states = {}  # states of discretized variables
-            self.data_sets = [dataset_name]
 
-    def load_names(self):
+    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:
-            self.data_sets = f.read().splitlines()
+            sets = f.read().splitlines()
-            self.class_names = [default_class] * len(self.data_sets)
+            sets = [x for x in sets if not x.startswith("#")]
-        if "," in self.data_sets[0]:
+            class_names = [default_class] * len(sets)
+        if "," in sets[0]:
             result = []
             class_names = []
-            for data in self.data_sets:
+            for data in sets:
-                name, class_name = data.split(",")
+                name, class_name, features = data.split(",", 2)
                 result.append(name)
                 class_names.append(class_name)
-            self.data_sets = result
+                self.continuous_features[name] = features
-            self.class_names = class_names
+            sets = result
+        else:
+            for name in sets:
+                self.continuous_features[name] = None
+        # Set as dataset list the dataset passed as argument
+        if dataset_name is None:
+            return class_names, sets
+        try:
+            class_name = class_names[sets.index(dataset_name)]
+        except ValueError:
+            raise ValueError(f"Unknown dataset: {dataset_name}")
+        return [class_name], [dataset_name]
 
-    def load(self, name):
+    def get_attributes(self, name):
+        tmp = self.discretize
+        self.discretize = False
+        X, y = self.load(name)
+        attr = SimpleNamespace()
+        attr.dataset = name
+        values, counts = np.unique(y, return_counts=True)
+        attr.classes = len(values)
+        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)]
-            return self.dataset.load(name, class_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
+            if dataframe:
+                return self.get_dataset()
+            return X, y
         except (ValueError, FileNotFoundError):
             raise ValueError(f"Unknown dataset: {name}")
 
+    def discretize_dataset(self, X, y):
+        """Supervised discretization with Fayyad and Irani's MDLP algorithm.
+
+        Parameters
+        ----------
+        X : np.ndarray
+            array (n_samples, n_features) of features
+        y : np.ndarray
+            array (n_samples,) of labels
+
+        Returns
+        -------
+        tuple (X, y) of numpy.ndarray
+        """
+        discretiz = FImdlp()
+        return discretiz.fit_transform(X, y)
+
     def __iter__(self) -> Diterator:
         return Diterator(self.data_sets)

benchmark/Experiments.py

@@ -1,4 +1,5 @@
 import os
+import sys
 import json
 import random
 import warnings
@@ -15,10 +16,13 @@ from sklearn.model_selection import (
 from .Utils import Folders, Files, NO_RESULTS
 from .Datasets import Datasets
 from .Models import Models
+from .Arguments import EnvData
 
 
 class Randomized:
-    seeds = [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]
+    @staticmethod
+    def seeds():
+        return json.loads(EnvData.load()["seeds"])
 
 
 class BestResults:
@@ -108,8 +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")
@@ -127,7 +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)
@@ -154,7 +173,7 @@ class Experiment:
         self.platform = platform
         self.progress_bar = progress_bar
         self.folds = folds
-        self.random_seeds = Randomized.seeds
+        self.random_seeds = Randomized.seeds()
         self.results = []
         self.duration = 0
         self._init_experiment()
@@ -162,6 +181,10 @@ class Experiment:
     def get_output_file(self):
         return self.output_file
 
+    @staticmethod
+    def get_python_version():
+        return "{}.{}".format(sys.version_info.major, sys.version_info.minor)
+
     def _build_classifier(self, random_state, hyperparameters):
         self.model = Models.get_model(self.model_name, random_state)
         clf = self.model
@@ -176,7 +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(
@@ -193,7 +229,8 @@ class Experiment:
                 shuffle=True, random_state=random_state, n_splits=self.folds
             )
             clf = self._build_classifier(random_state, hyperparameters)
-            self.version = clf.version() if hasattr(clf, "version") else "-"
+            fit_params = self._build_fit_params(name)
+            self.version = Models.get_version(self.model_name, clf)
             with warnings.catch_warnings():
                 warnings.filterwarnings("ignore")
                 res = cross_validate(
@@ -201,11 +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
@@ -237,12 +282,15 @@ 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
         output["duration"] = self.duration
         output["seeds"] = self.random_seeds
         output["platform"] = self.platform
+        output["language_version"] = self.get_python_version()
+        output["language"] = "Python"
         output["results"] = self.results
         with open(self.output_file, "w") as f:
             json.dump(output, f)
@@ -263,7 +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
@@ -301,7 +349,7 @@ class GridSearch:
         self.progress_bar = progress_bar
         self.folds = folds
         self.platform = platform
-        self.random_seeds = Randomized.seeds
+        self.random_seeds = Randomized.seeds()
         self.grid_file = os.path.join(
             Folders.results, Files.grid_input(score_name, model_name)
         )

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

@@ -8,9 +8,30 @@ from sklearn.ensemble import (
 )
 from sklearn.svm import SVC
 from stree import Stree
+from bayesclass.clfs import TAN, KDB, AODE, KDBNew, TANNew, AODENew
 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:
@@ -18,25 +39,31 @@ class Models:
     def define_models(random_state):
         return {
             "STree": Stree(random_state=random_state),
+            "TAN": TAN(random_state=random_state),
+            "KDB": KDB(k=2),
+            "TANNew": TANNew(random_state=random_state),
+            "KDBNew": KDBNew(k=2),
+            "AODENew": AODENew(random_state=random_state),
+            "AODE": AODE(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",
@@ -44,6 +71,7 @@ class Models:
             ),
             "GBC": GradientBoostingClassifier(random_state=random_state),
             "RandomForest": RandomForestClassifier(random_state=random_state),
+            "Mock": MockModel(random_state=random_state),
         }
 
     @staticmethod
@@ -89,3 +117,15 @@ class Models:
             nodes, leaves = result.nodes_leaves()
             depth = result.depth_ if hasattr(result, "depth_") else 0
         return nodes, leaves, depth
+
+    @staticmethod
+    def get_version(name, clf):
+        if hasattr(clf, "version"):
+            return clf.version()
+        if name in ["Cart", "ExtraTree", "RandomForest", "GBC", "SVC"]:
+            return sklearn.__version__
+        elif name.startswith("Bagging") or name.startswith("AdaBoost"):
+            return sklearn.__version__
+        elif name == "XGBoost":
+            return xgboost.__version__
+        return "Error"

benchmark/ResultsBase.py

@@ -0,0 +1,433 @@
+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()
+
+    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):
+        super().__init__(file_name=file_name, best_file=False)
+
+    def print_line(self, line) -> None:
+        pass
+
+    def header(self) -> None:
+        self.title = self.data["title"]
+        self.duration = self.data["duration"]
+
+    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

@@ -1,6 +1,8 @@
 import os
+import sys
 import subprocess
 
+PYTHON_VERSION = "{}.{}".format(sys.version_info.major, sys.version_info.minor)
 NO_RESULTS = "** No results found **"
 NO_ENV = "File .env not found"
 
@@ -11,6 +13,8 @@ class Folders:
     exreport = "exreport"
     report = os.path.join(exreport, "exreport_output")
     img = "img"
+    excel = "excel"
+    sql = "sql"
 
     @staticmethod
     def src():
@@ -25,6 +29,8 @@ class Files:
     exreport_pdf = "Rplots.pdf"
     benchmark_r = "benchmark.r"
     dot_env = ".env"
+    datasets_report_excel = "ReportDatasets.xlsx"
+    be_list_excel = "some_results.xlsx"
 
     @staticmethod
     def exreport_output(score):
@@ -102,7 +108,8 @@ 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
         )
@@ -111,7 +118,7 @@ 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)
@@ -122,6 +129,9 @@ 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
 
@@ -142,3 +152,7 @@ class TextColor:
     ENDC = "\033[0m"
     BOLD = "\033[1m"
     UNDERLINE = "\033[4m"
+    WHITE = "\033[97m"
+    GREY = "\033[90m"
+    BLACK = "\033[90m"
+    DEFAULT = "\033[99m"

benchmark/__init__.py

@@ -1,10 +1,17 @@
-from .Datasets import Datasets, DatasetsSurcov, DatasetsTanveer, DatasetsArff
+from .ResultsBase import Summary
+from .Datasets import (
+    Datasets,
+    DatasetsSurcov,
+    DatasetsTanveer,
+    DatasetsArff,
+)
 from .Experiments import Experiment
-from .Results import Report, Summary
+from .Results import Report
+from ._version import __version__
 
 __author__ = "Ricardo Montañana Gómez"
-__copyright__ = "Copyright 2020-2022, Ricardo Montañana Gómez"
+__copyright__ = "Copyright 2020-2023, Ricardo Montañana Gómez"
 __license__ = "MIT License"
 __author_email__ = "ricardo.montanana@alu.uclm.es"
 
-__all__ = ["Experiment", "Datasets", "Report", "Summary"]
+__all__ = ["Experiment", "Datasets", "Report", "Summary", __version__]

benchmark/_version.py

@@ -1 +1 @@
-__version__ = "0.1.1"
+__version__ = "0.5.0"

benchmark/scripts/be_benchmark.py

@@ -1,11 +1,11 @@
 #!/usr/bin/env python
-from benchmark.Results import Benchmark
+from benchmark.ResultsFiles import Benchmark
 from benchmark.Utils import Files
 from benchmark.Arguments import Arguments
 
 
 def main(args_test=None):
-    arguments = Arguments()
+    arguments = Arguments(prog="be_benchmark")
     arguments.xset("score").xset("excel").xset("tex_output").xset("quiet")
     args = arguments.parse(args_test)
     benchmark = Benchmark(score=args.score, visualize=not args.quiet)

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_best.py

@@ -21,5 +21,5 @@ def main(args_test=None):
         print(e)
     else:
         if args.report:
-            report = ReportBest(args.score, args.model, best=True, grid=False)
+            report = ReportBest(args.score, args.model, best=True)
             report.report()

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 +1,14 @@
+#!/usr/bin/env python
+import webbrowser
+from benchmark.scripts.flask_app.app import create_app
+
+
+# Launch a flask server to serve the results
+def main(args_test=None):
+    app = create_app()
+    app.config["TEST"] = args_test is not None
+    output = app.config["OUTPUT"]
+    print("Output is ", output)
+    if 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

@@ -0,0 +1,36 @@
+#!/usr/bin/env python
+import os
+from benchmark.Utils import Files, Folders
+from benchmark.Arguments import Arguments
+
+
+def main(args_test=None):
+    arguments = Arguments(prog="be_init_project")
+    arguments.add_argument("project_name", help="Project name")
+    args = arguments.parse(args_test)
+    folders = []
+    folders.append(args.project_name)
+    folders.append(os.path.join(args.project_name, Folders.results))
+    folders.append(os.path.join(args.project_name, Folders.hidden_results))
+    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}")
+            os.makedirs(folder)
+    except FileExistsError as e:
+        print(e)
+        exit(1)
+    env_src = os.path.join(Folders.src(), "..", f"{Files.dot_env}.dist")
+    env_to = os.path.join(args.project_name, Files.dot_env)
+    os.system(f"cp {env_src} {env_to}")
+    print("Done!")
+    print(
+        "Please, edit .env file with your settings and add a datasets folder"
+    )
+    print("with an all.txt file with the datasets you want to use.")
+    print("In that folder you have to include all the datasets you'll use.")

benchmark/scripts/be_list.py

@@ -1,19 +1,21 @@
 #! /usr/bin/env python
 import os
-from benchmark.Results import Summary
+from benchmark.ResultsBase import Summary
-from benchmark.Utils import Folders
+from benchmark.Utils import Files, Folders
 from benchmark.Arguments import Arguments
+from benchmark.Manager import Manage
 
 """List experiments of a model
 """
 
 
 def main(args_test=None):
-    arguments = Arguments()
+    arguments = Arguments(prog="be_list")
     arguments.xset("number").xset("model", required=False).xset("key")
-    arguments.xset("hidden").xset("nan").xset("score", required=False)
+    arguments.xset("score", required=False).xset("compare").xset("hidden")
+    arguments.xset("nan")
     args = arguments.parse(args_test)
-    data = Summary(hidden=args.hidden)
+    data = Summary(hidden=args.hidden, compare=args.compare)
     data.acquire()
     try:
         data.list_results(
@@ -21,33 +23,14 @@ def main(args_test=None):
             model=args.model,
             sort_key=args.key,
             number=args.number,
+            nan=args.nan,
         )
     except ValueError as e:
         print(e)
-    else:
+        return
-        if args.nan:
+    manager = Manage(data)
-            results_nan = []
+    excel_generated = manager.manage_results()
-            results = data.get_results_criteria(
+    if excel_generated:
-                score=args.score,
+        name = os.path.join(Folders.excel, Files.be_list_excel)
-                model=args.model,
+        print(f"Generated file: {name}")
-                input_data=None,
+        Files.open(name, test=args_test is not None)
-                sort_key=args.key,
-                number=args.number,
-            )
-            for result in results:
-                if result["metric"] != result["metric"]:
-                    results_nan.append(result)
-            if results_nan != []:
-                print(
-                    "\n"
-                    + "*" * 30
-                    + " Results with nan moved to hidden "
-                    + "*" * 30
-                )
-                data.list_results(input_data=results_nan)
-                for result in results_nan:
-                    name = result["file"]
-                    os.rename(
-                        os.path.join(Folders.results, name),
-                        os.path.join(Folders.hidden_results, name),
-                    )

benchmark/scripts/be_main.py

@@ -10,28 +10,39 @@ from benchmark.Arguments import Arguments
 
 
 def main(args_test=None):
-    arguments = Arguments()
+    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("hyperparameters").xset("paramfile").xset("report")
+    arguments.xset("report").xset("ignore_nan").xset("discretize")
-    arguments.xset("grid_paramfile").xset("dataset")
+    arguments.xset("fit_features")
+    arguments.add_exclusive(
+        ["grid_paramfile", "best_paramfile", "hyperparameters"]
+    )
+    arguments.xset(
+        "dataset", overrides="title", const="Test with only one dataset"
+    )
     args = arguments.parse(args_test)
     report = args.report or args.dataset is not None
     if args.grid_paramfile:
-        args.paramfile = False
+        args.best_paramfile = False
     try:
         job = Experiment(
             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.paramfile,
+            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

@@ -1,46 +1,88 @@
 #!/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
-file, and can compare results of report with best results obtained by model
+file, and can compare results of report wibth best results obtained by model
 If no argument is set, displays the datasets and its characteristics
 """
 
 
 def main(args_test=None):
-    arguments = Arguments()
+    is_test = args_test is not None
-    arguments.xset("file").xset("excel").xset("sql").xset("compare")
+    arguments = Arguments(prog="be_report")
-    arguments.xset("best").xset("grid").xset("model", required=False)
+    arguments.add_subparser()
-    arguments.xset("score", required=False)
+    arguments.add_subparsers_options(
+        (
+            "best",
+            "Report best results obtained by any model/score. "
+            "See be_build_best",
+        ),
+        [
+            ("model", dict(required=False)),
+            ("score", dict(required=False)),
+        ],
+    )
+    arguments.add_subparsers_options(
+        (
+            "grid",
+            "Report grid results obtained by any model/score. "
+            "See be_build_grid",
+        ),
+        [
+            ("model", dict(required=False)),
+            ("score", dict(required=False)),
+        ],
+    )
+    arguments.add_subparsers_options(
+        ("file", "Report file results"),
+        [
+            ("file_name", {}),
+            ("excel", {}),
+            ("sql", {}),
+            ("compare", {}),
+        ],
+    )
+    arguments.add_subparsers_options(
+        ("datasets", "Report datasets information"),
+        [
+            ("excel", {}),
+        ],
+    )
     args = arguments.parse(args_test)
-    if args.best:
+    match args.subcommand:
-        args.grid = None
+        case "best" | "grid":
-    if args.grid:
+            best = args.subcommand == "best"
-        args.best = None
+            report = ReportBest(args.score, args.model, best)
-    if args.file is None and args.best is None and args.grid is None:
-        ReportDatasets.report()
-    else:
-        if args.best is not None or args.grid is not None:
-            report = ReportBest(args.score, args.model, args.best, args.grid)
             report.report()
-        else:
+        case "file":
             try:
-                report = Report(args.file, args.compare)
+                report = Report(args.file_name, args.compare)
+                report.report()
             except FileNotFoundError as e:
                 print(e)
-            else:
+                return
-                report.report()
+            if args.sql:
-                if args.excel:
+                sql = SQLFile(args.file_name)
-                    excel = Excel(
+                sql.report()
-                        file_name=args.file,
+            if args.excel:
-                        compare=args.compare,
+                excel = Excel(
-                    )
+                    file_name=Path(args.file_name).name,
-                    excel.report()
+                    compare=args.compare,
-                    is_test = args_test is not None
+                )
-                    Files.open(excel.get_file_name(), is_test)
+                excel.report()
-                if args.sql:
+                Files.open(
-                    sql = SQL(args.file)
+                    os.path.join(Folders.excel, excel.get_file_name()), is_test
-                    sql.report()
+                )
+        case "datasets":
+            report = ReportDatasets(args.excel)
+            report.report()
+            if args.excel:
+                Files.open(report.get_file_name(), is_test)
+        case _:
+            arguments.print_help()

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/scripts/flask_app/.env

@@ -0,0 +1,2 @@
+OUTPUT="local"
+FRAMEWORK="bulma"

benchmark/scripts/flask_app/app.py

@@ -0,0 +1,39 @@
+#!/usr/bin/env python
+from flask import Flask
+from flask_bootstrap import Bootstrap5
+from flask_login import LoginManager
+from .config import Config
+from .models import User, db
+
+from .results.main import results
+from .main import main
+
+bootstrap = Bootstrap5()
+
+login_manager = LoginManager()
+
+
+@login_manager.user_loader
+def load_user(user_id):
+    return User.query.get(int(user_id))
+
+
+def make_shell_context():
+    return {"db": db, "User": User}
+
+
+def create_app():
+    app = Flask(__name__)
+    bootstrap.init_app(app)
+    # app.register_blueprint(results)
+    app.config.from_object(Config)
+    db.init_app(app)
+    login_manager.init_app(app)
+    login_manager.login_view = "main.login"
+    app.jinja_env.auto_reload = True
+    app.register_blueprint(results, url_prefix="/results")
+    app.register_blueprint(main)
+    app.shell_context_processor(make_shell_context)
+    with app.app_context():
+        db.create_all()
+    return app

benchmark/scripts/flask_app/config.py

@@ -0,0 +1,17 @@
+import os
+from dotenv import load_dotenv
+
+basedir = os.path.abspath(os.path.dirname(__file__))
+load_dotenv(os.path.join(basedir, ".env"))
+
+
+class Config(object):
+    FRAMEWORKS = ["bootstrap", "bulma"]
+    FRAMEWORK = os.environ.get("FRAMEWORK") or FRAMEWORKS[0]
+    OUTPUT = os.environ.get("OUTPUT") or "local"  # local or docker
+    TEMPLATES_AUTO_RELOAD = True
+    SECRET_KEY = os.environ.get("SECRET_KEY") or "really-hard-to-guess-key"
+    SQLALCHEMY_DATABASE_URI = os.environ.get(
+        "DATABASE_URL"
+    ) or "sqlite:///" + os.path.join(basedir, "app.db")
+    SQLALCHEMY_TRACK_MODIFICATIONS = False

benchmark/scripts/flask_app/forms.py

@@ -0,0 +1,22 @@
+from flask_wtf import FlaskForm
+from wtforms import (
+    StringField,
+    PasswordField,
+    BooleanField,
+    SubmitField,
+)
+from wtforms.validators import (
+    DataRequired,
+    Length,
+)
+
+
+class LoginForm(FlaskForm):
+    username = StringField(
+        "Username", validators=[DataRequired(), Length(1, 20)]
+    )
+    password = PasswordField(
+        "Password", validators=[DataRequired(), Length(4, 150)]
+    )
+    remember_me = BooleanField("Remember me")
+    submit = SubmitField()

benchmark/scripts/flask_app/main.py

@@ -0,0 +1,51 @@
+from flask import (
+    Blueprint,
+    render_template,
+    url_for,
+    flash,
+    redirect,
+    request,
+)
+from flask_login import login_user, current_user, logout_user, login_required
+from werkzeug.urls import url_parse
+from .forms import LoginForm
+from .models import User
+
+main = Blueprint("main", __name__)
+
+
+@main.route("/")
+@main.route("/index")
+def index():
+    return render_template("index.html")
+
+
+@main.route("/config")
+@login_required
+def config():
+    return render_template("config.html")
+
+
+@main.route("/login", methods=["GET", "POST"])
+def login():
+    if current_user.is_authenticated:
+        return redirect(url_for("main.index"))
+    form = LoginForm()
+    if form.validate_on_submit():
+        user = User.query.filter_by(username=form.username.data).first()
+        if user is None or not user.check_password(form.password.data):
+            flash("Invalid username or password")
+            return redirect(url_for("main.login"))
+        login_user(user, remember=form.remember_me.data)
+        flash("Logged in successfully.")
+        next_page = request.args.get("next")
+        if not next_page or url_parse(next_page).netloc != "":
+            next_page = url_for("main.index")
+        return redirect(next_page)
+    return render_template("login.html", title="Sign In", form=form)
+
+
+@main.route("/logout")
+def logout():
+    logout_user()
+    return redirect(url_for("main.index"))

benchmark/scripts/flask_app/models.py

@@ -0,0 +1,29 @@
+from hashlib import md5
+from flask_sqlalchemy import SQLAlchemy
+from sqlalchemy import Column, Integer, String
+from flask_login import UserMixin
+from werkzeug.security import generate_password_hash, check_password_hash
+
+db = SQLAlchemy()
+
+
+class User(UserMixin, db.Model):
+    id = Column(Integer, primary_key=True)
+    username = Column(String(64), index=True, unique=True)
+    email = Column(String(120), index=True, unique=True)
+    password_hash = Column(String(128))
+
+    def __repr__(self):
+        return "<User {} {}>".format(self.username, self.email)
+
+    def set_password(self, password):
+        self.password_hash = generate_password_hash(password)
+
+    def check_password(self, password):
+        return check_password_hash(self.password_hash, password)
+
+    def avatar(self, size):
+        digest = md5(self.email.lower().encode("utf-8")).hexdigest()
+        return "https://www.gravatar.com/avatar/{}?d=identicon&s={}".format(
+            digest, size
+        )

benchmark/scripts/flask_app/results/main.py

@@ -0,0 +1,46 @@
+import os
+import json
+import shutil
+import xlsxwriter
+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, current_app, request, redirect, url_for
+from flask_login import login_required
+
+results = Blueprint("results", __name__, template_folder="templates")
+
+
+@results.route("/select")
+@login_required
+def select(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",
+    )
+    return render_template("test.html")
+
+
+@results.route("/datasets")
+@login_required
+def datasets(compare="False"):
+    return render_template("test.html")

benchmark/scripts/flask_app/results/results.ant.py

@@ -0,0 +1,212 @@
+#!/usr/bin/env python
+# import os
+# import json
+# import shutil
+# import xlsxwriter
+# 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
+from flask import Blueprint, render_template
+
+
+results = Blueprint("results", __name__, template_folder="results")
+# 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
+
+
+@results.route("/results/<compare>")
+def results(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",
+    # )
+    return render_template("test.html")
+
+
+""" 
+@results.route("/datasets/<compare>")
+@results.route("datasets")
+def datasets(compare=False):
+    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],
+    )
+
+
+@results.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
+    print(f"back [{back}]")
+    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,
+    )
+
+
+@results.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]
+        ),
+    )
+
+
+@results.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()
+
+
+@results.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)
+
+
+@results.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))
+
+
+@results.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/flask_app/results/templates/_table_select.html

@@ -0,0 +1,50 @@
+{%- 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 -%}
+<table id="file-table"
+       class="table table-striped table-hover table-bordered">
+    <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>
+                <button class="btn btn-primary btn-small btn-danger"
+                        onclick="setCheckBoxes(false)">
+                    <i class="mdi mdi-checkbox-multiple-blank"></i>
+                </button>
+                <button class="btn btn-primary btn-small btn-success"
+                        onclick="setCheckBoxes(true)">
+                    <i class="mdi mdi-checkbox-multiple-marked"></i>
+                </button>
+            </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="text-end">{{ "%.6f" % data["score"] }}</td>
+                    <td>
+                        {{ get_button_tag("table-eye", "showFile('" ~ file ~ "') ") | safe }}
+                        {% set file_best = "best_results_" ~ parts[1] ~ "_" ~ parts[2] ~ ".json" %}
+                        {{ 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/flask_app/results/templates/select.html

@@ -0,0 +1,9 @@
+{% extends "base.html" %}
+{% block content %}
+    {% include "_table_select.html" %}
+{% endblock %}
+{% block jscript %}
+    {{ super() }}
+    <script src="https://cdn.datatables.net/1.10.25/js/jquery.dataTables.min.js"></script>
+    <script src="{{ url_for('static', filename="js/select.js") }}"></script>
+{% endblock %}

benchmark/scripts/flask_app/static/css/main.css

@@ -0,0 +1,51 @@
+.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;
+}
+
+body {
+  padding-bottom: 20px;
+}
+
+.navbar {
+  margin-bottom: 20px;
+}
+
+pre {
+    background: #ddd;
+    padding: 10px;
+}
+
+h2 {
+    margin-top: 20px;
+}
+
+footer {
+    margin: 20px;
+}

benchmark/scripts/flask_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/flask_app/static/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("selected")) {
+        $(this).removeClass("selected");
+      } else {
+        table
+          .$("tr.selected")
+          .removeClass("selected");
+        $(this).addClass("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/flask_app/templates/_nav.html

@@ -0,0 +1,30 @@
+{% from 'bootstrap5/nav.html' import render_nav_item %}
+<nav class="navbar navbar-expand-sm navbar-light bg-light mb-4 justify-content-end">
+    <div class="container">
+        <button class="navbar-toggler"
+                type="button"
+                data-bs-toggle="collapse"
+                data-bs-target="#navbarSupportedContent"
+                aria-controls="navbarSupportedContent"
+                aria-expanded="false"
+                aria-label="Toggle navigation">
+            <span class="navbar-toggler-icon"></span>
+        </button>
+        <div class="collapse navbar-collapse" id="navbarSupportedContent">
+            <!-- Left side of navbar -->
+            <ul class="navbar-nav me-auto">
+                {{ render_nav_item('main.index', 'Home') }}
+            </ul>
+            <ul class="navbar-nav justify-content-end">
+                {{ render_nav_item('results.select', 'Results') }}
+                {{ render_nav_item('results.datasets', 'Datasets') }}
+                {{ render_nav_item('main.config', 'Config') }}
+                {% if current_user.is_authenticated %}
+                    {{ render_nav_item('main.logout', 'Logout') }}
+                {% else %}
+                    {{ render_nav_item('main.login', 'Login') }}
+                {% endif %}
+            </ul>
+        </div>
+    </div>
+</nav>

benchmark/scripts/flask_app/templates/base.html

@@ -0,0 +1,27 @@
+<!DOCTYPE html>
+<html lang="en">
+    <head>
+        {% block head %}
+            <meta charset="utf-8">
+            <meta name="viewport"
+                  content="width=device-width, initial-scale=1, shrink-to-fit=no">
+            {% block styles %}{{ bootstrap.load_css() }}{% endblock %}
+            <title>Benchmark</title>
+        {% endblock %}
+    </head>
+    <body>
+        {% include "_nav.html" %}
+        {% with messages = get_flashed_messages() %}
+            {% if messages %}
+                {% for message in messages %}<div class="alert alert-info" role="alert">{{ message }}</div>{% endfor %}
+            {% endif %}
+        {% endwith %}
+        <div class="container">
+            {% block content %}{% endblock %}
+        </div>
+    </body>
+    {% block jscript %}
+        <script src="https://code.jquery.com/jquery-3.6.0.min.js"></script>
+        {{ bootstrap.load_js() }}
+    {% endblock %}
+</html>

benchmark/scripts/flask_app/templates/config.html

@@ -0,0 +1,5 @@
+{% extends "base.html" %}
+{% block content %}
+    <h1>Home</h1>
+    <p>Welcome to the home page!</p>
+{% endblock content %}

benchmark/scripts/flask_app/templates/index.html

@@ -0,0 +1,5 @@
+{% extends "base.html" %}
+{% block content %}
+    <h1>My First Heading</h1>
+    <p>My first paragraph.</p>
+{% endblock %}

benchmark/scripts/flask_app/templates/login.html

@@ -0,0 +1,6 @@
+{% extends 'base.html' %}
+{% from 'bootstrap5/form.html' import render_form %}
+{% block content %}
+    <h2>Login</h2>
+    {{ render_form(form) }}
+{% endblock content %}

benchmark/tests/.env

@@ -5,3 +5,10 @@ model=ODTE
 stratified=0
 # Source of data Tanveer/Surcov
 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

@@ -4,3 +4,10 @@ n_folds=5
 model=ODTE
 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

@@ -5,3 +5,10 @@ model=ODTE
 stratified=0
 # Source of data Tanveer/Surcov
 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

@@ -5,3 +5,10 @@ model=ODTE
 stratified=0
 # Source of data Tanveer/Surcov
 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/.gitignore

@@ -0,0 +1,2 @@
+ReportDatasets.xlsx 
+some_results.xlsx

benchmark/tests/Arguments_test.py

@@ -24,13 +24,11 @@ class ArgumentsTest(TestBase):
 
     def test_parameters(self):
         expected_parameters = {
-            "best": ("-b", "--best"),
+            "best_paramfile": ("-b", "--best_paramfile"),
             "color": ("-c", "--color"),
             "compare": ("-c", "--compare"),
             "dataset": ("-d", "--dataset"),
             "excel": ("-x", "--excel"),
-            "file": ("-f", "--file"),
-            "grid": ("-g", "--grid"),
             "grid_paramfile": ("-g", "--grid_paramfile"),
             "hidden": ("--hidden",),
             "hyperparameters": ("-p", "--hyperparameters"),
@@ -42,7 +40,6 @@ class ArgumentsTest(TestBase):
             "nan": ("--nan",),
             "number": ("-n", "--number"),
             "n_folds": ("-n", "--n_folds"),
-            "paramfile": ("-f", "--paramfile"),
             "platform": ("-P", "--platform"),
             "quiet": ("-q", "--quiet"),
             "report": ("-r", "--report"),
@@ -98,3 +95,27 @@ class ArgumentsTest(TestBase):
         finally:
             os.chdir(path)
         self.assertEqual(stderr.getvalue(), f"{NO_ENV}\n")
+
+    @patch("sys.stderr", new_callable=StringIO)
+    def test_overrides(self, stderr):
+        arguments = self.build_args()
+        arguments.xset("title")
+        arguments.xset("dataset", overrides="title", const="sample text")
+        test_args = ["-n", "3", "-m", "SVC", "-k", "1", "-d", "dataset"]
+        args = arguments.parse(test_args)
+        self.assertEqual(stderr.getvalue(), "")
+        self.assertEqual(args.title, "sample text")
+
+    @patch("sys.stderr", new_callable=StringIO)
+    def test_overrides_no_args(self, stderr):
+        arguments = self.build_args()
+        arguments.xset("title")
+        arguments.xset("dataset", overrides="title", const="sample text")
+        test_args = None
+        with self.assertRaises(SystemExit):
+            arguments.parse(test_args)
+        self.assertRegexpMatches(
+            stderr.getvalue(),
+            r"error: the following arguments are required: -m/--model, "
+            "-k/--key, --title",
+        )

benchmark/tests/Benchmark_test.py

@@ -4,7 +4,8 @@ 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__
 
 
 class BenchmarkTest(TestBase):
@@ -14,10 +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()
 
@@ -98,9 +99,16 @@ class BenchmarkTest(TestBase):
         benchmark.excel()
         file_name = benchmark.get_excel_file_name()
         book = load_workbook(file_name)
+        replace = None
+        with_this = None
         for sheet_name in book.sheetnames:
             sheet = book[sheet_name]
-            self.check_excel_sheet(sheet, f"exreport_excel_{sheet_name}")
+            if sheet_name == "Datasets":
-            # ExcelTest.generate_excel_sheet(
+                replace = self.benchmark_version
-            #     self, sheet, f"exreport_excel_{sheet_name}"
+                with_this = __version__
-            # )
+            self.check_excel_sheet(
+                sheet,
+                f"exreport_excel_{sheet_name}",
+                replace=replace,
+                with_this=with_this,
+            )

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
@@ -17,13 +16,27 @@ 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)
+        self.assertSequenceEqual(Randomized.seeds(), expected)
+
+    def test_Randomized_3_seeds(self):
+        self.set_env(".env.arff")
+        expected = [271, 314, 171]
+        self.assertSequenceEqual(Randomized.seeds(), expected)
+
+    def test_load_dataframe(self):
+        self.set_env(".env.arff")
+        dt = Datasets()
+        X, y = dt.load("iris", dataframe=False)
+        dataset = dt.load("iris", dataframe=True)
+        class_name = dt.get_class_name()
+        features = dt.get_features()
+        self.assertListEqual(y.tolist(), dataset[class_name].tolist())
+        for i in range(len(features)):
+            self.assertListEqual(
+                X[:, i].tolist(), dataset[features[i]].tolist()
+            )
 
     def test_Datasets_iterator(self):
         test = {

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

@@ -15,6 +15,8 @@ from odte import Odte
 from xgboost import XGBClassifier
 from .TestBase import TestBase
 from ..Models import Models
+import xgboost
+import sklearn
 
 
 class ModelTest(TestBase):
@@ -33,22 +35,54 @@ class ModelTest(TestBase):
         for key, value in test.items():
             self.assertIsInstance(Models.get_model(key), value)
 
+    def test_Models_version(self):
+        def ver_stree():
+            return "1.2.3"
+
+        def ver_wodt():
+            return "h.j.k"
+
+        def ver_odte():
+            return "4.5.6"
+
+        test = {
+            "STree": [ver_stree, "1.2.3"],
+            "Wodt": [ver_wodt, "h.j.k"],
+            "ODTE": [ver_odte, "4.5.6"],
+            "RandomForest": [None, "7.8.9"],
+            "BaggingStree": [None, "x.y.z"],
+            "AdaBoostStree": [None, "w.x.z"],
+            "XGBoost": [None, "10.11.12"],
+        }
+        for key, value in test.items():
+            clf = Models.get_model(key)
+            if key in ["STree", "Wodt", "ODTE"]:
+                clf.version = value[0]
+            elif key == "XGBoost":
+                xgboost.__version__ = value[1]
+            else:
+                sklearn.__version__ = value[1]
+            self.assertEqual(Models.get_version(key, clf), value[1])
+
+    def test_bogus_Model_Version(self):
+        self.assertEqual(Models.get_version("unknown", None), "Error")
+
     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):

benchmark/tests/Report_test.py

@@ -2,11 +2,17 @@ import os
 from io import StringIO
 from unittest.mock import patch
 from .TestBase import TestBase
-from ..Results import Report, BaseReport, ReportBest, ReportDatasets
+from ..Results import Report, ReportBest
+from ..ResultsFiles import ReportDatasets
+from ..ResultsBase import BaseReport
+from ..Manager import get_input
 from ..Utils import Symbols
 
 
 class ReportTest(TestBase):
+    def test_get_input(self):
+        self.assertEqual(get_input(is_test=True), "test")
+
     def test_BaseReport(self):
         with patch.multiple(BaseReport, __abstractmethods__=set()):
             file_name = os.path.join(
@@ -60,19 +66,40 @@ 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):
             _ = Report("unknown_file")
 
     def test_report_best(self):
-        report = ReportBest("accuracy", "STree", best=True, grid=False)
+        report = ReportBest("accuracy", "STree", best=True)
         with patch(self.output, new=StringIO()) as stdout:
             report.report()
         self.check_output_file(stdout, "report_best")
 
     def test_report_grid(self):
-        report = ReportBest("accuracy", "STree", best=False, grid=True)
+        report = ReportBest("accuracy", "STree", best=False)
         with patch(self.output, new=StringIO()) as stdout:
             report.report()
         file_name = "report_grid.test"
@@ -81,20 +108,21 @@ class ReportTest(TestBase):
         output_text = stdout.getvalue().splitlines()
         # Compare replacing STree version
         for line, index in zip(expected, range(len(expected))):
-            if "1.2.4" in line:
+            if self.stree_version in line:
                 # replace STree version
                 line = self.replace_STree_version(line, output_text, index)
-
             self.assertEqual(line, output_text[index])
 
-    def test_report_best_both(self):
-        report = ReportBest("accuracy", "STree", best=True, grid=True)
-        with patch(self.output, new=StringIO()) as stdout:
-            report.report()
-        self.check_output_file(stdout, "report_best")
-
     @patch("sys.stdout", new_callable=StringIO)
     def test_report_datasets(self, mock_output):
         report = ReportDatasets()
         report.report()
-        self.check_output_file(mock_output, "report_datasets")
+        file_name = f"report_datasets{self.ext}"
+        with open(os.path.join(self.test_files, file_name)) as f:
+            expected = f.read()
+        output_text = mock_output.getvalue().splitlines()
+        for line, index in zip(expected.splitlines(), range(len(expected))):
+            if self.benchmark_version in line:
+                # replace benchmark version
+                line = self.replace_benchmark_version(line, output_text, index)
+            self.assertEqual(line, output_text[index])

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
@@ -15,8 +16,14 @@ class TestBase(unittest.TestCase):
         self.test_files = "test_files"
         self.output = "sys.stdout"
         self.ext = ".test"
+        self.benchmark_version = "0.2.0"
+        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)
@@ -24,6 +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):
@@ -31,7 +39,9 @@ class TestBase(unittest.TestCase):
                     if value is not None:
                         print(f'{row};{col};"{value}"', file=f)
 
-    def check_excel_sheet(self, sheet, file_name):
+    def check_excel_sheet(
+        self, sheet, file_name, replace=None, with_this=None
+    ):
         file_name += self.ext
         with open(os.path.join(self.test_files, file_name), "r") as f:
             expected = csv.reader(f, delimiter=";")
@@ -43,6 +53,9 @@ class TestBase(unittest.TestCase):
                         value = float(value)
                     except ValueError:
                         pass
+                if replace is not None and isinstance(value, str):
+                    if replace in value:
+                        value = value.replace(replace, with_this)
                 self.assertEqual(sheet.cell(int(row), int(col)).value, value)
 
     def check_output_file(self, output, file_name):
@@ -51,10 +64,15 @@ class TestBase(unittest.TestCase):
             expected = f.read()
         self.assertEqual(output.getvalue(), expected)
 
-    @staticmethod
+    def replace_STree_version(self, line, output, index):
-    def replace_STree_version(line, output, index):
+        idx = line.find(self.stree_version)
-        idx = line.find("1.2.4")
+        return line.replace(self.stree_version, output[index][idx : idx + 5])
-        return line.replace("1.2.4", output[index][idx : idx + 5])
+
+    def replace_benchmark_version(self, line, output, index):
+        idx = line.find(self.benchmark_version)
+        return line.replace(
+            self.benchmark_version, output[index][idx : idx + 5]
+        )
 
     def check_file_file(self, computed_file, expected_file):
         with open(computed_file) as f:

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
         )
@@ -178,6 +180,13 @@ class UtilTest(TestBase):
             "model": "ODTE",
             "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",
         }
         computed = EnvData().load()
         self.assertDictEqual(computed, expected)

benchmark/tests/__init__.py

@@ -13,6 +13,7 @@ from .PairCheck_test import PairCheckTest
 from .Arguments_test import ArgumentsTest
 from .scripts.Be_Pair_check_test import BePairCheckTest
 from .scripts.Be_List_test import BeListTest
+from .scripts.Be_Init_Project_test import BeInitProjectTest
 from .scripts.Be_Report_test import BeReportTest
 from .scripts.Be_Summary_test import BeSummaryTest
 from .scripts.Be_Grid_test import BeGridTest

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. 1.3.1, 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. 1.3.1, 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

@@ -1,57 +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",
-  "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

@@ -1,43 +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": "-",
-  "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

@@ -1,55 +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,
-  "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

@@ -1,49 +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",
-  "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

@@ -1,49 +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",
-  "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

@@ -2,6 +2,7 @@ import os
 from openpyxl import load_workbook
 from ...Utils import NO_RESULTS, Folders, Files
 from ..TestBase import TestBase
+from ..._version import __version__
 
 
 class BeBenchmarkTest(TestBase):
@@ -15,16 +16,16 @@ 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()
 
     def test_be_benchmark_complete(self):
         stdout, stderr = self.execute_script(
-            "be_benchmark", ["-s", self.score, "-q", "1", "-t", "1", "-x", "1"]
+            "be_benchmark", ["-s", self.score, "-q", "-t", "-x"]
         )
         self.assertEqual(stderr.getvalue(), "")
         # Check output
@@ -40,16 +41,26 @@ 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
+        with_this = None
         for sheet_name in book.sheetnames:
             sheet = book[sheet_name]
-            self.check_excel_sheet(sheet, f"exreport_excel_{sheet_name}")
+            if sheet_name == "Datasets":
+                replace = self.benchmark_version
+                with_this = __version__
+            self.check_excel_sheet(
+                sheet,
+                f"exreport_excel_{sheet_name}",
+                replace=replace,
+                with_this=with_this,
+            )
 
     def test_be_benchmark_single(self):
         stdout, stderr = self.execute_script(
-            "be_benchmark", ["-s", self.score, "-q", "1"]
+            "be_benchmark", ["-s", self.score, "-q"]
         )
         self.assertEqual(stderr.getvalue(), "")
         # Check output

benchmark/tests/scripts/Be_Best_test.py

@@ -67,7 +67,7 @@ class BeBestTest(TestBase):
 
     def test_be_build_best_report(self):
         stdout, _ = self.execute_script(
-            "be_build_best", ["-s", "accuracy", "-m", "ODTE", "-r", "1"]
+            "be_build_best", ["-s", "accuracy", "-m", "ODTE", "-r"]
         )
         expected_data = {
             "balance-scale": [

benchmark/tests/scripts/Be_Grid_test.py

@@ -4,6 +4,10 @@ from ...Utils import Folders, Files
 from ..TestBase import TestBase
 
 
+def get_test():
+    return "hola"
+
+
 class BeGridTest(TestBase):
     def setUp(self):
         self.prepare_scripts_env()
@@ -65,7 +69,7 @@ class BeGridTest(TestBase):
     def test_be_grid_no_input(self):
         stdout, stderr = self.execute_script(
             "be_grid",
-            ["-m", "ODTE", "-s", "f1-weighted", "-q", "1"],
+            ["-m", "ODTE", "-s", "f1-weighted", "-q"],
         )
         self.assertEqual(stderr.getvalue(), "")
         grid_file = os.path.join(

benchmark/tests/scripts/Be_Init_Project_test.py

@@ -0,0 +1,67 @@
+import os
+from io import StringIO
+from unittest.mock import patch
+from ..TestBase import TestBase
+from ...Utils import Folders
+
+
+class BeInitProjectTest(TestBase):
+    def setUp(self):
+        self.prepare_scripts_env()
+
+    def tearDown(self):
+        if os.path.exists("test_project"):
+            os.system("rm -rf test_project")
+
+    def assertIsFile(self, file_name):
+        if not os.path.isfile(file_name):
+            raise AssertionError(f"File {str(file_name)} does not exist")
+
+    def assertIsFolder(self, path):
+        if not os.path.exists(path):
+            raise AssertionError(f"Folder {str(path)} does not exist")
+
+    def test_be_init_project(self):
+        test_project = "test_project"
+        stdout, stderr = self.execute_script("be_init_project", [test_project])
+        self.assertEqual(stderr.getvalue(), "")
+        self.check_output_file(stdout, "be_init_project")
+        # check folders
+        expected = [
+            Folders.results,
+            Folders.hidden_results,
+            Folders.exreport,
+            Folders.report,
+            Folders.img,
+            Folders.excel,
+        ]
+        for folder in expected:
+            self.assertIsFolder(os.path.join(test_project, folder))
+        self.assertIsFile(os.path.join(test_project, ".env"))
+        os.system(f"rm -rf {test_project}")
+
+    @patch("sys.stdout", new_callable=StringIO)
+    @patch("sys.stderr", new_callable=StringIO)
+    def test_be_init_project_no_arguments(self, stdout, stderr):
+        with self.assertRaises(SystemExit) as cm:
+            module = self.search_script("be_init_project")
+            module.main("")
+        self.assertEqual(cm.exception.code, 2)
+        self.check_output_file(stdout, "be_init_project_no_arguments")
+        self.assertEqual(stderr.getvalue(), "")
+
+    @patch("sys.stdout", new_callable=StringIO)
+    @patch("sys.stderr", new_callable=StringIO)
+    def test_be_init_project_twice(self, stdout, stderr):
+        test_project = "test_project"
+        self.execute_script("be_init_project", [test_project])
+        with self.assertRaises(SystemExit) as cm:
+            module = self.search_script("be_init_project")
+            module.main([test_project])
+        self.assertEqual(cm.exception.code, 1)
+        self.assertEqual(
+            stderr.getvalue(),
+            f"Creating folder {test_project}\n"
+            f"[Errno 17] File exists: '{test_project}'\n",
+        )
+        self.assertEqual(stdout.getvalue(), "")

benchmark/tests/scripts/Be_List_test.py

@@ -1,5 +1,8 @@
 import os
-from ...Utils import Folders, NO_RESULTS
+import shutil
+from unittest.mock import patch
+from openpyxl import load_workbook
+from ...Utils import Folders, Files, NO_RESULTS
 from ..TestBase import TestBase
 
 
@@ -7,19 +10,94 @@ class BeListTest(TestBase):
     def setUp(self):
         self.prepare_scripts_env()
 
-    def test_be_list(self):
+    @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, "summary_list_model")
+        self.check_output_file(stdout, "be_list_model")
 
-    def test_be_list_no_data(self):
+    @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.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.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.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(os.path.join(Folders.excel, Files.be_list_excel))
+        sheet = book["STree"]
+        self.check_excel_sheet(sheet, "excel")
+
+    @patch(
+        "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(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.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"]
         )
         self.assertEqual(stderr.getvalue(), "")
         self.assertEqual(stdout.getvalue(), f"{NO_RESULTS}\n")
 
-    def test_be_list_nan(self):
+    @patch(
+        "benchmark.Manager.get_input",
+        side_effect=iter(["d 0", "y", "", "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)
+            target = os.path.join(target_folder, file_name)
+            shutil.copyfile(source, target)
+
+        file_name = (
+            "results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:"
+            "35_0.json"
+        )
+        # move nan result from hidden to results
+        copy_files(Folders.hidden_results, Folders.results, file_name)
+        try:
+            # list and delete result
+            stdout, stderr = self.execute_script("be_list", "")
+            self.assertEqual(stderr.getvalue(), "")
+            self.check_output_file(stdout, "be_list_delete")
+        except Exception:
+            # delete the result copied if be_list couldn't
+            os.unlink(os.path.join(Folders.results, file_name))
+            self.fail("test_be_list_delete() should not raise exception")
+
+    @patch(
+        "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):
             source = os.path.join(source_folder, file_name)
             target = os.path.join(target_folder, file_name)
@@ -32,19 +110,44 @@ class BeListTest(TestBase):
         # move nan result from hidden to results
         swap_files(Folders.hidden_results, Folders.results, file_name)
         try:
-            # list and move nan result to hidden
+            # list and move nan result to hidden again
-            stdout, stderr = self.execute_script("be_list", ["--nan", "1"])
+            stdout, stderr = self.execute_script("be_list", "")
             self.assertEqual(stderr.getvalue(), "")
-            self.check_output_file(stdout, "be_list_nan")
+            self.check_output_file(stdout, "be_list_hide")
         except Exception:
-            # move back nan result file if be_list couldn't
+            # delete the result copied if be_list couldn't
             swap_files(Folders.results, Folders.hidden_results, file_name)
-            self.fail("test_be_list_nan() should not raise exception")
+            self.fail("test_be_list_hide() should not raise exception")
 
-    def test_be_list_nan_no_nan(self):
+    @patch("benchmark.Manager.get_input", side_effect=iter(["h 0", "q"]))
-        stdout, stderr = self.execute_script("be_list", ["--nan", "1"])
+    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_no_nan")
+        self.check_output_file(stdout, "be_list_already_hidden")
+
+    @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.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.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()

benchmark/tests/scripts/Be_Main_test.py

@@ -1,4 +1,5 @@
 import os
+import json
 from io import StringIO
 from unittest.mock import patch
 from ...Results import Report
@@ -24,19 +25,21 @@ 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):
         stdout, _ = self.execute_script(
             "be_main",
-            ["-s", self.score, "-m", "STree", "--title", "test", "-r", "1"],
+            ["-s", self.score, "-m", "STree", "--title", "test", "-r"],
         )
         # keep the report name to delete it after
         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):
@@ -66,10 +69,8 @@ class BeMainTest(TestBase):
                 "STree",
                 "--title",
                 "test",
-                "-f",
+                "-b",
-                "1",
                 "-r",
-                "1",
             ],
         )
         # keep the report name to delete it after
@@ -79,6 +80,48 @@ class BeMainTest(TestBase):
             stdout, "be_main_best", [0, 2, 3, 5, 6, 7, 8, 9, 12, 13, 14]
         )
 
+    @patch("sys.stdout", new_callable=StringIO)
+    @patch("sys.stderr", new_callable=StringIO)
+    def test_be_main_incompatible_params(self, stdout, stderr):
+        m1 = (
+            "be_main: error: argument -b/--best_paramfile: not allowed with "
+            "argument -p/--hyperparameters"
+        )
+        m2 = (
+            "be_main: error: argument -g/--grid_paramfile: not allowed with "
+            "argument -p/--hyperparameters"
+        )
+        m3 = (
+            "be_main: error: argument -g/--grid_paramfile: not allowed with "
+            "argument -p/--hyperparameters"
+        )
+        m4 = m1
+        p0 = [
+            "-s",
+            self.score,
+            "-m",
+            "SVC",
+            "--title",
+            "test",
+        ]
+        pset = json.dumps(dict(C=17))
+        p1 = p0.copy()
+        p1.extend(["-p", pset, "-b"])
+        p2 = p0.copy()
+        p2.extend(["-p", pset, "-g"])
+        p3 = p0.copy()
+        p3.extend(["-p", pset, "-g", "-b"])
+        p4 = p0.copy()
+        p4.extend(["-b", "-g"])
+        parameters = [(p1, m1), (p2, m2), (p3, m3), (p4, m4)]
+        for parameter, message in parameters:
+            with self.assertRaises(SystemExit) as msg:
+                module = self.search_script("be_main")
+                module.main(parameter)
+            self.assertEqual(msg.exception.code, 2)
+            self.assertEqual(stderr.getvalue(), "")
+            self.assertRegexpMatches(stdout.getvalue(), message)
+
     def test_be_main_best_params_non_existent(self):
         model = "GBC"
         stdout, stderr = self.execute_script(
@@ -90,10 +133,8 @@ class BeMainTest(TestBase):
                 model,
                 "--title",
                 "test",
-                "-f",
+                "-b",
-                "1",
                 "-r",
-                "1",
             ],
         )
         self.assertEqual(stderr.getvalue(), "")
@@ -117,9 +158,7 @@ class BeMainTest(TestBase):
                 "--title",
                 "test",
                 "-g",
-                "1",
                 "-r",
-                "1",
             ],
         )
         self.assertEqual(stderr.getvalue(), "")
@@ -142,9 +181,7 @@ class BeMainTest(TestBase):
                 "--title",
                 "test",
                 "-g",
-                "1",
                 "-r",
-                "1",
             ],
         )
         # keep the report name to delete it after

benchmark/tests/scripts/Be_Print_Strees_test.py

@@ -18,7 +18,7 @@ class BePrintStrees(TestBase):
         for name in self.datasets:
             stdout, _ = self.execute_script(
                 "be_print_strees",
-                ["-d", name, "-q", "1"],
+                ["-d", name, "-q"],
             )
             file_name = os.path.join(Folders.img, f"stree_{name}.png")
             self.files.append(file_name)
@@ -27,13 +27,13 @@ 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:
             stdout, _ = self.execute_script(
                 "be_print_strees",
-                ["-d", name, "-q", "1", "-c", "1"],
+                ["-d", name, "-q", "-c"],
             )
             file_name = os.path.join(Folders.img, f"stree_{name}.png")
             self.files.append(file_name)

benchmark/tests/scripts/Be_Report_test.py

@@ -1,7 +1,10 @@
 import os
 from openpyxl import load_workbook
-from ...Utils import Folders
+from io import StringIO
+from unittest.mock import patch
+from ...Utils import Folders, Files
 from ..TestBase import TestBase
+from ..._version import __version__
 
 
 class BeReportTest(TestBase):
@@ -10,10 +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.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):
@@ -21,38 +31,70 @@ class BeReportTest(TestBase):
             "results",
             "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json",
         )
-        stdout, stderr = self.execute_script("be_report", ["-f", file_name])
+        stdout, stderr = self.execute_script("be_report", ["file", file_name])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "report")
 
     def test_be_report_not_found(self):
-        stdout, stderr = self.execute_script("be_report", ["-f", "unknown"])
+        stdout, stderr = self.execute_script("be_report", ["file", "unknown"])
         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", ["-f", file_name, "-c", "1"]
+            "be_report", ["file", file_name, "-c"]
         )
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "report_compared")
 
     def test_be_report_datatsets(self):
-        stdout, stderr = self.execute_script("be_report", [])
+        stdout, stderr = self.execute_script("be_report", ["datasets"])
         self.assertEqual(stderr.getvalue(), "")
-        self.check_output_file(stdout, "report_datasets")
+        file_name = f"report_datasets{self.ext}"
+        with open(os.path.join(self.test_files, file_name)) as f:
+            expected = f.read()
+        output_text = stdout.getvalue().splitlines()
+        for line, index in zip(expected.splitlines(), range(len(expected))):
+            if self.benchmark_version in line:
+                # replace benchmark version
+                line = self.replace_benchmark_version(line, output_text, index)
+            self.assertEqual(line, output_text[index])
+
+    def test_be_report_datasets_excel(self):
+        stdout, stderr = self.execute_script("be_report", ["datasets", "-x"])
+        self.assertEqual(stderr.getvalue(), "")
+        file_name = f"report_datasets{self.ext}"
+        with open(os.path.join(self.test_files, file_name)) as f:
+            expected = f.read()
+        output_text = stdout.getvalue().splitlines()
+        for line, index in zip(expected.splitlines(), range(len(expected))):
+            if self.benchmark_version in line:
+                # 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(), Folders.excel, Files.datasets_report_excel
+        )
+        book = load_workbook(file_name)
+        sheet = book["Datasets"]
+        self.check_excel_sheet(
+            sheet,
+            "exreport_excel_Datasets",
+            replace=self.benchmark_version,
+            with_this=__version__,
+        )
 
     def test_be_report_best(self):
         stdout, stderr = self.execute_script(
-            "be_report", ["-s", "accuracy", "-m", "STree", "-b", "1"]
+            "be_report", ["best", "-s", "accuracy", "-m", "STree"]
         )
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "report_best")
 
     def test_be_report_grid(self):
         stdout, stderr = self.execute_script(
-            "be_report", ["-s", "accuracy", "-m", "STree", "-g", "1"]
+            "be_report", ["grid", "-s", "accuracy", "-m", "STree"]
         )
         self.assertEqual(stderr.getvalue(), "")
         file_name = "report_grid.test"
@@ -66,22 +108,36 @@ class BeReportTest(TestBase):
                 line = self.replace_STree_version(line, output_text, index)
             self.assertEqual(line, output_text[index])
 
-    def test_be_report_best_both(self):
+    @patch("sys.stderr", new_callable=StringIO)
-        stdout, stderr = self.execute_script(
+    def test_be_report_unknown_subcommand(self, stderr):
-            "be_report",
+        with self.assertRaises(SystemExit) as msg:
-            ["-s", "accuracy", "-m", "STree", "-b", "1", "-g", "1"],
+            module = self.search_script("be_report")
-        )
+            module.main(["unknown"])
+        self.assertEqual(msg.exception.code, 2)
+        self.check_output_file(stderr, "report_unknown_subcommand")
+
+    def test_be_report_without_subcommand(self):
+        stdout, stderr = self.execute_script("be_report", "")
         self.assertEqual(stderr.getvalue(), "")
-        self.check_output_file(stdout, "report_best")
+        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"
         stdout, stderr = self.execute_script(
             "be_report",
-            ["-f", file_name, "-x", "1", "-c", "1"],
+            ["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"]
@@ -93,10 +149,10 @@ class BeReportTest(TestBase):
         file_name = "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json"
         stdout, stderr = self.execute_script(
             "be_report",
-            ["-f", file_name, "-x", "1"],
+            ["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"]
@@ -108,10 +164,10 @@ class BeReportTest(TestBase):
         file_name = "results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.json"
         stdout, stderr = self.execute_script(
             "be_report",
-            ["-f", file_name, "-q", "1"],
+            ["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

@@ -0,0 +1,12 @@
+Creating folder test_project
+Creating folder test_project/results
+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.
+In that folder you have to include all the datasets you'll use.

benchmark/tests/test_files/be_init_project_no_arguments.test

@@ -0,0 +1,2 @@
+usage: be_init_project [-h] project_name
+be_init_project: error: the following arguments are required: project_name

benchmark/tests/test_files/be_list_already_hidden.test

@@ -0,0 +1,5 @@
+ #  Date       File                                                             Score    Time(h) Title
+=== ========== ================================================================ ======== ======= =======================
+  0 2022-05-04 results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_0.json      nan   3.091 Default hyperparameters
+  1 2021-11-01 results_accuracy_STree_iMac27_2021-11-01_23:55:16_0.json          0.97446   0.098 default
+Already hidden

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_default.test

@@ -0,0 +1,7 @@
+ #  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

benchmark/tests/test_files/be_list_delete.test

@@ -0,0 +1,16 @@
+ #  Date       File                                                             Score    Time(h) Title
+=== ========== ================================================================ ======== ======= ============================================
+  0 2022-05-04 results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_0.json      nan   3.091 Default hyperparameters
+  1 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
+  2 2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json   0.03627   0.076 Test default paramters with RandomForest
+  3 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json     0.03790   1.143 default B
+  4 2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json          0.04158   0.943 default A
+  5 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json          0.04544   0.173 With gridsearched hyperparameters
+Deleting results/results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_0.json
+ #  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

benchmark/tests/test_files/be_list_hidden.test

@@ -0,0 +1,4 @@
+ #  Date       File                                                             Score    Time(h) Title
+=== ========== ================================================================ ======== ======= =======================
+  0 2022-05-04 results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_0.json      nan   3.091 Default hyperparameters
+  1 2021-11-01 results_accuracy_STree_iMac27_2021-11-01_23:55:16_0.json          0.97446   0.098 default

benchmark/tests/test_files/be_list_hidden_nan.test

@@ -0,0 +1,3 @@
+ #  Date       File                                                             Score    Time(h) Title
+=== ========== ================================================================ ======== ======= =======================
+  0 2022-05-04 results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_0.json      nan   3.091 Default hyperparameters

benchmark/tests/test_files/be_list_hide.test

@@ -0,0 +1,16 @@
+ #  Date       File                                                             Score    Time(h) Title
+=== ========== ================================================================ ======== ======= ============================================
+  0 2022-05-04 results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_0.json      nan   3.091 Default hyperparameters
+  1 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
+  2 2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json   0.03627   0.076 Test default paramters with RandomForest
+  3 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json     0.03790   1.143 default B
+  4 2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json          0.04158   0.943 default A
+  5 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json          0.04544   0.173 With gridsearched hyperparameters
+Hiding results/results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_0.json
+ #  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

benchmark/tests/test_files/be_list_model.test

@@ -0,0 +1,5 @@
+ #  Date       File                                                          Score    Time(h) Title
+=== ========== ============================================================= ======== ======= =================================
+  0 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json  0.03790   1.143 default B
+  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

benchmark/tests/test_files/be_list_model_2.test

@@ -0,0 +1,10 @@
+ #  Date       File                                                          Score    Time(h) Title
+=== ========== ============================================================= ======== ======= =================================
+  0 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json  0.03790   1.143 default B
+  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
+ #  Date       File                                                          Score    Time(h) Title
+=== ========== ============================================================= ======== ======= =================================
+  0 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json  0.03790   1.143 default B
+  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

benchmark/tests/test_files/be_list_model_invalid.test

@@ -0,0 +1,6 @@
+ #  Date       File                                                          Score    Time(h) Title
+=== ========== ============================================================= ======== ======= =================================
+  0 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json  0.03790   1.143 default B
+  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
+Invalid option. Try again!

benchmark/tests/test_files/be_list_nan.test

@@ -1,13 +0,0 @@
-Date       File                                                             Score    Time(h) Title
-========== ================================================================ ======== ======= ============================================
-2022-05-04 results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_0.json      nan   3.091 Default hyperparameters
-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
-2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json   0.03627   0.076 Test default paramters with RandomForest
-2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json     0.03790   1.143 default B
-2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json          0.04158   0.943 default A
-2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json          0.04544   0.173 With gridsearched hyperparameters
-
-****************************** Results with nan moved to hidden ******************************
-Date       File                                                             Score    Time(h) Title
-========== ================================================================ ======== ======= =======================
-2022-05-04 results_accuracy_XGBoost_MacBookpro16_2022-05-04_11:00:35_0.json      nan   3.091 Default hyperparameters

benchmark/tests/test_files/be_list_no_nan.test

@@ -1,7 +0,0 @@
-Date       File                                                            Score    Time(h) Title
-========== =============================================================== ======== ======= ============================================
-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
-2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest
-2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
-2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
-2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched hyperparameters

benchmark/tests/test_files/be_list_report.test

@@ -0,0 +1,21 @@
+ #  Date       File                                                          Score    Time(h) Title
+=== ========== ============================================================= ======== ======= =================================
+  0 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json  0.03790   1.143 default B
+  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
+*************************************************************************************************************************
+* 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  Discretized: False                          *
+* Execution took 4115.04 seconds,   1.14 hours, on macbook-pro                                                          *
+* Score is accuracy                                                                                                     *
+*************************************************************************************************************************
+
+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'} 
+*************************************************************************************************************************
+* ✗ 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

@@ -0,0 +1,7 @@
+ #  Date       File                                                          Score    Time(h) Title
+=== ========== ============================================================= ======== ======= =================================
+  0 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json  0.03790   1.143 default B
+  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: excel/some_results.xlsx

benchmark/tests/test_files/be_list_report_excel_2.test

@@ -0,0 +1,8 @@
+ #  Date       File                                                          Score    Time(h) Title
+=== ========== ============================================================= ======== ======= =================================
+  0 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json  0.03790   1.143 default B
+  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
+Added results/results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json to some_results.xlsx
+Generated file: excel/some_results.xlsx