Update version info

Add Discretizer to Datasets
Add excel to report datasets
Add report datasets sheet to benchmark excel

.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

@@ -8,25 +8,22 @@ jobs:
     name: Build
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         with:
           fetch-depth: 0
-      - name: Get project version
-        id: step_one
-        run: |
-          version=$(git describe --tags --abbrev=0)
-          echo "project_version=$version" >> $GITHUB_ENV
+      - run: echo "project_version=$(git describe --tags --abbrev=0)" >> $GITHUB_ENV
       - uses: sonarsource/sonarqube-scan-action@master
         env:
           SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
           SONAR_HOST_URL: ${{ secrets.SONAR_HOST_URL }}
-          with:
-            args: >
-              -Dsonar.projectVersion=${{ env.project_version }}
-              -Dsonar.python.version=3.10
+        with:
+          args: >
+            -Dsonar.projectVersion=${{ env.project_version }}
+            -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
-        timeout-minutes: 5
-        env:
-          SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
+      #- uses: sonarsource/sonarqube-quality-gate-action@master
+      #  timeout-minutes: 5
+      #  env:
+      #    SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
+      #    SONAR_HOST_URL: ${{ secrets.SONAR_HOST_URL }}

.github/workflows/main.yml

@@ -13,10 +13,13 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest, ubuntu-latest]
-        python: ["3.10"]
+        python: ["3.10", "3.11"]
+        exclude:
+          - os: macos-latest
+            python: "3.11"
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Set up Python ${{ matrix.python }}
         uses: actions/setup-python@v2
         with:
@@ -46,7 +49,7 @@ jobs:
       - name: Lint
         run: |
           black --check --diff benchmark
-          flake8 --count benchmark
+          flake8 --count benchmark --ignore=E203,W503
       - name: Tests
         run: |
           coverage run -m unittest -v benchmark.tests

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

benchmark/Arguments.py

@@ -1,6 +1,6 @@
 import sys
 import argparse
-from .Experiments import Models
+from .Models import Models
 from .Utils import Files, NO_ENV
 
 ALL_METRICS = (

benchmark/Datasets.py

@@ -0,0 +1,186 @@
+import os
+import pandas as pd
+import numpy as np
+from scipy.io import arff
+from .Utils import Files
+from .Arguments import EnvData
+from mdlp.discretization import MDLP
+
+
+class Diterator:
+    def __init__(self, data):
+        self._stack = data.copy()
+
+    def __next__(self):
+        if len(self._stack) == 0:
+            raise StopIteration()
+        return self._stack.pop(0)
+
+
+class DatasetsArff:
+    @staticmethod
+    def dataset_names(name):
+        return f"{name}.arff"
+
+    @staticmethod
+    def folder():
+        return "datasets"
+
+    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.dropna(axis=0, how="any", inplace=True)
+        X = df.drop(class_name, axis=1)
+        self.features = X.columns
+        self.class_name = class_name
+        y, _ = pd.factorize(df[class_name])
+        X = X.to_numpy()
+        return X, y
+
+
+class DatasetsTanveer:
+    @staticmethod
+    def dataset_names(name):
+        return f"{name}_R.dat"
+
+    @staticmethod
+    def folder():
+        return "data"
+
+    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()
+        y = data["clase"].to_numpy()
+        return X, y
+
+
+class DatasetsSurcov:
+    @staticmethod
+    def dataset_names(name):
+        return f"{name}.csv"
+
+    @staticmethod
+    def folder():
+        return "datasets"
+
+    def load(self, name, *args):
+        file_name = os.path.join(self.folder(), self.dataset_names(name))
+        data = pd.read_csv(
+            file_name,
+            index_col=0,
+        )
+        data.dropna(axis=0, how="any", inplace=True)
+        self.columns = data.columns
+        col_list = ["class"]
+        X = data.drop(col_list, axis=1).to_numpy()
+        y = data["class"].to_numpy()
+        return X, y
+
+
+class Datasets:
+    def __init__(self, dataset_name=None):
+        envData = EnvData.load()
+        class_name = getattr(
+            __import__(__name__),
+            f"Datasets{envData['source_data']}",
+        )
+        self.load = (
+            self.load_discretized
+            if envData["discretize"] == "1"
+            else self.load_continuous
+        )
+        self.dataset = class_name()
+        self.class_names = []
+        self._load_names()
+        if dataset_name is not None:
+            try:
+                class_name = self.class_names[
+                    self.data_sets.index(dataset_name)
+                ]
+                self.class_names = [class_name]
+            except ValueError:
+                raise ValueError(f"Unknown dataset: {dataset_name}")
+            self.data_sets = [dataset_name]
+
+    def _load_names(self):
+        file_name = os.path.join(self.dataset.folder(), Files.index)
+        default_class = "class"
+        with open(file_name) as f:
+            self.data_sets = f.read().splitlines()
+            self.class_names = [default_class] * len(self.data_sets)
+        if "," in self.data_sets[0]:
+            result = []
+            class_names = []
+            for data in self.data_sets:
+                name, class_name = data.split(",")
+                result.append(name)
+                class_names.append(class_name)
+            self.data_sets = result
+            self.class_names = class_names
+
+    def get_attributes(self, name):
+        class Attributes:
+            pass
+
+        X, y = self.load_continuous(name)
+        attr = Attributes()
+        values, counts = np.unique(y, return_counts=True)
+        comp = ""
+        sep = ""
+        for count in counts:
+            comp += f"{sep}{count/sum(counts)*100:5.2f}%"
+            sep = "/ "
+        attr.balance = comp
+        attr.classes = len(np.unique(y))
+        attr.samples = X.shape[0]
+        attr.features = X.shape[1]
+        return attr
+
+    def get_features(self):
+        return self.dataset.features
+
+    def get_class_name(self):
+        return self.dataset.class_name
+
+    def load_continuous(self, name):
+        try:
+            class_name = self.class_names[self.data_sets.index(name)]
+            return self.dataset.load(name, class_name)
+        except (ValueError, FileNotFoundError):
+            raise ValueError(f"Unknown dataset: {name}")
+
+    def discretize(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 = MDLP(random_state=17, dtype=np.int32)
+        Xdisc = discretiz.fit_transform(X, y)
+        return Xdisc
+
+    def load_discretized(self, name, dataframe=False):
+        X, yd = self.load_continuous(name)
+        Xd = self.discretize(X, yd)
+        dataset = pd.DataFrame(Xd, columns=self.get_features())
+        dataset[self.get_class_name()] = yd
+        if dataframe:
+            return dataset
+        return Xd, yd
+
+    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
@@ -6,7 +7,6 @@ import time
 from datetime import datetime
 from tqdm import tqdm
 import numpy as np
-import pandas as pd
 from sklearn.model_selection import (
     StratifiedKFold,
     KFold,
@@ -14,91 +14,15 @@ from sklearn.model_selection import (
     cross_validate,
 )
 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]
-
-
-class Diterator:
-    def __init__(self, data):
-        self._stack = data.copy()
-
-    def __next__(self):
-        if len(self._stack) == 0:
-            raise StopIteration()
-        return self._stack.pop(0)
-
-
-class DatasetsTanveer:
     @staticmethod
-    def dataset_names(name):
-        return f"{name}_R.dat"
-
-    @staticmethod
-    def folder():
-        return "data"
-
-    def load(self, name):
-        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()
-        y = data["clase"].to_numpy()
-        return X, y
-
-
-class DatasetsSurcov:
-    @staticmethod
-    def dataset_names(name):
-        return f"{name}.csv"
-
-    @staticmethod
-    def folder():
-        return "datasets"
-
-    def load(self, name):
-        file_name = os.path.join(self.folder(), self.dataset_names(name))
-        data = pd.read_csv(
-            file_name,
-            index_col=0,
-        )
-        data.dropna(axis=0, how="any", inplace=True)
-        self.columns = data.columns
-        col_list = ["class"]
-        X = data.drop(col_list, axis=1).to_numpy()
-        y = data["class"].to_numpy()
-        return X, y
-
-
-class Datasets:
-    def __init__(self, dataset_name=None):
-        envData = EnvData.load()
-        class_name = getattr(
-            __import__(__name__),
-            f"Datasets{envData['source_data']}",
-        )
-        self.dataset = class_name()
-        if dataset_name is None:
-            file_name = os.path.join(self.dataset.folder(), Files.index)
-            with open(file_name) as f:
-                self.data_sets = f.read().splitlines()
-        else:
-            self.data_sets = [dataset_name]
-
-    def load(self, name):
-        try:
-            return self.dataset.load(name)
-        except FileNotFoundError:
-            raise ValueError(f"Unknown dataset: {name}")
-
-    def __iter__(self) -> Diterator:
-        return Diterator(self.data_sets)
+    def seeds():
+        return json.loads(EnvData.load()["seeds"])
 
 
 class BestResults:
@@ -234,7 +158,7 @@ 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()
@@ -242,6 +166,10 @@ 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
@@ -273,7 +201,7 @@ 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 "-"
+            self.version = Models.get_version(self.model_name, clf)
             with warnings.catch_warnings():
                 warnings.filterwarnings("ignore")
                 res = cross_validate(
@@ -323,6 +251,8 @@ class Experiment:
         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)
@@ -381,7 +311,7 @@ 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/Models.py

@@ -8,9 +8,12 @@ from sklearn.ensemble import (
 )
 from sklearn.svm import SVC
 from stree import Stree
+from bayesclass import TAN, KDB, AODE
 from wodt import Wodt
 from odte import Odte
 from xgboost import XGBClassifier
+import sklearn
+import xgboost
 
 
 class Models:
@@ -18,6 +21,9 @@ class Models:
     def define_models(random_state):
         return {
             "STree": Stree(random_state=random_state),
+            "TAN": TAN(random_state=random_state),
+            "KDB": KDB(k=3),
+            "AODE": AODE(random_state=random_state),
             "Cart": DecisionTreeClassifier(random_state=random_state),
             "ExtraTree": ExtraTreeClassifier(random_state=random_state),
             "Wodt": Wodt(random_state=random_state),
@@ -89,3 +95,15 @@ 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/Results.py

@@ -1,4 +1,5 @@
 import os
+import sys
 from operator import itemgetter
 import math
 import json
@@ -6,16 +7,44 @@ import abc
 import shutil
 import subprocess
 import xlsxwriter
+from xlsxwriter.exceptions import DuplicateWorksheetName
 import numpy as np
-from .Experiments import Datasets, BestResults
+from .Experiments import BestResults
+from .Datasets import Datasets
+from .Arguments import EnvData, ALL_METRICS
 from .Utils import (
     Folders,
     Files,
     Symbols,
-    BEST_ACCURACY_STREE,
     TextColor,
     NO_RESULTS,
 )
+from ._version import __version__
+
+
+def get_input(is_test):
+    return "test" if is_test else input()
+
+
+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):
@@ -29,7 +58,20 @@ class BaseReport(abc.ABC):
         with open(self.file_name) as f:
             self.data = json.load(f)
         self.best_acc_file = best_file
-        self.lines = self.data if best_file else self.data["results"]
+        if best_file:
+            self.lines = self.data
+        else:
+            self.lines = self.data["results"]
+            self.score_name = self.data["score_name"]
+        self.__compute_best_results_ever()
+
+    def __compute_best_results_ever(self):
+        args = EnvData.load()
+        key = args["source_data"]
+        best = BestResultsEver()
+        self.best_score_name, self.best_score_value = best.get_name_value(
+            key, self.score_name
+        )
 
     def _get_accuracy(self, item):
         return self.data[item][0] if self.best_acc_file else item["score"]
@@ -68,6 +110,12 @@ class BaseReport(abc.ABC):
         }
         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
@@ -82,10 +130,10 @@ class BaseReport(abc.ABC):
 
 
 class Report(BaseReport):
-    header_lengths = [30, 5, 5, 3, 7, 7, 7, 15, 16, 15]
+    header_lengths = [30, 6, 5, 3, 7, 7, 7, 15, 17, 15]
     header_cols = [
         "Dataset",
-        "Samp",
+        "Sampl.",
         "Feat.",
         "Cls",
         "Nodes",
@@ -141,7 +189,7 @@ class Report(BaseReport):
         )
         i += 1
         print(
-            f"{result['time']:9.6f}±{result['time_std']:6.4f} ",
+            f"{result['time']:10.6f}±{result['time_std']:6.4f} ",
             end="",
         )
         i += 1
@@ -155,7 +203,8 @@ class Report(BaseReport):
             self._compare_totals = {}
         self.header_line("*")
         self.header_line(
-            f" Report {self.data['model']} ver. {self.data['version']}"
+            f" {self.data['model']} ver. {self.data['version']}"
+            f" {self.data['language']} ver. {self.data['language_version']}"
             f" with {self.data['folds']} Folds "
             f"cross validation and {len(self.data['seeds'])} random seeds. "
             f"{self.data['date']} {self.data['time']}"
@@ -187,8 +236,8 @@ class Report(BaseReport):
                     f" {key} {self._status_meaning(key)} .....: {value:2d}"
                 )
         self.header_line(
-            f" Accuracy compared to stree_default (liblinear-ovr) .: "
-            f"{accuracy/BEST_ACCURACY_STREE:7.4f}"
+            f" {self._get_message_best_accuracy()} "
+            f"{accuracy/self._get_best_accuracy():7.4f}"
         )
         self.header_line("*")
 
@@ -208,12 +257,12 @@ class ReportBest(BaseReport):
             if best
             else Files.grid_output(score, model)
         )
+        file_name = os.path.join(Folders.results, name)
         self.best = best
         self.grid = grid
-        file_name = os.path.join(Folders.results, name)
-        super().__init__(file_name, best_file=True)
         self.score_name = score
         self.model = model
+        super().__init__(file_name, best_file=True)
 
     def header_line(self, text: str) -> None:
         length = sum(self.header_lengths) + len(self.header_lengths) - 3
@@ -253,8 +302,8 @@ class ReportBest(BaseReport):
     def footer(self, accuracy):
         self.header_line("*")
         self.header_line(
-            f" Scores compared to stree_default accuracy (liblinear-ovr) .: "
-            f"{accuracy/BEST_ACCURACY_STREE:7.4f}"
+            f" {self._get_message_best_accuracy()} "
+            f"{accuracy/self._get_best_accuracy():7.4f}"
         )
         self.header_line("*")
 
@@ -284,7 +333,17 @@ class Excel(BaseReport):
         else:
             self.book = book
             self.close = False
-        self.sheet = self.book.add_worksheet(self.data["model"])
+        suffix = ""
+        num = 1
+        while True:
+            try:
+                self.sheet = self.book.add_worksheet(
+                    self.data["model"] + suffix
+                )
+                break
+            except DuplicateWorksheetName:
+                num += 1
+                suffix = str(num)
         self.max_hyper_width = 0
         self.col_hyperparams = 0
 
@@ -306,7 +365,8 @@ class Excel(BaseReport):
 
     def get_title(self):
         return (
-            f" Report {self.data['model']} ver. {self.data['version']}"
+            f" {self.data['model']} ver. {self.data['version']}"
+            f" {self.data['language']} ver. {self.data['language_version']}"
             f" with {self.data['folds']} Folds "
             f"cross validation and {len(self.data['seeds'])} random seeds. "
             f"{self.data['date']} {self.data['time']}"
@@ -508,8 +568,8 @@ class Excel(BaseReport):
                 self.sheet.write(self.row, 3, self._status_meaning(key), bold)
                 self.row += 1
         message = (
-            f"** Accuracy compared to stree_default (liblinear-ovr) .: "
-            f"{accuracy/BEST_ACCURACY_STREE:7.4f}"
+            f"** {self._get_message_best_accuracy()} "
+            f"{accuracy/self._get_best_accuracy():7.4f}"
         )
         bold = self.book.add_format({"bold": True, "font_size": 14})
         # set width of the hyperparams column with the maximum width
@@ -523,37 +583,251 @@ class Excel(BaseReport):
             self.sheet.set_row(c, 20)
         self.sheet.set_row(0, 25)
         self.sheet.freeze_panes(6, 1)
-        self.sheet.hide_gridlines()
+        self.sheet.hide_gridlines(2)
         if self.close:
             self.book.close()
 
 
 class ReportDatasets:
+    row = 6
+    # alternate lines colors
+    color1 = "#DCE6F1"
+    color2 = "#FDE9D9"
+    color3 = "#B1A0C7"
+
+    def __init__(self, excel=False, book=None):
+        self.excel = excel
+        self.env = EnvData().load()
+        self.close = False
+        self.output = True
+        self.header_text = f"Datasets used in benchmark ver. {__version__}"
+        if excel:
+            self.max_length = 0
+            if book is None:
+                self.excel_file_name = Files.datasets_report_excel
+                self.book = xlsxwriter.Workbook(
+                    self.excel_file_name, {"nan_inf_to_errors": True}
+                )
+                self.set_properties(self.get_title())
+                self.close = True
+            else:
+                self.book = book
+                self.output = False
+            self.sheet = self.book.add_worksheet("Datasets")
+
+    def set_properties(self, title):
+        self.book.set_properties(
+            {
+                "title": title,
+                "subject": "Machine learning results",
+                "author": "Ricardo Montañana Gómez",
+                "manager": "Dr. J. A. Gámez, Dr. J. M. Puerta",
+                "company": "UCLM",
+                "comments": "Created with Python and XlsxWriter",
+            }
+        )
+
     @staticmethod
-    def report():
+    def get_python_version():
+        return "{}.{}".format(sys.version_info.major, sys.version_info.minor)
+
+    def get_title(self):
+        return (
+            f" Benchmark ver. {__version__} - "
+            f" Python ver. {self.get_python_version()}"
+            f" with {self.env['n_folds']} Folds cross validation "
+            f" Discretization: {self.env['discretize']}  "
+            f"Stratification: {self.env['stratified']}"
+        )
+
+    def get_file_name(self):
+        return self.excel_file_name
+
+    def header(self):
+        merge_format = self.book.add_format(
+            {
+                "border": 1,
+                "bold": 1,
+                "align": "center",
+                "valign": "vcenter",
+                "font_size": 18,
+                "bg_color": self.color3,
+            }
+        )
+        merge_format_subheader = self.book.add_format(
+            {
+                "border": 1,
+                "bold": 1,
+                "align": "center",
+                "valign": "vcenter",
+                "font_size": 16,
+                "bg_color": self.color1,
+            }
+        )
+        merge_format_subheader_right = self.book.add_format(
+            {
+                "border": 1,
+                "bold": 1,
+                "align": "right",
+                "valign": "vcenter",
+                "font_size": 16,
+                "bg_color": self.color1,
+            }
+        )
+        merge_format_subheader_left = self.book.add_format(
+            {
+                "border": 1,
+                "bold": 1,
+                "align": "left",
+                "valign": "vcenter",
+                "font_size": 16,
+                "bg_color": self.color1,
+            }
+        )
+        self.sheet.merge_range(0, 0, 0, 4, self.header_text, merge_format)
+        self.sheet.merge_range(
+            1,
+            0,
+            4,
+            0,
+            f" Default score {self.env['score']}",
+            merge_format_subheader,
+        )
+        self.sheet.merge_range(
+            1,
+            1,
+            1,
+            3,
+            "Cross validation",
+            merge_format_subheader_right,
+        )
+        self.sheet.write(
+            1, 4, f"{self.env['n_folds']} Folds", merge_format_subheader_left
+        )
+        self.sheet.merge_range(
+            2,
+            1,
+            2,
+            3,
+            "Stratified",
+            merge_format_subheader_right,
+        )
+        self.sheet.write(
+            2,
+            4,
+            f"{'True' if self.env['stratified']=='1' else 'False'}",
+            merge_format_subheader_left,
+        )
+        self.sheet.merge_range(
+            3,
+            1,
+            3,
+            3,
+            "Discretized",
+            merge_format_subheader_right,
+        )
+        self.sheet.write(
+            3,
+            4,
+            f"{'True' if self.env['discretize']=='1' else 'False'}",
+            merge_format_subheader_left,
+        )
+        self.sheet.merge_range(
+            4,
+            1,
+            4,
+            3,
+            "Seeds",
+            merge_format_subheader_right,
+        )
+        self.sheet.write(
+            4, 4, f"{self.env['seeds']}", merge_format_subheader_left
+        )
+        self.update_max_length(len(self.env["seeds"]) + 1)
+        header_cols = [
+            ("Dataset", 30),
+            ("Samples", 10),
+            ("Features", 10),
+            ("Classes", 10),
+            ("Balance", 50),
+        ]
+        bold = self.book.add_format(
+            {
+                "bold": True,
+                "font_size": 14,
+                "bg_color": self.color3,
+                "border": 1,
+            }
+        )
+        i = 0
+        for item, length in header_cols:
+            self.sheet.write(5, i, item, bold)
+            self.sheet.set_column(i, i, length)
+            i += 1
+
+    def footer(self):
+        # set Balance column width to max length
+        self.sheet.set_column(4, 4, self.max_length)
+        self.sheet.freeze_panes(6, 1)
+        self.sheet.hide_gridlines(2)
+        if self.close:
+            self.book.close()
+
+    def print_line(self, result):
+        size_n = 14
+        integer = self.book.add_format(
+            {"num_format": "#,###", "font_size": size_n, "border": 1}
+        )
+        normal = self.book.add_format({"font_size": size_n, "border": 1})
+        col = 0
+        if self.row % 2 == 0:
+            normal.set_bg_color(self.color1)
+            integer.set_bg_color(self.color1)
+        else:
+            normal.set_bg_color(self.color2)
+            integer.set_bg_color(self.color2)
+        self.sheet.write(self.row, col, result.dataset, normal)
+        self.sheet.write(self.row, col + 1, result.samples, integer)
+        self.sheet.write(self.row, col + 2, result.features, integer)
+        self.sheet.write(self.row, col + 3, result.classes, normal)
+        self.sheet.write(self.row, col + 4, result.balance, normal)
+        self.update_max_length(len(result.balance))
+        self.row += 1
+
+    def update_max_length(self, value):
+        if value > self.max_length:
+            self.max_length = value
+
+    def report(self):
         data_sets = Datasets()
         color_line = TextColor.LINE1
-        print(color_line, end="")
-        print(f"{'Dataset':30s} Samp. Feat. Cls Balance")
-        print("=" * 30 + " ===== ===== === " + "=" * 40)
+        if self.excel:
+            self.header()
+        if self.output:
+            print(color_line, end="")
+            print(self.header_text)
+            print("")
+            print(f"{'Dataset':30s} Sampl. Feat. Cls Balance")
+            print("=" * 30 + " ====== ===== === " + "=" * 60)
         for dataset in data_sets:
-            X, y = data_sets.load(dataset)
+            attributes = data_sets.get_attributes(dataset)
+            attributes.dataset = dataset
+            if self.excel:
+                self.print_line(attributes)
             color_line = (
                 TextColor.LINE2
                 if color_line == TextColor.LINE1
                 else TextColor.LINE1
             )
-            values, counts = np.unique(y, return_counts=True)
-            comp = ""
-            sep = ""
-            for count in counts:
-                comp += f"{sep}{count/sum(counts)*100:5.2f}%"
-                sep = "/ "
-            print(color_line, end="")
-            print(
-                f"{dataset:30s} {X.shape[0]:5,d} {X.shape[1]:5,d} "
-                f"{len(np.unique(y)):3d} {comp:40s}"
-            )
+            if self.output:
+                print(color_line, end="")
+                print(
+                    f"{dataset:30s} {attributes.samples:6,d} "
+                    f"{attributes.features:5,d} {attributes.classes:3d} "
+                    f"{attributes.balance:40s}"
+                )
+        if self.excel:
+            self.footer()
 
 
 class SQL(BaseReport):
@@ -633,6 +907,13 @@ class Benchmark:
         self._report = {}
         self._datasets = set()
         self.visualize = visualize
+        self.__compute_best_results_ever()
+
+    def __compute_best_results_ever(self):
+        args = EnvData.load()
+        key = args["source_data"]
+        best = BestResultsEver()
+        _, self.best_score_value = best.get_name_value(key, self._score)
 
     def get_result_file_name(self):
         return os.path.join(Folders.exreport, Files.exreport(self._score))
@@ -970,7 +1251,7 @@ class Benchmark:
                 sheet.write_formula(
                     row,
                     col + 1,
-                    f"=sum({range_metric})/{BEST_ACCURACY_STREE}",
+                    f"=sum({range_metric})/{self.best_score_value}",
                     decimal_total,
                 )
                 range_rank = (
@@ -1018,7 +1299,12 @@ class Benchmark:
                 k = Excel(file_name=file_name, book=book)
                 k.report()
             sheet.freeze_panes(6, 1)
-            sheet.hide_gridlines()
+            sheet.hide_gridlines(2)
+
+        def add_datasets_sheet():
+            # Add datasets sheet
+            re = ReportDatasets(excel=True, book=book)
+            re.report()
 
         def exreport_output():
             file_name = os.path.join(
@@ -1046,6 +1332,7 @@ class Benchmark:
         footer()
         models_files()
         exreport_output()
+        add_datasets_sheet()
         book.close()
 
 
@@ -1062,13 +1349,14 @@ class StubReport(BaseReport):
 
     def footer(self, accuracy: float) -> None:
         self.accuracy = accuracy
-        self.score = accuracy / BEST_ACCURACY_STREE
+        self.score = accuracy / self._get_best_accuracy()
 
 
 class Summary:
     def __init__(self, hidden=False) -> None:
         self.results = Files().get_all_results(hidden=hidden)
         self.data = []
+        self.data_filtered = []
         self.datasets = {}
         self.models = set()
         self.hidden = hidden
@@ -1145,13 +1433,14 @@ class Summary:
         number=0,
     ) -> None:
         """Print the list of results"""
-        data = self.get_results_criteria(
-            score, model, input_data, sort_key, number
-        )
-        if data == []:
+        if self.data_filtered == []:
+            self.data_filtered = self.get_results_criteria(
+                score, model, input_data, sort_key, number
+            )
+        if self.data_filtered == []:
             raise ValueError(NO_RESULTS)
-        max_file = max(len(x["file"]) for x in data)
-        max_title = max(len(x["title"]) for x in data)
+        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
@@ -1160,10 +1449,11 @@ class Summary:
             color2 = TextColor.LINE2
         print(color1, end="")
         print(
-            f"{'Date':10s} {'File':{max_file}s} {'Score':8s} {'Time(h)':7s} "
-            f"{'Title':s}"
+            f" #  {'Date':10s} {'File':{max_file}s} {'Score':8s} "
+            f"{'Time(h)':7s} {'Title':s}"
         )
         print(
+            "===",
             "=" * 10
             + " "
             + "=" * max_file
@@ -1172,21 +1462,60 @@ class Summary:
             + " "
             + "=" * 7
             + " "
-            + "=" * max_title
+            + "=" * max_title,
         )
         print(
             "\n".join(
                 [
-                    (color2 if n % 2 == 0 else color1)
-                    + f"{x['date']} {x['file']:{max_file}s} "
+                    (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(data)
+                    for n, x in enumerate(self.data_filtered)
                 ]
             )
         )
 
+    def manage_results(self, excel, is_test):
+        """Manage results showed in the summary
+        return True if excel file is created False otherwise
+        """
+        num = ""
+        book = None
+        while True:
+            print(
+                "Which result do you want to report? (q to quit, r to list "
+                "again, number to report): ",
+                end="",
+            )
+            num = get_input(is_test)
+            if num == "r":
+                self.list_results()
+            if num == "q":
+                if excel:
+                    if book is not None:
+                        book.close()
+                        return True
+                return False
+            if num.isdigit() and int(num) < len(self.data) and int(num) >= 0:
+                rep = Report(self.data_filtered[int(num)]["file"], self.hidden)
+                rep.report()
+                if excel and not self.hidden:
+                    if book is None:
+                        file_name = Files.be_list_excel
+                        book = xlsxwriter.Workbook(
+                            file_name, {"nan_inf_to_errors": True}
+                        )
+                    excel = Excel(
+                        file_name=self.data_filtered[int(num)]["file"],
+                        book=book,
+                    )
+                    excel.report()
+            else:
+                if num not in ("r", "q"):
+                    print(f"Invalid option {num}. Try again!")
+
     def show_result(self, data: dict, title: str = "") -> None:
         def whites(n: int) -> str:
             return " " * n + color1 + "*"

benchmark/Utils.py

@@ -1,7 +1,8 @@
 import os
+import sys
 import subprocess
 
-BEST_ACCURACY_STREE = 40.282203
+PYTHON_VERSION = "{}.{}".format(sys.version_info.major, sys.version_info.minor)
 NO_RESULTS = "** No results found **"
 NO_ENV = "File .env not found"
 
@@ -26,6 +27,8 @@ 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):

benchmark/__init__.py

@@ -1,9 +1,16 @@
-from .Experiments import Experiment, Datasets, DatasetsSurcov, DatasetsTanveer
+from .Datasets import (
+    Datasets,
+    DatasetsSurcov,
+    DatasetsTanveer,
+    DatasetsArff,
+)
+from .Experiments import Experiment
 from .Results import Report, Summary
+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__ = "0.4.0"

benchmark/scripts/be_build_best.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 from benchmark.Results import ReportBest
-from benchmark.Experiments import Datasets, BestResults
+from benchmark.Experiments import BestResults
+from benchmark.Datasets import Datasets
 from benchmark.Arguments import Arguments
 
 """Build a json file with the best results of a model and its hyperparameters

benchmark/scripts/be_grid.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
-from benchmark.Experiments import GridSearch, Datasets
+from benchmark.Experiments import GridSearch
+from benchmark.Datasets import Datasets
 from benchmark.Arguments import Arguments
 
 """Do experiment and build result file, optionally print report with results

benchmark/scripts/be_list.py

@@ -1,7 +1,7 @@
 #! /usr/bin/env python
 import os
 from benchmark.Results import Summary
-from benchmark.Utils import Folders
+from benchmark.Utils import Folders, Files
 from benchmark.Arguments import Arguments
 
 """List experiments of a model
@@ -12,6 +12,7 @@ def main(args_test=None):
     arguments = Arguments()
     arguments.xset("number").xset("model", required=False).xset("key")
     arguments.xset("hidden").xset("nan").xset("score", required=False)
+    arguments.xset("excel")
     args = arguments.parse(args_test)
     data = Summary(hidden=args.hidden)
     data.acquire()
@@ -22,32 +23,39 @@ def main(args_test=None):
             sort_key=args.key,
             number=args.number,
         )
+        is_test = args_test is not None
+        if not args.nan:
+            excel_generated = data.manage_results(args.excel, is_test)
+            if args.excel and excel_generated:
+                print(f"Generated file: {Files.be_list_excel}")
+                Files.open(Files.be_list_excel, is_test)
     except ValueError as e:
         print(e)
-    else:
-        if args.nan:
-            results_nan = []
-            results = data.get_results_criteria(
-                score=args.score,
-                model=args.model,
-                input_data=None,
-                sort_key=args.key,
-                number=args.number,
+        return
+    if args.nan:
+        results_nan = []
+        results = data.get_results_criteria(
+            score=args.score,
+            model=args.model,
+            input_data=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
             )
-            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.data_filtered = []
+            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),
                 )
-                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

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 import os
-from benchmark.Experiments import Experiment, Datasets
+from benchmark.Experiments import Experiment
+from benchmark.Datasets import Datasets
 from benchmark.Results import Report
 from benchmark.Arguments import Arguments
 

benchmark/scripts/be_print_strees.py

@@ -3,7 +3,7 @@ import os
 import json
 from stree import Stree
 from graphviz import Source
-from benchmark.Experiments import Datasets
+from benchmark.Datasets import Datasets
 from benchmark.Utils import Files, Folders
 from benchmark.Arguments import Arguments
 

benchmark/scripts/be_report.py

@@ -21,7 +21,11 @@ def main(args_test=None):
     if args.grid:
         args.best = None
     if args.file is None and args.best is None and args.grid is None:
-        ReportDatasets.report()
+        report = ReportDatasets(args.excel)
+        report.report()
+        if args.excel:
+            is_test = args_test is not None
+            Files.open(report.get_file_name(), is_test)
     else:
         if args.best is not None or args.grid is not None:
             report = ReportBest(args.score, args.model, args.best, args.grid)

benchmark/tests/.env

@@ -5,3 +5,5 @@ 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

benchmark/tests/.env.arff

@@ -0,0 +1,8 @@
+score=accuracy
+platform=MacBookpro16
+n_folds=5
+model=ODTE
+stratified=0
+source_data=Arff
+seeds=[271, 314, 171]
+discretize=1

benchmark/tests/.env.dist

@@ -5,3 +5,5 @@ 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

benchmark/tests/.env.surcov

@@ -5,3 +5,5 @@ 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

benchmark/tests/.gitignore

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

benchmark/tests/Benchmark_test.py

@@ -5,6 +5,7 @@ from openpyxl import load_workbook
 from .TestBase import TestBase
 from ..Utils import Folders, Files, NO_RESULTS
 from ..Results import Benchmark
+from .._version import __version__
 
 
 class BenchmarkTest(TestBase):
@@ -89,6 +90,15 @@ class BenchmarkTest(TestBase):
         self.assertTrue(os.path.exists(benchmark.get_tex_file()))
         self.check_file_file(benchmark.get_tex_file(), "exreport_tex")
 
+    @staticmethod
+    def generate_excel_sheet(test, sheet, file_name):
+        with open(os.path.join("test_files", file_name), "w") as f:
+            for row in range(1, sheet.max_row + 1):
+                for col in range(1, sheet.max_column + 1):
+                    value = sheet.cell(row=row, column=col).value
+                    if value is not None:
+                        print(f'{row};{col};"{value}"', file=f)
+
     def test_excel_output(self):
         benchmark = Benchmark("accuracy", visualize=False)
         benchmark.compile_results()
@@ -98,9 +108,16 @@ 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}")
-            # ExcelTest.generate_excel_sheet(
-            #     self, 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,
+            )

benchmark/tests/BestResults_test.py

@@ -1,6 +1,7 @@
 import os
 from .TestBase import TestBase
-from ..Experiments import BestResults, Datasets
+from ..Experiments import BestResults
+from ..Datasets import Datasets
 
 
 class BestResultTest(TestBase):

benchmark/tests/Dataset_test.py

@@ -1,6 +1,7 @@
 import shutil
 from .TestBase import TestBase
-from ..Experiments import Randomized, Datasets
+from ..Experiments import Randomized
+from ..Datasets import Datasets
 
 
 class DatasetTest(TestBase):
@@ -22,12 +23,31 @@ class DatasetTest(TestBase):
 
     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_discretized("iris", dataframe=False)
+        dataset = dt.load_discretized("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 = {
             ".env.dist": ["balance-scale", "balloons"],
             ".env.surcov": ["iris", "wine"],
+            ".env.arff": ["iris", "wine"],
         }
         for key, value in test.items():
             self.set_env(key)
@@ -51,6 +71,11 @@ class DatasetTest(TestBase):
         self.assertSequenceEqual(X.shape, (625, 4))
         self.assertSequenceEqual(y.shape, (625,))
 
+    def test_create_with_unknown_dataset(self):
+        with self.assertRaises(ValueError) as msg:
+            Datasets("unknown")
+        self.assertEqual(str(msg.exception), "Unknown dataset: unknown")
+
     def test_load_unknown_dataset(self):
         dt = Datasets()
         with self.assertRaises(ValueError) as msg:
@@ -61,6 +86,7 @@ class DatasetTest(TestBase):
         test = {
             ".env.dist": "balloons",
             ".env.surcov": "wine",
+            ".env.arff": "iris",
         }
         for key, value in test.items():
             self.set_env(key)

benchmark/tests/Experiment_test.py

@@ -1,6 +1,7 @@
 import json
 from .TestBase import TestBase
-from ..Experiments import Experiment, Datasets
+from ..Experiments import Experiment
+from ..Datasets import Datasets
 
 
 class ExperimentTest(TestBase):

benchmark/tests/GridSearch_test.py

@@ -1,6 +1,7 @@
 import json
 from .TestBase import TestBase
-from ..Experiments import GridSearch, Datasets
+from ..Experiments import GridSearch
+from ..Datasets import Datasets
 
 
 class GridSearchTest(TestBase):
@@ -77,7 +78,9 @@ class GridSearchTest(TestBase):
                 "v. 1.2.4, Computed on Test on 2022-02-22 at 12:00:00 took 1s",
             ],
         }
-        self.assertSequenceEqual(data, expected)
+        for key, value in expected.items():
+            self.assertEqual(data[key][0], value[0])
+            self.assertDictEqual(data[key][1], value[1])
 
     def test_duration_message(self):
         expected = ["47.234s", "5.421m", "1.177h"]

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):
@@ -33,6 +35,38 @@ 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)

benchmark/tests/Report_test.py

@@ -2,11 +2,14 @@ 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, BaseReport, ReportBest, ReportDatasets, 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(
@@ -75,7 +78,17 @@ class ReportTest(TestBase):
         report = ReportBest("accuracy", "STree", best=False, grid=True)
         with patch(self.output, new=StringIO()) as stdout:
             report.report()
-        self.check_output_file(stdout, "report_grid")
+        file_name = "report_grid.test"
+        with open(os.path.join(self.test_files, file_name)) as f:
+            expected = f.read().splitlines()
+        output_text = stdout.getvalue().splitlines()
+        # Compare replacing STree version
+        for line, index in zip(expected, range(len(expected))):
+            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)
@@ -87,4 +100,12 @@ class ReportTest(TestBase):
     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/TestBase.py

@@ -14,6 +14,9 @@ class TestBase(unittest.TestCase):
         os.chdir(os.path.dirname(os.path.abspath(__file__)))
         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)
 
     def remove_files(self, files, folder):
@@ -30,8 +33,10 @@ class TestBase(unittest.TestCase):
                     if value is not None:
                         print(f'{row};{col};"{value}"', file=f)
 
-    def check_excel_sheet(self, sheet, file_name):
-        file_name += ".test"
+    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=";")
             for row, col, value in expected:
@@ -42,18 +47,31 @@ 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):
-        file_name += ".test"
+        file_name += self.ext
         with open(os.path.join(self.test_files, file_name)) as f:
             expected = f.read()
         self.assertEqual(output.getvalue(), expected)
 
+    def replace_STree_version(self, line, output, index):
+        idx = line.find(self.stree_version)
+        return line.replace(self.stree_version, 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:
             computed = f.read()
-        expected_file += ".test"
+        expected_file += self.ext
         with open(os.path.join(self.test_files, expected_file)) as f:
             expected = f.read()
         self.assertEqual(computed, expected)

benchmark/tests/Util_test.py

@@ -178,6 +178,8 @@ class UtilTest(TestBase):
             "model": "ODTE",
             "stratified": "0",
             "source_data": "Tanveer",
+            "seeds": "[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]",
+            "discretize": "0",
         }
         computed = EnvData().load()
         self.assertDictEqual(computed, expected)

benchmark/tests/datasets/all.txt

@@ -1,2 +1,2 @@
-iris
-wine
+iris,class
+wine,class

benchmark/tests/datasets/hayes-roth.arff

@@ -0,0 +1,305 @@
+% 1. Title: Hayes-Roth & Hayes-Roth (1977) Database
+% 
+% 2. Source Information:
+%    (a) Creators: Barbara and Frederick Hayes-Roth
+%    (b) Donor: David W. Aha (aha@ics.uci.edu) (714) 856-8779   
+%    (c) Date: March, 1989
+% 
+% 3. Past Usage:
+%     1. Hayes-Roth, B., & Hayes-Roth, F. (1977).  Concept learning and the
+%        recognition and classification of exemplars.  Journal of Verbal Learning
+%        and Verbal Behavior, 16, 321-338.
+%        -- Results: 
+%           -- Human subjects classification and recognition performance:
+% 	       1. decreases with distance from the prototype,
+% 	       2. is better on unseen prototypes than old instances, and
+% 	       3. improves with presentation frequency during learning.
+%     2. Anderson, J.R., & Kline, P.J. (1979).  A learning system and its 
+%        psychological implications.  In Proceedings of the Sixth International
+%        Joint Conference on Artificial Intelligence (pp. 16-21).  Tokyo, Japan:
+%        Morgan Kaufmann.
+%        -- Partitioned the results into 4 classes:
+% 	    1. prototypes
+% 	    2. near-prototypes with high presentation frequency during learning
+% 	    3. near-prototypes with low presentation frequency during learning
+% 	    4. instances that are far from protoypes
+%        -- Described evidence that ACT's classification confidence and
+%           recognition behaviors closely simulated human subjects' behaviors.
+%     3. Aha, D.W. (1989).  Incremental learning of independent, overlapping, and
+%        graded concept descriptions with an instance-based process framework.
+%        Manuscript submitted for publication.
+%        -- Used same partition as Anderson & Kline
+%        -- Described evidence that Bloom's classification confidence behavior
+% 	  is similar to the human subjects' behavior.  Bloom fitted the data
+% 	  more closely than did ACT. 
+% 
+% 4. Relevant Information:
+%      This database contains 5 numeric-valued attributes.  Only a subset of
+%      3 are used during testing (the latter 3).  Furthermore, only 2 of the
+%      3 concepts are "used" during testing (i.e., those with the prototypes
+%      000 and 111).  I've mapped all values to their zero-indexing equivalents.
+% 
+%      Some instances could be placed in either category 0 or 1.  I've followed
+%      the authors' suggestion, placing them in each category with equal
+%      probability.
+% 
+%      I've replaced the actual values of the attributes (i.e., hobby has values
+%      chess, sports and stamps) with numeric values.  I think this is how 
+%      the authors' did this when testing the categorization models described
+%      in the paper.  I find this unfair.  While the subjects were able to bring
+%      background knowledge to bear on the attribute values and their
+%      relationships, the algorithms were provided with no such knowledge.  I'm
+%      uncertain whether the 2 distractor attributes (name and hobby) are
+%      presented to the authors' algorithms during testing.  However, it is clear
+%      that only the age, educational status, and marital status attributes are
+%      given during the human subjects' transfer tests.  
+%     
+% 5. Number of Instances: 132 training instances, 28 test instances
+% 
+% 6. Number of Attributes: 5 plus the class membership attribute.  3 concepts.
+% 
+% 7. Attribute Information:
+%       -- 1. name: distinct for each instance and represented numerically
+%       -- 2. hobby: nominal values ranging between 1 and 3
+%       -- 3. age: nominal values ranging between 1 and 4
+%       -- 4. educational level: nominal values ranging between 1 and 4
+%       -- 5. marital status: nominal values ranging between 1 and 4
+%       -- 6. class: nominal value between 1 and 3
+% 
+% 9. Missing Attribute Values: none
+% 
+% 10. Class Distribution: see below
+% 
+% 11. Detailed description of the experiment:
+%   1. 3 categories (1, 2, and neither -- which I call 3)
+%      -- some of the instances could be classified in either class 1 or 2, and
+%         they have been evenly distributed between the two classes
+%   2. 5 Attributes
+%      -- A. name (a randomly-generated number between 1 and 132)
+%      -- B. hobby (a randomly-generated number between 1 and 3)
+%      -- C. age (a number between 1 and 4)
+%      -- D. education level (a number between 1 and 4)
+%      -- E. marital status (a number between 1 and 4)
+%   3. Classification: 
+%      -- only attributes C-E are diagnostic; values for A and B are ignored
+%      -- Class Neither: if a 4 occurs for any attribute C-E
+%      -- Class 1: Otherwise, if (# of 1's)>(# of 2's) for attributes C-E
+%      -- Class 2: Otherwise, if (# of 2's)>(# of 1's) for attributes C-E
+%      -- Either 1 or 2: Otherwise, if (# of 2's)=(# of 1's) for attributes C-E
+%   4. Prototypes:
+%      -- Class 1: 111
+%      -- Class 2: 222
+%      -- Class Either: 333
+%      -- Class Neither: 444  
+%   5. Number of training instances: 132
+%      -- Each instance presented 0, 1, or 10 times
+%      -- None of the prototypes seen during training
+%      -- 3 instances from each of categories 1, 2, and either are repeated 
+%         10 times each
+%      -- 3 additional instances from the Either category are shown during
+%         learning
+%   5. Number of test instances: 28
+%      -- All 9 class 1
+%      -- All 9 class 2
+%      -- All 6 class Either
+%      -- All 4 prototypes
+%      --------------------
+%      --    28 total
+% 
+% Observations of interest:
+%   1. Relative classification confidence of 
+%      -- prototypes for classes 1 and 2 (2 instances)
+%         (Anderson calls these Class 1 instances)
+%      -- instances of class 1 with frequency 10 during training and
+%         instances of class 2 with frequency 10 during training that
+%         are 1 value away from their respective prototypes (6 instances)
+%         (Anderson calls these Class 2 instances)
+%      -- instances of class 1 with frequency 1 during training and 
+%         instances of class 2 with frequency 1 during training that
+%         are 1 value away from their respective prototypes (6 instances)
+%         (Anderson calls these Class 3 instances)
+%      -- instances of class 1 with frequency 1 during training and 
+%         instances of class 2 with frequency 1 during training that
+%         are 2 values away from their respective prototypes (6 instances)
+%         (Anderson calls these Class 4 instances)
+%  2. Relative classification recognition of them also
+% 
+% Some Expected results:
+%    Both frequency and distance from prototype will effect the classification
+%    accuracy of instances.  Greater the frequency, higher the classification
+%    confidence.  Closer to prototype, higher the classification confidence.
+%
+% Information about the dataset
+% CLASSTYPE: nominal
+% CLASSINDEX: last
+%
+
+@relation hayes-roth
+
+@attribute hobby INTEGER
+@attribute age INTEGER
+@attribute educational_level INTEGER
+@attribute marital_status INTEGER
+@attribute class {1,2,3,4}
+
+@data
+2,1,1,2,1
+2,1,3,2,2
+3,1,4,1,3
+2,4,2,2,3
+1,1,3,4,3
+1,1,3,2,2
+3,1,3,2,2
+3,4,2,4,3
+2,2,1,1,1
+3,2,1,1,1
+1,2,1,1,1
+2,2,3,4,3
+1,1,2,1,1
+2,1,2,2,2
+2,4,1,4,3
+1,1,3,3,1
+3,2,1,2,2
+1,2,1,1,1
+3,3,2,1,1
+3,1,3,2,1
+1,2,2,1,2
+3,2,1,3,1
+2,1,2,1,1
+3,2,1,3,1
+2,3,2,1,1
+3,2,2,1,2
+3,2,1,3,2
+2,1,2,2,2
+1,1,3,2,1
+3,2,1,1,1
+1,4,1,1,3
+2,2,1,3,1
+1,2,1,3,2
+1,1,1,2,1
+2,4,3,1,3
+3,1,2,2,2
+1,1,2,2,2
+3,2,2,1,2
+1,2,1,2,2
+3,4,3,2,3
+2,2,2,1,2
+2,2,1,2,2
+3,2,1,3,2
+3,2,1,1,1
+3,1,2,1,1
+1,2,1,3,2
+2,1,1,2,1
+1,1,1,2,1
+1,2,2,3,2
+3,3,1,1,1
+3,3,3,1,1
+3,2,1,2,2
+3,2,1,2,2
+3,1,2,1,1
+1,1,1,2,1
+2,1,3,2,1
+2,2,2,1,2
+2,1,2,1,1
+2,2,1,3,1
+2,1,2,2,2
+1,2,4,2,3
+2,2,1,2,2
+1,1,2,4,3
+1,3,2,1,1
+2,4,4,2,3
+2,3,2,1,1
+3,1,2,2,2
+1,1,2,2,2
+1,3,2,4,3
+1,1,2,2,2
+3,1,4,2,3
+2,1,3,2,2
+1,1,3,2,2
+3,1,3,2,1
+1,2,4,4,3
+1,4,2,1,3
+2,1,2,1,1
+3,4,1,2,3
+2,2,1,1,1
+1,1,2,1,1
+2,2,4,3,3
+3,1,2,2,2
+1,1,3,2,1
+1,2,1,3,1
+1,4,4,1,3
+3,3,3,2,2
+2,2,1,3,2
+3,3,2,1,2
+1,1,1,3,1
+2,2,1,2,2
+2,2,2,1,2
+2,3,2,3,2
+1,3,2,1,2
+2,2,1,2,2
+1,1,1,2,1
+3,2,2,1,2
+3,2,1,1,1
+1,1,2,1,1
+3,1,4,4,3
+3,3,2,1,2
+2,3,2,1,2
+2,1,3,1,1
+1,2,1,2,2
+3,1,1,2,1
+2,2,4,1,3
+1,2,2,1,2
+2,3,2,1,2
+2,2,1,4,3
+1,4,2,3,3
+2,2,1,1,1
+1,2,1,1,1
+2,2,3,2,2
+1,3,2,1,1
+3,1,2,1,1
+3,1,1,2,1
+3,3,1,4,3
+2,3,4,1,3
+1,2,3,3,2
+3,3,2,2,2
+3,3,4,2,3
+1,2,2,1,2
+2,1,1,4,3
+3,1,2,2,2
+3,2,2,4,3
+2,3,1,3,1
+2,1,1,2,1
+3,4,1,3,3
+1,1,4,3,3
+2,1,2,1,1
+1,2,1,2,2
+1,2,2,1,2
+3,1,1,2,1
+1,1,1,2,1
+1,1,2,1,1
+1,2,1,1,1
+1,1,1,3,1
+1,1,3,1,1
+1,3,1,1,1
+1,1,3,3,1
+1,3,1,3,1
+1,3,3,1,1
+1,2,2,1,2
+1,2,1,2,2
+1,1,2,2,2
+1,2,2,3,2
+1,2,3,2,2
+1,3,2,2,2
+1,2,3,3,2
+1,3,2,3,2
+1,3,3,2,2
+1,1,3,2,1
+1,3,2,1,2
+1,2,1,3,1
+1,2,3,1,2
+1,1,2,3,1
+1,3,1,2,2
+1,1,1,1,1
+1,2,2,2,2
+1,3,3,3,1
+1,4,4,4,3

benchmark/tests/datasets/iris.arff

@@ -0,0 +1,225 @@
+% 1. Title: Iris Plants Database
+% 
+% 2. Sources:
+%      (a) Creator: R.A. Fisher
+%      (b) Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
+%      (c) Date: July, 1988
+% 
+% 3. Past Usage:
+%    - Publications: too many to mention!!!  Here are a few.
+%    1. Fisher,R.A. "The use of multiple measurements in taxonomic problems"
+%       Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions
+%       to Mathematical Statistics" (John Wiley, NY, 1950).
+%    2. Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.
+%       (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.
+%    3. Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
+%       Structure and Classification Rule for Recognition in Partially Exposed
+%       Environments".  IEEE Transactions on Pattern Analysis and Machine
+%       Intelligence, Vol. PAMI-2, No. 1, 67-71.
+%       -- Results:
+%          -- very low misclassification rates (0% for the setosa class)
+%    4. Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule".  IEEE 
+%       Transactions on Information Theory, May 1972, 431-433.
+%       -- Results:
+%          -- very low misclassification rates again
+%    5. See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al's AUTOCLASS II
+%       conceptual clustering system finds 3 classes in the data.
+% 
+% 4. Relevant Information:
+%    --- This is perhaps the best known database to be found in the pattern
+%        recognition literature.  Fisher's paper is a classic in the field
+%        and is referenced frequently to this day.  (See Duda & Hart, for
+%        example.)  The data set contains 3 classes of 50 instances each,
+%        where each class refers to a type of iris plant.  One class is
+%        linearly separable from the other 2; the latter are NOT linearly
+%        separable from each other.
+%    --- Predicted attribute: class of iris plant.
+%    --- This is an exceedingly simple domain.
+% 
+% 5. Number of Instances: 150 (50 in each of three classes)
+% 
+% 6. Number of Attributes: 4 numeric, predictive attributes and the class
+% 
+% 7. Attribute Information:
+%    1. sepal length in cm
+%    2. sepal width in cm
+%    3. petal length in cm
+%    4. petal width in cm
+%    5. class: 
+%       -- Iris Setosa
+%       -- Iris Versicolour
+%       -- Iris Virginica
+% 
+% 8. Missing Attribute Values: None
+% 
+% Summary Statistics:
+%  	           Min  Max   Mean    SD   Class Correlation
+%    sepal length: 4.3  7.9   5.84  0.83    0.7826   
+%     sepal width: 2.0  4.4   3.05  0.43   -0.4194
+%    petal length: 1.0  6.9   3.76  1.76    0.9490  (high!)
+%     petal width: 0.1  2.5   1.20  0.76    0.9565  (high!)
+% 
+% 9. Class Distribution: 33.3% for each of 3 classes.
+
+@RELATION iris
+
+@ATTRIBUTE sepallength	REAL
+@ATTRIBUTE sepalwidth 	REAL
+@ATTRIBUTE petallength 	REAL
+@ATTRIBUTE petalwidth	REAL
+@ATTRIBUTE class 	{Iris-setosa,Iris-versicolor,Iris-virginica}
+
+@DATA
+5.1,3.5,1.4,0.2,Iris-setosa
+4.9,3.0,1.4,0.2,Iris-setosa
+4.7,3.2,1.3,0.2,Iris-setosa
+4.6,3.1,1.5,0.2,Iris-setosa
+5.0,3.6,1.4,0.2,Iris-setosa
+5.4,3.9,1.7,0.4,Iris-setosa
+4.6,3.4,1.4,0.3,Iris-setosa
+5.0,3.4,1.5,0.2,Iris-setosa
+4.4,2.9,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.4,3.7,1.5,0.2,Iris-setosa
+4.8,3.4,1.6,0.2,Iris-setosa
+4.8,3.0,1.4,0.1,Iris-setosa
+4.3,3.0,1.1,0.1,Iris-setosa
+5.8,4.0,1.2,0.2,Iris-setosa
+5.7,4.4,1.5,0.4,Iris-setosa
+5.4,3.9,1.3,0.4,Iris-setosa
+5.1,3.5,1.4,0.3,Iris-setosa
+5.7,3.8,1.7,0.3,Iris-setosa
+5.1,3.8,1.5,0.3,Iris-setosa
+5.4,3.4,1.7,0.2,Iris-setosa
+5.1,3.7,1.5,0.4,Iris-setosa
+4.6,3.6,1.0,0.2,Iris-setosa
+5.1,3.3,1.7,0.5,Iris-setosa
+4.8,3.4,1.9,0.2,Iris-setosa
+5.0,3.0,1.6,0.2,Iris-setosa
+5.0,3.4,1.6,0.4,Iris-setosa
+5.2,3.5,1.5,0.2,Iris-setosa
+5.2,3.4,1.4,0.2,Iris-setosa
+4.7,3.2,1.6,0.2,Iris-setosa
+4.8,3.1,1.6,0.2,Iris-setosa
+5.4,3.4,1.5,0.4,Iris-setosa
+5.2,4.1,1.5,0.1,Iris-setosa
+5.5,4.2,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.0,3.2,1.2,0.2,Iris-setosa
+5.5,3.5,1.3,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+4.4,3.0,1.3,0.2,Iris-setosa
+5.1,3.4,1.5,0.2,Iris-setosa
+5.0,3.5,1.3,0.3,Iris-setosa
+4.5,2.3,1.3,0.3,Iris-setosa
+4.4,3.2,1.3,0.2,Iris-setosa
+5.0,3.5,1.6,0.6,Iris-setosa
+5.1,3.8,1.9,0.4,Iris-setosa
+4.8,3.0,1.4,0.3,Iris-setosa
+5.1,3.8,1.6,0.2,Iris-setosa
+4.6,3.2,1.4,0.2,Iris-setosa
+5.3,3.7,1.5,0.2,Iris-setosa
+5.0,3.3,1.4,0.2,Iris-setosa
+7.0,3.2,4.7,1.4,Iris-versicolor
+6.4,3.2,4.5,1.5,Iris-versicolor
+6.9,3.1,4.9,1.5,Iris-versicolor
+5.5,2.3,4.0,1.3,Iris-versicolor
+6.5,2.8,4.6,1.5,Iris-versicolor
+5.7,2.8,4.5,1.3,Iris-versicolor
+6.3,3.3,4.7,1.6,Iris-versicolor
+4.9,2.4,3.3,1.0,Iris-versicolor
+6.6,2.9,4.6,1.3,Iris-versicolor
+5.2,2.7,3.9,1.4,Iris-versicolor
+5.0,2.0,3.5,1.0,Iris-versicolor
+5.9,3.0,4.2,1.5,Iris-versicolor
+6.0,2.2,4.0,1.0,Iris-versicolor
+6.1,2.9,4.7,1.4,Iris-versicolor
+5.6,2.9,3.6,1.3,Iris-versicolor
+6.7,3.1,4.4,1.4,Iris-versicolor
+5.6,3.0,4.5,1.5,Iris-versicolor
+5.8,2.7,4.1,1.0,Iris-versicolor
+6.2,2.2,4.5,1.5,Iris-versicolor
+5.6,2.5,3.9,1.1,Iris-versicolor
+5.9,3.2,4.8,1.8,Iris-versicolor
+6.1,2.8,4.0,1.3,Iris-versicolor
+6.3,2.5,4.9,1.5,Iris-versicolor
+6.1,2.8,4.7,1.2,Iris-versicolor
+6.4,2.9,4.3,1.3,Iris-versicolor
+6.6,3.0,4.4,1.4,Iris-versicolor
+6.8,2.8,4.8,1.4,Iris-versicolor
+6.7,3.0,5.0,1.7,Iris-versicolor
+6.0,2.9,4.5,1.5,Iris-versicolor
+5.7,2.6,3.5,1.0,Iris-versicolor
+5.5,2.4,3.8,1.1,Iris-versicolor
+5.5,2.4,3.7,1.0,Iris-versicolor
+5.8,2.7,3.9,1.2,Iris-versicolor
+6.0,2.7,5.1,1.6,Iris-versicolor
+5.4,3.0,4.5,1.5,Iris-versicolor
+6.0,3.4,4.5,1.6,Iris-versicolor
+6.7,3.1,4.7,1.5,Iris-versicolor
+6.3,2.3,4.4,1.3,Iris-versicolor
+5.6,3.0,4.1,1.3,Iris-versicolor
+5.5,2.5,4.0,1.3,Iris-versicolor
+5.5,2.6,4.4,1.2,Iris-versicolor
+6.1,3.0,4.6,1.4,Iris-versicolor
+5.8,2.6,4.0,1.2,Iris-versicolor
+5.0,2.3,3.3,1.0,Iris-versicolor
+5.6,2.7,4.2,1.3,Iris-versicolor
+5.7,3.0,4.2,1.2,Iris-versicolor
+5.7,2.9,4.2,1.3,Iris-versicolor
+6.2,2.9,4.3,1.3,Iris-versicolor
+5.1,2.5,3.0,1.1,Iris-versicolor
+5.7,2.8,4.1,1.3,Iris-versicolor
+6.3,3.3,6.0,2.5,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+7.1,3.0,5.9,2.1,Iris-virginica
+6.3,2.9,5.6,1.8,Iris-virginica
+6.5,3.0,5.8,2.2,Iris-virginica
+7.6,3.0,6.6,2.1,Iris-virginica
+4.9,2.5,4.5,1.7,Iris-virginica
+7.3,2.9,6.3,1.8,Iris-virginica
+6.7,2.5,5.8,1.8,Iris-virginica
+7.2,3.6,6.1,2.5,Iris-virginica
+6.5,3.2,5.1,2.0,Iris-virginica
+6.4,2.7,5.3,1.9,Iris-virginica
+6.8,3.0,5.5,2.1,Iris-virginica
+5.7,2.5,5.0,2.0,Iris-virginica
+5.8,2.8,5.1,2.4,Iris-virginica
+6.4,3.2,5.3,2.3,Iris-virginica
+6.5,3.0,5.5,1.8,Iris-virginica
+7.7,3.8,6.7,2.2,Iris-virginica
+7.7,2.6,6.9,2.3,Iris-virginica
+6.0,2.2,5.0,1.5,Iris-virginica
+6.9,3.2,5.7,2.3,Iris-virginica
+5.6,2.8,4.9,2.0,Iris-virginica
+7.7,2.8,6.7,2.0,Iris-virginica
+6.3,2.7,4.9,1.8,Iris-virginica
+6.7,3.3,5.7,2.1,Iris-virginica
+7.2,3.2,6.0,1.8,Iris-virginica
+6.2,2.8,4.8,1.8,Iris-virginica
+6.1,3.0,4.9,1.8,Iris-virginica
+6.4,2.8,5.6,2.1,Iris-virginica
+7.2,3.0,5.8,1.6,Iris-virginica
+7.4,2.8,6.1,1.9,Iris-virginica
+7.9,3.8,6.4,2.0,Iris-virginica
+6.4,2.8,5.6,2.2,Iris-virginica
+6.3,2.8,5.1,1.5,Iris-virginica
+6.1,2.6,5.6,1.4,Iris-virginica
+7.7,3.0,6.1,2.3,Iris-virginica
+6.3,3.4,5.6,2.4,Iris-virginica
+6.4,3.1,5.5,1.8,Iris-virginica
+6.0,3.0,4.8,1.8,Iris-virginica
+6.9,3.1,5.4,2.1,Iris-virginica
+6.7,3.1,5.6,2.4,Iris-virginica
+6.9,3.1,5.1,2.3,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+6.8,3.2,5.9,2.3,Iris-virginica
+6.7,3.3,5.7,2.5,Iris-virginica
+6.7,3.0,5.2,2.3,Iris-virginica
+6.3,2.5,5.0,1.9,Iris-virginica
+6.5,3.0,5.2,2.0,Iris-virginica
+6.2,3.4,5.4,2.3,Iris-virginica
+5.9,3.0,5.1,1.8,Iris-virginica
+%
+%
+%

benchmark/tests/datasets/wine.arff

@@ -0,0 +1,302 @@
+% 1. Title of Database: Wine recognition data
+% 	Updated Sept 21, 1998 by C.Blake : Added attribute information
+% 
+% 2. Sources:
+%    (a) Forina, M. et al, PARVUS - An Extendible Package for Data
+%        Exploration, Classification and Correlation. Institute of Pharmaceutical
+%        and Food Analysis and Technologies, Via Brigata Salerno, 
+%        16147 Genoa, Italy.
+% 
+%    (b) Stefan Aeberhard, email: stefan@coral.cs.jcu.edu.au
+%    (c) July 1991
+% 3. Past Usage:
+% 
+%    (1)
+%    S. Aeberhard, D. Coomans and O. de Vel,
+%    Comparison of Classifiers in High Dimensional Settings,
+%    Tech. Rep. no. 92-02, (1992), Dept. of Computer Science and Dept. of
+%    Mathematics and Statistics, James Cook University of North Queensland.
+%    (Also submitted to Technometrics).
+% 
+%    The data was used with many others for comparing various 
+%    classifiers. The classes are separable, though only RDA 
+%    has achieved 100% correct classification.
+%    (RDA : 100%, QDA 99.4%, LDA 98.9%, 1NN 96.1% (z-transformed data))
+%    (All results using the leave-one-out technique)
+% 
+%    In a classification context, this is a well posed problem 
+%    with "well behaved" class structures. A good data set 
+%    for first testing of a new classifier, but not very 
+%    challenging.
+% 
+%    (2) 
+%    S. Aeberhard, D. Coomans and O. de Vel,
+%    "THE CLASSIFICATION PERFORMANCE OF RDA"
+%    Tech. Rep. no. 92-01, (1992), Dept. of Computer Science and Dept. of
+%    Mathematics and Statistics, James Cook University of North Queensland.
+%    (Also submitted to Journal of Chemometrics).
+% 
+%    Here, the data was used to illustrate the superior performance of
+%    the use of a new appreciation function with RDA. 
+% 
+% 4. Relevant Information:
+% 
+%    -- These data are the results of a chemical analysis of
+%       wines grown in the same region in Italy but derived from three
+%       different cultivars.
+%       The analysis determined the quantities of 13 constituents
+%       found in each of the three types of wines. 
+% 
+%    -- I think that the initial data set had around 30 variables, but 
+%       for some reason I only have the 13 dimensional version. 
+%       I had a list of what the 30 or so variables were, but a.) 
+%       I lost it, and b.), I would not know which 13 variables
+%       are included in the set.
+% 
+%    -- The attributes are (dontated by Riccardo Leardi, 
+% 	riclea@anchem.unige.it )
+%  	1) Alcohol
+%  	2) Malic acid
+%  	3) Ash
+% 	4) Alcalinity of ash  
+%  	5) Magnesium
+% 	6) Total phenols
+%  	7) Flavanoids
+%  	8) Nonflavanoid phenols
+%  	9) Proanthocyanins
+% 	10)Color intensity
+%  	11)Hue
+%  	12)OD280/OD315 of diluted wines
+%  	13)Proline            
+% 
+% 5. Number of Instances
+% 
+%       	class 1 59
+% 	class 2 71
+% 	class 3 48
+% 
+% 6. Number of Attributes 
+% 	
+% 	13
+% 
+% 7. For Each Attribute:
+% 
+% 	All attributes are continuous
+% 	
+% 	No statistics available, but suggest to standardise
+% 	variables for certain uses (e.g. for us with classifiers
+% 	which are NOT scale invariant)
+% 
+% 	NOTE: 1st attribute is class identifier (1-3)
+% 
+% 8. Missing Attribute Values:
+% 
+% 	None
+% 
+% 9. Class Distribution: number of instances per class
+% 
+%       	class 1 59
+% 	class 2 71
+% 	class 3 48
+%
+% Information about the dataset
+% CLASSTYPE: nominal
+% CLASSINDEX: first
+%
+
+@relation wine
+
+@attribute class {1,2,3}
+@attribute Alcohol REAL
+@attribute Malic_acid REAL
+@attribute Ash REAL
+@attribute Alcalinity_of_ash REAL
+@attribute Magnesium INTEGER
+@attribute Total_phenols REAL
+@attribute Flavanoids REAL
+@attribute Nonflavanoid_phenols REAL
+@attribute Proanthocyanins REAL
+@attribute Color_intensity REAL
+@attribute Hue REAL
+@attribute OD280/OD315_of_diluted_wines REAL
+@attribute Proline INTEGER
+
+@data
+1,14.23,1.71,2.43,15.6,127,2.8,3.06,.28,2.29,5.64,1.04,3.92,1065
+1,13.2,1.78,2.14,11.2,100,2.65,2.76,.26,1.28,4.38,1.05,3.4,1050
+1,13.16,2.36,2.67,18.6,101,2.8,3.24,.3,2.81,5.68,1.03,3.17,1185
+1,14.37,1.95,2.5,16.8,113,3.85,3.49,.24,2.18,7.8,.86,3.45,1480
+1,13.24,2.59,2.87,21,118,2.8,2.69,.39,1.82,4.32,1.04,2.93,735
+1,14.2,1.76,2.45,15.2,112,3.27,3.39,.34,1.97,6.75,1.05,2.85,1450
+1,14.39,1.87,2.45,14.6,96,2.5,2.52,.3,1.98,5.25,1.02,3.58,1290
+1,14.06,2.15,2.61,17.6,121,2.6,2.51,.31,1.25,5.05,1.06,3.58,1295
+1,14.83,1.64,2.17,14,97,2.8,2.98,.29,1.98,5.2,1.08,2.85,1045
+1,13.86,1.35,2.27,16,98,2.98,3.15,.22,1.85,7.22,1.01,3.55,1045
+1,14.1,2.16,2.3,18,105,2.95,3.32,.22,2.38,5.75,1.25,3.17,1510
+1,14.12,1.48,2.32,16.8,95,2.2,2.43,.26,1.57,5,1.17,2.82,1280
+1,13.75,1.73,2.41,16,89,2.6,2.76,.29,1.81,5.6,1.15,2.9,1320
+1,14.75,1.73,2.39,11.4,91,3.1,3.69,.43,2.81,5.4,1.25,2.73,1150
+1,14.38,1.87,2.38,12,102,3.3,3.64,.29,2.96,7.5,1.2,3,1547
+1,13.63,1.81,2.7,17.2,112,2.85,2.91,.3,1.46,7.3,1.28,2.88,1310
+1,14.3,1.92,2.72,20,120,2.8,3.14,.33,1.97,6.2,1.07,2.65,1280
+1,13.83,1.57,2.62,20,115,2.95,3.4,.4,1.72,6.6,1.13,2.57,1130
+1,14.19,1.59,2.48,16.5,108,3.3,3.93,.32,1.86,8.7,1.23,2.82,1680
+1,13.64,3.1,2.56,15.2,116,2.7,3.03,.17,1.66,5.1,.96,3.36,845
+1,14.06,1.63,2.28,16,126,3,3.17,.24,2.1,5.65,1.09,3.71,780
+1,12.93,3.8,2.65,18.6,102,2.41,2.41,.25,1.98,4.5,1.03,3.52,770
+1,13.71,1.86,2.36,16.6,101,2.61,2.88,.27,1.69,3.8,1.11,4,1035
+1,12.85,1.6,2.52,17.8,95,2.48,2.37,.26,1.46,3.93,1.09,3.63,1015
+1,13.5,1.81,2.61,20,96,2.53,2.61,.28,1.66,3.52,1.12,3.82,845
+1,13.05,2.05,3.22,25,124,2.63,2.68,.47,1.92,3.58,1.13,3.2,830
+1,13.39,1.77,2.62,16.1,93,2.85,2.94,.34,1.45,4.8,.92,3.22,1195
+1,13.3,1.72,2.14,17,94,2.4,2.19,.27,1.35,3.95,1.02,2.77,1285
+1,13.87,1.9,2.8,19.4,107,2.95,2.97,.37,1.76,4.5,1.25,3.4,915
+1,14.02,1.68,2.21,16,96,2.65,2.33,.26,1.98,4.7,1.04,3.59,1035
+1,13.73,1.5,2.7,22.5,101,3,3.25,.29,2.38,5.7,1.19,2.71,1285
+1,13.58,1.66,2.36,19.1,106,2.86,3.19,.22,1.95,6.9,1.09,2.88,1515
+1,13.68,1.83,2.36,17.2,104,2.42,2.69,.42,1.97,3.84,1.23,2.87,990
+1,13.76,1.53,2.7,19.5,132,2.95,2.74,.5,1.35,5.4,1.25,3,1235
+1,13.51,1.8,2.65,19,110,2.35,2.53,.29,1.54,4.2,1.1,2.87,1095
+1,13.48,1.81,2.41,20.5,100,2.7,2.98,.26,1.86,5.1,1.04,3.47,920
+1,13.28,1.64,2.84,15.5,110,2.6,2.68,.34,1.36,4.6,1.09,2.78,880
+1,13.05,1.65,2.55,18,98,2.45,2.43,.29,1.44,4.25,1.12,2.51,1105
+1,13.07,1.5,2.1,15.5,98,2.4,2.64,.28,1.37,3.7,1.18,2.69,1020
+1,14.22,3.99,2.51,13.2,128,3,3.04,.2,2.08,5.1,.89,3.53,760
+1,13.56,1.71,2.31,16.2,117,3.15,3.29,.34,2.34,6.13,.95,3.38,795
+1,13.41,3.84,2.12,18.8,90,2.45,2.68,.27,1.48,4.28,.91,3,1035
+1,13.88,1.89,2.59,15,101,3.25,3.56,.17,1.7,5.43,.88,3.56,1095
+1,13.24,3.98,2.29,17.5,103,2.64,2.63,.32,1.66,4.36,.82,3,680
+1,13.05,1.77,2.1,17,107,3,3,.28,2.03,5.04,.88,3.35,885
+1,14.21,4.04,2.44,18.9,111,2.85,2.65,.3,1.25,5.24,.87,3.33,1080
+1,14.38,3.59,2.28,16,102,3.25,3.17,.27,2.19,4.9,1.04,3.44,1065
+1,13.9,1.68,2.12,16,101,3.1,3.39,.21,2.14,6.1,.91,3.33,985
+1,14.1,2.02,2.4,18.8,103,2.75,2.92,.32,2.38,6.2,1.07,2.75,1060
+1,13.94,1.73,2.27,17.4,108,2.88,3.54,.32,2.08,8.90,1.12,3.1,1260
+1,13.05,1.73,2.04,12.4,92,2.72,3.27,.17,2.91,7.2,1.12,2.91,1150
+1,13.83,1.65,2.6,17.2,94,2.45,2.99,.22,2.29,5.6,1.24,3.37,1265
+1,13.82,1.75,2.42,14,111,3.88,3.74,.32,1.87,7.05,1.01,3.26,1190
+1,13.77,1.9,2.68,17.1,115,3,2.79,.39,1.68,6.3,1.13,2.93,1375
+1,13.74,1.67,2.25,16.4,118,2.6,2.9,.21,1.62,5.85,.92,3.2,1060
+1,13.56,1.73,2.46,20.5,116,2.96,2.78,.2,2.45,6.25,.98,3.03,1120
+1,14.22,1.7,2.3,16.3,118,3.2,3,.26,2.03,6.38,.94,3.31,970
+1,13.29,1.97,2.68,16.8,102,3,3.23,.31,1.66,6,1.07,2.84,1270
+1,13.72,1.43,2.5,16.7,108,3.4,3.67,.19,2.04,6.8,.89,2.87,1285
+2,12.37,.94,1.36,10.6,88,1.98,.57,.28,.42,1.95,1.05,1.82,520
+2,12.33,1.1,2.28,16,101,2.05,1.09,.63,.41,3.27,1.25,1.67,680
+2,12.64,1.36,2.02,16.8,100,2.02,1.41,.53,.62,5.75,.98,1.59,450
+2,13.67,1.25,1.92,18,94,2.1,1.79,.32,.73,3.8,1.23,2.46,630
+2,12.37,1.13,2.16,19,87,3.5,3.1,.19,1.87,4.45,1.22,2.87,420
+2,12.17,1.45,2.53,19,104,1.89,1.75,.45,1.03,2.95,1.45,2.23,355
+2,12.37,1.21,2.56,18.1,98,2.42,2.65,.37,2.08,4.6,1.19,2.3,678
+2,13.11,1.01,1.7,15,78,2.98,3.18,.26,2.28,5.3,1.12,3.18,502
+2,12.37,1.17,1.92,19.6,78,2.11,2,.27,1.04,4.68,1.12,3.48,510
+2,13.34,.94,2.36,17,110,2.53,1.3,.55,.42,3.17,1.02,1.93,750
+2,12.21,1.19,1.75,16.8,151,1.85,1.28,.14,2.5,2.85,1.28,3.07,718
+2,12.29,1.61,2.21,20.4,103,1.1,1.02,.37,1.46,3.05,.906,1.82,870
+2,13.86,1.51,2.67,25,86,2.95,2.86,.21,1.87,3.38,1.36,3.16,410
+2,13.49,1.66,2.24,24,87,1.88,1.84,.27,1.03,3.74,.98,2.78,472
+2,12.99,1.67,2.6,30,139,3.3,2.89,.21,1.96,3.35,1.31,3.5,985
+2,11.96,1.09,2.3,21,101,3.38,2.14,.13,1.65,3.21,.99,3.13,886
+2,11.66,1.88,1.92,16,97,1.61,1.57,.34,1.15,3.8,1.23,2.14,428
+2,13.03,.9,1.71,16,86,1.95,2.03,.24,1.46,4.6,1.19,2.48,392
+2,11.84,2.89,2.23,18,112,1.72,1.32,.43,.95,2.65,.96,2.52,500
+2,12.33,.99,1.95,14.8,136,1.9,1.85,.35,2.76,3.4,1.06,2.31,750
+2,12.7,3.87,2.4,23,101,2.83,2.55,.43,1.95,2.57,1.19,3.13,463
+2,12,.92,2,19,86,2.42,2.26,.3,1.43,2.5,1.38,3.12,278
+2,12.72,1.81,2.2,18.8,86,2.2,2.53,.26,1.77,3.9,1.16,3.14,714
+2,12.08,1.13,2.51,24,78,2,1.58,.4,1.4,2.2,1.31,2.72,630
+2,13.05,3.86,2.32,22.5,85,1.65,1.59,.61,1.62,4.8,.84,2.01,515
+2,11.84,.89,2.58,18,94,2.2,2.21,.22,2.35,3.05,.79,3.08,520
+2,12.67,.98,2.24,18,99,2.2,1.94,.3,1.46,2.62,1.23,3.16,450
+2,12.16,1.61,2.31,22.8,90,1.78,1.69,.43,1.56,2.45,1.33,2.26,495
+2,11.65,1.67,2.62,26,88,1.92,1.61,.4,1.34,2.6,1.36,3.21,562
+2,11.64,2.06,2.46,21.6,84,1.95,1.69,.48,1.35,2.8,1,2.75,680
+2,12.08,1.33,2.3,23.6,70,2.2,1.59,.42,1.38,1.74,1.07,3.21,625
+2,12.08,1.83,2.32,18.5,81,1.6,1.5,.52,1.64,2.4,1.08,2.27,480
+2,12,1.51,2.42,22,86,1.45,1.25,.5,1.63,3.6,1.05,2.65,450
+2,12.69,1.53,2.26,20.7,80,1.38,1.46,.58,1.62,3.05,.96,2.06,495
+2,12.29,2.83,2.22,18,88,2.45,2.25,.25,1.99,2.15,1.15,3.3,290
+2,11.62,1.99,2.28,18,98,3.02,2.26,.17,1.35,3.25,1.16,2.96,345
+2,12.47,1.52,2.2,19,162,2.5,2.27,.32,3.28,2.6,1.16,2.63,937
+2,11.81,2.12,2.74,21.5,134,1.6,.99,.14,1.56,2.5,.95,2.26,625
+2,12.29,1.41,1.98,16,85,2.55,2.5,.29,1.77,2.9,1.23,2.74,428
+2,12.37,1.07,2.1,18.5,88,3.52,3.75,.24,1.95,4.5,1.04,2.77,660
+2,12.29,3.17,2.21,18,88,2.85,2.99,.45,2.81,2.3,1.42,2.83,406
+2,12.08,2.08,1.7,17.5,97,2.23,2.17,.26,1.4,3.3,1.27,2.96,710
+2,12.6,1.34,1.9,18.5,88,1.45,1.36,.29,1.35,2.45,1.04,2.77,562
+2,12.34,2.45,2.46,21,98,2.56,2.11,.34,1.31,2.8,.8,3.38,438
+2,11.82,1.72,1.88,19.5,86,2.5,1.64,.37,1.42,2.06,.94,2.44,415
+2,12.51,1.73,1.98,20.5,85,2.2,1.92,.32,1.48,2.94,1.04,3.57,672
+2,12.42,2.55,2.27,22,90,1.68,1.84,.66,1.42,2.7,.86,3.3,315
+2,12.25,1.73,2.12,19,80,1.65,2.03,.37,1.63,3.4,1,3.17,510
+2,12.72,1.75,2.28,22.5,84,1.38,1.76,.48,1.63,3.3,.88,2.42,488
+2,12.22,1.29,1.94,19,92,2.36,2.04,.39,2.08,2.7,.86,3.02,312
+2,11.61,1.35,2.7,20,94,2.74,2.92,.29,2.49,2.65,.96,3.26,680
+2,11.46,3.74,1.82,19.5,107,3.18,2.58,.24,3.58,2.9,.75,2.81,562
+2,12.52,2.43,2.17,21,88,2.55,2.27,.26,1.22,2,.9,2.78,325
+2,11.76,2.68,2.92,20,103,1.75,2.03,.6,1.05,3.8,1.23,2.5,607
+2,11.41,.74,2.5,21,88,2.48,2.01,.42,1.44,3.08,1.1,2.31,434
+2,12.08,1.39,2.5,22.5,84,2.56,2.29,.43,1.04,2.9,.93,3.19,385
+2,11.03,1.51,2.2,21.5,85,2.46,2.17,.52,2.01,1.9,1.71,2.87,407
+2,11.82,1.47,1.99,20.8,86,1.98,1.6,.3,1.53,1.95,.95,3.33,495
+2,12.42,1.61,2.19,22.5,108,2,2.09,.34,1.61,2.06,1.06,2.96,345
+2,12.77,3.43,1.98,16,80,1.63,1.25,.43,.83,3.4,.7,2.12,372
+2,12,3.43,2,19,87,2,1.64,.37,1.87,1.28,.93,3.05,564
+2,11.45,2.4,2.42,20,96,2.9,2.79,.32,1.83,3.25,.8,3.39,625
+2,11.56,2.05,3.23,28.5,119,3.18,5.08,.47,1.87,6,.93,3.69,465
+2,12.42,4.43,2.73,26.5,102,2.2,2.13,.43,1.71,2.08,.92,3.12,365
+2,13.05,5.8,2.13,21.5,86,2.62,2.65,.3,2.01,2.6,.73,3.1,380
+2,11.87,4.31,2.39,21,82,2.86,3.03,.21,2.91,2.8,.75,3.64,380
+2,12.07,2.16,2.17,21,85,2.6,2.65,.37,1.35,2.76,.86,3.28,378
+2,12.43,1.53,2.29,21.5,86,2.74,3.15,.39,1.77,3.94,.69,2.84,352
+2,11.79,2.13,2.78,28.5,92,2.13,2.24,.58,1.76,3,.97,2.44,466
+2,12.37,1.63,2.3,24.5,88,2.22,2.45,.4,1.9,2.12,.89,2.78,342
+2,12.04,4.3,2.38,22,80,2.1,1.75,.42,1.35,2.6,.79,2.57,580
+3,12.86,1.35,2.32,18,122,1.51,1.25,.21,.94,4.1,.76,1.29,630
+3,12.88,2.99,2.4,20,104,1.3,1.22,.24,.83,5.4,.74,1.42,530
+3,12.81,2.31,2.4,24,98,1.15,1.09,.27,.83,5.7,.66,1.36,560
+3,12.7,3.55,2.36,21.5,106,1.7,1.2,.17,.84,5,.78,1.29,600
+3,12.51,1.24,2.25,17.5,85,2,.58,.6,1.25,5.45,.75,1.51,650
+3,12.6,2.46,2.2,18.5,94,1.62,.66,.63,.94,7.1,.73,1.58,695
+3,12.25,4.72,2.54,21,89,1.38,.47,.53,.8,3.85,.75,1.27,720
+3,12.53,5.51,2.64,25,96,1.79,.6,.63,1.1,5,.82,1.69,515
+3,13.49,3.59,2.19,19.5,88,1.62,.48,.58,.88,5.7,.81,1.82,580
+3,12.84,2.96,2.61,24,101,2.32,.6,.53,.81,4.92,.89,2.15,590
+3,12.93,2.81,2.7,21,96,1.54,.5,.53,.75,4.6,.77,2.31,600
+3,13.36,2.56,2.35,20,89,1.4,.5,.37,.64,5.6,.7,2.47,780
+3,13.52,3.17,2.72,23.5,97,1.55,.52,.5,.55,4.35,.89,2.06,520
+3,13.62,4.95,2.35,20,92,2,.8,.47,1.02,4.4,.91,2.05,550
+3,12.25,3.88,2.2,18.5,112,1.38,.78,.29,1.14,8.21,.65,2,855
+3,13.16,3.57,2.15,21,102,1.5,.55,.43,1.3,4,.6,1.68,830
+3,13.88,5.04,2.23,20,80,.98,.34,.4,.68,4.9,.58,1.33,415
+3,12.87,4.61,2.48,21.5,86,1.7,.65,.47,.86,7.65,.54,1.86,625
+3,13.32,3.24,2.38,21.5,92,1.93,.76,.45,1.25,8.42,.55,1.62,650
+3,13.08,3.9,2.36,21.5,113,1.41,1.39,.34,1.14,9.40,.57,1.33,550
+3,13.5,3.12,2.62,24,123,1.4,1.57,.22,1.25,8.60,.59,1.3,500
+3,12.79,2.67,2.48,22,112,1.48,1.36,.24,1.26,10.8,.48,1.47,480
+3,13.11,1.9,2.75,25.5,116,2.2,1.28,.26,1.56,7.1,.61,1.33,425
+3,13.23,3.3,2.28,18.5,98,1.8,.83,.61,1.87,10.52,.56,1.51,675
+3,12.58,1.29,2.1,20,103,1.48,.58,.53,1.4,7.6,.58,1.55,640
+3,13.17,5.19,2.32,22,93,1.74,.63,.61,1.55,7.9,.6,1.48,725
+3,13.84,4.12,2.38,19.5,89,1.8,.83,.48,1.56,9.01,.57,1.64,480
+3,12.45,3.03,2.64,27,97,1.9,.58,.63,1.14,7.5,.67,1.73,880
+3,14.34,1.68,2.7,25,98,2.8,1.31,.53,2.7,13,.57,1.96,660
+3,13.48,1.67,2.64,22.5,89,2.6,1.1,.52,2.29,11.75,.57,1.78,620
+3,12.36,3.83,2.38,21,88,2.3,.92,.5,1.04,7.65,.56,1.58,520
+3,13.69,3.26,2.54,20,107,1.83,.56,.5,.8,5.88,.96,1.82,680
+3,12.85,3.27,2.58,22,106,1.65,.6,.6,.96,5.58,.87,2.11,570
+3,12.96,3.45,2.35,18.5,106,1.39,.7,.4,.94,5.28,.68,1.75,675
+3,13.78,2.76,2.3,22,90,1.35,.68,.41,1.03,9.58,.7,1.68,615
+3,13.73,4.36,2.26,22.5,88,1.28,.47,.52,1.15,6.62,.78,1.75,520
+3,13.45,3.7,2.6,23,111,1.7,.92,.43,1.46,10.68,.85,1.56,695
+3,12.82,3.37,2.3,19.5,88,1.48,.66,.4,.97,10.26,.72,1.75,685
+3,13.58,2.58,2.69,24.5,105,1.55,.84,.39,1.54,8.66,.74,1.8,750
+3,13.4,4.6,2.86,25,112,1.98,.96,.27,1.11,8.5,.67,1.92,630
+3,12.2,3.03,2.32,19,96,1.25,.49,.4,.73,5.5,.66,1.83,510
+3,12.77,2.39,2.28,19.5,86,1.39,.51,.48,.64,9.899999,.57,1.63,470
+3,14.16,2.51,2.48,20,91,1.68,.7,.44,1.24,9.7,.62,1.71,660
+3,13.71,5.65,2.45,20.5,95,1.68,.61,.52,1.06,7.7,.64,1.74,740
+3,13.4,3.91,2.48,23,102,1.8,.75,.43,1.41,7.3,.7,1.56,750
+3,13.27,4.28,2.26,20,120,1.59,.69,.43,1.35,10.2,.59,1.56,835
+3,13.17,2.59,2.37,20,120,1.65,.68,.53,1.46,9.3,.6,1.62,840
+3,14.13,4.1,2.74,24.5,96,2.05,.76,.56,1.35,9.2,.61,1.6,560

benchmark/tests/results/grid_output_accuracy_STree.json

@@ -6,7 +6,7 @@
             "kernel": "liblinear",
             "multiclass_strategy": "ovr"
         },
-        "v. 1.2.4, Computed on Test on 2022-02-22 at 12:00:00 took 1s"
+        "v. 1.3.0, Computed on Test on 2022-02-22 at 12:00:00 took 1s"
     ],
     "balloons": [
         0.625,
@@ -15,6 +15,6 @@
             "kernel": "linear",
             "multiclass_strategy": "ovr"
         },
-        "v. 1.2.4, Computed on Test on 2022-02-22 at 12:00:00 took 1s"
+        "v. 1.3.0, Computed on Test on 2022-02-22 at 12:00:00 took 1s"
     ]
 }

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

@@ -3,6 +3,8 @@
   "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",

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

@@ -3,6 +3,8 @@
   "title": "Test default paramters with RandomForest",
   "model": "RandomForest",
   "version": "-",
+  "language_version": "3.11x",
+  "language": "Python",
   "stratified": false,
   "folds": 5,
   "date": "2022-01-14",

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

@@ -3,6 +3,8 @@
   "model": "STree",
   "stratified": false,
   "folds": 5,
+  "language_version": "3.11x",
+  "language": "Python",
   "date": "2021-09-30",
   "time": "11:42:07",
   "duration": 624.2505249977112,

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

@@ -1,6 +1,8 @@
 {
   "score_name": "accuracy",
   "model": "STree",
+  "language": "Python",
+  "language_version": "3.11x",
   "stratified": false,
   "folds": 5,
   "date": "2021-10-27",

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

@@ -1,6 +1,8 @@
 {
   "score_name": "accuracy",
   "model": "STree",
+  "language_version": "3.11x",
+  "language": "Python",
   "stratified": false,
   "folds": 5,
   "date": "2021-11-01",

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):
@@ -43,9 +44,19 @@ class BeBenchmarkTest(TestBase):
             Folders.exreport, 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(

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()

benchmark/tests/scripts/Be_List_test.py

@@ -1,5 +1,7 @@
 import os
-from ...Utils import Folders, NO_RESULTS
+from unittest.mock import patch
+from openpyxl import load_workbook
+from ...Utils import Folders, Files, NO_RESULTS
 from ..TestBase import TestBase
 
 
@@ -7,12 +9,64 @@ class BeListTest(TestBase):
     def setUp(self):
         self.prepare_scripts_env()
 
-    def test_be_list(self):
+    @patch("benchmark.Results.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.Results.get_input", side_effect=iter(["x", "q"]))
+    def test_be_list_invalid_option(self, input_data):
+        stdout, stderr = self.execute_script("be_list", ["-m", "STree"])
+        self.assertEqual(stderr.getvalue(), "")
+        self.check_output_file(stdout, "be_list_model_invalid")
+
+    @patch("benchmark.Results.get_input", side_effect=iter(["0", "q"]))
+    def test_be_list_report(self, input_data):
+        stdout, stderr = self.execute_script("be_list", ["-m", "STree"])
+        self.assertEqual(stderr.getvalue(), "")
+        self.check_output_file(stdout, "be_list_report")
+
+    @patch("benchmark.Results.get_input", side_effect=iter(["q"]))
+    def test_be_list_report_excel_none(self, input_data):
+        stdout, stderr = self.execute_script(
+            "be_list", ["-m", "STree", "-x", "1"]
+        )
+        self.assertEqual(stderr.getvalue(), "")
+        self.check_output_file(stdout, "be_list_model")
+
+    @patch("benchmark.Results.get_input", side_effect=iter(["r", "q"]))
+    def test_be_list_twice(self, input_data):
+        stdout, stderr = self.execute_script("be_list", ["-m", "STree"])
+        self.assertEqual(stderr.getvalue(), "")
+        self.check_output_file(stdout, "be_list_model_2")
+
+    @patch("benchmark.Results.get_input", side_effect=iter(["2", "q"]))
+    def test_be_list_report_excel(self, input_data):
+        stdout, stderr = self.execute_script(
+            "be_list", ["-m", "STree", "-x", "1"]
+        )
+        self.assertEqual(stderr.getvalue(), "")
+        self.check_output_file(stdout, "be_list_report_excel")
+        book = load_workbook(Files.be_list_excel)
+        sheet = book["STree"]
+        self.check_excel_sheet(sheet, "excel")
+
+    @patch("benchmark.Results.get_input", side_effect=iter(["2", "1", "q"]))
+    def test_be_list_report_excel_twice(self, input_data):
+        stdout, stderr = self.execute_script(
+            "be_list", ["-m", "STree", "-x", "1"]
+        )
+        self.assertEqual(stderr.getvalue(), "")
+        self.check_output_file(stdout, "be_list_report_excel_2")
+        book = load_workbook(Files.be_list_excel)
+        sheet = book["STree"]
+        self.check_excel_sheet(sheet, "excel")
+        sheet = book["STree2"]
+        self.check_excel_sheet(sheet, "excel2")
+
+    @patch("benchmark.Results.get_input", return_value="q")
+    def test_be_list_no_data(self, input_data):
         stdout, stderr = self.execute_script(
             "be_list", ["-m", "Wodt", "-s", "f1-macro"]
         )
@@ -41,7 +95,8 @@ class BeListTest(TestBase):
             swap_files(Folders.results, Folders.hidden_results, file_name)
             self.fail("test_be_list_nan() should not raise exception")
 
-    def test_be_list_nan_no_nan(self):
+    @patch("benchmark.Results.get_input", return_value="q")
+    def test_be_list_nan_no_nan(self, input_data):
         stdout, stderr = self.execute_script("be_list", ["--nan", "1"])
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "be_list_no_nan")

benchmark/tests/scripts/Be_Report_test.py

@@ -1,7 +1,8 @@
 import os
 from openpyxl import load_workbook
-from ...Utils import Folders
+from ...Utils import Folders, Files
 from ..TestBase import TestBase
+from ..._version import __version__
 
 
 class BeReportTest(TestBase):
@@ -14,6 +15,7 @@ class BeReportTest(TestBase):
             "results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.xlsx",
         ]
         self.remove_files(files, Folders.results)
+        self.remove_files([Files.datasets_report_excel], os.getcwd())
         return super().tearDown()
 
     def test_be_report(self):
@@ -41,7 +43,37 @@ class BeReportTest(TestBase):
     def test_be_report_datatsets(self):
         stdout, stderr = self.execute_script("be_report", [])
         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", ["-x", "1"])
+        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(), 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(
@@ -55,7 +87,16 @@ class BeReportTest(TestBase):
             "be_report", ["-s", "accuracy", "-m", "STree", "-g", "1"]
         )
         self.assertEqual(stderr.getvalue(), "")
-        self.check_output_file(stdout, "report_grid")
+        file_name = "report_grid.test"
+        with open(os.path.join(self.test_files, file_name)) as f:
+            expected = f.read().splitlines()
+        output_text = stdout.getvalue().splitlines()
+        # Compare replacing STree version
+        for line, index in zip(expected, range(len(expected))):
+            if "1.2.4" in line:
+                # replace STree version
+                line = self.replace_STree_version(line, output_text, index)
+            self.assertEqual(line, output_text[index])
 
     def test_be_report_best_both(self):
         stdout, stderr = self.execute_script(

benchmark/tests/test_files/be_build_best_report.test

@@ -7,5 +7,5 @@ Dataset                        Score    File/Message
 balance-scale                  0.963520 results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.json                       {'base_estimator__C': 57, 'base_estimator__gamma': 0.1, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1} 
 balloons                       0.785000 results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.json                       {'base_estimator__C': 5, 'base_estimator__gamma': 0.14, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1} 
 ******************************************************************************************************************************************************************
-* Scores compared to stree_default accuracy (liblinear-ovr) .:  0.0434                                                                                           *
+* accuracy compared to STree_default (liblinear-ovr) .:  0.0434                                                                                                  *
 ******************************************************************************************************************************************************************

benchmark/tests/test_files/be_list_model.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
+Which result do you want to report? (q to quit, r to list again, number to report): 

benchmark/tests/test_files/be_list_model_2.test

@@ -0,0 +1,11 @@
+ #  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
+Which result do you want to report? (q to quit, r to list again, number to report):  #  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
+Which result do you want to report? (q to quit, r to list again, number to report): 

benchmark/tests/test_files/be_list_model_invalid.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
+Which result do you want to report? (q to quit, r to list again, number to report): Invalid option x. Try again!
+Which result do you want to report? (q to quit, r to list again, number to report): 

benchmark/tests/test_files/be_list_nan.test

@@ -1,13 +1,13 @@
-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
+ #  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
 
 ****************************** 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
+ #  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_no_nan.test

@@ -1,7 +1,7 @@
-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
+ #  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_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
+Which result do you want to report? (q to quit, r to list again, number to report): *************************************************************************************************************************
+* 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                                              *
+* 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'} 
+*************************************************************************************************************************
+* accuracy compared to STree_default (liblinear-ovr) .:  0.0379                                                         *
+*************************************************************************************************************************
+Which result do you want to report? (q to quit, r to list again, number to report): 

benchmark/tests/test_files/be_list_report_excel.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
+Which result do you want to report? (q to quit, r to list again, number to report): *************************************************************************************************************************
+* STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07             *
+* With gridsearched hyperparameters                                                                                     *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Execution took  624.25 seconds,   0.17 hours, on iMac27                                                               *
+* Score is accuracy                                                                                                     *
+*************************************************************************************************************************
+
+Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score           Time              Hyperparameters 
+============================== ====== ===== === ======= ======= ======= =============== ================= =============== 
+balance-scale                     625     4   3    7.00    4.00    3.00 0.970560±0.0150   0.014049±0.0020 {'C': 10000.0, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+balloons                           16     4   2    3.00    2.00    2.00 0.860000±0.2850   0.000854±0.0000 {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+*************************************************************************************************************************
+* accuracy compared to STree_default (liblinear-ovr) .:  0.0454                                                         *
+*************************************************************************************************************************
+Which result do you want to report? (q to quit, r to list again, number to report): Generated file: some_results.xlsx

benchmark/tests/test_files/be_list_report_excel_2.test

@@ -0,0 +1,36 @@
+ #  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
+Which result do you want to report? (q to quit, r to list again, number to report): *************************************************************************************************************************
+* STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07             *
+* With gridsearched hyperparameters                                                                                     *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Execution took  624.25 seconds,   0.17 hours, on iMac27                                                               *
+* Score is accuracy                                                                                                     *
+*************************************************************************************************************************
+
+Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score           Time              Hyperparameters 
+============================== ====== ===== === ======= ======= ======= =============== ================= =============== 
+balance-scale                     625     4   3    7.00    4.00    3.00 0.970560±0.0150   0.014049±0.0020 {'C': 10000.0, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+balloons                           16     4   2    3.00    2.00    2.00 0.860000±0.2850   0.000854±0.0000 {'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'} 
+*************************************************************************************************************************
+* accuracy compared to STree_default (liblinear-ovr) .:  0.0454                                                         *
+*************************************************************************************************************************
+Which result do you want to report? (q to quit, r to list again, number to report): *************************************************************************************************************************
+* STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-10-27 09:40:40             *
+* default A                                                                                                             *
+* Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1] Stratified: False                                              *
+* Execution took 3395.01 seconds,   0.94 hours, on iMac27                                                               *
+* Score is accuracy                                                                                                     *
+*************************************************************************************************************************
+
+Dataset                        Sampl. Feat. Cls Nodes   Leaves  Depth   Score           Time              Hyperparameters 
+============================== ====== ===== === ======= ======= ======= =============== ================= =============== 
+balance-scale                     625     4   3   11.08    5.90    5.90 0.980000±0.0010   0.285207±0.0603 {'splitter': 'best', 'max_features': 'auto'} 
+balloons                           16     4   2    4.12    2.56    2.56 0.695000±0.2757   0.021201±0.0035 {'splitter': 'best', 'max_features': 'auto'} 
+*************************************************************************************************************************
+* accuracy compared to STree_default (liblinear-ovr) .:  0.0416                                                         *
+*************************************************************************************************************************
+Which result do you want to report? (q to quit, r to list again, number to report): Generated file: some_results.xlsx

benchmark/tests/test_files/be_main_best.test

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

benchmark/tests/test_files/be_main_complete.test

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

benchmark/tests/test_files/be_main_dataset.test

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

benchmark/tests/test_files/be_main_grid.test

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

benchmark/tests/test_files/be_summary_list_model.test

@@ -26,10 +26,10 @@
 * results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json                      *
 *                                                                               *
 *********************************************************************************
-Date       File                                                            Score    Time(h) Title
-========== =============================================================== ======== ======= ============================================
-2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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
-2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
-2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
-2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest
+ #  Date       File                                                            Score    Time(h) Title
+=== ========== =============================================================== ======== ======= ============================================
+  0 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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 2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
+  3 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
+  4 2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest

benchmark/tests/test_files/be_summary_list_score.test

@@ -26,10 +26,10 @@
 * results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json                      *
 *                                                                               *
 *********************************************************************************
-Date       File                                                            Score    Time(h) Title
-========== =============================================================== ======== ======= ============================================
-2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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
-2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
-2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
-2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest
+ #  Date       File                                                            Score    Time(h) Title
+=== ========== =============================================================== ======== ======= ============================================
+  0 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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 2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
+  3 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
+  4 2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest

benchmark/tests/test_files/be_summary_list_score_all.test

@@ -26,13 +26,13 @@
 * results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json                      *
 *                                                                               *
 *********************************************************************************
-Date       File                                                            Score    Time(h) Title
-========== =============================================================== ======== ======= ============================================
-2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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
-2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
-2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
-2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest
+ #  Date       File                                                            Score    Time(h) Title
+=== ========== =============================================================== ======== ======= ============================================
+  0 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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 2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
+  3 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
+  4 2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest
 ** No results found **
 ** No results found **
 ** No results found **

benchmark/tests/test_files/be_summary_list_score_model.test

@@ -26,10 +26,10 @@
 * results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json                      *
 *                                                                               *
 *********************************************************************************
-Date       File                                                            Score    Time(h) Title
-========== =============================================================== ======== ======= ============================================
-2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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
-2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
-2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
-2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest
+ #  Date       File                                                            Score    Time(h) Title
+=== ========== =============================================================== ======== ======= ============================================
+  0 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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 2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
+  3 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
+  4 2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest

benchmark/tests/test_files/excel.test

@@ -1,4 +1,4 @@
-1;1;" Report STree ver. 1.2.3 with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07"
+1;1;" STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07"
 2;1;" With gridsearched hyperparameters"
 3;1;" Score is accuracy"
 3;2;" Execution time"
@@ -45,4 +45,4 @@
 8;10;"0.0008541679382324218"
 8;11;"3.629469326417878e-05"
 8;12;"{'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'}"
-10;1;"** Accuracy compared to stree_default (liblinear-ovr) .:  0.0454"
+10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0454"

benchmark/tests/test_files/excel2.test

@@ -0,0 +1,48 @@
+1;1;" STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-10-27 09:40:40"
+2;1;" default A"
+3;1;" Score is accuracy"
+3;2;" Execution time"
+3;5;"3,395.01 s"
+3;7;" "
+3;8;"Platform"
+3;9;"iMac27"
+3;10;"Random seeds: [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+4;5;"  0.94 h"
+4;10;"Stratified: False"
+6;1;"Dataset"
+6;2;"Samples"
+6;3;"Features"
+6;4;"Classes"
+6;5;"Nodes"
+6;6;"Leaves"
+6;7;"Depth"
+6;8;"Score"
+6;9;"Score Std."
+6;10;"Time"
+6;11;"Time Std."
+6;12;"Hyperparameters"
+7;1;"balance-scale"
+7;2;"625"
+7;3;"4"
+7;4;"3"
+7;5;"11.08"
+7;6;"5.9"
+7;7;"5.9"
+7;8;"0.98"
+7;9;"0.001"
+7;10;"0.2852065515518188"
+7;11;"0.06031593282605064"
+7;12;"{'splitter': 'best', 'max_features': 'auto'}"
+8;1;"balloons"
+8;2;"16"
+8;3;"4"
+8;4;"2"
+8;5;"4.12"
+8;6;"2.56"
+8;7;"2.56"
+8;8;"0.695"
+8;9;"0.2756860130252853"
+8;10;"0.02120100021362305"
+8;11;"0.003526023309468471"
+8;12;"{'splitter': 'best', 'max_features': 'auto'}"
+10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0416"

benchmark/tests/test_files/excel_add_ODTE.test

@@ -1,4 +1,4 @@
-1;1;" Report ODTE ver. 0.3.2 with 5 Folds cross validation and 10 random seeds. 2022-04-20 10:52:20"
+1;1;" ODTE ver. 0.3.2 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2022-04-20 10:52:20"
 2;1;" Gridsearched hyperparams v022.1b random_init"
 3;1;" Score is accuracy"
 3;2;" Execution time"
@@ -45,4 +45,4 @@
 8;10;"0.1156062078475952"
 8;11;"0.0127842418285999"
 8;12;"{'base_estimator__C': 5, 'base_estimator__gamma': 0.14, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
-10;1;"** Accuracy compared to stree_default (liblinear-ovr) .:  0.0434"
+10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0434"

benchmark/tests/test_files/excel_add_STree.test

@@ -1,4 +1,4 @@
-1;1;" Report STree ver. 1.2.3 with 5 Folds cross validation and 10 random seeds. 2021-10-27 09:40:40"
+1;1;" STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-10-27 09:40:40"
 2;1;" default A"
 3;1;" Score is accuracy"
 3;2;" Execution time"
@@ -43,4 +43,4 @@
 8;10;"0.02120100021362305"
 8;11;"0.003526023309468471"
 8;12;"{'splitter': 'best', 'max_features': 'auto'}"
-10;1;"** Accuracy compared to stree_default (liblinear-ovr) .:  0.0416"
+10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0416"

benchmark/tests/test_files/excel_compared.test

@@ -1,4 +1,4 @@
-1;1;" Report STree ver. 1.2.3 with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07"
+1;1;" STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07"
 2;1;" With gridsearched hyperparameters"
 3;1;" Score is accuracy"
 3;2;" Execution time"
@@ -49,4 +49,4 @@
 11;2;"✔"
 11;3;1
 11;4;"Equal to best"
-13;1;"** Accuracy compared to stree_default (liblinear-ovr) .:  0.0454"
+13;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0454"

benchmark/tests/test_files/exreport_excel_Datasets.test

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

benchmark/tests/test_files/exreport_excel_ODTE.test

@@ -1,4 +1,4 @@
-1;1;" Report ODTE ver. 0.3.2 with 5 Folds cross validation and 10 random seeds. 2022-04-20 10:52:20"
+1;1;" ODTE ver. 0.3.2 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2022-04-20 10:52:20"
 2;1;" Gridsearched hyperparams v022.1b random_init"
 3;1;" Score is accuracy"
 3;2;" Execution time"
@@ -45,4 +45,4 @@
 8;10;"0.1156062078475952"
 8;11;"0.0127842418285999"
 8;12;"{'base_estimator__C': 5, 'base_estimator__gamma': 0.14, 'base_estimator__kernel': 'rbf', 'base_estimator__multiclass_strategy': 'ovr', 'n_estimators': 100, 'n_jobs': -1}"
-10;1;"** Accuracy compared to stree_default (liblinear-ovr) .:  0.0434"
+10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0434"

benchmark/tests/test_files/exreport_excel_RandomForest.test

@@ -1,4 +1,4 @@
-1;1;" Report RandomForest ver. - with 5 Folds cross validation and 10 random seeds. 2022-01-14 12:39:30"
+1;1;" RandomForest ver. - Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2022-01-14 12:39:30"
 2;1;" Test default paramters with RandomForest"
 3;1;" Score is accuracy"
 3;2;" Execution time"
@@ -45,4 +45,4 @@
 8;10;"0.07016648769378662"
 8;11;"0.002460508923990468"
 8;12;"{}"
-10;1;"** Accuracy compared to stree_default (liblinear-ovr) .:  0.0363"
+10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0363"

benchmark/tests/test_files/exreport_excel_STree.test

@@ -1,4 +1,4 @@
-1;1;" Report STree ver. 1.2.3 with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07"
+1;1;" STree ver. 1.2.3 Python ver. 3.11x with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07"
 2;1;" With gridsearched hyperparameters"
 3;1;" Score is accuracy"
 3;2;" Execution time"
@@ -45,4 +45,4 @@
 8;10;"0.0008541679382324218"
 8;11;"3.629469326417878e-05"
 8;12;"{'C': 7, 'gamma': 0.1, 'kernel': 'rbf', 'max_iter': 10000.0, 'multiclass_strategy': 'ovr'}"
-10;1;"** Accuracy compared to stree_default (liblinear-ovr) .:  0.0454"
+10;1;"** accuracy compared to STree_default (liblinear-ovr) .:  0.0454"

benchmark/tests/test_files/report.test

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

benchmark/tests/test_files/report_best.test

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

benchmark/tests/test_files/report_compared.test

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

benchmark/tests/test_files/report_datasets.test

@@ -1,4 +1,6 @@
-Dataset                        Samp. Feat. Cls Balance
-============================== ===== ===== === ========================================
-balance-scale                    625     4   3  7.84%/ 46.08%/ 46.08%                  
-balloons                          16     4   2 56.25%/ 43.75%                          
+Datasets used in benchmark ver. 0.2.0
+
+Dataset                        Sampl. Feat. Cls Balance
+============================== ====== ===== === ============================================================
+balance-scale                     625     4   3  7.84%/ 46.08%/ 46.08%                  
+balloons                           16     4   2 56.25%/ 43.75%                          

benchmark/tests/test_files/report_grid.test

@@ -7,5 +7,5 @@ Dataset                        Score    File/Message
 balance-scale                  0.919995 v. 1.2.4, Computed on Test on 2022-02-22 at 12:00:00 took 1s                 {'C': 1.0, 'kernel': 'liblinear', 'multiclass_strategy': 'ovr'} 
 balloons                       0.625000 v. 1.2.4, Computed on Test on 2022-02-22 at 12:00:00 took 1s                 {'C': 1.0, 'kernel': 'linear', 'multiclass_strategy': 'ovr'} 
 ******************************************************************************************************************************************************************
-* Scores compared to stree_default accuracy (liblinear-ovr) .:  0.0384                                                                                           *
+* accuracy compared to STree_default (liblinear-ovr) .:  0.0384                                                                                                  *
 ******************************************************************************************************************************************************************

benchmark/tests/test_files/summary_list_hidden.test

@@ -1,4 +1,4 @@
-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
-2021-11-01 results_accuracy_STree_iMac27_2021-11-01_23:55:16_0.json          0.97446   0.098 default
+ #  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/summary_list_model.test

@@ -1,5 +1,5 @@
-Date       File                                                          Score    Time(h) Title
-========== ============================================================= ======== ======= =================================
-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
+ #  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/summary_list_n.test

@@ -1,5 +1,5 @@
-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
+ #  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

benchmark/tests/test_files/summary_list_score.test

@@ -1,7 +1,7 @@
-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
+ #  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/summary_show_top.test

@@ -1,7 +1,7 @@
-Date       File                                                            Score    Time(h) Title
-========== =============================================================== ======== ======= ============================================
-2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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
-2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
-2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
-2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest
+ #  Date       File                                                            Score    Time(h) Title
+=== ========== =============================================================== ======== ======= ============================================
+  0 2021-09-30 results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json         0.04544   0.173 With gridsearched 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 2021-10-27 results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json         0.04158   0.943 default A
+  3 2021-11-01 results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json    0.03790   1.143 default B
+  4 2022-01-14 results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json  0.03627   0.076 Test default paramters with RandomForest

requirements.txt

@@ -1,10 +1,15 @@
 pandas
 scikit-learn
+scipy
 odte
+cython
+mdlp-discretization
 mufs
+bayesclass @ git+ssh://git@github.com/doctorado-ml/bayesclass.git
 xlsxwriter
 openpyxl
 tqdm
 xgboost
 graphviz
 Wodt @ git+ssh://git@github.com/doctorado-ml/Wodt.git#egg=Wodt
+unittest-xml-reporting

setup.py

@@ -49,15 +49,14 @@ setuptools.setup(
     name="benchmark",
     version=get_data("version", "_version.py"),
     license=get_data("license"),
-    description="Oblique decision tree with svm nodes",
+    description="Benchmark of models with different datasets",
     long_description=readme(),
     long_description_content_type="text/markdown",
     packages=setuptools.find_packages(),
     url="https://github.com/Doctorado-ML/benchmark",
     author=get_data("author"),
     author_email=get_data("author_email"),
-    keywords="scikit-learn oblique-classifier oblique-decision-tree decision-\
-    tree svm svc",
+    keywords="scikit-learn benchmark",
     classifiers=[
         "Development Status :: 4 - Beta",
         "License :: OSI Approved :: " + get_data("license"),

weka_test.ipynb

@@ -0,0 +1,526 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "0e48f7d2-7481-4eca-9c38-56d21c203093",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "DEBUG:weka.core.jvm:Adding bundled jars\n",
+      "DEBUG:weka.core.jvm:Classpath=['/Users/rmontanana/miniconda3/envs/pyweka/lib/python3.10/site-packages/javabridge/jars/rhino-1.7R4.jar', '/Users/rmontanana/miniconda3/envs/pyweka/lib/python3.10/site-packages/javabridge/jars/runnablequeue.jar', '/Users/rmontanana/miniconda3/envs/pyweka/lib/python3.10/site-packages/javabridge/jars/cpython.jar', '/Users/rmontanana/miniconda3/envs/pyweka/lib/python3.10/site-packages/weka/lib/python-weka-wrapper.jar', '/Users/rmontanana/miniconda3/envs/pyweka/lib/python3.10/site-packages/weka/lib/weka.jar']\n",
+      "DEBUG:weka.core.jvm:MaxHeapSize=default\n",
+      "DEBUG:weka.core.jvm:Package support disabled\n",
+      "WARNING: An illegal reflective access operation has occurred\n",
+      "WARNING: Illegal reflective access by weka.core.WekaPackageClassLoaderManager (file:/Users/rmontanana/miniconda3/envs/pyweka/lib/python3.10/site-packages/weka/lib/weka.jar) to method java.lang.ClassLoader.defineClass(java.lang.String,byte[],int,int,java.security.ProtectionDomain)\n",
+      "WARNING: Please consider reporting this to the maintainers of weka.core.WekaPackageClassLoaderManager\n",
+      "WARNING: Use --illegal-access=warn to enable warnings of further illegal reflective access operations\n",
+      "WARNING: All illegal access operations will be denied in a future release\n"
+     ]
+    }
+   ],
+   "source": [
+    "import weka.core.jvm as jvm\n",
+    "jvm.start()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2ac4e479-3818-4562-a967-bb303d8dd573",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from weka.core.converters import Loader\n",
+    "data_dir = \"/Users/rmontanana/Code/discretizbench/datasets/\"\n",
+    "loader = Loader(classname=\"weka.core.converters.ArffLoader\")\n",
+    "data = loader.load_file(data_dir + \"iris.arff\")\n",
+    "data.class_is_last()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ceb9f912-db42-4cbc-808f-48b5a9d89d44",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "@relation iris\n",
+      "\n",
+      "@attribute sepallength numeric\n",
+      "@attribute sepalwidth numeric\n",
+      "@attribute petallength numeric\n",
+      "@attribute petalwidth numeric\n",
+      "@attribute class {Iris-setosa,Iris-versicolor,Iris-virginica}\n",
+      "\n",
+      "@data\n",
+      "5.1,3.5,1.4,0.2,Iris-setosa\n",
+      "4.9,3,1.4,0.2,Iris-setosa\n",
+      "4.7,3.2,1.3,0.2,Iris-setosa\n",
+      "4.6,3.1,1.5,0.2,Iris-setosa\n",
+      "5,3.6,1.4,0.2,Iris-setosa\n",
+      "5.4,3.9,1.7,0.4,Iris-setosa\n",
+      "4.6,3.4,1.4,0.3,Iris-setosa\n",
+      "5,3.4,1.5,0.2,Iris-setosa\n",
+      "4.4,2.9,1.4,0.2,Iris-setosa\n",
+      "4.9,3.1,1.5,0.1,Iris-setosa\n",
+      "5.4,3.7,1.5,0.2,Iris-setosa\n",
+      "4.8,3.4,1.6,0.2,Iris-setosa\n",
+      "4.8,3,1.4,0.1,Iris-setosa\n",
+      "4.3,3,1.1,0.1,Iris-setosa\n",
+      "5.8,4,1.2,0.2,Iris-setosa\n",
+      "5.7,4.4,1.5,0.4,Iris-setosa\n",
+      "5.4,3.9,1.3,0.4,Iris-setosa\n",
+      "5.1,3.5,1.4,0.3,Iris-setosa\n",
+      "5.7,3.8,1.7,0.3,Iris-setosa\n",
+      "5.1,3.8,1.5,0.3,Iris-setosa\n",
+      "5.4,3.4,1.7,0.2,Iris-setosa\n",
+      "5.1,3.7,1.5,0.4,Iris-setosa\n",
+      "4.6,3.6,1,0.2,Iris-setosa\n",
+      "5.1,3.3,1.7,0.5,Iris-setosa\n",
+      "4.8,3.4,1.9,0.2,Iris-setosa\n",
+      "5,3,1.6,0.2,Iris-setosa\n",
+      "5,3.4,1.6,0.4,Iris-setosa\n",
+      "5.2,3.5,1.5,0.2,Iris-setosa\n",
+      "5.2,3.4,1.4,0.2,Iris-setosa\n",
+      "4.7,3.2,1.6,0.2,Iris-setosa\n",
+      "4.8,3.1,1.6,0.2,Iris-setosa\n",
+      "5.4,3.4,1.5,0.4,Iris-setosa\n",
+      "5.2,4.1,1.5,0.1,Iris-setosa\n",
+      "5.5,4.2,1.4,0.2,Iris-setosa\n",
+      "4.9,3.1,1.5,0.1,Iris-setosa\n",
+      "5,3.2,1.2,0.2,Iris-setosa\n",
+      "5.5,3.5,1.3,0.2,Iris-setosa\n",
+      "4.9,3.1,1.5,0.1,Iris-setosa\n",
+      "4.4,3,1.3,0.2,Iris-setosa\n",
+      "5.1,3.4,1.5,0.2,Iris-setosa\n",
+      "5,3.5,1.3,0.3,Iris-setosa\n",
+      "4.5,2.3,1.3,0.3,Iris-setosa\n",
+      "4.4,3.2,1.3,0.2,Iris-setosa\n",
+      "5,3.5,1.6,0.6,Iris-setosa\n",
+      "5.1,3.8,1.9,0.4,Iris-setosa\n",
+      "4.8,3,1.4,0.3,Iris-setosa\n",
+      "5.1,3.8,1.6,0.2,Iris-setosa\n",
+      "4.6,3.2,1.4,0.2,Iris-setosa\n",
+      "5.3,3.7,1.5,0.2,Iris-setosa\n",
+      "5,3.3,1.4,0.2,Iris-setosa\n",
+      "7,3.2,4.7,1.4,Iris-versicolor\n",
+      "6.4,3.2,4.5,1.5,Iris-versicolor\n",
+      "6.9,3.1,4.9,1.5,Iris-versicolor\n",
+      "5.5,2.3,4,1.3,Iris-versicolor\n",
+      "6.5,2.8,4.6,1.5,Iris-versicolor\n",
+      "5.7,2.8,4.5,1.3,Iris-versicolor\n",
+      "6.3,3.3,4.7,1.6,Iris-versicolor\n",
+      "4.9,2.4,3.3,1,Iris-versicolor\n",
+      "6.6,2.9,4.6,1.3,Iris-versicolor\n",
+      "5.2,2.7,3.9,1.4,Iris-versicolor\n",
+      "5,2,3.5,1,Iris-versicolor\n",
+      "5.9,3,4.2,1.5,Iris-versicolor\n",
+      "6,2.2,4,1,Iris-versicolor\n",
+      "6.1,2.9,4.7,1.4,Iris-versicolor\n",
+      "5.6,2.9,3.6,1.3,Iris-versicolor\n",
+      "6.7,3.1,4.4,1.4,Iris-versicolor\n",
+      "5.6,3,4.5,1.5,Iris-versicolor\n",
+      "5.8,2.7,4.1,1,Iris-versicolor\n",
+      "6.2,2.2,4.5,1.5,Iris-versicolor\n",
+      "5.6,2.5,3.9,1.1,Iris-versicolor\n",
+      "5.9,3.2,4.8,1.8,Iris-versicolor\n",
+      "6.1,2.8,4,1.3,Iris-versicolor\n",
+      "6.3,2.5,4.9,1.5,Iris-versicolor\n",
+      "6.1,2.8,4.7,1.2,Iris-versicolor\n",
+      "6.4,2.9,4.3,1.3,Iris-versicolor\n",
+      "6.6,3,4.4,1.4,Iris-versicolor\n",
+      "6.8,2.8,4.8,1.4,Iris-versicolor\n",
+      "6.7,3,5,1.7,Iris-versicolor\n",
+      "6,2.9,4.5,1.5,Iris-versicolor\n",
+      "5.7,2.6,3.5,1,Iris-versicolor\n",
+      "5.5,2.4,3.8,1.1,Iris-versicolor\n",
+      "5.5,2.4,3.7,1,Iris-versicolor\n",
+      "5.8,2.7,3.9,1.2,Iris-versicolor\n",
+      "6,2.7,5.1,1.6,Iris-versicolor\n",
+      "5.4,3,4.5,1.5,Iris-versicolor\n",
+      "6,3.4,4.5,1.6,Iris-versicolor\n",
+      "6.7,3.1,4.7,1.5,Iris-versicolor\n",
+      "6.3,2.3,4.4,1.3,Iris-versicolor\n",
+      "5.6,3,4.1,1.3,Iris-versicolor\n",
+      "5.5,2.5,4,1.3,Iris-versicolor\n",
+      "5.5,2.6,4.4,1.2,Iris-versicolor\n",
+      "6.1,3,4.6,1.4,Iris-versicolor\n",
+      "5.8,2.6,4,1.2,Iris-versicolor\n",
+      "5,2.3,3.3,1,Iris-versicolor\n",
+      "5.6,2.7,4.2,1.3,Iris-versicolor\n",
+      "5.7,3,4.2,1.2,Iris-versicolor\n",
+      "5.7,2.9,4.2,1.3,Iris-versicolor\n",
+      "6.2,2.9,4.3,1.3,Iris-versicolor\n",
+      "5.1,2.5,3,1.1,Iris-versicolor\n",
+      "5.7,2.8,4.1,1.3,Iris-versicolor\n",
+      "6.3,3.3,6,2.5,Iris-virginica\n",
+      "5.8,2.7,5.1,1.9,Iris-virginica\n",
+      "7.1,3,5.9,2.1,Iris-virginica\n",
+      "6.3,2.9,5.6,1.8,Iris-virginica\n",
+      "6.5,3,5.8,2.2,Iris-virginica\n",
+      "7.6,3,6.6,2.1,Iris-virginica\n",
+      "4.9,2.5,4.5,1.7,Iris-virginica\n",
+      "7.3,2.9,6.3,1.8,Iris-virginica\n",
+      "6.7,2.5,5.8,1.8,Iris-virginica\n",
+      "7.2,3.6,6.1,2.5,Iris-virginica\n",
+      "6.5,3.2,5.1,2,Iris-virginica\n",
+      "6.4,2.7,5.3,1.9,Iris-virginica\n",
+      "6.8,3,5.5,2.1,Iris-virginica\n",
+      "5.7,2.5,5,2,Iris-virginica\n",
+      "5.8,2.8,5.1,2.4,Iris-virginica\n",
+      "6.4,3.2,5.3,2.3,Iris-virginica\n",
+      "6.5,3,5.5,1.8,Iris-virginica\n",
+      "7.7,3.8,6.7,2.2,Iris-virginica\n",
+      "7.7,2.6,6.9,2.3,Iris-virginica\n",
+      "6,2.2,5,1.5,Iris-virginica\n",
+      "6.9,3.2,5.7,2.3,Iris-virginica\n",
+      "5.6,2.8,4.9,2,Iris-virginica\n",
+      "7.7,2.8,6.7,2,Iris-virginica\n",
+      "6.3,2.7,4.9,1.8,Iris-virginica\n",
+      "6.7,3.3,5.7,2.1,Iris-virginica\n",
+      "7.2,3.2,6,1.8,Iris-virginica\n",
+      "6.2,2.8,4.8,1.8,Iris-virginica\n",
+      "6.1,3,4.9,1.8,Iris-virginica\n",
+      "6.4,2.8,5.6,2.1,Iris-virginica\n",
+      "7.2,3,5.8,1.6,Iris-virginica\n",
+      "7.4,2.8,6.1,1.9,Iris-virginica\n",
+      "7.9,3.8,6.4,2,Iris-virginica\n",
+      "6.4,2.8,5.6,2.2,Iris-virginica\n",
+      "6.3,2.8,5.1,1.5,Iris-virginica\n",
+      "6.1,2.6,5.6,1.4,Iris-virginica\n",
+      "7.7,3,6.1,2.3,Iris-virginica\n",
+      "6.3,3.4,5.6,2.4,Iris-virginica\n",
+      "6.4,3.1,5.5,1.8,Iris-virginica\n",
+      "6,3,4.8,1.8,Iris-virginica\n",
+      "6.9,3.1,5.4,2.1,Iris-virginica\n",
+      "6.7,3.1,5.6,2.4,Iris-virginica\n",
+      "6.9,3.1,5.1,2.3,Iris-virginica\n",
+      "5.8,2.7,5.1,1.9,Iris-virginica\n",
+      "6.8,3.2,5.9,2.3,Iris-virginica\n",
+      "6.7,3.3,5.7,2.5,Iris-virginica\n",
+      "6.7,3,5.2,2.3,Iris-virginica\n",
+      "6.3,2.5,5,1.9,Iris-virginica\n",
+      "6.5,3,5.2,2,Iris-virginica\n",
+      "6.2,3.4,5.4,2.3,Iris-virginica\n",
+      "5.9,3,5.1,1.8,Iris-virginica\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "ded59d25-c34c-4fb8-a35f-1162f1218414",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from weka.classifiers import Classifier\n",
+    "cls = Classifier(classname=\"weka.classifiers.trees.J48\", options=[\"-C\", \"0.3\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "4c82f2ae-4071-4571-9a19-433b98463143",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['-C', '0.3', '-M', '2']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(cls.options)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "4c5c7893-ebbe-407d-872c-fd0bf41f8dc8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "weka.classifiers.trees.J48 -C 0.3 -M 2\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(cls.to_commandline())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "7b73c18d-e0b0-469d-8a60-03bae8e01128",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "2: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "3: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "4: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "5: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "6: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "7: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "8: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "9: label index=0.0, class distribution=[0.96326708 0.02223308 0.01449983]\n",
+      "10: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "11: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "12: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "13: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "14: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "15: label index=0.0, class distribution=[0.9382677  0.03162683 0.03010547]\n",
+      "16: label index=0.0, class distribution=[0.9382677  0.03162683 0.03010547]\n",
+      "17: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "18: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "19: label index=0.0, class distribution=[0.9382677  0.03162683 0.03010547]\n",
+      "20: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "21: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "22: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "23: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "24: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "25: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "26: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "27: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "28: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "29: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "30: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "31: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "32: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "33: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "34: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "35: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "36: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "37: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "38: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "39: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "40: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "41: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "42: label index=0.0, class distribution=[0.96326708 0.02223308 0.01449983]\n",
+      "43: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "44: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "45: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "46: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "47: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "48: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "49: label index=0.0, class distribution=[0.99688403 0.00188598 0.00122999]\n",
+      "50: label index=0.0, class distribution=[0.99487322 0.00310305 0.00202373]\n",
+      "51: label index=1.0, class distribution=[0.00545355 0.97466198 0.01988447]\n",
+      "52: label index=1.0, class distribution=[0.00545355 0.97466198 0.01988447]\n",
+      "53: label index=1.0, class distribution=[0.010867   0.52425197 0.46488102]\n",
+      "54: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "55: label index=1.0, class distribution=[0.00228744 0.97269152 0.02502104]\n",
+      "56: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "57: label index=1.0, class distribution=[0.00545355 0.97466198 0.01988447]\n",
+      "58: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "59: label index=1.0, class distribution=[0.00228744 0.97269152 0.02502104]\n",
+      "60: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "61: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "62: label index=1.0, class distribution=[0.00732671 0.98195521 0.01071808]\n",
+      "63: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "64: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "65: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "66: label index=1.0, class distribution=[0.00545355 0.97466198 0.01988447]\n",
+      "67: label index=1.0, class distribution=[0.00732671 0.98195521 0.01071808]\n",
+      "68: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "69: label index=1.0, class distribution=[0.00228744 0.97269152 0.02502104]\n",
+      "70: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "71: label index=2.0, class distribution=[0.00920087 0.06127297 0.92952615]\n",
+      "72: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "73: label index=2.0, class distribution=[0.00409632 0.47019227 0.5257114 ]\n",
+      "74: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "75: label index=1.0, class distribution=[0.00228744 0.97269152 0.02502104]\n",
+      "76: label index=1.0, class distribution=[0.00545355 0.97466198 0.01988447]\n",
+      "77: label index=2.0, class distribution=[0.00409632 0.47019227 0.5257114 ]\n",
+      "78: label index=1.0, class distribution=[0.010867   0.52425197 0.46488102]\n",
+      "79: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "80: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "81: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "82: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "83: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "84: label index=1.0, class distribution=[0.02353491 0.65433551 0.32212958]\n",
+      "85: label index=1.0, class distribution=[0.01727259 0.943168   0.03955941]\n",
+      "86: label index=1.0, class distribution=[0.06513736 0.90310001 0.03176263]\n",
+      "87: label index=1.0, class distribution=[0.00545355 0.97466198 0.01988447]\n",
+      "88: label index=1.0, class distribution=[0.00228744 0.97269152 0.02502104]\n",
+      "89: label index=1.0, class distribution=[0.00732671 0.98195521 0.01071808]\n",
+      "90: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "91: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "92: label index=1.0, class distribution=[0.00732671 0.98195521 0.01071808]\n",
+      "93: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "94: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "95: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "96: label index=1.0, class distribution=[0.00732671 0.98195521 0.01071808]\n",
+      "97: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "98: label index=1.0, class distribution=[0.00228744 0.97269152 0.02502104]\n",
+      "99: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "100: label index=1.0, class distribution=[0.00308382 0.98338244 0.01353374]\n",
+      "101: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "102: label index=2.0, class distribution=[0.01274667 0.02829538 0.95895795]\n",
+      "103: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "104: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "105: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "106: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "107: label index=1.0, class distribution=[0.00725727 0.94287877 0.04986396]\n",
+      "108: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "109: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "110: label index=2.0, class distribution=[0.00431289 0.0395258  0.95616131]\n",
+      "111: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "112: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "113: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "114: label index=2.0, class distribution=[0.01274667 0.02829538 0.95895795]\n",
+      "115: label index=2.0, class distribution=[0.01274667 0.02829538 0.95895795]\n",
+      "116: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "117: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "118: label index=2.0, class distribution=[0.00431289 0.0395258  0.95616131]\n",
+      "119: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "120: label index=1.0, class distribution=[0.02353491 0.65433551 0.32212958]\n",
+      "121: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "122: label index=2.0, class distribution=[0.01274667 0.02829538 0.95895795]\n",
+      "123: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "124: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "125: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "126: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "127: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "128: label index=2.0, class distribution=[0.00920087 0.06127297 0.92952615]\n",
+      "129: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "130: label index=1.0, class distribution=[0.010867   0.52425197 0.46488102]\n",
+      "131: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "132: label index=2.0, class distribution=[0.00431289 0.0395258  0.95616131]\n",
+      "133: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "134: label index=2.0, class distribution=[0.00409632 0.47019227 0.5257114 ]\n",
+      "135: label index=1.0, class distribution=[0.02353491 0.65433551 0.32212958]\n",
+      "136: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "137: label index=2.0, class distribution=[0.00431289 0.0395258  0.95616131]\n",
+      "138: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "139: label index=2.0, class distribution=[0.00920087 0.06127297 0.92952615]\n",
+      "140: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "141: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "142: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "143: label index=2.0, class distribution=[0.01274667 0.02829538 0.95895795]\n",
+      "144: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "145: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "146: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "147: label index=2.0, class distribution=[0.00139749 0.01280739 0.98579512]\n",
+      "148: label index=2.0, class distribution=[0.00102485 0.02817698 0.97079816]\n",
+      "149: label index=2.0, class distribution=[0.00431289 0.0395258  0.95616131]\n",
+      "150: label index=2.0, class distribution=[0.00920087 0.06127297 0.92952615]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from weka.classifiers import Classifier\n",
+    "cls = Classifier(classname=\"weka.classifiers.bayes.BayesNet\", options=[\"-Q\", \"weka.classifiers.bayes.net.search.local.TAN\"])\n",
+    "cls.build_classifier(data)\n",
+    "\n",
+    "for index, inst in enumerate(data):\n",
+    "    pred = cls.classify_instance(inst)\n",
+    "    dist = cls.distribution_for_instance(inst)\n",
+    "    print(str(index+1) + \": label index=\" + str(pred) + \", class distribution=\" + str(dist))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "0b74f00a-15b3-4177-bb8c-e02ed1a3fd38",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Bayes Network Classifier\n",
+      "Using ADTree\n",
+      "#attributes=5 #classindex=4\n",
+      "Network structure (nodes followed by parents)\n",
+      "sepallength(3): class \n",
+      "sepalwidth(3): class petalwidth \n",
+      "petallength(3): class sepallength \n",
+      "petalwidth(3): class petallength \n",
+      "class(3): \n",
+      "LogScore Bayes: -484.0749140715054\n",
+      "LogScore BDeu: -653.8524681760015\n",
+      "LogScore MDL: -654.6252712234647\n",
+      "LogScore ENTROPY: -499.2955771064808\n",
+      "LogScore AIC: -561.2955771064808\n",
+      "\n"
+     ]
+    },
+    {
+     "ename": "OSError",
+     "evalue": "[Errno 63] File name too long: '<?xml version=\"1.0\"?>\\n<!-- DTD for the XMLBIF 0.3 format -->\\n<!DOCTYPE BIF [\\n\\t<!ELEMENT BIF ( NETWORK )*>\\n\\t      <!ATTLIST BIF VERSION CDATA #REQUIRED>\\n\\t<!ELEMENT NETWORK ( NAME, ( PROPERTY | VARIABLE | DEFINITION )* )>\\n\\t<!ELEMENT NAME (#PCDATA)>\\n\\t<!ELEMENT VARIABLE ( NAME, ( OUTCOME |  PROPERTY )* ) >\\n\\t      <!ATTLIST VARIABLE TYPE (nature|decision|utility) \"nature\">\\n\\t<!ELEMENT OUTCOME (#PCDATA)>\\n\\t<!ELEMENT DEFINITION ( FOR | GIVEN | TABLE | PROPERTY )* >\\n\\t<!ELEMENT FOR (#PCDATA)>\\n\\t<!ELEMENT GIVEN (#PCDATA)>\\n\\t<!ELEMENT TABLE (#PCDATA)>\\n\\t<!ELEMENT PROPERTY (#PCDATA)>\\n]>\\n\\n\\n<BIF VERSION=\"0.3\">\\n<NETWORK>\\n<NAME>iris-weka.filters.supervised.attribute.Discretize-Rfirst-last-precision6-weka.filters.unsupervised.attribute.ReplaceMissingValues</NAME>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>sepallength</NAME>\\n<OUTCOME>&apos;\\\\&apos;(-inf-5.55]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(5.55-6.15]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(6.15-inf)\\\\&apos;&apos;</OUTCOME>\\n</VARIABLE>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>sepalwidth</NAME>\\n<OUTCOME>&apos;\\\\&apos;(-inf-2.95]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(2.95-3.35]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(3.35-inf)\\\\&apos;&apos;</OUTCOME>\\n</VARIABLE>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>petallength</NAME>\\n<OUTCOME>&apos;\\\\&apos;(-inf-2.45]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(2.45-4.75]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(4.75-inf)\\\\&apos;&apos;</OUTCOME>\\n</VARIABLE>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>petalwidth</NAME>\\n<OUTCOME>&apos;\\\\&apos;(-inf-0.8]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(0.8-1.75]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(1.75-inf)\\\\&apos;&apos;</OUTCOME>\\n</VARIABLE>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>class</NAME>\\n<OUTCOME>Iris-setosa</OUTCOME>\\n<OUTCOME>Iris-versicolor</OUTCOME>\\n<OUTCOME>Iris-virginica</OUTCOME>\\n</VARIABLE>\\n<DEFINITION>\\n<FOR>sepallength</FOR>\\n<GIVEN>class</GIVEN>\\n<TABLE>\\n0.9223300970873787 0.06796116504854369 0.009708737864077669 \\n0.22330097087378642 0.4563106796116505 0.32038834951456313 \\n0.02912621359223301 0.20388349514563106 0.7669902912621359 \\n</TABLE>\\n</DEFINITION>\\n<DEFINITION>\\n<FOR>sepalwidth</FOR>\\n<GIVEN>class</GIVEN>\\n<GIVEN>petalwidth</GIVEN>\\n<TABLE>\\n0.04854368932038835 0.3592233009708738 0.5922330097087378 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.6831683168316832 0.2871287128712871 0.0297029702970297 \\n0.2 0.6 0.2 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.6923076923076923 0.23076923076923078 0.07692307692307693 \\n0.3763440860215054 0.5053763440860215 0.11827956989247312 \\n</TABLE>\\n</DEFINITION>\\n<DEFINITION>\\n<FOR>petallength</FOR>\\n<GIVEN>class</GIVEN>\\n<GIVEN>sepallength</GIVEN>\\n<TABLE>\\n0.979381443298969 0.010309278350515464 0.010309278350515464 \\n0.7777777777777778 0.1111111111111111 0.1111111111111111 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.04 0.92 0.04 \\n0.02040816326530612 0.8775510204081632 0.10204081632653061 \\n0.02857142857142857 0.7142857142857143 0.2571428571428571 \\n0.2 0.6 0.2 \\n0.043478260869565216 0.043478260869565216 0.9130434782608695 \\n0.012345679012345678 0.012345679012345678 0.9753086419753086 \\n</TABLE>\\n</DEFINITION>\\n<DEFINITION>\\n<FOR>petalwidth</FOR>\\n<GIVEN>class</GIVEN>\\n<GIVEN>petallength</GIVEN>\\n<TABLE>\\n0.9805825242718447 0.009708737864077669 0.009708737864077669 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.01098901098901099 0.978021978021978 0.01098901098901099 \\n0.06666666666666667 0.7333333333333333 0.2 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.2 0.6 0.2 \\n0.009900990099009901 0.0891089108910891 0.900990099009901 \\n</TABLE>\\n</DEFINITION>\\n<DEFINITION>\\n<FOR>class</FOR>\\n<TABLE>\\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n</TABLE>\\n</DEFINITION>\\n</NETWORK>\\n</BIF>\\n'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mOSError\u001b[0m                                   Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn [13], line 9\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;28mcls\u001b[39m)\n\u001b[1;32m      8\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mweka\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mplot\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgraph\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mgraph\u001b[39;00m  \u001b[38;5;66;03m# NB: pygraphviz and PIL are required\u001b[39;00m\n\u001b[0;32m----> 9\u001b[0m \u001b[43mgraph\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplot_dot_graph\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgraph\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/pyweka/lib/python3.10/site-packages/weka/plot/graph.py:49\u001b[0m, in \u001b[0;36mplot_dot_graph\u001b[0;34m(graph, filename)\u001b[0m\n\u001b[1;32m     46\u001b[0m     logger\u001b[38;5;241m.\u001b[39merror(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPIL is not installed, cannot display graph plot!\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m     47\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[0;32m---> 49\u001b[0m agraph \u001b[38;5;241m=\u001b[39m \u001b[43mAGraph\u001b[49m\u001b[43m(\u001b[49m\u001b[43mgraph\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     50\u001b[0m agraph\u001b[38;5;241m.\u001b[39mlayout(prog\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdot\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m     51\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m filename \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
+      "File \u001b[0;32m~/miniconda3/envs/pyweka/lib/python3.10/site-packages/pygraphviz/agraph.py:157\u001b[0m, in \u001b[0;36mAGraph.__init__\u001b[0;34m(self, thing, filename, data, string, handle, name, strict, directed, **attr)\u001b[0m\n\u001b[1;32m    154\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_owns_handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m    155\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m filename \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    156\u001b[0m     \u001b[38;5;66;03m# load new graph from file (creates self.handle)\u001b[39;00m\n\u001b[0;32m--> 157\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    158\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m string \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    159\u001b[0m     \u001b[38;5;66;03m# load new graph from string (creates self.handle)\u001b[39;00m\n\u001b[1;32m    160\u001b[0m     \u001b[38;5;66;03m# get the charset from the string to properly encode it for\u001b[39;00m\n\u001b[1;32m    161\u001b[0m     \u001b[38;5;66;03m# writing to the temporary file in from_string()\u001b[39;00m\n\u001b[1;32m    162\u001b[0m     match \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msearch(\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcharset\u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124ms*=\u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124ms*\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m([^\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m]+)\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m, string)\n",
+      "File \u001b[0;32m~/miniconda3/envs/pyweka/lib/python3.10/site-packages/pygraphviz/agraph.py:1243\u001b[0m, in \u001b[0;36mAGraph.read\u001b[0;34m(self, path)\u001b[0m\n\u001b[1;32m   1233\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mread\u001b[39m(\u001b[38;5;28mself\u001b[39m, path):\n\u001b[1;32m   1234\u001b[0m     \u001b[38;5;124;03m\"\"\"Read graph from dot format file on path.\u001b[39;00m\n\u001b[1;32m   1235\u001b[0m \n\u001b[1;32m   1236\u001b[0m \u001b[38;5;124;03m    path can be a file name or file handle\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1241\u001b[0m \n\u001b[1;32m   1242\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m-> 1243\u001b[0m     fh \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_fh\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1244\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1245\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_close_handle()\n",
+      "File \u001b[0;32m~/miniconda3/envs/pyweka/lib/python3.10/site-packages/pygraphviz/agraph.py:1791\u001b[0m, in \u001b[0;36mAGraph._get_fh\u001b[0;34m(self, path, mode)\u001b[0m\n\u001b[1;32m   1789\u001b[0m         fh \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpopen(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbzcat \u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m path)  \u001b[38;5;66;03m# probably not portable\u001b[39;00m\n\u001b[1;32m   1790\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1791\u001b[0m         fh \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1792\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(path, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mwrite\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m   1793\u001b[0m     \u001b[38;5;66;03m# Note, mode of file handle is unchanged.\u001b[39;00m\n\u001b[1;32m   1794\u001b[0m     fh \u001b[38;5;241m=\u001b[39m path\n",
+      "\u001b[0;31mOSError\u001b[0m: [Errno 63] File name too long: '<?xml version=\"1.0\"?>\\n<!-- DTD for the XMLBIF 0.3 format -->\\n<!DOCTYPE BIF [\\n\\t<!ELEMENT BIF ( NETWORK )*>\\n\\t      <!ATTLIST BIF VERSION CDATA #REQUIRED>\\n\\t<!ELEMENT NETWORK ( NAME, ( PROPERTY | VARIABLE | DEFINITION )* )>\\n\\t<!ELEMENT NAME (#PCDATA)>\\n\\t<!ELEMENT VARIABLE ( NAME, ( OUTCOME |  PROPERTY )* ) >\\n\\t      <!ATTLIST VARIABLE TYPE (nature|decision|utility) \"nature\">\\n\\t<!ELEMENT OUTCOME (#PCDATA)>\\n\\t<!ELEMENT DEFINITION ( FOR | GIVEN | TABLE | PROPERTY )* >\\n\\t<!ELEMENT FOR (#PCDATA)>\\n\\t<!ELEMENT GIVEN (#PCDATA)>\\n\\t<!ELEMENT TABLE (#PCDATA)>\\n\\t<!ELEMENT PROPERTY (#PCDATA)>\\n]>\\n\\n\\n<BIF VERSION=\"0.3\">\\n<NETWORK>\\n<NAME>iris-weka.filters.supervised.attribute.Discretize-Rfirst-last-precision6-weka.filters.unsupervised.attribute.ReplaceMissingValues</NAME>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>sepallength</NAME>\\n<OUTCOME>&apos;\\\\&apos;(-inf-5.55]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(5.55-6.15]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(6.15-inf)\\\\&apos;&apos;</OUTCOME>\\n</VARIABLE>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>sepalwidth</NAME>\\n<OUTCOME>&apos;\\\\&apos;(-inf-2.95]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(2.95-3.35]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(3.35-inf)\\\\&apos;&apos;</OUTCOME>\\n</VARIABLE>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>petallength</NAME>\\n<OUTCOME>&apos;\\\\&apos;(-inf-2.45]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(2.45-4.75]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(4.75-inf)\\\\&apos;&apos;</OUTCOME>\\n</VARIABLE>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>petalwidth</NAME>\\n<OUTCOME>&apos;\\\\&apos;(-inf-0.8]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(0.8-1.75]\\\\&apos;&apos;</OUTCOME>\\n<OUTCOME>&apos;\\\\&apos;(1.75-inf)\\\\&apos;&apos;</OUTCOME>\\n</VARIABLE>\\n<VARIABLE TYPE=\"nature\">\\n<NAME>class</NAME>\\n<OUTCOME>Iris-setosa</OUTCOME>\\n<OUTCOME>Iris-versicolor</OUTCOME>\\n<OUTCOME>Iris-virginica</OUTCOME>\\n</VARIABLE>\\n<DEFINITION>\\n<FOR>sepallength</FOR>\\n<GIVEN>class</GIVEN>\\n<TABLE>\\n0.9223300970873787 0.06796116504854369 0.009708737864077669 \\n0.22330097087378642 0.4563106796116505 0.32038834951456313 \\n0.02912621359223301 0.20388349514563106 0.7669902912621359 \\n</TABLE>\\n</DEFINITION>\\n<DEFINITION>\\n<FOR>sepalwidth</FOR>\\n<GIVEN>class</GIVEN>\\n<GIVEN>petalwidth</GIVEN>\\n<TABLE>\\n0.04854368932038835 0.3592233009708738 0.5922330097087378 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.6831683168316832 0.2871287128712871 0.0297029702970297 \\n0.2 0.6 0.2 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.6923076923076923 0.23076923076923078 0.07692307692307693 \\n0.3763440860215054 0.5053763440860215 0.11827956989247312 \\n</TABLE>\\n</DEFINITION>\\n<DEFINITION>\\n<FOR>petallength</FOR>\\n<GIVEN>class</GIVEN>\\n<GIVEN>sepallength</GIVEN>\\n<TABLE>\\n0.979381443298969 0.010309278350515464 0.010309278350515464 \\n0.7777777777777778 0.1111111111111111 0.1111111111111111 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.04 0.92 0.04 \\n0.02040816326530612 0.8775510204081632 0.10204081632653061 \\n0.02857142857142857 0.7142857142857143 0.2571428571428571 \\n0.2 0.6 0.2 \\n0.043478260869565216 0.043478260869565216 0.9130434782608695 \\n0.012345679012345678 0.012345679012345678 0.9753086419753086 \\n</TABLE>\\n</DEFINITION>\\n<DEFINITION>\\n<FOR>petalwidth</FOR>\\n<GIVEN>class</GIVEN>\\n<GIVEN>petallength</GIVEN>\\n<TABLE>\\n0.9805825242718447 0.009708737864077669 0.009708737864077669 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.01098901098901099 0.978021978021978 0.01098901098901099 \\n0.06666666666666667 0.7333333333333333 0.2 \\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n0.2 0.6 0.2 \\n0.009900990099009901 0.0891089108910891 0.900990099009901 \\n</TABLE>\\n</DEFINITION>\\n<DEFINITION>\\n<FOR>class</FOR>\\n<TABLE>\\n0.3333333333333333 0.3333333333333333 0.3333333333333333 \\n</TABLE>\\n</DEFINITION>\\n</NETWORK>\\n</BIF>\\n'"
+     ]
+    }
+   ],
+   "source": [
+    "from weka.classifiers import Classifier\n",
+    "\n",
+    "cls = Classifier(classname=\"weka.classifiers.bayes.BayesNet\", options=[\"-Q\", \"weka.classifiers.bayes.net.search.local.TAN\"])\n",
+    "cls.build_classifier(data)\n",
+    "\n",
+    "print(cls)\n",
+    "\n",
+    "import weka.plot.graph as graph  # NB: pygraphviz and PIL are required\n",
+    "graph.plot_dot_graph(cls.graph)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3f59f200-4f23-4add-86ae-6df1494ede82",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}