Doctorado-ML/benchmark
1
0
Fork 0
mirror of https://github.com/Doctorado-ML/benchmark.git synced 2025-08-17 16:35:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

merge into: Doctorado-ML:discretiz
Branches Tags
Doctorado-ML:main Doctorado-ML:covbench Doctorado-ML:rmontanana-patch-1 Doctorado-ML:flask Doctorado-ML:flask-new Doctorado-ML:refactor_args Doctorado-ML:add_excel_belist Doctorado-ML:language_version Doctorado-ML:discretiz Doctorado-ML:refactor_arguments
Doctorado-ML:v0.2.0 Doctorado-ML:v0.1.1
...
pull from: Doctorado-ML:language_version
Branches Tags
Doctorado-ML:covbench Doctorado-ML:main Doctorado-ML:rmontanana-patch-1 Doctorado-ML:flask Doctorado-ML:flask-new Doctorado-ML:refactor_args Doctorado-ML:add_excel_belist Doctorado-ML:language_version Doctorado-ML:discretiz Doctorado-ML:refactor_arguments
Doctorado-ML:v0.2.0 Doctorado-ML:v0.1.1

15 Commits
discretiz ... language_v

Author SHA1 Message Date
Ricardo Montañana
9039a634cf Exclude macos-latest with python 3.11 (no torch) 2022-11-13 22:14:01 +01:00
Ricardo Montañana
5b5d385b4c Fix uppercase mistake in filename 2022-11-13 20:04:26 +01:00
Ricardo Montañana
6ebcc31c36 Add bayesclass to requirements 2022-11-13 18:34:54 +01:00
Ricardo Montañana
cd2d803ff5 Update requirements 2022-11-13 18:10:42 +01:00
Ricardo Montañana
6aec5b2a97 Add tests to excel in report datasets 2022-11-13 17:44:45 +01:00
Ricardo Montañana
f1b9dc1fef Add excel to report dataset 2022-11-13 14:46:41 +01:00
Ricardo Montañana
2e6f49de8e Add discretize key to .env.dist 2022-11-12 19:38:14 +01:00
Ricardo Montañana
2d61cd11c2 refactor Discretization in datasets 2022-11-12 19:37:46 +01:00
Ricardo Montañana
4b442a46f2 Add Discretizer to Datasets 2022-11-10 11:47:01 +01:00
Ricardo Montañana
feaf85d0b8 Add Dataset load return a pandas dataframe 2022-11-04 18:40:50 +01:00
Ricardo Montañana
0d87e670f7 Disable sonar quality gate in CI 
Update base score for Arff STree
 2022-11-01 16:53:22 +01:00
Ricardo Montañana
1e83db7956 Fix lint errors and update version info 2022-11-01 13:22:53 +01:00
Ricardo Montañana
8cf823e843 Add custom seeds to .env 2022-11-01 12:24:50 +01:00
Ricardo Montañana
97718e6e82 Add Language and language version to reports 2022-11-01 02:07:24 +01:00
Ricardo Montañana Gómez
5532beb88a Merge pull request #3 from Doctorado-ML/discretiz 
Add Arff data source for experiments
Add consistent comparative results to reports
 2022-10-25 16:55:04 +02:00
45 changed files with 1029 additions and 68 deletions
Expand all files Collapse all files

2
.env.dist
View File

@@ -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

1
.flake8
View File

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

11
.github/workflows/build.yml vendored
View File

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

7
.github/workflows/main.yml vendored
View File

@@ -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:

81
benchmark/Datasets.py
View File

@@ -1,8 +1,10 @@
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:
@@ -24,14 +26,18 @@ class DatasetsArff:
def folder():
return "datasets"
def load(self, name, class_name):
def load(self, name, class_name, dataframe):
file_name = os.path.join(self.folder(), self.dataset_names(name))
data = arff.loadarff(file_name)
df = pd.DataFrame(data[0])
df = df.dropna()
X = df.drop(class_name, axis=1).to_numpy()
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])
return X, y
df[class_name] = y
X = X.to_numpy()
return df if dataframe else (X, y)
class DatasetsTanveer:
@@ -43,7 +49,7 @@ class DatasetsTanveer:
def folder():
return "data"
def load(self, name, _):
def load(self, name, *args):
file_name = os.path.join(self.folder(), self.dataset_names(name))
data = pd.read_csv(
file_name,
@@ -64,7 +70,7 @@ class DatasetsSurcov:
def folder():
return "datasets"
def load(self, name, _):
def load(self, name, *args):
file_name = os.path.join(self.folder(), self.dataset_names(name))
data = pd.read_csv(
file_name,
@@ -80,15 +86,19 @@ class DatasetsSurcov:
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()
self._load_names()
if dataset_name is not None:
try:
class_name = self.class_names[
@@ -99,7 +109,7 @@ class Datasets:
raise ValueError(f"Unknown dataset: {dataset_name}")
self.data_sets = [dataset_name]
def load_names(self):
def _load_names(self):
file_name = os.path.join(self.dataset.folder(), Files.index)
default_class = "class"
with open(file_name) as f:
@@ -115,12 +125,61 @@ class Datasets:
self.data_sets = result
self.class_names = class_names
def load(self, name):
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, dataframe=False):
try:
class_name = self.class_names[self.data_sets.index(name)]
return self.dataset.load(name, class_name)
return self.dataset.load(name, class_name, dataframe)
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()
Xdisc = discretiz.fit_transform(X, y)
return Xdisc.astype(int), y.astype(int)
def load_discretized(self, name, dataframe=False):
X, y = self.load_continuous(name)
X, y = self.discretize(X, y)
dataset = pd.DataFrame(X, columns=self.get_features())
dataset[self.get_class_name()] = y
return dataset if dataframe else X, y
def __iter__(self) -> Diterator:
return Diterator(self.data_sets)

18
benchmark/Experiments.py
View File

@@ -1,4 +1,5 @@
import os
import sys
import json
import random
import warnings
@@ -15,10 +16,13 @@ from sklearn.model_selection import (
from .Utils import Folders, Files, NO_RESULTS
from .Datasets import Datasets
from .Models import Models
from .Arguments import EnvData
class Randomized:
seeds = [57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]
@staticmethod
def seeds():
return json.loads(EnvData.load()["seeds"])
class BestResults:
@@ -154,7 +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()
@@ -162,6 +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
@@ -193,7 +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(
@@ -243,6 +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)
@@ -301,7 +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)
)

16
benchmark/Models.py
View File

@@ -8,9 +8,12 @@ from sklearn.ensemble import (
)
from sklearn.svm import SVC
from stree import Stree
from bayesclass import TAN
from wodt import Wodt
from odte import Odte
from xgboost import XGBClassifier
import sklearn
import xgboost
class Models:
@@ -18,6 +21,7 @@ class Models:
def define_models(random_state):
return {
"STree": Stree(random_state=random_state),
"TAN": TAN(random_state=random_state),
"Cart": DecisionTreeClassifier(random_state=random_state),
"ExtraTree": ExtraTreeClassifier(random_state=random_state),
"Wodt": Wodt(random_state=random_state),
@@ -89,3 +93,15 @@ 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"

256
benchmark/Results.py
View File

@@ -1,4 +1,5 @@
import os
import sys
from operator import itemgetter
import math
import json
@@ -17,6 +18,7 @@ from .Utils import (
TextColor,
NO_RESULTS,
)
from ._version import __version__
class BestResultsEver:
@@ -33,7 +35,7 @@ class BestResultsEver:
]
self.data["Arff"]["accuracy"] = [
"STree_default (linear-ovo)",
21.9765,
22.063496,
]
def get_name_value(self, key, score):
@@ -196,7 +198,8 @@ 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']}"
@@ -347,7 +350,8 @@ 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']}"
@@ -564,37 +568,251 @@ 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
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 + " ===== ====== === " + "=" * 40)
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 = "/ "
if self.output:
print(color_line, end="")
print(
f"{dataset:30s} {X.shape[0]:6,d} {X.shape[1]:5,d} "
f"{len(np.unique(y)):3d} {comp:40s}"
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):
@@ -1066,7 +1284,12 @@ 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(
@@ -1094,6 +1317,7 @@ class Benchmark:
footer()
models_files()
exreport_output()
add_datasets_sheet()
book.close()

3
benchmark/Utils.py
View File

@@ -1,6 +1,8 @@
import os
import sys
import subprocess
PYTHON_VERSION = "{}.{}".format(sys.version_info.major, sys.version_info.minor)
NO_RESULTS = "** No results found **"
NO_ENV = "File .env not found"
@@ -25,6 +27,7 @@ class Files:
exreport_pdf = "Rplots.pdf"
benchmark_r = "benchmark.r"
dot_env = ".env"
datasets_report_excel = "ReportDatasets.xlsx"
@staticmethod
def exreport_output(score):

12
benchmark/__init__.py
View File

@@ -1,10 +1,16 @@
from .Datasets import Datasets, DatasetsSurcov, DatasetsTanveer, DatasetsArff
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__]

1
benchmark/_version Normal file
View File

@@ -0,0 +1 @@
__version__ = "0.7.1"

2
benchmark/_version.py
View File

@@ -1 +1 @@
__version__ = "0.1.1"
__version__ = "0.2.0"

6
benchmark/scripts/be_report.py
View File

@@ -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)

2
benchmark/tests/.env
View File

@@ -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

2
benchmark/tests/.env.arff
View File

@@ -4,3 +4,5 @@ n_folds=5
model=ODTE
stratified=0
source_data=Arff
seeds=[271, 314, 171]
discretize=1

2
benchmark/tests/.env.dist
View File

@@ -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

2
benchmark/tests/.env.surcov
View File

@@ -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

1
benchmark/tests/.gitignore vendored Normal file
View File

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

12
benchmark/tests/Benchmark_test.py
View File

@@ -89,6 +89,15 @@ 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()
@@ -101,6 +110,3 @@ class BenchmarkTest(TestBase):
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}"
# )

7
benchmark/tests/Dataset_test.py
View File

@@ -23,7 +23,12 @@ 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_Datasets_iterator(self):
test = {

34
benchmark/tests/Models_test.py
View File

@@ -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)

2
benchmark/tests/Util_test.py
View File

@@ -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)

2
benchmark/tests/results/results_accuracy_ODTE_Galgo_2022-04-20_10:52:20_0.json
View File

@@ -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",

2
benchmark/tests/results/results_accuracy_RandomForest_iMac27_2022-01-14_12:39:30_0.json
View File

@@ -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",

2
benchmark/tests/results/results_accuracy_STree_iMac27_2021-09-30_11:42:07_0.json
View File

@@ -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,

2
benchmark/tests/results/results_accuracy_STree_iMac27_2021-10-27_09:40:40_0.json
View File

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

2
benchmark/tests/results/results_accuracy_STree_macbook-pro_2021-11-01_19:17:07_0.json
View File

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

11
benchmark/tests/scripts/Be_Report_test.py
View File

@@ -1,6 +1,6 @@
import os
from openpyxl import load_workbook
from ...Utils import Folders
from ...Utils import Folders, Files
from ..TestBase import TestBase
@@ -43,6 +43,15 @@ class BeReportTest(TestBase):
self.assertEqual(stderr.getvalue(), "")
self.check_output_file(stdout, "report_datasets")
def test_be_report_datasets_excel(self):
stdout, stderr = self.execute_script("be_report", ["-x", "1"])
self.assertEqual(stderr.getvalue(), "")
self.check_output_file(stdout, "report_datasets")
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")
def test_be_report_best(self):
stdout, stderr = self.execute_script(
"be_report", ["-s", "accuracy", "-m", "STree", "-b", "1"]

2
benchmark/tests/test_files/be_main_best.test
View File

@@ -1,5 +1,5 @@
************************************************************************************************************************
* Report STree ver. 1.2.4 with 5 Folds cross validation and 10 random seeds. 2022-05-09 00:15:25 *
* 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 *

2
benchmark/tests/test_files/be_main_complete.test
View File

@@ -1,5 +1,5 @@
************************************************************************************************************************
* Report STree ver. 1.2.4 with 5 Folds cross validation and 10 random seeds. 2022-05-08 20:14:43 *
* 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 *

2
benchmark/tests/test_files/be_main_dataset.test
View File

@@ -1,5 +1,5 @@
************************************************************************************************************************
* Report STree ver. 1.2.4 with 5 Folds cross validation and 10 random seeds. 2022-05-08 19:38:28 *
* 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 *

2
benchmark/tests/test_files/be_main_grid.test
View File

@@ -1,5 +1,5 @@
************************************************************************************************************************
* Report STree ver. 1.2.4 with 5 Folds cross validation and 10 random seeds. 2022-05-09 00:21:06 *
* 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 *

2
benchmark/tests/test_files/excel.test
View File

@@ -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"

2
benchmark/tests/test_files/excel_add_ODTE.test
View File

@@ -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"

2
benchmark/tests/test_files/excel_add_STree.test
View File

@@ -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"

2
benchmark/tests/test_files/excel_compared.test
View File

@@ -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"

25
benchmark/tests/test_files/exreport_excel_Datasets.test Normal file
View File

@@ -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%"

2
benchmark/tests/test_files/exreport_excel_ODTE.test
View File

@@ -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"

2
benchmark/tests/test_files/exreport_excel_RandomForest.test
View File

@@ -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"

2
benchmark/tests/test_files/exreport_excel_STree.test
View File

@@ -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"

2
benchmark/tests/test_files/report.test
View File

@@ -1,5 +1,5 @@
************************************************************************************************************************
* Report STree ver. 1.2.3 with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07 *
* 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 *

2
benchmark/tests/test_files/report_compared.test
View File

@@ -1,5 +1,5 @@
************************************************************************************************************************
* Report STree ver. 1.2.3 with 5 Folds cross validation and 10 random seeds. 2021-09-30 11:42:07 *
* 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 *

6
benchmark/tests/test_files/report_datasets.test
View File

@@ -1,4 +1,6 @@
Dataset Sampl. Feat. Cls Balance
============================== ===== ====== === ========================================
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%

3
requirements.txt
View File

@@ -2,7 +2,10 @@ pandas
scikit-learn
scipy
odte
cython
mdlp-discretization
mufs
bayesclass @ git+ssh://git@github.com/doctorado-ml/bayesclass.git
xlsxwriter
openpyxl
tqdm

526
weka_test.ipynb Normal file
View File

@@ -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
}