Doctorado-ML/stree
1
1
Fork 0
mirror of https://github.com/Doctorado-ML/STree.git synced 2025-08-15 07:26:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Package doc #7 (#34)

Browse Source 
* Add first doc info to sources

* Update doc to separate classes in api

* Refactor build_predictor

* Fix random_sate issue in non linear kernels

* Refactor score method using base class implementation

* Some quality refactoring

* Fix codecov config.

* Add sigmoid kernel

* Refactor setup and add Makefile
This commit is contained in:
Ricardo Montañana Gómez
2021-04-26 09:10:01 +02:00
committed by GitHub
parent 02de394c96
commit e19d10f6a7
23 changed files with 369 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
LICENSE
View File

@@ -1,6 +1,6 @@
MIT License MIT License
Copyright (c) 2020 Doctorado-ML Copyright (c) 2020-2021, Ricardo Montañana Gómez
Permission is hereby granted, free of charge, to any person obtaining a copy Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal of this software and associated documentation files (the "Software"), to deal

39
Makefile Normal file
View File

@@ -0,0 +1,39 @@
SHELL := /bin/bash
.DEFAULT_GOAL := help
.PHONY: coverage deps help lint push test
coverage: ## Run tests with coverage
coverage erase
coverage run -m unittest -v stree.tests
coverage report -m
deps: ## Install dependencies
pip install -r requirements.txt
lint: ## Lint and static-check
black stree
flake8 stree
mypy stree
push: ## Push code with tags
git push && git push --tags
test: ## Run tests
python -m unittest -v stree.tests
help: ## Show help message
@IFS=$$'\n' ; \
help_lines=(`fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/##/:/'`); \
printf "%s\n\n" "Usage: make [task]"; \
printf "%-20s %s\n" "task" "help" ; \
printf "%-20s %s\n" "------" "----" ; \
for help_line in $${help_lines[@]}; do \
IFS=$$':' ; \
help_split=($$help_line) ; \
help_command=`echo $${help_split[0]} | sed -e 's/^ *//' -e 's/ *$$//'` ; \
help_info=`echo $${help_split[2]} | sed -e 's/^ *//' -e 's/ *$$//'` ; \
printf '\033[36m'; \
printf "%-20s %s" $$help_command ; \
printf '\033[0m'; \
printf "%s\n" $$help_info; \
done

11
README.md
View File

@@ -14,6 +14,10 @@ Oblique Tree classifier based on SVM nodes. The nodes are built and splitted wit
pip install git+https://github.com/doctorado-ml/stree pip install git+https://github.com/doctorado-ml/stree
``` ```
## Documentation
Can be found in
## Examples ## Examples
### Jupyter notebooks ### Jupyter notebooks
@@ -33,7 +37,7 @@ pip install git+https://github.com/doctorado-ml/stree
| | **Hyperparameter** | **Type/Values** | **Default** | **Meaning** | | | **Hyperparameter** | **Type/Values** | **Default** | **Meaning** |
| --- | ------------------ | ------------------------------------------------------ | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | --- | ------------------ | ------------------------------------------------------ | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| \* | C | \<float\> | 1.0 | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. | | \* | C | \<float\> | 1.0 | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. |
| \* | kernel | {"linear", "poly", "rbf"} | linear | Specifies the kernel type to be used in the algorithm. It must be one of ‘linear’, ‘poly’ or ‘rbf’. | | \* | kernel | {"linear", "poly", "rbf", "sigmoid"} | linear | Specifies the kernel type to be used in the algorithm. It must be one of ‘linear’, ‘poly’ or ‘rbf’. |
| \* | max_iter | \<int\> | 1e5 | Hard limit on iterations within solver, or -1 for no limit. | | \* | max_iter | \<int\> | 1e5 | Hard limit on iterations within solver, or -1 for no limit. |
| \* | random_state | \<int\> | None | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls | | \* | random_state | \<int\> | None | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls |
| | max_depth | \<int\> | None | Specifies the maximum depth of the tree | | | max_depth | \<int\> | None | Specifies the maximum depth of the tree |
@@ -45,6 +49,7 @@ pip install git+https://github.com/doctorado-ml/stree
| | min_samples_split | \<int\> | 0 | The minimum number of samples required to split an internal node. 0 (default) for any | | | min_samples_split | \<int\> | 0 | The minimum number of samples required to split an internal node. 0 (default) for any |
| | max_features | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. | | | max_features | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. |
| | splitter | {"best", "random"} | random | The strategy used to choose the feature set at each node (only used if max_features != num_features). <br>Supported strategies are “best” to choose the best feature set and “random” to choose a random combination. <br>The algorithm generates 5 candidates at most to choose from in both strategies. | | | splitter | {"best", "random"} | random | The strategy used to choose the feature set at each node (only used if max_features != num_features). <br>Supported strategies are “best” to choose the best feature set and “random” to choose a random combination. <br>The algorithm generates 5 candidates at most to choose from in both strategies. |
| | normalize | \<bool\> | False | If standardization of features should be applied on each node with the samples that reach it |
\* Hyperparameter used by the support vector classifier of every node \* Hyperparameter used by the support vector classifier of every node
@@ -61,3 +66,7 @@ Once we have the column to take into account for the split, the algorithm splits
```bash ```bash
python -m unittest -v stree.tests python -m unittest -v stree.tests
``` ```
## License
STree is [MIT](https://github.com/doctorado-ml/stree/blob/master/LICENSE) licensed

10
codecov.yml
View File

@@ -1,12 +1,12 @@
overage: coverage:
status: status:
project: project:
default: default:
target: 90% target: 100%
comment: comment:
layout: "reach, diff, flags, files" layout: "reach, diff, flags, files"
behavior: default behavior: default
require_changes: false require_changes: false
require_base: yes require_base: yes
require_head: yes require_head: yes
branches: null branches: null

20
docs/Makefile Normal file
View File

@@ -0,0 +1,20 @@
# Minimal makefile for Sphinx documentation
#
# You can set these variables from the command line, and also
# from the environment for the first two.
SPHINXOPTS ?=
SPHINXBUILD ?= sphinx-build
SOURCEDIR = source
BUILDDIR = build
# Put it first so that "make" without argument is like "make help".
help:
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
.PHONY: help Makefile
# Catch-all target: route all unknown targets to Sphinx using the new
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
%: Makefile
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

3
docs/requirements.txt Normal file
View File

@@ -0,0 +1,3 @@
sphinx
sphinx-rtd-theme
myst-parser

9
docs/source/api/Siterator.rst Normal file
View File

@@ -0,0 +1,9 @@
Siterator
=========
.. automodule:: stree
.. autoclass:: Siterator
:members:
:undoc-members:
:private-members:
:show-inheritance:

9
docs/source/api/Snode.rst Normal file
View File

@@ -0,0 +1,9 @@
Snode
=====
.. automodule:: stree
.. autoclass:: Snode
:members:
:undoc-members:
:private-members:
:show-inheritance:

9
docs/source/api/Splitter.rst Normal file
View File

@@ -0,0 +1,9 @@
Splitter
========
.. automodule:: stree
.. autoclass:: Splitter
:members:
:undoc-members:
:private-members:
:show-inheritance:

9
docs/source/api/Stree.rst Normal file
View File

@@ -0,0 +1,9 @@
Stree
=====
.. automodule:: stree
.. autoclass:: Stree
:members:
:undoc-members:
:private-members:
:show-inheritance:

11
docs/source/api/index.rst Normal file
View File

@@ -0,0 +1,11 @@
API index
=========
.. toctree::
:maxdepth: 2
:caption: Contents:
Stree
Splitter
Snode
Siterator

55
docs/source/conf.py Normal file
View File

@@ -0,0 +1,55 @@
# Configuration file for the Sphinx documentation builder.
#
# This file only contains a selection of the most common options. For a full
# list see the documentation:
# https://www.sphinx-doc.org/en/master/usage/configuration.html
# -- Path setup --------------------------------------------------------------
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
#
import os
import sys
sys.path.insert(0, os.path.abspath("../../stree/"))
# -- Project information -----------------------------------------------------
project = "STree"
copyright = "2020 - 2021, Ricardo Montañana Gómez"
author = "Ricardo Montañana Gómez"
# The full version, including alpha/beta/rc tags
release = "1.0"
# -- General configuration ---------------------------------------------------
# Add any Sphinx extension module names here, as strings. They can be
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
# ones.
extensions = ["myst_parser", "sphinx.ext.autodoc", "sphinx.ext.viewcode"]
# Add any paths that contain templates here, relative to this directory.
templates_path = ["_templates"]
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
# This pattern also affects html_static_path and html_extra_path.
exclude_patterns = []
# -- Options for HTML output -------------------------------------------------
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
#
html_theme = "sphinx_rtd_theme"
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ["_static"]

44
docs/source/example.md Normal file
View File

@@ -0,0 +1,44 @@
# Examples
## Notebooks
- [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/benchmark.ipynb) Benchmark
- [![benchmark](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
- [![features](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
- [![Gridsearch](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/gridsearch.ipynb) Gridsearch
- [![Ensemble](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/ensemble.ipynb) Ensembles
## Sample Code
```python
import time
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
from stree import Stree
random_state = 1
X, y = load_iris(return_X_y=True)
Xtrain, Xtest, ytrain, ytest = train_test_split(
X, y, test_size=0.2, random_state=random_state
)
now = time.time()
print("Predicting with max_features=sqrt(n_features)")
clf = Stree(random_state=random_state, max_features="auto")
clf.fit(Xtrain, ytrain)
print(f"Took {time.time() - now:.2f} seconds to train")
print(clf)
print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}")
print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}")
print("=" * 40)
print("Predicting with max_features=n_features")
clf = Stree(random_state=random_state)
clf.fit(Xtrain, ytrain)
print(f"Took {time.time() - now:.2f} seconds to train")
print(clf)
print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}")
print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}")
```

BIN
docs/source/example.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 3.1 MiB

28
docs/source/hyperparameters.md Normal file
View File

@@ -0,0 +1,28 @@
# Hyperparameters
| | **Hyperparameter** | **Type/Values** | **Default** | **Meaning** |
| --- | ------------------ | ------------------------------------------------------ | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| \* | C | \<float\> | 1.0 | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. |
| \* | kernel | {"linear", "poly", "rbf"} | linear | Specifies the kernel type to be used in the algorithm. It must be one of ‘linear’, ‘poly’ or ‘rbf’. |
| \* | max_iter | \<int\> | 1e5 | Hard limit on iterations within solver, or -1 for no limit. |
| \* | random_state | \<int\> | None | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls |
| | max_depth | \<int\> | None | Specifies the maximum depth of the tree |
| \* | tol | \<float\> | 1e-4 | Tolerance for stopping criterion. |
| \* | degree | \<int\> | 3 | Degree of the polynomial kernel function (‘poly’). Ignored by all other kernels. |
| \* | gamma | {"scale", "auto"} or \<float\> | scale | Kernel coefficient for ‘rbf’ and ‘poly’.<br>if gamma='scale' (default) is passed then it uses 1 / (n_features \* X.var()) as value of gamma,<br>if ‘auto’, uses 1 / n_features. |
| | split_criteria | {"impurity", "max_samples"} | impurity | Decides (just in case of a multi class classification) which column (class) use to split the dataset in a node\*\* |
| | criterion | {“gini”, “entropy”} | entropy | The function to measure the quality of a split (only used if max_features != num_features). <br>Supported criteria are “gini” for the Gini impurity and “entropy” for the information gain. |
| | min_samples_split | \<int\> | 0 | The minimum number of samples required to split an internal node. 0 (default) for any |
| | max_features | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. |
| | splitter | {"best", "random"} | random | The strategy used to choose the feature set at each node (only used if max_features != num_features). <br>Supported strategies are “best” to choose the best feature set and “random” to choose a random combination. <br>The algorithm generates 5 candidates at most to choose from in both strategies. |
| | normalize | \<bool\> | False | If standardization of features should be applied on each node with the samples that reach it |
\* Hyperparameter used by the support vector classifier of every node
\*\* **Splitting in a STree node**
The decision function is applied to the dataset and distances from samples to hyperplanes are computed in a matrix. This matrix has as many columns as classes the samples belongs to (if more than two, i.e. multiclass classification) or 1 column if it's a binary class dataset. In binary classification only one hyperplane is computed and therefore only one column is needed to store the distances of the samples to it. If three or more classes are present in the dataset we need as many hyperplanes as classes are there, and therefore one column per hyperplane is needed.
In case of multiclass classification we have to decide which column take into account to make the split, that depends on hyperparameter _split_criteria_, if "impurity" is chosen then STree computes information gain of every split candidate using each column and chooses the one that maximize the information gain, otherwise STree choses the column with more samples with a predicted class (the column with more positive numbers in it).
Once we have the column to take into account for the split, the algorithm splits samples with positive distances to hyperplane from the rest.

15
docs/source/index.rst Normal file
View File

@@ -0,0 +1,15 @@
Welcome to STree's documentation!
=================================
.. toctree::
:caption: Contents:
:titlesonly:
stree
install
hyperparameters
example
api/index
* :ref:`genindex`

16
docs/source/install.rst Normal file
View File

@@ -0,0 +1,16 @@
Install
=======
The main stable release
``pip install stree``
or the last development branch
``pip install git+https://github.com/doctorado-ml/stree``
Tests
*****
``python -m unittest -v stree.tests``

13
docs/source/stree.md Normal file
View File

@@ -0,0 +1,13 @@
# Stree
[![Codeship Status for Doctorado-ML/STree](https://app.codeship.com/projects/8b2bd350-8a1b-0138-5f2c-3ad36f3eb318/status?branch=master)](https://app.codeship.com/projects/399170)
[![codecov](https://codecov.io/gh/doctorado-ml/stree/branch/master/graph/badge.svg)](https://codecov.io/gh/doctorado-ml/stree)
[![Codacy Badge](https://app.codacy.com/project/badge/Grade/35fa3dfd53a24a339344b33d9f9f2f3d)](https://www.codacy.com/gh/Doctorado-ML/STree?utm_source=github.com&utm_medium=referral&utm_content=Doctorado-ML/STree&utm_campaign=Badge_Grade)
Oblique Tree classifier based on SVM nodes. The nodes are built and splitted with sklearn SVC models. Stree is a sklearn estimator and can be integrated in pipelines, grid searches, etc.
![Stree](./example.png)
## License
STree is [MIT](https://github.com/doctorado-ml/stree/blob/master/LICENSE) licensed

29
main.py
View File

@@ -1,29 +0,0 @@
import time
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
from stree import Stree
random_state = 1
X, y = load_iris(return_X_y=True)
Xtrain, Xtest, ytrain, ytest = train_test_split(
X, y, test_size=0.3, random_state=random_state
)
now = time.time()
print("Predicting with max_features=sqrt(n_features)")
clf = Stree(C=0.01, random_state=random_state, max_features="auto")
clf.fit(Xtrain, ytrain)
print(f"Took {time.time() - now:.2f} seconds to train")
print(clf)
print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}")
print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}")
print("=" * 40)
print("Predicting with max_features=n_features")
clf = Stree(C=0.01, random_state=random_state)
clf.fit(Xtrain, ytrain)
print(f"Took {time.time() - now:.2f} seconds to train")
print(clf)
print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}")
print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}")

19
setup.py
View File

@@ -1,7 +1,5 @@
import setuptools import setuptools
import stree
__version__ = "1.0rc1"
__author__ = "Ricardo Montañana Gómez"
def readme(): def readme():
@@ -9,22 +7,23 @@ def readme():
return f.read() return f.read()
VERSION = stree.__version__
setuptools.setup( setuptools.setup(
name="STree", name="STree",
version=__version__, version=stree.__version__,
license="MIT License", license=stree.__license__,
description="Oblique decision tree with svm nodes", description="Oblique decision tree with svm nodes",
long_description=readme(), long_description=readme(),
long_description_content_type="text/markdown", long_description_content_type="text/markdown",
packages=setuptools.find_packages(), packages=setuptools.find_packages(),
url="https://github.com/doctorado-ml/stree", url=stree.__url__,
author=__author__, author=stree.__author__,
author_email="ricardo.montanana@alu.uclm.es", author_email=stree.__author_email__,
keywords="scikit-learn oblique-classifier oblique-decision-tree decision-\ keywords="scikit-learn oblique-classifier oblique-decision-tree decision-\
tree svm svc", tree svm svc",
classifiers=[ classifiers=[
"Development Status :: 4 - Beta", "Development Status :: 5 - Production/Stable",
"License :: OSI Approved :: MIT License", "License :: OSI Approved :: " + stree.__license__,
"Programming Language :: Python :: 3.8", "Programming Language :: Python :: 3.8",
"Natural Language :: English", "Natural Language :: English",
"Topic :: Scientific/Engineering :: Artificial Intelligence", "Topic :: Scientific/Engineering :: Artificial Intelligence",

97
stree/Strees.py
View File

@@ -1,9 +1,5 @@
""" """
__author__ = "Ricardo Montañana Gómez" Oblique decision tree classifier based on SVM nodes
__copyright__ = "Copyright 2020, Ricardo Montañana Gómez"
__license__ = "MIT"
__version__ = "0.9"
Build an oblique tree classifier based on SVM nodes
""" """
import os import os
@@ -17,7 +13,6 @@ from sklearn.base import BaseEstimator, ClassifierMixin
from sklearn.svm import SVC, LinearSVC from sklearn.svm import SVC, LinearSVC
from sklearn.feature_selection import SelectKBest from sklearn.feature_selection import SelectKBest
from sklearn.preprocessing import StandardScaler from sklearn.preprocessing import StandardScaler
from sklearn.utils import check_consistent_length
from sklearn.utils.multiclass import check_classification_targets from sklearn.utils.multiclass import check_classification_targets
from sklearn.exceptions import ConvergenceWarning from sklearn.exceptions import ConvergenceWarning
from sklearn.utils.validation import ( from sklearn.utils.validation import (
@@ -26,7 +21,6 @@ from sklearn.utils.validation import (
check_is_fitted, check_is_fitted,
_check_sample_weight, _check_sample_weight,
) )
from sklearn.metrics._classification import _weighted_sum, _check_targets
class Snode: class Snode:
@@ -147,12 +141,11 @@ class Snode:
f"{self._belief: .6f} impurity={self._impurity:.4f} " f"{self._belief: .6f} impurity={self._impurity:.4f} "
f"counts={count_values}" f"counts={count_values}"
) )
else: return (
return ( f"{self._title} feaures={self._features} impurity="
f"{self._title} feaures={self._features} impurity=" f"{self._impurity:.4f} "
f"{self._impurity:.4f} " f"counts={count_values}"
f"counts={count_values}" )
)
class Siterator: class Siterator:
@@ -298,6 +291,23 @@ class Splitter:
def _select_best_set( def _select_best_set(
self, dataset: np.array, labels: np.array, features_sets: list self, dataset: np.array, labels: np.array, features_sets: list
) -> list: ) -> list:
"""Return the best set of features among feature_sets, the criterion is
the information gain
Parameters
----------
dataset : np.array
array of samples (# samples, # features)
labels : np.array
array of labels
features_sets : list
list of features sets to check
Returns
-------
list
best feature set
"""
max_gain = 0 max_gain = 0
selected = None selected = None
warnings.filterwarnings("ignore", category=ConvergenceWarning) warnings.filterwarnings("ignore", category=ConvergenceWarning)
@@ -451,6 +461,15 @@ class Splitter:
def partition(self, samples: np.array, node: Snode, train: bool): def partition(self, samples: np.array, node: Snode, train: bool):
"""Set the criteria to split arrays. Compute the indices of the samples """Set the criteria to split arrays. Compute the indices of the samples
that should go to one side of the tree (up) that should go to one side of the tree (up)
Parameters
----------
samples : np.array
array of samples (# samples, # features)
node : Snode
Node of the tree where partition is going to be made
train : bool
Train time - True / Test time - False
""" """
# data contains the distances of every sample to every class hyperplane # data contains the distances of every sample to every class hyperplane
# array of (m, nc) nc = # classes # array of (m, nc) nc = # classes
@@ -602,7 +621,9 @@ class Stree(BaseEstimator, ClassifierMixin):
f"Maximum depth has to be greater than 1... got (max_depth=\ f"Maximum depth has to be greater than 1... got (max_depth=\
{self.max_depth})" {self.max_depth})"
) )
kernels = ["linear", "rbf", "poly", "sigmoid"]
if self.kernel not in kernels:
raise ValueError(f"Kernel {self.kernel} not in {kernels}")
check_classification_targets(y) check_classification_targets(y)
X, y = check_X_y(X, y) X, y = check_X_y(X, y)
sample_weight = _check_sample_weight( sample_weight = _check_sample_weight(
@@ -633,7 +654,6 @@ class Stree(BaseEstimator, ClassifierMixin):
self.n_features_in_ = X.shape[1] self.n_features_in_ = X.shape[1]
self.max_features_ = self._initialize_max_features() self.max_features_ = self._initialize_max_features()
self.tree_ = self.train(X, y, sample_weight, 1, "root") self.tree_ = self.train(X, y, sample_weight, 1, "root")
self._build_predictor()
self.X_ = X self.X_ = X
self.y_ = y self.y_ = y
return self return self
@@ -681,6 +701,7 @@ class Stree(BaseEstimator, ClassifierMixin):
if np.unique(y).shape[0] == 1: if np.unique(y).shape[0] == 1:
# only 1 class => pure dataset # only 1 class => pure dataset
node.set_title(title + ", <pure>") node.set_title(title + ", <pure>")
node.make_predictor()
return node return node
# Train the model # Train the model
clf = self._build_clf() clf = self._build_clf()
@@ -699,6 +720,7 @@ class Stree(BaseEstimator, ClassifierMixin):
if X_U is None or X_D is None: if X_U is None or X_D is None:
# didn't part anything # didn't part anything
node.set_title(title + ", <cgaf>") node.set_title(title + ", <cgaf>")
node.make_predictor()
return node return node
node.set_up( node.set_up(
self.train(X_U, y_u, sw_u, depth + 1, title + f" - Up({depth+1})") self.train(X_U, y_u, sw_u, depth + 1, title + f" - Up({depth+1})")
@@ -710,20 +732,8 @@ class Stree(BaseEstimator, ClassifierMixin):
) )
return node return node
def _build_predictor(self):
"""Process the leaves to make them predictors"""
def run_tree(node: Snode):
if node.is_leaf():
node.make_predictor()
return
run_tree(node.get_down())
run_tree(node.get_up())
run_tree(self.tree_)
def _build_clf(self): def _build_clf(self):
"""Build the correct classifier for the node""" """Build the right classifier for the node"""
return ( return (
LinearSVC( LinearSVC(
max_iter=self.max_iter, max_iter=self.max_iter,
@@ -739,6 +749,7 @@ class Stree(BaseEstimator, ClassifierMixin):
C=self.C, C=self.C,
gamma=self.gamma, gamma=self.gamma,
degree=self.degree, degree=self.degree,
random_state=self.random_state,
) )
) )
@@ -820,36 +831,6 @@ class Stree(BaseEstimator, ClassifierMixin):
) )
return self.classes_[result] return self.classes_[result]
def score(
self, X: np.array, y: np.array, sample_weight: np.array = None
) -> float:
"""Compute accuracy of the prediction
Parameters
----------
X : np.array
dataset of samples to make predictions
y : np.array
samples labels
sample_weight : np.array, optional
weights of the samples. Rescale C per sample, by default None
Returns
-------
float
accuracy of the prediction
"""
# sklearn check
check_is_fitted(self)
check_classification_targets(y)
X, y = check_X_y(X, y)
y_pred = self.predict(X).reshape(y.shape)
# Compute accuracy for each possible representation
_, y_true, y_pred = _check_targets(y, y_pred)
check_consistent_length(y_true, y_pred, sample_weight)
score = y_true == y_pred
return _weighted_sum(score, sample_weight, normalize=True)
def nodes_leaves(self) -> tuple: def nodes_leaves(self) -> tuple:
"""Compute the number of nodes and leaves in the built tree """Compute the number of nodes and leaves in the built tree

8
stree/__init__.py
View File

@@ -1,3 +1,11 @@
from .Strees import Stree, Snode, Siterator, Splitter from .Strees import Stree, Snode, Siterator, Splitter
__version__ = "1.0"
__author__ = "Ricardo Montañana Gómez"
__copyright__ = "Copyright 2020-2021, Ricardo Montañana Gómez"
__license__ = "MIT License"
__author_email__ = "ricardo.montanana@alu.uclm.es"
__url__ = "https://github.com/doctorado-ml/stree"
__all__ = ["Stree", "Snode", "Siterator", "Splitter"] __all__ = ["Stree", "Snode", "Siterator", "Splitter"]

19
stree/tests/Stree_test.py
View File

@@ -21,6 +21,21 @@ class Stree_test(unittest.TestCase):
def setUp(cls): def setUp(cls):
os.environ["TESTING"] = "1" os.environ["TESTING"] = "1"
def test_valid_kernels(self):
valid_kernels = ["linear", "rbf", "poly", "sigmoid"]
X, y = load_dataset()
for kernel in valid_kernels:
clf = Stree(kernel=kernel)
clf.fit(X, y)
self.assertIsNotNone(clf.tree_)
def test_bogus_kernel(self):
kernel = "other"
X, y = load_dataset()
clf = Stree(kernel=kernel)
with self.assertRaises(ValueError):
clf.fit(X, y)
def _check_tree(self, node: Snode): def _check_tree(self, node: Snode):
"""Check recursively that the nodes that are not leaves have the """Check recursively that the nodes that are not leaves have the
correct number of labels and its sons have the right number of elements correct number of labels and its sons have the right number of elements
@@ -484,13 +499,13 @@ class Stree_test(unittest.TestCase):
clf.fit(X, y) clf.fit(X, y)
nodes, leaves = clf.nodes_leaves() nodes, leaves = clf.nodes_leaves()
self.assertEqual(25, nodes) self.assertEqual(25, nodes)
self.assertEquals(13, leaves) self.assertEqual(13, leaves)
X, y = load_wine(return_X_y=True) X, y = load_wine(return_X_y=True)
clf = Stree(random_state=self._random_state) clf = Stree(random_state=self._random_state)
clf.fit(X, y) clf.fit(X, y)
nodes, leaves = clf.nodes_leaves() nodes, leaves = clf.nodes_leaves()
self.assertEqual(9, nodes) self.assertEqual(9, nodes)
self.assertEquals(5, leaves) self.assertEqual(5, leaves)
def test_nodes_leaves_artificial(self): def test_nodes_leaves_artificial(self):
n1 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test1") n1 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test1")