mirror of
https://github.com/Doctorado-ML/STree.git
synced 2025-08-17 16:36:01 +00:00
Compare commits
39 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
cb80e8606b
|
|||
|
c93d3fbcc7
|
|||
|
f4ca4bbd5b
|
|||
|
e676ddbfcc
|
|||
|
dc637018e8 | ||
|
517013be09
|
|||
|
941c2ff5e0
|
|||
|
2ebf48145d
|
|||
|
7fbfd3622e
|
|||
|
bc839a80d6
|
|||
|
ba15ea2cc0
|
|||
|
85b56785c8
|
|||
|
b627bb7531
|
|||
|
5f8ca8f3bb
|
|||
|
|
fb8b9b344f | ||
|
036d1ba2a7
|
|||
|
4de74973b8
|
|||
|
|
28dd04b95a | ||
|
|
542bbce7db
|
||
|
|
5b791bc5bf | ||
|
|
c37f044e3a | ||
|
|
2f6ae648a1 | ||
|
|
93be8a89a8 | ||
|
82838fa3e0
|
|||
|
f0b2ce3c7b
|
|||
|
00ed57c015
|
|||
|
|
08222f109e | ||
|
cc931d8547
|
|||
|
b044a057df
|
|||
|
fc48bc8ba4
|
|||
|
|
8251f07674 | ||
|
|
0b15a5af11 | ||
|
|
28d905368b | ||
|
e5d49132ec
|
|||
|
8daecc4726
|
|||
|
|
bf678df159 | ||
|
|
36b08b1bcf | ||
|
36ff3da26d
|
|||
|
|
6b281ebcc8 |
58
.github/workflows/codeql-analysis.yml
vendored
58
.github/workflows/codeql-analysis.yml
vendored
@@ -2,12 +2,12 @@ name: "CodeQL"
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ master ]
|
||||
branches: [master]
|
||||
pull_request:
|
||||
# The branches below must be a subset of the branches above
|
||||
branches: [ master ]
|
||||
branches: [master]
|
||||
schedule:
|
||||
- cron: '16 17 * * 3'
|
||||
- cron: "16 17 * * 3"
|
||||
|
||||
jobs:
|
||||
analyze:
|
||||
@@ -17,40 +17,40 @@ jobs:
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
language: [ 'python' ]
|
||||
language: ["python"]
|
||||
# CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]
|
||||
# Learn more:
|
||||
# https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v2
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v2
|
||||
|
||||
# Initializes the CodeQL tools for scanning.
|
||||
- name: Initialize CodeQL
|
||||
uses: github/codeql-action/init@v1
|
||||
with:
|
||||
languages: ${{ matrix.language }}
|
||||
# If you wish to specify custom queries, you can do so here or in a config file.
|
||||
# By default, queries listed here will override any specified in a config file.
|
||||
# Prefix the list here with "+" to use these queries and those in the config file.
|
||||
# queries: ./path/to/local/query, your-org/your-repo/queries@main
|
||||
# Initializes the CodeQL tools for scanning.
|
||||
- name: Initialize CodeQL
|
||||
uses: github/codeql-action/init@v2
|
||||
with:
|
||||
languages: ${{ matrix.language }}
|
||||
# If you wish to specify custom queries, you can do so here or in a config file.
|
||||
# By default, queries listed here will override any specified in a config file.
|
||||
# Prefix the list here with "+" to use these queries and those in the config file.
|
||||
# queries: ./path/to/local/query, your-org/your-repo/queries@main
|
||||
|
||||
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
|
||||
# If this step fails, then you should remove it and run the build manually (see below)
|
||||
- name: Autobuild
|
||||
uses: github/codeql-action/autobuild@v1
|
||||
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
|
||||
# If this step fails, then you should remove it and run the build manually (see below)
|
||||
- name: Autobuild
|
||||
uses: github/codeql-action/autobuild@v2
|
||||
|
||||
# ℹ️ Command-line programs to run using the OS shell.
|
||||
# 📚 https://git.io/JvXDl
|
||||
# ℹ️ Command-line programs to run using the OS shell.
|
||||
# 📚 https://git.io/JvXDl
|
||||
|
||||
# ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
|
||||
# and modify them (or add more) to build your code if your project
|
||||
# uses a compiled language
|
||||
# ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
|
||||
# and modify them (or add more) to build your code if your project
|
||||
# uses a compiled language
|
||||
|
||||
#- run: |
|
||||
# make bootstrap
|
||||
# make release
|
||||
#- run: |
|
||||
# make bootstrap
|
||||
# make release
|
||||
|
||||
- name: Perform CodeQL Analysis
|
||||
uses: github/codeql-action/analyze@v1
|
||||
- name: Perform CodeQL Analysis
|
||||
uses: github/codeql-action/analyze@v2
|
||||
|
||||
12
.github/workflows/main.yml
vendored
12
.github/workflows/main.yml
vendored
@@ -12,13 +12,13 @@ jobs:
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
matrix:
|
||||
os: [macos-latest, ubuntu-latest]
|
||||
python: [3.8]
|
||||
os: [macos-latest, ubuntu-latest, windows-latest]
|
||||
python: [3.11, 3.12]
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python ${{ matrix.python }}
|
||||
uses: actions/setup-python@v2
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ matrix.python }}
|
||||
- name: Install dependencies
|
||||
@@ -28,14 +28,14 @@ jobs:
|
||||
pip install -q --upgrade codecov coverage black flake8 codacy-coverage
|
||||
- name: Lint
|
||||
run: |
|
||||
black --check --diff stree
|
||||
# black --check --diff stree
|
||||
flake8 --count stree
|
||||
- name: Tests
|
||||
run: |
|
||||
coverage run -m unittest -v stree.tests
|
||||
coverage xml
|
||||
- name: Upload coverage to Codecov
|
||||
uses: codecov/codecov-action@v1
|
||||
uses: codecov/codecov-action@v4
|
||||
with:
|
||||
token: ${{ secrets.CODECOV_TOKEN }}
|
||||
files: ./coverage.xml
|
||||
|
||||
@@ -3,8 +3,12 @@ version: 2
|
||||
sphinx:
|
||||
configuration: docs/source/conf.py
|
||||
|
||||
build:
|
||||
os: ubuntu-22.04
|
||||
tools:
|
||||
python: "3.12"
|
||||
|
||||
python:
|
||||
version: 3.8
|
||||
install:
|
||||
- requirements: requirements.txt
|
||||
- requirements: docs/requirements.txt
|
||||
37
CITATION.cff
Normal file
37
CITATION.cff
Normal file
@@ -0,0 +1,37 @@
|
||||
cff-version: 1.2.0
|
||||
message: "If you use this software, please cite it as below."
|
||||
authors:
|
||||
- family-names: "Montañana"
|
||||
given-names: "Ricardo"
|
||||
orcid: "https://orcid.org/0000-0003-3242-5452"
|
||||
- family-names: "Gámez"
|
||||
given-names: "José A."
|
||||
orcid: "https://orcid.org/0000-0003-1188-1117"
|
||||
- family-names: "Puerta"
|
||||
given-names: "José M."
|
||||
orcid: "https://orcid.org/0000-0002-9164-5191"
|
||||
title: "STree"
|
||||
version: 1.2.3
|
||||
doi: 10.5281/zenodo.5504083
|
||||
date-released: 2021-11-02
|
||||
url: "https://github.com/Doctorado-ML/STree"
|
||||
preferred-citation:
|
||||
type: article
|
||||
authors:
|
||||
- family-names: "Montañana"
|
||||
given-names: "Ricardo"
|
||||
orcid: "https://orcid.org/0000-0003-3242-5452"
|
||||
- family-names: "Gámez"
|
||||
given-names: "José A."
|
||||
orcid: "https://orcid.org/0000-0003-1188-1117"
|
||||
- family-names: "Puerta"
|
||||
given-names: "José M."
|
||||
orcid: "https://orcid.org/0000-0002-9164-5191"
|
||||
doi: "10.1007/978-3-030-85713-4_6"
|
||||
journal: "Lecture Notes in Computer Science"
|
||||
month: 9
|
||||
start: 54
|
||||
end: 64
|
||||
title: "STree: A Single Multi-class Oblique Decision Tree Based on Support Vector Machines"
|
||||
volume: 12882
|
||||
year: 2021
|
||||
1
MANIFEST.in
Normal file
1
MANIFEST.in
Normal file
@@ -0,0 +1 @@
|
||||
include README.md LICENSE
|
||||
42
Makefile
42
Makefile
@@ -1,40 +1,36 @@
|
||||
SHELL := /bin/bash
|
||||
.DEFAULT_GOAL := help
|
||||
.PHONY: coverage deps help lint push test doc build
|
||||
.PHONY: audit coverage help lint test doc doc-clean build
|
||||
|
||||
coverage: ## Run tests with coverage
|
||||
coverage erase
|
||||
coverage run -m unittest -v stree.tests
|
||||
coverage report -m
|
||||
@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
|
||||
lint: ## Lint source files
|
||||
@black stree
|
||||
@flake8 stree
|
||||
|
||||
test: ## Run tests
|
||||
python -m unittest -v stree.tests
|
||||
@python -m unittest -v stree.tests
|
||||
|
||||
doc: ## Update documentation
|
||||
make -C docs --makefile=Makefile html
|
||||
@make -C docs --makefile=Makefile html
|
||||
|
||||
build: ## Build package
|
||||
rm -fr dist/*
|
||||
rm -fr build/*
|
||||
python setup.py sdist bdist_wheel
|
||||
@rm -fr dist/*
|
||||
@rm -fr build/*
|
||||
@hatch build
|
||||
|
||||
doc-clean: ## Update documentation
|
||||
make -C docs --makefile=Makefile clean
|
||||
doc-clean: ## Clean documentation folders
|
||||
@make -C docs --makefile=Makefile clean
|
||||
|
||||
help: ## Show help message
|
||||
audit: ## Audit pip
|
||||
@pip-audit
|
||||
|
||||
help: ## Show this help message
|
||||
@IFS=$$'\n' ; \
|
||||
help_lines=(`fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/##/:/'`); \
|
||||
help_lines=(`grep -Fh "##" $(MAKEFILE_LIST) | grep -Fv fgrep | sed -e 's/\\$$//' | sed -e 's/##/:/'`); \
|
||||
printf "%s\n\n" "Usage: make [task]"; \
|
||||
printf "%-20s %s\n" "task" "help" ; \
|
||||
printf "%-20s %s\n" "------" "----" ; \
|
||||
|
||||
56
README.md
56
README.md
@@ -1,21 +1,23 @@
|
||||
# STree
|
||||
|
||||
|
||||
[](https://github.com/Doctorado-ML/STree/actions/workflows/codeql-analysis.yml)
|
||||
[](https://codecov.io/gh/doctorado-ml/stree)
|
||||
[](https://www.codacy.com/gh/Doctorado-ML/STree?utm_source=github.com&utm_medium=referral&utm_content=Doctorado-ML/STree&utm_campaign=Badge_Grade)
|
||||
[](https://lgtm.com/projects/g/Doctorado-ML/STree/context:python)
|
||||
[](https://badge.fury.io/py/STree)
|
||||
|
||||
|
||||
[](https://deepwiki.com/Doctorado-ML/STree)
|
||||
[](https://zenodo.org/badge/latestdoi/262658230)
|
||||
|
||||
|
||||
# STree
|
||||
|
||||
|
||||
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.
|
||||
|
||||
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
pip install git+https://github.com/doctorado-ml/stree
|
||||
pip install Stree
|
||||
```
|
||||
|
||||
## Documentation
|
||||
@@ -26,8 +28,6 @@ Can be found in [stree.readthedocs.io](https://stree.readthedocs.io/en/stable/)
|
||||
|
||||
### Jupyter notebooks
|
||||
|
||||
- [](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/benchmark.ipynb) Benchmark
|
||||
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
|
||||
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
|
||||
@@ -38,24 +38,24 @@ Can be found in [stree.readthedocs.io](https://stree.readthedocs.io/en/stable/)
|
||||
|
||||
## 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 | {"liblinear", "linear", "poly", "rbf", "sigmoid"} | linear | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’. liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library |
|
||||
| \* | 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’, ‘poly’ and ‘sigmoid’.<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\*\*. max_samples is incompatible with 'ovo' multiclass_strategy |
|
||||
| | 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", "mutual", "cfs", "fcbf"} | "random" | The strategy used to choose the feature set at each node (only used if max_features < num_features). Supported strategies are: **“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features. **“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them. **"mutual"**: Chooses the best features w.r.t. their mutual info with the label. **"cfs"**: Apply Correlation-based Feature Selection. **"fcbf"**: Apply Fast Correlation-Based Filter |
|
||||
| | normalize | \<bool\> | False | If standardization of features should be applied on each node with the samples that reach it |
|
||||
| \* | multiclass_strategy | {"ovo", "ovr"} | "ovo" | Strategy to use with multiclass datasets, **"ovo"**: one versus one. **"ovr"**: one versus rest |
|
||||
|
||||
| | **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 | {"liblinear", "linear", "poly", "rbf", "sigmoid"} | linear | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’. liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library |
|
||||
| \* | 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’, ‘poly’ and ‘sigmoid’.<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\*\*. max_samples is incompatible with 'ovo' multiclass_strategy |
|
||||
| | 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", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random" | The strategy used to choose the feature set at each node (only used if max_features < num_features).
|
||||
Supported strategies are: **“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features. **“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them. **“trandom”**: The algorithm generates only one random combination. **"mutual"**: Chooses the best features w.r.t. their mutual info with the label. **"cfs"**: Apply Correlation-based Feature Selection. **"fcbf"**: Apply Fast Correlation-Based Filter. **"iwss"**: IWSS based algorithm |
|
||||
| | normalize | \<bool\> | False | If standardization of features should be applied on each node with the samples that reach it |
|
||||
| \* | multiclass_strategy | {"ovo", "ovr"} | "ovo" | Strategy to use with multiclass datasets, **"ovo"**: one versus one. **"ovr"**: one versus rest |
|
||||
|
||||
\* Hyperparameter used by the support vector classifier of every node
|
||||
|
||||
@@ -76,3 +76,7 @@ python -m unittest -v stree.tests
|
||||
## License
|
||||
|
||||
STree is [MIT](https://github.com/doctorado-ml/stree/blob/master/LICENSE) licensed
|
||||
|
||||
## Reference
|
||||
|
||||
R. Montañana, J. A. Gámez, J. M. Puerta, "STree: a single multi-class oblique decision tree based on support vector machines.", 2021 LNAI 12882, pg. 54-64
|
||||
|
||||
@@ -1,9 +1,10 @@
|
||||
Siterator
|
||||
=========
|
||||
|
||||
.. automodule:: Splitter
|
||||
.. automodule:: stree
|
||||
.. autoclass:: Siterator
|
||||
:members:
|
||||
:undoc-members:
|
||||
:private-members:
|
||||
:show-inheritance:
|
||||
:noindex:
|
||||
@@ -1,9 +1,9 @@
|
||||
Snode
|
||||
=====
|
||||
|
||||
.. automodule:: Splitter
|
||||
.. autoclass:: Snode
|
||||
.. autoclass:: stree.Splitter.Snode
|
||||
:members:
|
||||
:undoc-members:
|
||||
:private-members:
|
||||
:show-inheritance:
|
||||
:noindex:
|
||||
@@ -1,9 +1,10 @@
|
||||
Splitter
|
||||
========
|
||||
|
||||
.. automodule:: Splitter
|
||||
.. automodule:: stree.Splitter
|
||||
.. autoclass:: Splitter
|
||||
:members:
|
||||
:undoc-members:
|
||||
:private-members:
|
||||
:show-inheritance:
|
||||
:noindex:
|
||||
@@ -7,3 +7,4 @@ Stree
|
||||
:undoc-members:
|
||||
:private-members:
|
||||
:show-inheritance:
|
||||
:noindex:
|
||||
@@ -6,27 +6,21 @@
|
||||
|
||||
# -- 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
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
|
||||
|
||||
import stree
|
||||
|
||||
sys.path.insert(0, os.path.abspath("../../stree/"))
|
||||
|
||||
|
||||
# -- Project information -----------------------------------------------------
|
||||
|
||||
project = "STree"
|
||||
copyright = "2020 - 2021, Ricardo Montañana Gómez"
|
||||
copyright = "2020 - 2024, Ricardo Montañana Gómez"
|
||||
author = "Ricardo Montañana Gómez"
|
||||
|
||||
# The full version, including alpha/beta/rc tags
|
||||
version = stree.__version__
|
||||
release = version
|
||||
|
||||
version = release = stree.__version__
|
||||
|
||||
# -- General configuration ---------------------------------------------------
|
||||
|
||||
@@ -54,4 +48,4 @@ 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"]
|
||||
html_static_path = []
|
||||
|
||||
@@ -2,8 +2,6 @@
|
||||
|
||||
## Notebooks
|
||||
|
||||
- [](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/benchmark.ipynb) Benchmark
|
||||
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
|
||||
|
||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
|
||||
|
||||
@@ -1,22 +1,22 @@
|
||||
# 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 | {"liblinear", "linear", "poly", "rbf", "sigmoid"} | linear | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’. liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library |
|
||||
| \* | 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’, ‘poly’ and ‘sigmoid’.<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\*\*. max_samples is incompatible with 'ovo' multiclass_strategy |
|
||||
| | 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", "mutual", "cfs", "fcbf"} | "random" | The strategy used to choose the feature set at each node (only used if max_features < num_features). Supported strategies are: **“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features. **“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them. **"mutual"**: Chooses the best features w.r.t. their mutual info with the label. **"cfs"**: Apply Correlation-based Feature Selection. **"fcbf"**: Apply Fast Correlation-Based Filter |
|
||||
| | normalize | \<bool\> | False | If standardization of features should be applied on each node with the samples that reach it |
|
||||
| \* | multiclass_strategy | {"ovo", "ovr"} | "ovo" | Strategy to use with multiclass datasets, **"ovo"**: one versus one. **"ovr"**: one versus rest |
|
||||
| | **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 | {"liblinear", "linear", "poly", "rbf", "sigmoid"} | linear | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’.<br>liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library |
|
||||
| \* | 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’, ‘poly’ and ‘sigmoid’.<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\*\*.<br>max_samples is incompatible with 'ovo' multiclass_strategy |
|
||||
| | 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", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random" | The strategy used to choose the feature set at each node (only used if max_features < num_features).<br>Supported strategies are:<br>**“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features.<br>**“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them.<br>**“trandom”**: The algorithm generates only one random combination.<br>**"mutual"**: Chooses the best features w.r.t. their mutual info with the label.<br>**"cfs"**: Apply Correlation-based Feature Selection.<br>**"fcbf"**: Apply Fast Correlation-Based Filter.<br>**"iwss"**: IWSS based algorithm |
|
||||
| | normalize | \<bool\> | False | If standardization of features should be applied on each node with the samples that reach it |
|
||||
| \* | multiclass_strategy | {"ovo", "ovr"} | "ovo" | Strategy to use with multiclass datasets:<br>**"ovo"**: one versus one.<br>**"ovr"**: one versus rest |
|
||||
|
||||
\* Hyperparameter used by the support vector classifier of every node
|
||||
|
||||
|
||||
@@ -5,7 +5,6 @@ Welcome to STree's documentation!
|
||||
:caption: Contents:
|
||||
:titlesonly:
|
||||
|
||||
|
||||
stree
|
||||
install
|
||||
hyperparameters
|
||||
|
||||
@@ -1,9 +1,12 @@
|
||||
# STree
|
||||
|
||||
[](https://app.codeship.com/projects/399170)
|
||||
|
||||
[](https://codecov.io/gh/doctorado-ml/stree)
|
||||
[](https://www.codacy.com/gh/Doctorado-ML/STree?utm_source=github.com&utm_medium=referral&utm_content=Doctorado-ML/STree&utm_campaign=Badge_Grade)
|
||||
[](https://lgtm.com/projects/g/Doctorado-ML/STree/context:python)
|
||||
[](https://badge.fury.io/py/STree)
|
||||
|
||||
[](https://zenodo.org/badge/latestdoi/262658230)
|
||||
|
||||
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.
|
||||
|
||||
|
||||
@@ -178,7 +178,7 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Stree\n",
|
||||
"stree = Stree(random_state=random_state, C=.01, max_iter=1e3)"
|
||||
"stree = Stree(random_state=random_state, C=.01, max_iter=1000, kernel=\"liblinear\", multiclass_strategy=\"ovr\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -198,7 +198,7 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# SVC (linear)\n",
|
||||
"svc = LinearSVC(random_state=random_state, C=.01, max_iter=1e3)"
|
||||
"svc = LinearSVC(random_state=random_state, C=.01, max_iter=1000)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@@ -1,253 +1,253 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Test Gridsearch\n",
|
||||
"with different kernels and different configurations"
|
||||
]
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Test Gridsearch\n",
|
||||
"with different kernels and different configurations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Setup\n",
|
||||
"Uncomment the next cell if STree is not already installed"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#\n",
|
||||
"# Google Colab setup\n",
|
||||
"#\n",
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree\n",
|
||||
"!pip install pandas"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "zIHKVxthDZEa"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import random\n",
|
||||
"import os\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np\n",
|
||||
"from sklearn.ensemble import AdaBoostClassifier\n",
|
||||
"from sklearn.svm import LinearSVC\n",
|
||||
"from sklearn.model_selection import GridSearchCV, train_test_split\n",
|
||||
"from stree import Stree"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "IEmq50QgDZEi"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if not os.path.isfile('data/creditcard.csv'):\n",
|
||||
" !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
|
||||
" !tar xzf creditcard.tgz"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "z9Q-YUfBDZEq",
|
||||
"outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"random_state=1\n",
|
||||
"\n",
|
||||
"def load_creditcard(n_examples=0):\n",
|
||||
" df = pd.read_csv('data/creditcard.csv')\n",
|
||||
" print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
|
||||
" print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
|
||||
" y = df.Class\n",
|
||||
" X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
|
||||
" if n_examples > 0:\n",
|
||||
" # Take first n_examples samples\n",
|
||||
" X = X[:n_examples, :]\n",
|
||||
" y = y[:n_examples, :]\n",
|
||||
" else:\n",
|
||||
" # Take all the positive samples with a number of random negatives\n",
|
||||
" if n_examples < 0:\n",
|
||||
" Xt = X[(y == 1).ravel()]\n",
|
||||
" yt = y[(y == 1).ravel()]\n",
|
||||
" indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
|
||||
" X = np.append(Xt, X[indices], axis=0)\n",
|
||||
" y = np.append(yt, y[indices], axis=0)\n",
|
||||
" print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
|
||||
" print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
|
||||
" print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
|
||||
" Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
|
||||
" return Xtrain, Xtest, ytrain, ytest\n",
|
||||
"\n",
|
||||
"data = load_creditcard(-1000) # Take all true samples + 1000 of the others\n",
|
||||
"# data = load_creditcard(5000) # Take the first 5000 samples\n",
|
||||
"# data = load_creditcard(0) # Take all the samples\n",
|
||||
"\n",
|
||||
"Xtrain = data[0]\n",
|
||||
"Xtest = data[1]\n",
|
||||
"ytrain = data[2]\n",
|
||||
"ytest = data[3]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Tests"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "HmX3kR4PDZEw"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"parameters = [{\n",
|
||||
" 'base_estimator': [Stree(random_state=random_state)],\n",
|
||||
" 'n_estimators': [10, 25],\n",
|
||||
" 'learning_rate': [.5, 1],\n",
|
||||
" 'estimator__split_criteria': ['max_samples', 'impurity'],\n",
|
||||
" 'estimator__tol': [.1, 1e-02],\n",
|
||||
" 'estimator__max_depth': [3, 5, 7],\n",
|
||||
" 'estimator__C': [1, 7, 55],\n",
|
||||
" 'estimator__kernel': ['linear']\n",
|
||||
"},\n",
|
||||
"{\n",
|
||||
" 'base_estimator': [Stree(random_state=random_state)],\n",
|
||||
" 'n_estimators': [10, 25],\n",
|
||||
" 'learning_rate': [.5, 1],\n",
|
||||
" 'estimator__split_criteria': ['max_samples', 'impurity'],\n",
|
||||
" 'estimator__tol': [.1, 1e-02],\n",
|
||||
" 'estimator__max_depth': [3, 5, 7],\n",
|
||||
" 'estimator__C': [1, 7, 55],\n",
|
||||
" 'estimator__degree': [3, 5, 7],\n",
|
||||
" 'estimator__kernel': ['poly']\n",
|
||||
"},\n",
|
||||
"{\n",
|
||||
" 'base_estimator': [Stree(random_state=random_state)],\n",
|
||||
" 'n_estimators': [10, 25],\n",
|
||||
" 'learning_rate': [.5, 1],\n",
|
||||
" 'estimator__split_criteria': ['max_samples', 'impurity'],\n",
|
||||
" 'estimator__tol': [.1, 1e-02],\n",
|
||||
" 'estimator__max_depth': [3, 5, 7],\n",
|
||||
" 'estimator__C': [1, 7, 55],\n",
|
||||
" 'estimator__gamma': [.1, 1, 10],\n",
|
||||
" 'estimator__kernel': ['rbf']\n",
|
||||
"}]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"Stree().get_params()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "CrcB8o6EDZE5",
|
||||
"outputId": "7703413a-d563-4289-a13b-532f38f82762",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
|
||||
"grid = GridSearchCV(clf, parameters, verbose=5, n_jobs=-1, return_train_score=True)\n",
|
||||
"grid.fit(Xtrain, ytrain)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "ZjX88NoYDZE8",
|
||||
"outputId": "285163c8-fa33-4915-8ae7-61c4f7844344",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"Best estimator: \", grid.best_estimator_)\n",
|
||||
"print(\"Best hyperparameters: \", grid.best_params_)\n",
|
||||
"print(\"Best accuracy: \", grid.best_score_)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Best estimator: AdaBoostClassifier(algorithm='SAMME',\n",
|
||||
" base_estimator=Stree(C=55, max_depth=7, random_state=1,\n",
|
||||
" split_criteria='max_samples', tol=0.1),\n",
|
||||
" learning_rate=0.5, n_estimators=25, random_state=1)\n",
|
||||
"Best hyperparameters: {'base_estimator': Stree(C=55, max_depth=7, random_state=1, split_criteria='max_samples', tol=0.1), 'estimator__C': 55, 'estimator__kernel': 'linear', 'estimator__max_depth': 7, 'estimator__split_criteria': 'max_samples', 'estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 25}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Best accuracy: 0.9511777695988222"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"name": "gridsearch.ipynb",
|
||||
"provenance": []
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"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": "3.8.2-final"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Setup\n",
|
||||
"Uncomment the next cell if STree is not already installed"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#\n",
|
||||
"# Google Colab setup\n",
|
||||
"#\n",
|
||||
"#!pip install git+https://github.com/doctorado-ml/stree\n",
|
||||
"!pip install pandas"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "zIHKVxthDZEa"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import random\n",
|
||||
"import os\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np\n",
|
||||
"from sklearn.ensemble import AdaBoostClassifier\n",
|
||||
"from sklearn.svm import LinearSVC\n",
|
||||
"from sklearn.model_selection import GridSearchCV, train_test_split\n",
|
||||
"from stree import Stree"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "IEmq50QgDZEi"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if not os.path.isfile('data/creditcard.csv'):\n",
|
||||
" !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
|
||||
" !tar xzf creditcard.tgz"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "z9Q-YUfBDZEq",
|
||||
"outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"random_state=1\n",
|
||||
"\n",
|
||||
"def load_creditcard(n_examples=0):\n",
|
||||
" df = pd.read_csv('data/creditcard.csv')\n",
|
||||
" print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
|
||||
" print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
|
||||
" y = df.Class\n",
|
||||
" X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
|
||||
" if n_examples > 0:\n",
|
||||
" # Take first n_examples samples\n",
|
||||
" X = X[:n_examples, :]\n",
|
||||
" y = y[:n_examples, :]\n",
|
||||
" else:\n",
|
||||
" # Take all the positive samples with a number of random negatives\n",
|
||||
" if n_examples < 0:\n",
|
||||
" Xt = X[(y == 1).ravel()]\n",
|
||||
" yt = y[(y == 1).ravel()]\n",
|
||||
" indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
|
||||
" X = np.append(Xt, X[indices], axis=0)\n",
|
||||
" y = np.append(yt, y[indices], axis=0)\n",
|
||||
" print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
|
||||
" print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
|
||||
" print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
|
||||
" Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
|
||||
" return Xtrain, Xtest, ytrain, ytest\n",
|
||||
"\n",
|
||||
"data = load_creditcard(-1000) # Take all true samples + 1000 of the others\n",
|
||||
"# data = load_creditcard(5000) # Take the first 5000 samples\n",
|
||||
"# data = load_creditcard(0) # Take all the samples\n",
|
||||
"\n",
|
||||
"Xtrain = data[0]\n",
|
||||
"Xtest = data[1]\n",
|
||||
"ytrain = data[2]\n",
|
||||
"ytest = data[3]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Tests"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "HmX3kR4PDZEw"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"parameters = [{\n",
|
||||
" 'base_estimator': [Stree(random_state=random_state)],\n",
|
||||
" 'n_estimators': [10, 25],\n",
|
||||
" 'learning_rate': [.5, 1],\n",
|
||||
" 'base_estimator__split_criteria': ['max_samples', 'impurity'],\n",
|
||||
" 'base_estimator__tol': [.1, 1e-02],\n",
|
||||
" 'base_estimator__max_depth': [3, 5, 7],\n",
|
||||
" 'base_estimator__C': [1, 7, 55],\n",
|
||||
" 'base_estimator__kernel': ['linear']\n",
|
||||
"},\n",
|
||||
"{\n",
|
||||
" 'base_estimator': [Stree(random_state=random_state)],\n",
|
||||
" 'n_estimators': [10, 25],\n",
|
||||
" 'learning_rate': [.5, 1],\n",
|
||||
" 'base_estimator__split_criteria': ['max_samples', 'impurity'],\n",
|
||||
" 'base_estimator__tol': [.1, 1e-02],\n",
|
||||
" 'base_estimator__max_depth': [3, 5, 7],\n",
|
||||
" 'base_estimator__C': [1, 7, 55],\n",
|
||||
" 'base_estimator__degree': [3, 5, 7],\n",
|
||||
" 'base_estimator__kernel': ['poly']\n",
|
||||
"},\n",
|
||||
"{\n",
|
||||
" 'base_estimator': [Stree(random_state=random_state)],\n",
|
||||
" 'n_estimators': [10, 25],\n",
|
||||
" 'learning_rate': [.5, 1],\n",
|
||||
" 'base_estimator__split_criteria': ['max_samples', 'impurity'],\n",
|
||||
" 'base_estimator__tol': [.1, 1e-02],\n",
|
||||
" 'base_estimator__max_depth': [3, 5, 7],\n",
|
||||
" 'base_estimator__C': [1, 7, 55],\n",
|
||||
" 'base_estimator__gamma': [.1, 1, 10],\n",
|
||||
" 'base_estimator__kernel': ['rbf']\n",
|
||||
"}]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"Stree().get_params()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "CrcB8o6EDZE5",
|
||||
"outputId": "7703413a-d563-4289-a13b-532f38f82762",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
|
||||
"grid = GridSearchCV(clf, parameters, verbose=5, n_jobs=-1, return_train_score=True)\n",
|
||||
"grid.fit(Xtrain, ytrain)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {},
|
||||
"colab_type": "code",
|
||||
"id": "ZjX88NoYDZE8",
|
||||
"outputId": "285163c8-fa33-4915-8ae7-61c4f7844344",
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"Best estimator: \", grid.best_estimator_)\n",
|
||||
"print(\"Best hyperparameters: \", grid.best_params_)\n",
|
||||
"print(\"Best accuracy: \", grid.best_score_)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Best estimator: AdaBoostClassifier(algorithm='SAMME',\n",
|
||||
" base_estimator=Stree(C=55, max_depth=7, random_state=1,\n",
|
||||
" split_criteria='max_samples', tol=0.1),\n",
|
||||
" learning_rate=0.5, n_estimators=25, random_state=1)\n",
|
||||
"Best hyperparameters: {'base_estimator': Stree(C=55, max_depth=7, random_state=1, split_criteria='max_samples', tol=0.1), 'base_estimator__C': 55, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 7, 'base_estimator__split_criteria': 'max_samples', 'base_estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 25}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Best accuracy: 0.9511777695988222"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"name": "gridsearch.ipynb",
|
||||
"provenance": []
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"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": "3.8.2-final"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -1,5 +1,65 @@
|
||||
[build-system]
|
||||
requires = ["hatchling"]
|
||||
build-backend = "hatchling.build"
|
||||
|
||||
[project]
|
||||
name = "STree"
|
||||
dependencies = ["scikit-learn>1.0", "mufs"]
|
||||
license = { file = "LICENSE" }
|
||||
description = "Oblique decision tree with svm nodes."
|
||||
readme = "README.md"
|
||||
authors = [
|
||||
{ name = "Ricardo Montañana", email = "ricardo.montanana@alu.uclm.es" },
|
||||
]
|
||||
dynamic = ['version']
|
||||
requires-python = ">=3.11"
|
||||
keywords = [
|
||||
"scikit-learn",
|
||||
"oblique-classifier",
|
||||
"oblique-decision-tree",
|
||||
"decision-tree",
|
||||
"svm",
|
||||
"svc",
|
||||
]
|
||||
classifiers = [
|
||||
"Development Status :: 5 - Production/Stable",
|
||||
"Intended Audience :: Science/Research",
|
||||
"Intended Audience :: Developers",
|
||||
"Topic :: Software Development",
|
||||
"Topic :: Scientific/Engineering",
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Natural Language :: English",
|
||||
"Operating System :: OS Independent",
|
||||
"Programming Language :: Python :: 3.11",
|
||||
"Programming Language :: Python :: 3.12",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
dev = ["black", "flake8", "coverage", "hatch", "pip-audit"]
|
||||
doc = ["sphinx", "myst-parser", "sphinx_rtd_theme", "sphinx-autodoc-typehints"]
|
||||
|
||||
[project.urls]
|
||||
Code = "https://github.com/Doctorado-ML/STree"
|
||||
Documentation = "https://stree.readthedocs.io/en/latest/index.html"
|
||||
|
||||
[tool.hatch.version]
|
||||
path = "stree/_version.py"
|
||||
|
||||
[tool.hatch.build.targets.sdist]
|
||||
include = ["/stree"]
|
||||
|
||||
[tool.coverage.run]
|
||||
branch = true
|
||||
source = ["stree"]
|
||||
command_line = "-m unittest discover -s stree.tests"
|
||||
|
||||
[tool.coverage.report]
|
||||
show_missing = true
|
||||
fail_under = 100
|
||||
|
||||
[tool.black]
|
||||
line-length = 79
|
||||
target-version = ["py311"]
|
||||
include = '\.pyi?$'
|
||||
exclude = '''
|
||||
/(
|
||||
|
||||
@@ -1,2 +1,3 @@
|
||||
scikit-learn>0.24
|
||||
scikit-learn==1.5.2
|
||||
coverage
|
||||
mufs
|
||||
@@ -1 +0,0 @@
|
||||
python-3.8
|
||||
50
setup.py
50
setup.py
@@ -1,50 +0,0 @@
|
||||
import setuptools
|
||||
|
||||
|
||||
def readme():
|
||||
with open("README.md") as f:
|
||||
return f.read()
|
||||
|
||||
|
||||
def get_data(field):
|
||||
item = ""
|
||||
with open("stree/__init__.py") as f:
|
||||
for line in f.readlines():
|
||||
if line.startswith(f"__{field}__"):
|
||||
delim = '"' if '"' in line else "'"
|
||||
item = line.split(delim)[1]
|
||||
break
|
||||
else:
|
||||
raise RuntimeError(f"Unable to find {field} string.")
|
||||
return item
|
||||
|
||||
|
||||
setuptools.setup(
|
||||
name="STree",
|
||||
version=get_data("version"),
|
||||
license=get_data("license"),
|
||||
description="Oblique decision tree with svm nodes",
|
||||
long_description=readme(),
|
||||
long_description_content_type="text/markdown",
|
||||
packages=setuptools.find_packages(),
|
||||
url="https://github.com/Doctorado-ML/STree#stree",
|
||||
project_urls={
|
||||
"Code": "https://github.com/Doctorado-ML/STree",
|
||||
"Documentation": "https://stree.readthedocs.io/en/latest/index.html",
|
||||
},
|
||||
author=get_data("author"),
|
||||
author_email=get_data("author_email"),
|
||||
keywords="scikit-learn oblique-classifier oblique-decision-tree decision-\
|
||||
tree svm svc",
|
||||
classifiers=[
|
||||
"Development Status :: 5 - Production/Stable",
|
||||
"License :: OSI Approved :: " + get_data("license"),
|
||||
"Programming Language :: Python :: 3.8",
|
||||
"Natural Language :: English",
|
||||
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
||||
"Intended Audience :: Science/Research",
|
||||
],
|
||||
install_requires=["scikit-learn", "mufs"],
|
||||
test_suite="stree.tests",
|
||||
zip_safe=False,
|
||||
)
|
||||
@@ -16,8 +16,28 @@ from mufs import MUFS
|
||||
|
||||
|
||||
class Snode:
|
||||
"""Nodes of the tree that keeps the svm classifier and if testing the
|
||||
"""
|
||||
Nodes of the tree that keeps the svm classifier and if testing the
|
||||
dataset assigned to it
|
||||
|
||||
Parameters
|
||||
----------
|
||||
clf : SVC
|
||||
Classifier used
|
||||
X : np.ndarray
|
||||
input dataset in train time (only in testing)
|
||||
y : np.ndarray
|
||||
input labes in train time
|
||||
features : np.array
|
||||
features used to compute hyperplane
|
||||
impurity : float
|
||||
impurity of the node
|
||||
title : str
|
||||
label describing the route to the node
|
||||
weight : np.ndarray, optional
|
||||
weights applied to input dataset in train time, by default None
|
||||
scaler : StandardScaler, optional
|
||||
scaler used if any, by default None
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
@@ -48,6 +68,7 @@ class Snode:
|
||||
self._impurity = impurity
|
||||
self._partition_column: int = -1
|
||||
self._scaler = scaler
|
||||
self._proba = None
|
||||
|
||||
@classmethod
|
||||
def copy(cls, node: "Snode") -> "Snode":
|
||||
@@ -107,23 +128,44 @@ class Snode:
|
||||
def get_up(self) -> "Snode":
|
||||
return self._up
|
||||
|
||||
def make_predictor(self):
|
||||
def make_predictor(self, num_classes: int) -> None:
|
||||
"""Compute the class of the predictor and its belief based on the
|
||||
subdataset of the node only if it is a leaf
|
||||
"""
|
||||
if not self.is_leaf():
|
||||
return
|
||||
classes, card = np.unique(self._y, return_counts=True)
|
||||
if len(classes) > 1:
|
||||
self._proba = np.zeros((num_classes,), dtype=np.int64)
|
||||
for c, n in zip(classes, card):
|
||||
self._proba[c] = n
|
||||
try:
|
||||
max_card = max(card)
|
||||
self._class = classes[card == max_card][0]
|
||||
self._belief = max_card / np.sum(card)
|
||||
except ValueError:
|
||||
self._class = None
|
||||
|
||||
def graph(self):
|
||||
"""
|
||||
Return a string representing the node in graphviz format
|
||||
"""
|
||||
output = ""
|
||||
count_values = np.unique(self._y, return_counts=True)
|
||||
if self.is_leaf():
|
||||
output += (
|
||||
f'N{id(self)} [shape=box style=filled label="'
|
||||
f"class={self._class} impurity={self._impurity:.3f} "
|
||||
f'counts={self._proba}"];\n'
|
||||
)
|
||||
else:
|
||||
self._belief = 1
|
||||
try:
|
||||
self._class = classes[0]
|
||||
except IndexError:
|
||||
self._class = None
|
||||
output += (
|
||||
f'N{id(self)} [label="#features={len(self._features)} '
|
||||
f"classes={count_values[0]} samples={count_values[1]} "
|
||||
f'({sum(count_values[1])})" fontcolor=black];\n'
|
||||
)
|
||||
output += f"N{id(self)} -> N{id(self.get_up())} [color=black];\n"
|
||||
output += f"N{id(self)} -> N{id(self.get_down())} [color=black];\n"
|
||||
return output
|
||||
|
||||
def __str__(self) -> str:
|
||||
count_values = np.unique(self._y, return_counts=True)
|
||||
@@ -165,6 +207,56 @@ class Siterator:
|
||||
|
||||
|
||||
class Splitter:
|
||||
"""
|
||||
Splits a dataset in two based on different criteria
|
||||
|
||||
Parameters
|
||||
----------
|
||||
clf : SVC, optional
|
||||
classifier, by default None
|
||||
criterion : str, optional
|
||||
The function to measure the quality of a split (only used if
|
||||
max_features != num_features). Supported criteria are “gini” for the
|
||||
Gini impurity and “entropy” for the information gain., by default
|
||||
"entropy", by default None
|
||||
feature_select : str, optional
|
||||
The strategy used to choose the feature set at each node (only used if
|
||||
max_features < num_features). Supported strategies are: “best”: sklearn
|
||||
SelectKBest algorithm is used in every node to choose the max_features
|
||||
best features. “random”: The algorithm generates 5 candidates and
|
||||
choose the best (max. info. gain) of them. “trandom”: The algorithm
|
||||
generates only one random combination. "mutual": Chooses the best
|
||||
features w.r.t. their mutual info with the label. "cfs": Apply
|
||||
Correlation-based Feature Selection. "fcbf": Apply Fast Correlation-
|
||||
Based, by default None
|
||||
criteria : str, optional
|
||||
ecides (just in case of a multi class classification) which column
|
||||
(class) use to split the dataset in a node. max_samples is
|
||||
incompatible with 'ovo' multiclass_strategy, by default None
|
||||
min_samples_split : int, optional
|
||||
The minimum number of samples required to split an internal node. 0
|
||||
(default) for any, by default None
|
||||
random_state : optional
|
||||
Controls the pseudo random number generation for shuffling the data for
|
||||
probability estimates. Ignored when probability is False.Pass an int
|
||||
for reproducible output across multiple function calls, by
|
||||
default None
|
||||
normalize : bool, optional
|
||||
If standardization of features should be applied on each node with the
|
||||
samples that reach it , by default False
|
||||
|
||||
Raises
|
||||
------
|
||||
ValueError
|
||||
clf has to be a sklearn estimator
|
||||
ValueError
|
||||
criterion must be gini or entropy
|
||||
ValueError
|
||||
criteria has to be max_samples or impurity
|
||||
ValueError
|
||||
splitter must be in {random, best, mutual, cfs, fcbf}
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
clf: SVC = None,
|
||||
@@ -201,10 +293,19 @@ class Splitter:
|
||||
f"criteria has to be max_samples or impurity; got ({criteria})"
|
||||
)
|
||||
|
||||
if feature_select not in ["random", "best", "mutual", "cfs", "fcbf"]:
|
||||
if feature_select not in [
|
||||
"random",
|
||||
"trandom",
|
||||
"best",
|
||||
"mutual",
|
||||
"cfs",
|
||||
"fcbf",
|
||||
"iwss",
|
||||
]:
|
||||
raise ValueError(
|
||||
"splitter must be in {random, best, mutual, cfs, fcbf} got "
|
||||
f"({feature_select})"
|
||||
"splitter must be in {random, trandom, best, mutual, cfs, "
|
||||
"fcbf, iwss} "
|
||||
f"got ({feature_select})"
|
||||
)
|
||||
self.criterion_function = getattr(self, f"_{self._criterion}")
|
||||
self.decision_criteria = getattr(self, f"_{self._criteria}")
|
||||
@@ -235,6 +336,31 @@ class Splitter:
|
||||
features_sets = self._generate_spaces(n_features, max_features)
|
||||
return self._select_best_set(dataset, labels, features_sets)
|
||||
|
||||
@staticmethod
|
||||
def _fs_trandom(
|
||||
dataset: np.array, labels: np.array, max_features: int
|
||||
) -> tuple:
|
||||
"""Return the a random feature set combination
|
||||
|
||||
Parameters
|
||||
----------
|
||||
dataset : np.array
|
||||
array of samples
|
||||
labels : np.array
|
||||
labels of the dataset
|
||||
max_features : int
|
||||
number of features of the subspace
|
||||
(< number of features in dataset)
|
||||
|
||||
Returns
|
||||
-------
|
||||
tuple
|
||||
indices of the features selected
|
||||
"""
|
||||
# Random feature reduction
|
||||
n_features = dataset.shape[1]
|
||||
return tuple(sorted(random.sample(range(n_features), max_features)))
|
||||
|
||||
@staticmethod
|
||||
def _fs_best(
|
||||
dataset: np.array, labels: np.array, max_features: int
|
||||
@@ -262,9 +388,8 @@ class Splitter:
|
||||
.get_support(indices=True)
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _fs_mutual(
|
||||
dataset: np.array, labels: np.array, max_features: int
|
||||
self, dataset: np.array, labels: np.array, max_features: int
|
||||
) -> tuple:
|
||||
"""Return the best features with mutual information with labels
|
||||
|
||||
@@ -284,10 +409,13 @@ class Splitter:
|
||||
indices of the features selected
|
||||
"""
|
||||
# return best features with mutual info with the label
|
||||
feature_list = mutual_info_classif(dataset, labels)
|
||||
feature_list = mutual_info_classif(
|
||||
dataset, labels, random_state=self._random_state
|
||||
)
|
||||
return tuple(
|
||||
sorted(
|
||||
range(len(feature_list)), key=lambda sub: feature_list[sub]
|
||||
range(len(feature_list)),
|
||||
key=lambda sub: feature_list[sub],
|
||||
)[-max_features:]
|
||||
)
|
||||
|
||||
@@ -339,6 +467,31 @@ class Splitter:
|
||||
mufs = MUFS(max_features=max_features, discrete=False)
|
||||
return mufs.fcbf(dataset, labels, 5e-4).get_results()
|
||||
|
||||
@staticmethod
|
||||
def _fs_iwss(
|
||||
dataset: np.array, labels: np.array, max_features: int
|
||||
) -> tuple:
|
||||
"""Correlattion-based feature selection based on iwss with max_features
|
||||
limit
|
||||
|
||||
Parameters
|
||||
----------
|
||||
dataset : np.array
|
||||
array of samples
|
||||
labels : np.array
|
||||
labels of the dataset
|
||||
max_features : int
|
||||
number of features of the subspace
|
||||
(< number of features in dataset)
|
||||
|
||||
Returns
|
||||
-------
|
||||
tuple
|
||||
indices of the features selected
|
||||
"""
|
||||
mufs = MUFS(max_features=max_features, discrete=False)
|
||||
return mufs.iwss(dataset, labels, 0.25).get_results()
|
||||
|
||||
def partition_impurity(self, y: np.array) -> np.array:
|
||||
return self.criterion_function(y)
|
||||
|
||||
@@ -377,7 +530,10 @@ class Splitter:
|
||||
return entropy
|
||||
|
||||
def information_gain(
|
||||
self, labels: np.array, labels_up: np.array, labels_dn: np.array
|
||||
self,
|
||||
labels: np.array,
|
||||
labels_up: np.array,
|
||||
labels_dn: np.array,
|
||||
) -> float:
|
||||
"""Compute information gain of a split candidate
|
||||
|
||||
@@ -590,7 +746,7 @@ class Splitter:
|
||||
Train time - True / Test time - False
|
||||
"""
|
||||
# data contains the distances of every sample to every class hyperplane
|
||||
# array of (m, nc) nc = # classes
|
||||
# array of (m, nc) nc = k if ovr, nc = k*(k-1)/2 if ovo
|
||||
data = self._distances(node, samples)
|
||||
if data.shape[0] < self._min_samples_split:
|
||||
# there aren't enough samples to split
|
||||
|
||||
322
stree/Strees.py
322
stree/Strees.py
@@ -17,21 +17,129 @@ from sklearn.utils.validation import (
|
||||
_check_sample_weight,
|
||||
)
|
||||
from .Splitter import Splitter, Snode, Siterator
|
||||
from ._version import __version__
|
||||
|
||||
|
||||
class Stree(BaseEstimator, ClassifierMixin):
|
||||
"""Estimator that is based on binary trees of svm nodes
|
||||
"""
|
||||
Estimator that is based on binary trees of svm nodes
|
||||
can deal with sample_weights in predict, used in boosting sklearn methods
|
||||
inheriting from BaseEstimator implements get_params and set_params methods
|
||||
inheriting from ClassifierMixin implement the attribute _estimator_type
|
||||
with "classifier" as value
|
||||
|
||||
Parameters
|
||||
----------
|
||||
C : float, optional
|
||||
Regularization parameter. The strength of the regularization is
|
||||
inversely proportional to C. Must be strictly positive., by default 1.0
|
||||
kernel : str, optional
|
||||
Specifies the kernel type to be used in the algorithm. It must be one
|
||||
of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’. liblinear uses
|
||||
[liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and
|
||||
the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/)
|
||||
library through scikit-learn library, by default "linear"
|
||||
max_iter : int, optional
|
||||
Hard limit on iterations within solver, or -1 for no limit., by default
|
||||
1e5
|
||||
random_state : int, optional
|
||||
Controls the pseudo random number generation for shuffling the data for
|
||||
probability estimates. Ignored when probability is False.Pass an int
|
||||
for reproducible output across multiple function calls, by
|
||||
default None
|
||||
max_depth : int, optional
|
||||
Specifies the maximum depth of the tree, by default None
|
||||
tol : float, optional
|
||||
Tolerance for stopping, by default 1e-4
|
||||
degree : int, optional
|
||||
Degree of the polynomial kernel function (‘poly’). Ignored by all other
|
||||
kernels., by default 3
|
||||
gamma : str, optional
|
||||
Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’.if gamma='scale'
|
||||
(default) is passed then it uses 1 / (n_features * X.var()) as value
|
||||
of gamma,if ‘auto’, uses 1 / n_features., by default "scale"
|
||||
split_criteria : str, optional
|
||||
Decides (just in case of a multi class classification) which column
|
||||
(class) use to split the dataset in a node. max_samples is
|
||||
incompatible with 'ovo' multiclass_strategy, by default "impurity"
|
||||
criterion : str, optional
|
||||
The function to measure the quality of a split (only used if
|
||||
max_features != num_features). Supported criteria are “gini” for the
|
||||
Gini impurity and “entropy” for the information gain., by default
|
||||
"entropy"
|
||||
min_samples_split : int, optional
|
||||
The minimum number of samples required to split an internal node. 0
|
||||
(default) for any, by default 0
|
||||
max_features : optional
|
||||
The number of features to consider when looking for the split: If int,
|
||||
then consider max_features features at each split. If float, then
|
||||
max_features is a fraction and int(max_features * n_features) features
|
||||
are considered at each split. If “auto”, then max_features=
|
||||
sqrt(n_features). If “sqrt”, then max_features=sqrt(n_features). If
|
||||
“log2”, then max_features=log2(n_features). If None, then max_features=
|
||||
n_features., by default None
|
||||
splitter : str, optional
|
||||
The strategy used to choose the feature set at each node (only used if
|
||||
max_features < num_features). Supported strategies are: “best”: sklearn
|
||||
SelectKBest algorithm is used in every node to choose the max_features
|
||||
best features. “random”: The algorithm generates 5 candidates and
|
||||
choose the best (max. info. gain) of them. “trandom”: The algorithm
|
||||
generates only one random combination. "mutual": Chooses the best
|
||||
features w.r.t. their mutual info with the label. "cfs": Apply
|
||||
Correlation-based Feature Selection. "fcbf": Apply Fast Correlation-
|
||||
Based , by default "random"
|
||||
multiclass_strategy : str, optional
|
||||
Strategy to use with multiclass datasets, "ovo": one versus one. "ovr":
|
||||
one versus rest, by default "ovo"
|
||||
normalize : bool, optional
|
||||
If standardization of features should be applied on each node with the
|
||||
samples that reach it , by default False
|
||||
|
||||
Attributes
|
||||
----------
|
||||
classes_ : ndarray of shape (n_classes,)
|
||||
The classes labels.
|
||||
|
||||
n_classes_ : int
|
||||
The number of classes
|
||||
|
||||
n_iter_ : int
|
||||
Max number of iterations in classifier
|
||||
|
||||
depth_ : int
|
||||
Max depht of the tree
|
||||
|
||||
n_features_ : int
|
||||
The number of features when ``fit`` is performed.
|
||||
|
||||
n_features_in_ : int
|
||||
Number of features seen during :term:`fit`.
|
||||
|
||||
max_features_ : int
|
||||
Number of features to use in hyperplane computation
|
||||
|
||||
tree_ : Node
|
||||
root of the tree
|
||||
|
||||
X_ : ndarray
|
||||
points to the input dataset
|
||||
|
||||
y_ : ndarray
|
||||
points to the input labels
|
||||
|
||||
References
|
||||
----------
|
||||
R. Montañana, J. A. Gámez, J. M. Puerta, "STree: a single multi-class
|
||||
oblique decision tree based on support vector machines.", 2021 LNAI 12882
|
||||
|
||||
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
C: float = 1.0,
|
||||
kernel: str = "linear",
|
||||
max_iter: int = 1e5,
|
||||
max_iter: int = int(1e5),
|
||||
random_state: int = None,
|
||||
max_depth: int = None,
|
||||
tol: float = 1e-4,
|
||||
@@ -60,6 +168,17 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
self.splitter = splitter
|
||||
self.normalize = normalize
|
||||
self.multiclass_strategy = multiclass_strategy
|
||||
self.depth_ = 0
|
||||
|
||||
@staticmethod
|
||||
def version() -> str:
|
||||
"""Return the version of the package."""
|
||||
return __version__
|
||||
|
||||
def __call__(self) -> None:
|
||||
"""Only added to comply with scikit-learn base sestimator for
|
||||
ensembles"""
|
||||
pass
|
||||
|
||||
def _more_tags(self) -> dict:
|
||||
"""Required by sklearn to supply features of the classifier
|
||||
@@ -71,7 +190,10 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
return {"requires_y": True}
|
||||
|
||||
def fit(
|
||||
self, X: np.ndarray, y: np.ndarray, sample_weight: np.array = None
|
||||
self,
|
||||
X: np.ndarray,
|
||||
y: np.ndarray,
|
||||
sample_weight: np.array = None,
|
||||
) -> "Stree":
|
||||
"""Build the tree based on the dataset of samples and its labels
|
||||
|
||||
@@ -200,7 +322,7 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
if np.unique(y).shape[0] == 1:
|
||||
# only 1 class => pure dataset
|
||||
node.set_title(title + ", <pure>")
|
||||
node.make_predictor()
|
||||
node.make_predictor(self.n_classes_)
|
||||
return node
|
||||
# Train the model
|
||||
clf = self._build_clf()
|
||||
@@ -219,14 +341,18 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
if X_U is None or X_D is None:
|
||||
# didn't part anything
|
||||
node.set_title(title + ", <cgaf>")
|
||||
node.make_predictor()
|
||||
node.make_predictor(self.n_classes_)
|
||||
return node
|
||||
node.set_up(
|
||||
self._train(X_U, y_u, sw_u, depth + 1, title + f" - Up({depth+1})")
|
||||
)
|
||||
node.set_down(
|
||||
self._train(
|
||||
X_D, y_d, sw_d, depth + 1, title + f" - Down({depth+1})"
|
||||
X_D,
|
||||
y_d,
|
||||
sw_d,
|
||||
depth + 1,
|
||||
title + f" - Down({depth+1})",
|
||||
)
|
||||
)
|
||||
return node
|
||||
@@ -253,28 +379,100 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
)
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _reorder_results(y: np.array, indices: np.array) -> np.array:
|
||||
"""Reorder an array based on the array of indices passed
|
||||
def __predict_class(self, X: np.array) -> np.array:
|
||||
"""Compute the predicted class for the samples in X. Returns the number
|
||||
of samples of each class in the corresponding leaf node.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
y : np.array
|
||||
data untidy
|
||||
indices : np.array
|
||||
indices used to set order
|
||||
X : np.array
|
||||
Array of samples
|
||||
|
||||
Returns
|
||||
-------
|
||||
np.array
|
||||
array y ordered
|
||||
Array of shape (n_samples, n_classes) with the number of samples
|
||||
of each class in the corresponding leaf node
|
||||
"""
|
||||
# return array of same type given in y
|
||||
y_ordered = y.copy()
|
||||
indices = indices.astype(int)
|
||||
for i, index in enumerate(indices):
|
||||
y_ordered[index] = y[i]
|
||||
return y_ordered
|
||||
|
||||
def compute_prediction(xp, indices, node):
|
||||
if xp is None:
|
||||
return
|
||||
if node.is_leaf():
|
||||
# set a class for indices
|
||||
result[indices] = node._proba
|
||||
return
|
||||
self.splitter_.partition(xp, node, train=False)
|
||||
x_u, x_d = self.splitter_.part(xp)
|
||||
i_u, i_d = self.splitter_.part(indices)
|
||||
compute_prediction(x_u, i_u, node.get_up())
|
||||
compute_prediction(x_d, i_d, node.get_down())
|
||||
|
||||
# setup prediction & make it happen
|
||||
result = np.zeros((X.shape[0], self.n_classes_))
|
||||
indices = np.arange(X.shape[0])
|
||||
compute_prediction(X, indices, self.tree_)
|
||||
return result
|
||||
|
||||
def check_predict(self, X) -> np.array:
|
||||
"""Checks predict and predict_proba preconditions. If input X is not an
|
||||
np.array convert it to one.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
X : np.ndarray
|
||||
Array of samples
|
||||
|
||||
Returns
|
||||
-------
|
||||
np.array
|
||||
Array of samples
|
||||
|
||||
Raises
|
||||
------
|
||||
ValueError
|
||||
If number of features of X is different of the number of features
|
||||
in training data
|
||||
"""
|
||||
check_is_fitted(self, ["tree_"])
|
||||
# Input validation
|
||||
X = check_array(X)
|
||||
if X.shape[1] != self.n_features_:
|
||||
raise ValueError(
|
||||
f"Expected {self.n_features_} features but got "
|
||||
f"({X.shape[1]})"
|
||||
)
|
||||
return X
|
||||
|
||||
def predict_proba(self, X: np.array) -> np.array:
|
||||
"""Predict class probabilities of the input samples X.
|
||||
|
||||
The predicted class probability is the fraction of samples of the same
|
||||
class in a leaf.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
X : dataset of samples.
|
||||
|
||||
Returns
|
||||
-------
|
||||
proba : array of shape (n_samples, n_classes)
|
||||
The class probabilities of the input samples.
|
||||
|
||||
Raises
|
||||
------
|
||||
ValueError
|
||||
if dataset with inconsistent number of features
|
||||
NotFittedError
|
||||
if model is not fitted
|
||||
"""
|
||||
|
||||
X = self.check_predict(X)
|
||||
# return # of samples of each class in leaf node
|
||||
values = self.__predict_class(X)
|
||||
normalizer = values.sum(axis=1)[:, np.newaxis]
|
||||
normalizer[normalizer == 0.0] = 1.0
|
||||
return values / normalizer
|
||||
|
||||
def predict(self, X: np.array) -> np.array:
|
||||
"""Predict labels for each sample in dataset passed
|
||||
@@ -296,40 +494,45 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
NotFittedError
|
||||
if model is not fitted
|
||||
"""
|
||||
X = self.check_predict(X)
|
||||
return self.classes_[np.argmax(self.__predict_class(X), axis=1)]
|
||||
|
||||
def predict_class(
|
||||
xp: np.array, indices: np.array, node: Snode
|
||||
) -> np.array:
|
||||
if xp is None:
|
||||
return [], []
|
||||
def get_nodes(self) -> int:
|
||||
"""Return the number of nodes in the tree
|
||||
|
||||
Returns
|
||||
-------
|
||||
int
|
||||
number of nodes
|
||||
"""
|
||||
nodes = 0
|
||||
for _ in self:
|
||||
nodes += 1
|
||||
return nodes
|
||||
|
||||
def get_leaves(self) -> int:
|
||||
"""Return the number of leaves in the tree
|
||||
|
||||
Returns
|
||||
-------
|
||||
int
|
||||
number of leaves
|
||||
"""
|
||||
leaves = 0
|
||||
for node in self:
|
||||
if node.is_leaf():
|
||||
# set a class for every sample in dataset
|
||||
prediction = np.full((xp.shape[0], 1), node._class)
|
||||
return prediction, indices
|
||||
self.splitter_.partition(xp, node, train=False)
|
||||
x_u, x_d = self.splitter_.part(xp)
|
||||
i_u, i_d = self.splitter_.part(indices)
|
||||
prx_u, prin_u = predict_class(x_u, i_u, node.get_up())
|
||||
prx_d, prin_d = predict_class(x_d, i_d, node.get_down())
|
||||
return np.append(prx_u, prx_d), np.append(prin_u, prin_d)
|
||||
leaves += 1
|
||||
return leaves
|
||||
|
||||
# sklearn check
|
||||
check_is_fitted(self, ["tree_"])
|
||||
# Input validation
|
||||
X = check_array(X)
|
||||
if X.shape[1] != self.n_features_:
|
||||
raise ValueError(
|
||||
f"Expected {self.n_features_} features but got "
|
||||
f"({X.shape[1]})"
|
||||
)
|
||||
# setup prediction & make it happen
|
||||
indices = np.arange(X.shape[0])
|
||||
result = (
|
||||
self._reorder_results(*predict_class(X, indices, self.tree_))
|
||||
.astype(int)
|
||||
.ravel()
|
||||
)
|
||||
return self.classes_[result]
|
||||
def get_depth(self) -> int:
|
||||
"""Return the depth of the tree
|
||||
|
||||
Returns
|
||||
-------
|
||||
int
|
||||
depth of the tree
|
||||
"""
|
||||
return self.depth_
|
||||
|
||||
def nodes_leaves(self) -> tuple:
|
||||
"""Compute the number of nodes and leaves in the built tree
|
||||
@@ -362,6 +565,23 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
tree = None
|
||||
return Siterator(tree)
|
||||
|
||||
def graph(self, title="") -> str:
|
||||
"""Graphviz code representing the tree
|
||||
|
||||
Returns
|
||||
-------
|
||||
str
|
||||
graphviz code
|
||||
"""
|
||||
output = (
|
||||
"digraph STree {\nlabel=<STree "
|
||||
f"{title}>\nfontsize=30\nfontcolor=blue\nlabelloc=t\n"
|
||||
)
|
||||
for node in self:
|
||||
output += node.graph()
|
||||
output += "}\n"
|
||||
return output
|
||||
|
||||
def __str__(self) -> str:
|
||||
"""String representation of the tree
|
||||
|
||||
|
||||
@@ -1,10 +1,9 @@
|
||||
from .Strees import Stree, Siterator
|
||||
|
||||
__version__ = "1.2.1"
|
||||
from ._version import __version__
|
||||
|
||||
__author__ = "Ricardo Montañana Gómez"
|
||||
__copyright__ = "Copyright 2020-2021, Ricardo Montañana Gómez"
|
||||
__license__ = "MIT License"
|
||||
__author_email__ = "ricardo.montanana@alu.uclm.es"
|
||||
|
||||
__all__ = ["Stree", "Siterator"]
|
||||
__all__ = ["__version__", "Stree", "Siterator"]
|
||||
|
||||
1
stree/_version.py
Normal file
1
stree/_version.py
Normal file
@@ -0,0 +1 @@
|
||||
__version__ = "1.4.0"
|
||||
@@ -67,10 +67,28 @@ class Snode_test(unittest.TestCase):
|
||||
|
||||
def test_make_predictor_on_leaf(self):
|
||||
test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
|
||||
test.make_predictor()
|
||||
test.make_predictor(2)
|
||||
self.assertEqual(1, test._class)
|
||||
self.assertEqual(0.75, test._belief)
|
||||
self.assertEqual(-1, test._partition_column)
|
||||
self.assertListEqual([1, 3], test._proba.tolist())
|
||||
|
||||
def test_make_predictor_on_not_leaf(self):
|
||||
test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
|
||||
test.set_up(Snode(None, [1], [1], [], 0.0, "another_test"))
|
||||
test.make_predictor(2)
|
||||
self.assertIsNone(test._class)
|
||||
self.assertEqual(0, test._belief)
|
||||
self.assertEqual(-1, test._partition_column)
|
||||
self.assertEqual(-1, test.get_up()._partition_column)
|
||||
self.assertIsNone(test._proba)
|
||||
|
||||
def test_make_predictor_on_leaf_bogus_data(self):
|
||||
test = Snode(None, [1, 2, 3, 4], [], [], 0.0, "test")
|
||||
test.make_predictor(2)
|
||||
self.assertIsNone(test._class)
|
||||
self.assertEqual(-1, test._partition_column)
|
||||
self.assertListEqual([0, 0], test._proba.tolist())
|
||||
|
||||
def test_set_title(self):
|
||||
test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
|
||||
@@ -97,21 +115,6 @@ class Snode_test(unittest.TestCase):
|
||||
test.set_features([1, 2])
|
||||
self.assertListEqual([1, 2], test.get_features())
|
||||
|
||||
def test_make_predictor_on_not_leaf(self):
|
||||
test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
|
||||
test.set_up(Snode(None, [1], [1], [], 0.0, "another_test"))
|
||||
test.make_predictor()
|
||||
self.assertIsNone(test._class)
|
||||
self.assertEqual(0, test._belief)
|
||||
self.assertEqual(-1, test._partition_column)
|
||||
self.assertEqual(-1, test.get_up()._partition_column)
|
||||
|
||||
def test_make_predictor_on_leaf_bogus_data(self):
|
||||
test = Snode(None, [1, 2, 3, 4], [], [], 0.0, "test")
|
||||
test.make_predictor()
|
||||
self.assertIsNone(test._class)
|
||||
self.assertEqual(-1, test._partition_column)
|
||||
|
||||
def test_copy_node(self):
|
||||
px = [1, 2, 3, 4]
|
||||
py = [1]
|
||||
|
||||
@@ -285,3 +285,28 @@ class Splitter_test(unittest.TestCase):
|
||||
Xs, computed = tcl.get_subspace(X, y, rs)
|
||||
self.assertListEqual(expected, list(computed))
|
||||
self.assertListEqual(X[:, expected].tolist(), Xs.tolist())
|
||||
|
||||
def test_get_iwss_subspaces(self):
|
||||
results = [
|
||||
(4, [1, 5, 9, 12]),
|
||||
(6, [1, 5, 9, 12, 4, 15]),
|
||||
]
|
||||
for rs, expected in results:
|
||||
X, y = load_dataset(n_features=20, n_informative=7)
|
||||
tcl = self.build(feature_select="iwss", random_state=rs)
|
||||
Xs, computed = tcl.get_subspace(X, y, rs)
|
||||
self.assertListEqual(expected, list(computed))
|
||||
self.assertListEqual(X[:, expected].tolist(), Xs.tolist())
|
||||
|
||||
def test_get_trandom_subspaces(self):
|
||||
results = [
|
||||
(4, [3, 7, 9, 12]),
|
||||
(6, [0, 1, 2, 8, 15, 18]),
|
||||
(7, [1, 2, 4, 8, 10, 12, 13]),
|
||||
]
|
||||
for rs, expected in results:
|
||||
X, y = load_dataset(n_features=20, n_informative=7)
|
||||
tcl = self.build(feature_select="trandom", random_state=rs)
|
||||
Xs, computed = tcl.get_subspace(X, y, rs)
|
||||
self.assertListEqual(expected, list(computed))
|
||||
self.assertListEqual(X[:, expected].tolist(), Xs.tolist())
|
||||
|
||||
@@ -10,6 +10,7 @@ from sklearn.svm import LinearSVC
|
||||
from stree import Stree
|
||||
from stree.Splitter import Snode
|
||||
from .utils import load_dataset
|
||||
from .._version import __version__
|
||||
|
||||
|
||||
class Stree_test(unittest.TestCase):
|
||||
@@ -114,6 +115,38 @@ class Stree_test(unittest.TestCase):
|
||||
yp = clf.fit(X, y).predict(X[:num, :])
|
||||
self.assertListEqual(y[:num].tolist(), yp.tolist())
|
||||
|
||||
def test_multiple_predict_proba(self):
|
||||
expected = {
|
||||
"liblinear": {
|
||||
0: [0.02401129943502825, 0.9759887005649718],
|
||||
17: [0.9282970550576184, 0.07170294494238157],
|
||||
},
|
||||
"linear": {
|
||||
0: [0.029329608938547486, 0.9706703910614525],
|
||||
17: [0.9298469387755102, 0.07015306122448979],
|
||||
},
|
||||
"rbf": {
|
||||
0: [0.023448275862068966, 0.976551724137931],
|
||||
17: [0.9458064516129032, 0.05419354838709677],
|
||||
},
|
||||
"poly": {
|
||||
0: [0.01601164483260553, 0.9839883551673945],
|
||||
17: [0.9089790897908979, 0.0910209102091021],
|
||||
},
|
||||
}
|
||||
indices = [0, 17]
|
||||
X, y = load_dataset(self._random_state)
|
||||
for kernel in ["liblinear", "linear", "rbf", "poly"]:
|
||||
clf = Stree(
|
||||
kernel=kernel,
|
||||
multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
|
||||
random_state=self._random_state,
|
||||
)
|
||||
yp = clf.fit(X, y).predict_proba(X)
|
||||
for index in indices:
|
||||
for exp, comp in zip(expected[kernel][index], yp[index]):
|
||||
self.assertAlmostEqual(exp, comp)
|
||||
|
||||
def test_single_vs_multiple_prediction(self):
|
||||
"""Check if predicting sample by sample gives the same result as
|
||||
predicting all samples at once
|
||||
@@ -206,6 +239,7 @@ class Stree_test(unittest.TestCase):
|
||||
)
|
||||
tcl.fit(*load_dataset(self._random_state))
|
||||
self.assertEqual(depth, tcl.depth_)
|
||||
self.assertEqual(depth, tcl.get_depth())
|
||||
|
||||
def test_unfitted_tree_is_iterable(self):
|
||||
tcl = Stree()
|
||||
@@ -255,12 +289,12 @@ class Stree_test(unittest.TestCase):
|
||||
"impurity sigmoid": 0.824,
|
||||
},
|
||||
"Iris": {
|
||||
"max_samples liblinear": 0.9550561797752809,
|
||||
"max_samples liblinear": 0.9887640449438202,
|
||||
"max_samples linear": 1.0,
|
||||
"max_samples rbf": 0.6685393258426966,
|
||||
"max_samples poly": 0.6853932584269663,
|
||||
"max_samples sigmoid": 0.6404494382022472,
|
||||
"impurity liblinear": 0.9550561797752809,
|
||||
"impurity liblinear": 0.9887640449438202,
|
||||
"impurity linear": 1.0,
|
||||
"impurity rbf": 0.6685393258426966,
|
||||
"impurity poly": 0.6853932584269663,
|
||||
@@ -273,10 +307,10 @@ class Stree_test(unittest.TestCase):
|
||||
for criteria in ["max_samples", "impurity"]:
|
||||
for kernel in self._kernels:
|
||||
clf = Stree(
|
||||
max_iter=1e4,
|
||||
multiclass_strategy="ovr"
|
||||
if kernel == "liblinear"
|
||||
else "ovo",
|
||||
max_iter=int(1e4),
|
||||
multiclass_strategy=(
|
||||
"ovr" if kernel == "liblinear" else "ovo"
|
||||
),
|
||||
kernel=kernel,
|
||||
random_state=self._random_state,
|
||||
)
|
||||
@@ -357,6 +391,7 @@ class Stree_test(unittest.TestCase):
|
||||
|
||||
# Tests of score
|
||||
def test_score_binary(self):
|
||||
"""Check score for binary classification."""
|
||||
X, y = load_dataset(self._random_state)
|
||||
accuracies = [
|
||||
0.9506666666666667,
|
||||
@@ -379,6 +414,7 @@ class Stree_test(unittest.TestCase):
|
||||
self.assertAlmostEqual(accuracy_expected, accuracy_score)
|
||||
|
||||
def test_score_max_features(self):
|
||||
"""Check score using max_features."""
|
||||
X, y = load_dataset(self._random_state)
|
||||
clf = Stree(
|
||||
kernel="liblinear",
|
||||
@@ -390,6 +426,7 @@ class Stree_test(unittest.TestCase):
|
||||
self.assertAlmostEqual(0.9453333333333334, clf.score(X, y))
|
||||
|
||||
def test_bogus_splitter_parameter(self):
|
||||
"""Check that bogus splitter parameter raises exception."""
|
||||
clf = Stree(splitter="duck")
|
||||
with self.assertRaises(ValueError):
|
||||
clf.fit(*load_dataset())
|
||||
@@ -403,10 +440,10 @@ class Stree_test(unittest.TestCase):
|
||||
clf.fit(X, y)
|
||||
score = clf.score(X, y)
|
||||
# Check accuracy of the whole model
|
||||
self.assertAlmostEquals(0.98, score, 5)
|
||||
self.assertAlmostEqual(0.98, score, 5)
|
||||
svm = LinearSVC(random_state=0)
|
||||
svm.fit(X, y)
|
||||
self.assertAlmostEquals(0.9666666666666667, svm.score(X, y), 5)
|
||||
self.assertAlmostEqual(0.9666666666666667, svm.score(X, y), 5)
|
||||
data = svm.decision_function(X)
|
||||
expected = [
|
||||
0.4444444444444444,
|
||||
@@ -418,7 +455,7 @@ class Stree_test(unittest.TestCase):
|
||||
ty[data > 0] = 1
|
||||
ty = ty.astype(int)
|
||||
for i in range(3):
|
||||
self.assertAlmostEquals(
|
||||
self.assertAlmostEqual(
|
||||
expected[i],
|
||||
clf.splitter_._gini(ty[:, i]),
|
||||
)
|
||||
@@ -445,6 +482,7 @@ class Stree_test(unittest.TestCase):
|
||||
self.assertListEqual([47], resdn[1].tolist())
|
||||
|
||||
def test_score_multiclass_rbf(self):
|
||||
"""Test score for multiclass classification with rbf kernel."""
|
||||
X, y = load_dataset(
|
||||
random_state=self._random_state,
|
||||
n_classes=3,
|
||||
@@ -462,6 +500,7 @@ class Stree_test(unittest.TestCase):
|
||||
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
||||
|
||||
def test_score_multiclass_poly(self):
|
||||
"""Test score for multiclass classification with poly kernel."""
|
||||
X, y = load_dataset(
|
||||
random_state=self._random_state,
|
||||
n_classes=3,
|
||||
@@ -483,6 +522,7 @@ class Stree_test(unittest.TestCase):
|
||||
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
||||
|
||||
def test_score_multiclass_liblinear(self):
|
||||
"""Test score for multiclass classification with liblinear kernel."""
|
||||
X, y = load_dataset(
|
||||
random_state=self._random_state,
|
||||
n_classes=3,
|
||||
@@ -508,6 +548,7 @@ class Stree_test(unittest.TestCase):
|
||||
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
||||
|
||||
def test_score_multiclass_sigmoid(self):
|
||||
"""Test score for multiclass classification with sigmoid kernel."""
|
||||
X, y = load_dataset(
|
||||
random_state=self._random_state,
|
||||
n_classes=3,
|
||||
@@ -528,6 +569,7 @@ class Stree_test(unittest.TestCase):
|
||||
self.assertEqual(0.9662921348314607, clf2.fit(X, y).score(X, y))
|
||||
|
||||
def test_score_multiclass_linear(self):
|
||||
"""Test score for multiclass classification with linear kernel."""
|
||||
warnings.filterwarnings("ignore", category=ConvergenceWarning)
|
||||
warnings.filterwarnings("ignore", category=RuntimeWarning)
|
||||
X, y = load_dataset(
|
||||
@@ -551,15 +593,17 @@ class Stree_test(unittest.TestCase):
|
||||
)
|
||||
self.assertEqual(0.9526666666666667, clf2.fit(X, y).score(X, y))
|
||||
X, y = load_wine(return_X_y=True)
|
||||
self.assertEqual(0.9831460674157303, clf.fit(X, y).score(X, y))
|
||||
self.assertEqual(0.9887640449438202, clf.fit(X, y).score(X, y))
|
||||
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
||||
|
||||
def test_zero_all_sample_weights(self):
|
||||
"""Test exception raises when all sample weights are zero."""
|
||||
X, y = load_dataset(self._random_state)
|
||||
with self.assertRaises(ValueError):
|
||||
Stree().fit(X, y, np.zeros(len(y)))
|
||||
|
||||
def test_mask_samples_weighted_zero(self):
|
||||
"""Check that the weighted zero samples are masked."""
|
||||
X = np.array(
|
||||
[
|
||||
[1, 1],
|
||||
@@ -587,6 +631,7 @@ class Stree_test(unittest.TestCase):
|
||||
self.assertEqual(model2.score(X, y, w), 1)
|
||||
|
||||
def test_depth(self):
|
||||
"""Check depth of the tree."""
|
||||
X, y = load_dataset(
|
||||
random_state=self._random_state,
|
||||
n_classes=3,
|
||||
@@ -596,12 +641,15 @@ class Stree_test(unittest.TestCase):
|
||||
clf = Stree(random_state=self._random_state)
|
||||
clf.fit(X, y)
|
||||
self.assertEqual(6, clf.depth_)
|
||||
self.assertEqual(6, clf.get_depth())
|
||||
X, y = load_wine(return_X_y=True)
|
||||
clf = Stree(random_state=self._random_state)
|
||||
clf.fit(X, y)
|
||||
self.assertEqual(4, clf.depth_)
|
||||
self.assertEqual(4, clf.get_depth())
|
||||
|
||||
def test_nodes_leaves(self):
|
||||
"""Check number of nodes and leaves."""
|
||||
X, y = load_dataset(
|
||||
random_state=self._random_state,
|
||||
n_classes=3,
|
||||
@@ -612,15 +660,20 @@ class Stree_test(unittest.TestCase):
|
||||
clf.fit(X, y)
|
||||
nodes, leaves = clf.nodes_leaves()
|
||||
self.assertEqual(31, nodes)
|
||||
self.assertEqual(31, clf.get_nodes())
|
||||
self.assertEqual(16, leaves)
|
||||
self.assertEqual(16, clf.get_leaves())
|
||||
X, y = load_wine(return_X_y=True)
|
||||
clf = Stree(random_state=self._random_state)
|
||||
clf.fit(X, y)
|
||||
nodes, leaves = clf.nodes_leaves()
|
||||
self.assertEqual(11, nodes)
|
||||
self.assertEqual(11, clf.get_nodes())
|
||||
self.assertEqual(6, leaves)
|
||||
self.assertEqual(6, clf.get_leaves())
|
||||
|
||||
def test_nodes_leaves_artificial(self):
|
||||
"""Check leaves of artificial dataset."""
|
||||
n1 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test1")
|
||||
n2 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test2")
|
||||
n3 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test3")
|
||||
@@ -636,15 +689,19 @@ class Stree_test(unittest.TestCase):
|
||||
clf.tree_ = n1
|
||||
nodes, leaves = clf.nodes_leaves()
|
||||
self.assertEqual(6, nodes)
|
||||
self.assertEqual(6, clf.get_nodes())
|
||||
self.assertEqual(2, leaves)
|
||||
self.assertEqual(2, clf.get_leaves())
|
||||
|
||||
def test_bogus_multiclass_strategy(self):
|
||||
"""Check invalid multiclass strategy."""
|
||||
clf = Stree(multiclass_strategy="other")
|
||||
X, y = load_wine(return_X_y=True)
|
||||
with self.assertRaises(ValueError):
|
||||
clf.fit(X, y)
|
||||
|
||||
def test_multiclass_strategy(self):
|
||||
"""Check multiclass strategy."""
|
||||
X, y = load_wine(return_X_y=True)
|
||||
clf_o = Stree(multiclass_strategy="ovo")
|
||||
clf_r = Stree(multiclass_strategy="ovr")
|
||||
@@ -654,6 +711,7 @@ class Stree_test(unittest.TestCase):
|
||||
self.assertEqual(0.9269662921348315, score_r)
|
||||
|
||||
def test_incompatible_hyperparameters(self):
|
||||
"""Check incompatible hyperparameters."""
|
||||
X, y = load_wine(return_X_y=True)
|
||||
clf = Stree(kernel="liblinear", multiclass_strategy="ovo")
|
||||
with self.assertRaises(ValueError):
|
||||
@@ -661,3 +719,55 @@ class Stree_test(unittest.TestCase):
|
||||
clf = Stree(multiclass_strategy="ovo", split_criteria="max_samples")
|
||||
with self.assertRaises(ValueError):
|
||||
clf.fit(X, y)
|
||||
|
||||
def test_version(self):
|
||||
"""Check STree version."""
|
||||
clf = Stree()
|
||||
self.assertEqual(__version__, clf.version())
|
||||
|
||||
def test_call(self) -> None:
|
||||
"""Check call method."""
|
||||
clf = Stree()
|
||||
self.assertIsNone(clf())
|
||||
|
||||
def test_graph(self):
|
||||
"""Check graphviz representation of the tree."""
|
||||
X, y = load_wine(return_X_y=True)
|
||||
clf = Stree(random_state=self._random_state)
|
||||
|
||||
expected_head = (
|
||||
"digraph STree {\nlabel=<STree >\nfontsize=30\n"
|
||||
"fontcolor=blue\nlabelloc=t\n"
|
||||
)
|
||||
expected_tail = (
|
||||
' [shape=box style=filled label="class=1 impurity=0.000 '
|
||||
'counts=[0 1 0]"];\n}\n'
|
||||
)
|
||||
self.assertEqual(clf.graph(), expected_head + "}\n")
|
||||
clf.fit(X, y)
|
||||
computed = clf.graph()
|
||||
computed_head = computed[: len(expected_head)]
|
||||
num = -len(expected_tail)
|
||||
computed_tail = computed[num:]
|
||||
self.assertEqual(computed_head, expected_head)
|
||||
self.assertEqual(computed_tail, expected_tail)
|
||||
|
||||
def test_graph_title(self):
|
||||
X, y = load_wine(return_X_y=True)
|
||||
clf = Stree(random_state=self._random_state)
|
||||
expected_head = (
|
||||
"digraph STree {\nlabel=<STree Sample title>\nfontsize=30\n"
|
||||
"fontcolor=blue\nlabelloc=t\n"
|
||||
)
|
||||
expected_tail = (
|
||||
' [shape=box style=filled label="class=1 impurity=0.000 '
|
||||
'counts=[0 1 0]"];\n}\n'
|
||||
)
|
||||
self.assertEqual(clf.graph("Sample title"), expected_head + "}\n")
|
||||
clf.fit(X, y)
|
||||
computed = clf.graph("Sample title")
|
||||
computed_head = computed[: len(expected_head)]
|
||||
num = -len(expected_tail)
|
||||
computed_tail = computed[num:]
|
||||
self.assertEqual(computed_head, expected_head)
|
||||
self.assertEqual(computed_tail, expected_tail)
|
||||
|
||||
Reference in New Issue
Block a user