mirror of
https://github.com/Doctorado-ML/STree.git
synced 2025-08-17 16:36:01 +00:00
Compare commits
23 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
5b791bc5bf | ||
|
|
c37f044e3a | ||
|
|
2f6ae648a1 | ||
|
|
93be8a89a8 | ||
82838fa3e0
|
|||
|
f0b2ce3c7b
|
|||
|
00ed57c015
|
|||
|
|
08222f109e | ||
|
cc931d8547
|
|||
|
b044a057df
|
|||
|
fc48bc8ba4
|
|||
|
|
8251f07674 | ||
|
|
0b15a5af11 | ||
|
|
28d905368b | ||
|
e5d49132ec
|
|||
|
8daecc4726
|
|||
|
|
bf678df159 | ||
|
|
36b08b1bcf | ||
|
36ff3da26d
|
|||
|
|
6b281ebcc8 | ||
|
|
3aaddd096f | ||
|
|
15a5a4c407 | ||
|
|
0afe14a447 |
5
.github/workflows/main.yml
vendored
5
.github/workflows/main.yml
vendored
@@ -12,8 +12,8 @@ jobs:
|
|||||||
runs-on: ${{ matrix.os }}
|
runs-on: ${{ matrix.os }}
|
||||||
strategy:
|
strategy:
|
||||||
matrix:
|
matrix:
|
||||||
os: [macos-latest, ubuntu-latest]
|
os: [macos-latest, ubuntu-latest, windows-latest]
|
||||||
python: [3.8]
|
python: [3.8, "3.10"]
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
- uses: actions/checkout@v2
|
- uses: actions/checkout@v2
|
||||||
@@ -26,7 +26,6 @@ jobs:
|
|||||||
pip install -q --upgrade pip
|
pip install -q --upgrade pip
|
||||||
pip install -q -r requirements.txt
|
pip install -q -r requirements.txt
|
||||||
pip install -q --upgrade codecov coverage black flake8 codacy-coverage
|
pip install -q --upgrade codecov coverage black flake8 codacy-coverage
|
||||||
pip install -q git+https://github.com/doctorado-ml/mfs
|
|
||||||
- name: Lint
|
- name: Lint
|
||||||
run: |
|
run: |
|
||||||
black --check --diff stree
|
black --check --diff stree
|
||||||
|
|||||||
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
|
||||||
7
Makefile
7
Makefile
@@ -10,6 +10,9 @@ coverage: ## Run tests with coverage
|
|||||||
deps: ## Install dependencies
|
deps: ## Install dependencies
|
||||||
pip install -r requirements.txt
|
pip install -r requirements.txt
|
||||||
|
|
||||||
|
devdeps: ## Install development dependencies
|
||||||
|
pip install black pip-audit flake8 mypy coverage
|
||||||
|
|
||||||
lint: ## Lint and static-check
|
lint: ## Lint and static-check
|
||||||
black stree
|
black stree
|
||||||
flake8 stree
|
flake8 stree
|
||||||
@@ -26,11 +29,15 @@ doc: ## Update documentation
|
|||||||
|
|
||||||
build: ## Build package
|
build: ## Build package
|
||||||
rm -fr dist/*
|
rm -fr dist/*
|
||||||
|
rm -fr build/*
|
||||||
python setup.py sdist bdist_wheel
|
python setup.py sdist bdist_wheel
|
||||||
|
|
||||||
doc-clean: ## Update documentation
|
doc-clean: ## Update documentation
|
||||||
make -C docs --makefile=Makefile clean
|
make -C docs --makefile=Makefile clean
|
||||||
|
|
||||||
|
audit: ## Audit pip
|
||||||
|
pip-audit
|
||||||
|
|
||||||
help: ## Show help message
|
help: ## Show help message
|
||||||
@IFS=$$'\n' ; \
|
@IFS=$$'\n' ; \
|
||||||
help_lines=(`fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/##/:/'`); \
|
help_lines=(`fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/##/:/'`); \
|
||||||
|
|||||||
45
README.md
45
README.md
@@ -2,6 +2,9 @@
|
|||||||
[](https://codecov.io/gh/doctorado-ml/stree)
|
[](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://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://lgtm.com/projects/g/Doctorado-ML/STree/context:python)
|
||||||
|
[](https://badge.fury.io/py/STree)
|
||||||
|
|
||||||
|
[](https://zenodo.org/badge/latestdoi/262658230)
|
||||||
|
|
||||||
# STree
|
# STree
|
||||||
|
|
||||||
@@ -23,8 +26,6 @@ Can be found in [stree.readthedocs.io](https://stree.readthedocs.io/en/stable/)
|
|||||||
|
|
||||||
### Jupyter notebooks
|
### 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/benchmark.ipynb) Benchmark
|
||||||
|
|
||||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
|
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
|
||||||
@@ -35,24 +36,24 @@ Can be found in [stree.readthedocs.io](https://stree.readthedocs.io/en/stable/)
|
|||||||
|
|
||||||
## Hyperparameters
|
## Hyperparameters
|
||||||
|
|
||||||
| | **Hyperparameter** | **Type/Values** | **Default** | **Meaning** |
|
| | **Hyperparameter** | **Type/Values** | **Default** | **Meaning** |
|
||||||
| --- | ------------------- | ------------------------------------------------------ | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
| --- | ------------------- | -------------------------------------------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||||
| \* | C | \<float\> | 1.0 | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. |
|
| \* | C | \<float\> | 1.0 | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. |
|
||||||
| \* | kernel | {"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 |
|
| \* | 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. |
|
| \* | max_iter | \<int\> | 1e5 | Hard limit on iterations within solver, or -1 for no limit. |
|
||||||
| \* | random_state | \<int\> | None | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls |
|
| \* | random_state | \<int\> | None | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls |
|
||||||
| | max_depth | \<int\> | None | Specifies the maximum depth of the tree |
|
| | max_depth | \<int\> | None | Specifies the maximum depth of the tree |
|
||||||
| \* | tol | \<float\> | 1e-4 | Tolerance for stopping criterion. |
|
| \* | tol | \<float\> | 1e-4 | Tolerance for stopping criterion. |
|
||||||
| \* | degree | \<int\> | 3 | Degree of the polynomial kernel function (‘poly’). Ignored by all other kernels. |
|
| \* | 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. |
|
| \* | 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 |
|
| | 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. |
|
| | 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 |
|
| | min_samples_split | \<int\> | 0 | The minimum number of samples required to split an internal node. 0 (default) for any |
|
||||||
| | max_features | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. |
|
| | max_features | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. |
|
||||||
| | splitter | {"best", "random", "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 |
|
| | 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).
|
||||||
| | normalize | \<bool\> | False | If standardization of features should be applied on each node with the samples that reach it |
|
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 |
|
||||||
| \* | multiclass_strategy | {"ovo", "ovr"} | "ovo" | Strategy to use with multiclass datasets, **"ovo"**: one versus one. **"ovr"**: one versus rest |
|
| | 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
|
\* Hyperparameter used by the support vector classifier of every node
|
||||||
|
|
||||||
@@ -73,3 +74,7 @@ python -m unittest -v stree.tests
|
|||||||
## License
|
## License
|
||||||
|
|
||||||
STree is [MIT](https://github.com/doctorado-ml/stree/blob/master/LICENSE) licensed
|
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
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
sphinx
|
sphinx
|
||||||
sphinx-rtd-theme
|
sphinx-rtd-theme
|
||||||
myst-parser
|
myst-parser
|
||||||
git+https://github.com/doctorado-ml/stree
|
mufs
|
||||||
@@ -12,19 +12,18 @@
|
|||||||
#
|
#
|
||||||
import os
|
import os
|
||||||
import sys
|
import sys
|
||||||
import stree
|
from stree._version import __version__
|
||||||
|
|
||||||
sys.path.insert(0, os.path.abspath("../../stree/"))
|
sys.path.insert(0, os.path.abspath("../../stree/"))
|
||||||
|
|
||||||
|
|
||||||
# -- Project information -----------------------------------------------------
|
# -- Project information -----------------------------------------------------
|
||||||
|
|
||||||
project = "STree"
|
project = "STree"
|
||||||
copyright = "2020 - 2021, Ricardo Montañana Gómez"
|
copyright = "2020 - 2022, Ricardo Montañana Gómez"
|
||||||
author = "Ricardo Montañana Gómez"
|
author = "Ricardo Montañana Gómez"
|
||||||
|
|
||||||
# The full version, including alpha/beta/rc tags
|
# The full version, including alpha/beta/rc tags
|
||||||
version = stree.__version__
|
version = __version__
|
||||||
release = version
|
release = version
|
||||||
|
|
||||||
|
|
||||||
@@ -54,4 +53,4 @@ html_theme = "sphinx_rtd_theme"
|
|||||||
# Add any paths that contain custom static files (such as style sheets) here,
|
# 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,
|
# relative to this directory. They are copied after the builtin static files,
|
||||||
# so a file named "default.css" will overwrite the builtin "default.css".
|
# so a file named "default.css" will overwrite the builtin "default.css".
|
||||||
html_static_path = ["_static"]
|
html_static_path = []
|
||||||
|
|||||||
@@ -2,8 +2,6 @@
|
|||||||
|
|
||||||
## Notebooks
|
## 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/benchmark.ipynb) Benchmark
|
||||||
|
|
||||||
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
|
- [](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
|
||||||
|
|||||||
@@ -1,22 +1,22 @@
|
|||||||
# Hyperparameters
|
# Hyperparameters
|
||||||
|
|
||||||
| | **Hyperparameter** | **Type/Values** | **Default** | **Meaning** |
|
| | **Hyperparameter** | **Type/Values** | **Default** | **Meaning** |
|
||||||
| --- | ------------------- | ------------------------------------------------------ | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
| --- | ------------------- | -------------------------------------------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||||
| \* | C | \<float\> | 1.0 | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. |
|
| \* | C | \<float\> | 1.0 | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. |
|
||||||
| \* | kernel | {"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 |
|
| \* | 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. |
|
| \* | max_iter | \<int\> | 1e5 | Hard limit on iterations within solver, or -1 for no limit. |
|
||||||
| \* | random_state | \<int\> | None | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls |
|
| \* | random_state | \<int\> | None | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls |
|
||||||
| | max_depth | \<int\> | None | Specifies the maximum depth of the tree |
|
| | max_depth | \<int\> | None | Specifies the maximum depth of the tree |
|
||||||
| \* | tol | \<float\> | 1e-4 | Tolerance for stopping criterion. |
|
| \* | tol | \<float\> | 1e-4 | Tolerance for stopping criterion. |
|
||||||
| \* | degree | \<int\> | 3 | Degree of the polynomial kernel function (‘poly’). Ignored by all other kernels. |
|
| \* | 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. |
|
| \* | 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 |
|
| | 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. |
|
| | 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 |
|
| | min_samples_split | \<int\> | 0 | The minimum number of samples required to split an internal node. 0 (default) for any |
|
||||||
| | max_features | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. |
|
| | max_features | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. |
|
||||||
| | splitter | {"best", "random", "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 |
|
| | 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 |
|
| | 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 |
|
| \* | 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
|
\* Hyperparameter used by the support vector classifier of every node
|
||||||
|
|
||||||
|
|||||||
@@ -1,9 +1,12 @@
|
|||||||
# STree
|
# STree
|
||||||
|
|
||||||
[](https://app.codeship.com/projects/399170)
|
|
||||||
[](https://codecov.io/gh/doctorado-ml/stree)
|
[](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://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://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.
|
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": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
"# Stree\n",
|
"# Stree\n",
|
||||||
"stree = Stree(random_state=random_state, C=.01, max_iter=1e3)"
|
"stree = Stree(random_state=random_state, C=.01, max_iter=1e3, kernel=\"liblinear\", multiclass_strategy=\"ovr\")"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@@ -368,4 +368,4 @@
|
|||||||
},
|
},
|
||||||
"nbformat": 4,
|
"nbformat": 4,
|
||||||
"nbformat_minor": 4
|
"nbformat_minor": 4
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,253 +1,253 @@
|
|||||||
{
|
{
|
||||||
"cells": [
|
"cells": [
|
||||||
{
|
{
|
||||||
"cell_type": "markdown",
|
"cell_type": "markdown",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
"# Test Gridsearch\n",
|
"# Test Gridsearch\n",
|
||||||
"with different kernels and different configurations"
|
"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"
|
||||||
|
}
|
||||||
},
|
},
|
||||||
{
|
"nbformat": 4,
|
||||||
"cell_type": "markdown",
|
"nbformat_minor": 4
|
||||||
"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
|
|
||||||
}
|
|
||||||
|
|||||||
@@ -1,2 +1,2 @@
|
|||||||
scikit-learn>0.24
|
scikit-learn>0.24
|
||||||
mfs
|
mufs
|
||||||
14
setup.py
14
setup.py
@@ -1,4 +1,5 @@
|
|||||||
import setuptools
|
import setuptools
|
||||||
|
import os
|
||||||
|
|
||||||
|
|
||||||
def readme():
|
def readme():
|
||||||
@@ -6,9 +7,9 @@ def readme():
|
|||||||
return f.read()
|
return f.read()
|
||||||
|
|
||||||
|
|
||||||
def get_data(field):
|
def get_data(field, file_name="__init__.py"):
|
||||||
item = ""
|
item = ""
|
||||||
with open("stree/__init__.py") as f:
|
with open(os.path.join("stree", file_name)) as f:
|
||||||
for line in f.readlines():
|
for line in f.readlines():
|
||||||
if line.startswith(f"__{field}__"):
|
if line.startswith(f"__{field}__"):
|
||||||
delim = '"' if '"' in line else "'"
|
delim = '"' if '"' in line else "'"
|
||||||
@@ -19,9 +20,14 @@ def get_data(field):
|
|||||||
return item
|
return item
|
||||||
|
|
||||||
|
|
||||||
|
def get_requirements():
|
||||||
|
with open("requirements.txt") as f:
|
||||||
|
return f.read().splitlines()
|
||||||
|
|
||||||
|
|
||||||
setuptools.setup(
|
setuptools.setup(
|
||||||
name="STree",
|
name="STree",
|
||||||
version=get_data("version"),
|
version=get_data("version", "_version.py"),
|
||||||
license=get_data("license"),
|
license=get_data("license"),
|
||||||
description="Oblique decision tree with svm nodes",
|
description="Oblique decision tree with svm nodes",
|
||||||
long_description=readme(),
|
long_description=readme(),
|
||||||
@@ -44,7 +50,7 @@ setuptools.setup(
|
|||||||
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
||||||
"Intended Audience :: Science/Research",
|
"Intended Audience :: Science/Research",
|
||||||
],
|
],
|
||||||
install_requires=["scikit-learn", "numpy", "mfs"],
|
install_requires=get_requirements(),
|
||||||
test_suite="stree.tests",
|
test_suite="stree.tests",
|
||||||
zip_safe=False,
|
zip_safe=False,
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -12,12 +12,32 @@ from sklearn.feature_selection import SelectKBest, mutual_info_classif
|
|||||||
from sklearn.preprocessing import StandardScaler
|
from sklearn.preprocessing import StandardScaler
|
||||||
from sklearn.svm import SVC
|
from sklearn.svm import SVC
|
||||||
from sklearn.exceptions import ConvergenceWarning
|
from sklearn.exceptions import ConvergenceWarning
|
||||||
from mfs import MFS
|
from mufs import MUFS
|
||||||
|
|
||||||
|
|
||||||
class Snode:
|
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
|
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__(
|
def __init__(
|
||||||
@@ -48,6 +68,7 @@ class Snode:
|
|||||||
self._impurity = impurity
|
self._impurity = impurity
|
||||||
self._partition_column: int = -1
|
self._partition_column: int = -1
|
||||||
self._scaler = scaler
|
self._scaler = scaler
|
||||||
|
self._proba = None
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
def copy(cls, node: "Snode") -> "Snode":
|
def copy(cls, node: "Snode") -> "Snode":
|
||||||
@@ -107,23 +128,44 @@ class Snode:
|
|||||||
def get_up(self) -> "Snode":
|
def get_up(self) -> "Snode":
|
||||||
return self._up
|
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
|
"""Compute the class of the predictor and its belief based on the
|
||||||
subdataset of the node only if it is a leaf
|
subdataset of the node only if it is a leaf
|
||||||
"""
|
"""
|
||||||
if not self.is_leaf():
|
if not self.is_leaf():
|
||||||
return
|
return
|
||||||
classes, card = np.unique(self._y, return_counts=True)
|
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)
|
max_card = max(card)
|
||||||
self._class = classes[card == max_card][0]
|
self._class = classes[card == max_card][0]
|
||||||
self._belief = max_card / np.sum(card)
|
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:
|
else:
|
||||||
self._belief = 1
|
output += (
|
||||||
try:
|
f'N{id(self)} [label="#features={len(self._features)} '
|
||||||
self._class = classes[0]
|
f"classes={count_values[0]} samples={count_values[1]} "
|
||||||
except IndexError:
|
f'({sum(count_values[1])})" fontcolor=black];\n'
|
||||||
self._class = None
|
)
|
||||||
|
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:
|
def __str__(self) -> str:
|
||||||
count_values = np.unique(self._y, return_counts=True)
|
count_values = np.unique(self._y, return_counts=True)
|
||||||
@@ -165,6 +207,56 @@ class Siterator:
|
|||||||
|
|
||||||
|
|
||||||
class Splitter:
|
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__(
|
def __init__(
|
||||||
self,
|
self,
|
||||||
clf: SVC = None,
|
clf: SVC = None,
|
||||||
@@ -175,6 +267,7 @@ class Splitter:
|
|||||||
random_state=None,
|
random_state=None,
|
||||||
normalize=False,
|
normalize=False,
|
||||||
):
|
):
|
||||||
|
|
||||||
self._clf = clf
|
self._clf = clf
|
||||||
self._random_state = random_state
|
self._random_state = random_state
|
||||||
if random_state is not None:
|
if random_state is not None:
|
||||||
@@ -201,10 +294,19 @@ class Splitter:
|
|||||||
f"criteria has to be max_samples or impurity; got ({criteria})"
|
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(
|
raise ValueError(
|
||||||
"splitter must be in {random, best, mutual, cfs, fcbf} got "
|
"splitter must be in {random, trandom, best, mutual, cfs, "
|
||||||
f"({feature_select})"
|
"fcbf, iwss} "
|
||||||
|
f"got ({feature_select})"
|
||||||
)
|
)
|
||||||
self.criterion_function = getattr(self, f"_{self._criterion}")
|
self.criterion_function = getattr(self, f"_{self._criterion}")
|
||||||
self.decision_criteria = getattr(self, f"_{self._criteria}")
|
self.decision_criteria = getattr(self, f"_{self._criteria}")
|
||||||
@@ -235,6 +337,31 @@ class Splitter:
|
|||||||
features_sets = self._generate_spaces(n_features, max_features)
|
features_sets = self._generate_spaces(n_features, max_features)
|
||||||
return self._select_best_set(dataset, labels, features_sets)
|
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
|
@staticmethod
|
||||||
def _fs_best(
|
def _fs_best(
|
||||||
dataset: np.array, labels: np.array, max_features: int
|
dataset: np.array, labels: np.array, max_features: int
|
||||||
@@ -262,9 +389,8 @@ class Splitter:
|
|||||||
.get_support(indices=True)
|
.get_support(indices=True)
|
||||||
)
|
)
|
||||||
|
|
||||||
@staticmethod
|
|
||||||
def _fs_mutual(
|
def _fs_mutual(
|
||||||
dataset: np.array, labels: np.array, max_features: int
|
self, dataset: np.array, labels: np.array, max_features: int
|
||||||
) -> tuple:
|
) -> tuple:
|
||||||
"""Return the best features with mutual information with labels
|
"""Return the best features with mutual information with labels
|
||||||
|
|
||||||
@@ -284,7 +410,9 @@ class Splitter:
|
|||||||
indices of the features selected
|
indices of the features selected
|
||||||
"""
|
"""
|
||||||
# return best features with mutual info with the label
|
# 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(
|
return tuple(
|
||||||
sorted(
|
sorted(
|
||||||
range(len(feature_list)), key=lambda sub: feature_list[sub]
|
range(len(feature_list)), key=lambda sub: feature_list[sub]
|
||||||
@@ -312,8 +440,8 @@ class Splitter:
|
|||||||
tuple
|
tuple
|
||||||
indices of the features selected
|
indices of the features selected
|
||||||
"""
|
"""
|
||||||
mfs = MFS(max_features=max_features, discrete=False)
|
mufs = MUFS(max_features=max_features, discrete=False)
|
||||||
return mfs.cfs(dataset, labels).get_results()
|
return mufs.cfs(dataset, labels).get_results()
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def _fs_fcbf(
|
def _fs_fcbf(
|
||||||
@@ -336,8 +464,33 @@ class Splitter:
|
|||||||
tuple
|
tuple
|
||||||
indices of the features selected
|
indices of the features selected
|
||||||
"""
|
"""
|
||||||
mfs = MFS(max_features=max_features, discrete=False)
|
mufs = MUFS(max_features=max_features, discrete=False)
|
||||||
return mfs.fcbf(dataset, labels, 5e-4).get_results()
|
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:
|
def partition_impurity(self, y: np.array) -> np.array:
|
||||||
return self.criterion_function(y)
|
return self.criterion_function(y)
|
||||||
|
|||||||
275
stree/Strees.py
275
stree/Strees.py
@@ -17,21 +17,129 @@ from sklearn.utils.validation import (
|
|||||||
_check_sample_weight,
|
_check_sample_weight,
|
||||||
)
|
)
|
||||||
from .Splitter import Splitter, Snode, Siterator
|
from .Splitter import Splitter, Snode, Siterator
|
||||||
|
from ._version import __version__
|
||||||
|
|
||||||
|
|
||||||
class Stree(BaseEstimator, ClassifierMixin):
|
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
|
can deal with sample_weights in predict, used in boosting sklearn methods
|
||||||
inheriting from BaseEstimator implements get_params and set_params methods
|
inheriting from BaseEstimator implements get_params and set_params methods
|
||||||
inheriting from ClassifierMixin implement the attribute _estimator_type
|
inheriting from ClassifierMixin implement the attribute _estimator_type
|
||||||
with "classifier" as value
|
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__(
|
def __init__(
|
||||||
self,
|
self,
|
||||||
C: float = 1.0,
|
C: float = 1.0,
|
||||||
kernel: str = "linear",
|
kernel: str = "linear",
|
||||||
max_iter: int = 1e5,
|
max_iter: int = int(1e5),
|
||||||
random_state: int = None,
|
random_state: int = None,
|
||||||
max_depth: int = None,
|
max_depth: int = None,
|
||||||
tol: float = 1e-4,
|
tol: float = 1e-4,
|
||||||
@@ -45,6 +153,7 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
multiclass_strategy: str = "ovo",
|
multiclass_strategy: str = "ovo",
|
||||||
normalize: bool = False,
|
normalize: bool = False,
|
||||||
):
|
):
|
||||||
|
|
||||||
self.max_iter = max_iter
|
self.max_iter = max_iter
|
||||||
self.C = C
|
self.C = C
|
||||||
self.kernel = kernel
|
self.kernel = kernel
|
||||||
@@ -61,6 +170,11 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
self.normalize = normalize
|
self.normalize = normalize
|
||||||
self.multiclass_strategy = multiclass_strategy
|
self.multiclass_strategy = multiclass_strategy
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def version() -> str:
|
||||||
|
"""Return the version of the package."""
|
||||||
|
return __version__
|
||||||
|
|
||||||
def _more_tags(self) -> dict:
|
def _more_tags(self) -> dict:
|
||||||
"""Required by sklearn to supply features of the classifier
|
"""Required by sklearn to supply features of the classifier
|
||||||
make mandatory the labels array
|
make mandatory the labels array
|
||||||
@@ -200,7 +314,7 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
if np.unique(y).shape[0] == 1:
|
if np.unique(y).shape[0] == 1:
|
||||||
# only 1 class => pure dataset
|
# only 1 class => pure dataset
|
||||||
node.set_title(title + ", <pure>")
|
node.set_title(title + ", <pure>")
|
||||||
node.make_predictor()
|
node.make_predictor(self.n_classes_)
|
||||||
return node
|
return node
|
||||||
# Train the model
|
# Train the model
|
||||||
clf = self._build_clf()
|
clf = self._build_clf()
|
||||||
@@ -219,7 +333,7 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
if X_U is None or X_D is None:
|
if X_U is None or X_D is None:
|
||||||
# didn't part anything
|
# didn't part anything
|
||||||
node.set_title(title + ", <cgaf>")
|
node.set_title(title + ", <cgaf>")
|
||||||
node.make_predictor()
|
node.make_predictor(self.n_classes_)
|
||||||
return node
|
return node
|
||||||
node.set_up(
|
node.set_up(
|
||||||
self._train(X_U, y_u, sw_u, depth + 1, title + f" - Up({depth+1})")
|
self._train(X_U, y_u, sw_u, depth + 1, title + f" - Up({depth+1})")
|
||||||
@@ -253,28 +367,100 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
)
|
)
|
||||||
)
|
)
|
||||||
|
|
||||||
@staticmethod
|
def __predict_class(self, X: np.array) -> np.array:
|
||||||
def _reorder_results(y: np.array, indices: np.array) -> np.array:
|
"""Compute the predicted class for the samples in X. Returns the number
|
||||||
"""Reorder an array based on the array of indices passed
|
of samples of each class in the corresponding leaf node.
|
||||||
|
|
||||||
Parameters
|
Parameters
|
||||||
----------
|
----------
|
||||||
y : np.array
|
X : np.array
|
||||||
data untidy
|
Array of samples
|
||||||
indices : np.array
|
|
||||||
indices used to set order
|
|
||||||
|
|
||||||
Returns
|
Returns
|
||||||
-------
|
-------
|
||||||
np.array
|
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()
|
def compute_prediction(xp, indices, node):
|
||||||
indices = indices.astype(int)
|
if xp is None:
|
||||||
for i, index in enumerate(indices):
|
return
|
||||||
y_ordered[index] = y[i]
|
if node.is_leaf():
|
||||||
return y_ordered
|
# 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:
|
def predict(self, X: np.array) -> np.array:
|
||||||
"""Predict labels for each sample in dataset passed
|
"""Predict labels for each sample in dataset passed
|
||||||
@@ -296,40 +482,8 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
NotFittedError
|
NotFittedError
|
||||||
if model is not fitted
|
if model is not fitted
|
||||||
"""
|
"""
|
||||||
|
X = self.check_predict(X)
|
||||||
def predict_class(
|
return self.classes_[np.argmax(self.__predict_class(X), axis=1)]
|
||||||
xp: np.array, indices: np.array, node: Snode
|
|
||||||
) -> np.array:
|
|
||||||
if xp is None:
|
|
||||||
return [], []
|
|
||||||
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)
|
|
||||||
|
|
||||||
# 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 nodes_leaves(self) -> tuple:
|
def nodes_leaves(self) -> tuple:
|
||||||
"""Compute the number of nodes and leaves in the built tree
|
"""Compute the number of nodes and leaves in the built tree
|
||||||
@@ -362,6 +516,23 @@ class Stree(BaseEstimator, ClassifierMixin):
|
|||||||
tree = None
|
tree = None
|
||||||
return Siterator(tree)
|
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:
|
def __str__(self) -> str:
|
||||||
"""String representation of the tree
|
"""String representation of the tree
|
||||||
|
|
||||||
|
|||||||
@@ -1,7 +1,5 @@
|
|||||||
from .Strees import Stree, Siterator
|
from .Strees import Stree, Siterator
|
||||||
|
|
||||||
__version__ = "1.2"
|
|
||||||
|
|
||||||
__author__ = "Ricardo Montañana Gómez"
|
__author__ = "Ricardo Montañana Gómez"
|
||||||
__copyright__ = "Copyright 2020-2021, Ricardo Montañana Gómez"
|
__copyright__ = "Copyright 2020-2021, Ricardo Montañana Gómez"
|
||||||
__license__ = "MIT License"
|
__license__ = "MIT License"
|
||||||
|
|||||||
1
stree/_version.py
Normal file
1
stree/_version.py
Normal file
@@ -0,0 +1 @@
|
|||||||
|
__version__ = "1.3.1"
|
||||||
@@ -67,10 +67,28 @@ class Snode_test(unittest.TestCase):
|
|||||||
|
|
||||||
def test_make_predictor_on_leaf(self):
|
def test_make_predictor_on_leaf(self):
|
||||||
test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
|
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(1, test._class)
|
||||||
self.assertEqual(0.75, test._belief)
|
self.assertEqual(0.75, test._belief)
|
||||||
self.assertEqual(-1, test._partition_column)
|
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):
|
def test_set_title(self):
|
||||||
test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
|
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])
|
test.set_features([1, 2])
|
||||||
self.assertListEqual([1, 2], test.get_features())
|
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):
|
def test_copy_node(self):
|
||||||
px = [1, 2, 3, 4]
|
px = [1, 2, 3, 4]
|
||||||
py = [1]
|
py = [1]
|
||||||
|
|||||||
@@ -285,3 +285,28 @@ class Splitter_test(unittest.TestCase):
|
|||||||
Xs, computed = tcl.get_subspace(X, y, rs)
|
Xs, computed = tcl.get_subspace(X, y, rs)
|
||||||
self.assertListEqual(expected, list(computed))
|
self.assertListEqual(expected, list(computed))
|
||||||
self.assertListEqual(X[:, expected].tolist(), Xs.tolist())
|
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 import Stree
|
||||||
from stree.Splitter import Snode
|
from stree.Splitter import Snode
|
||||||
from .utils import load_dataset
|
from .utils import load_dataset
|
||||||
|
from .._version import __version__
|
||||||
|
|
||||||
|
|
||||||
class Stree_test(unittest.TestCase):
|
class Stree_test(unittest.TestCase):
|
||||||
@@ -114,6 +115,38 @@ class Stree_test(unittest.TestCase):
|
|||||||
yp = clf.fit(X, y).predict(X[:num, :])
|
yp = clf.fit(X, y).predict(X[:num, :])
|
||||||
self.assertListEqual(y[:num].tolist(), yp.tolist())
|
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):
|
def test_single_vs_multiple_prediction(self):
|
||||||
"""Check if predicting sample by sample gives the same result as
|
"""Check if predicting sample by sample gives the same result as
|
||||||
predicting all samples at once
|
predicting all samples at once
|
||||||
@@ -273,7 +306,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
for criteria in ["max_samples", "impurity"]:
|
for criteria in ["max_samples", "impurity"]:
|
||||||
for kernel in self._kernels:
|
for kernel in self._kernels:
|
||||||
clf = Stree(
|
clf = Stree(
|
||||||
max_iter=1e4,
|
max_iter=int(1e4),
|
||||||
multiclass_strategy="ovr"
|
multiclass_strategy="ovr"
|
||||||
if kernel == "liblinear"
|
if kernel == "liblinear"
|
||||||
else "ovo",
|
else "ovo",
|
||||||
@@ -357,6 +390,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
|
|
||||||
# Tests of score
|
# Tests of score
|
||||||
def test_score_binary(self):
|
def test_score_binary(self):
|
||||||
|
"""Check score for binary classification."""
|
||||||
X, y = load_dataset(self._random_state)
|
X, y = load_dataset(self._random_state)
|
||||||
accuracies = [
|
accuracies = [
|
||||||
0.9506666666666667,
|
0.9506666666666667,
|
||||||
@@ -379,6 +413,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertAlmostEqual(accuracy_expected, accuracy_score)
|
self.assertAlmostEqual(accuracy_expected, accuracy_score)
|
||||||
|
|
||||||
def test_score_max_features(self):
|
def test_score_max_features(self):
|
||||||
|
"""Check score using max_features."""
|
||||||
X, y = load_dataset(self._random_state)
|
X, y = load_dataset(self._random_state)
|
||||||
clf = Stree(
|
clf = Stree(
|
||||||
kernel="liblinear",
|
kernel="liblinear",
|
||||||
@@ -390,6 +425,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertAlmostEqual(0.9453333333333334, clf.score(X, y))
|
self.assertAlmostEqual(0.9453333333333334, clf.score(X, y))
|
||||||
|
|
||||||
def test_bogus_splitter_parameter(self):
|
def test_bogus_splitter_parameter(self):
|
||||||
|
"""Check that bogus splitter parameter raises exception."""
|
||||||
clf = Stree(splitter="duck")
|
clf = Stree(splitter="duck")
|
||||||
with self.assertRaises(ValueError):
|
with self.assertRaises(ValueError):
|
||||||
clf.fit(*load_dataset())
|
clf.fit(*load_dataset())
|
||||||
@@ -445,6 +481,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertListEqual([47], resdn[1].tolist())
|
self.assertListEqual([47], resdn[1].tolist())
|
||||||
|
|
||||||
def test_score_multiclass_rbf(self):
|
def test_score_multiclass_rbf(self):
|
||||||
|
"""Test score for multiclass classification with rbf kernel."""
|
||||||
X, y = load_dataset(
|
X, y = load_dataset(
|
||||||
random_state=self._random_state,
|
random_state=self._random_state,
|
||||||
n_classes=3,
|
n_classes=3,
|
||||||
@@ -462,6 +499,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
||||||
|
|
||||||
def test_score_multiclass_poly(self):
|
def test_score_multiclass_poly(self):
|
||||||
|
"""Test score for multiclass classification with poly kernel."""
|
||||||
X, y = load_dataset(
|
X, y = load_dataset(
|
||||||
random_state=self._random_state,
|
random_state=self._random_state,
|
||||||
n_classes=3,
|
n_classes=3,
|
||||||
@@ -483,6 +521,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
||||||
|
|
||||||
def test_score_multiclass_liblinear(self):
|
def test_score_multiclass_liblinear(self):
|
||||||
|
"""Test score for multiclass classification with liblinear kernel."""
|
||||||
X, y = load_dataset(
|
X, y = load_dataset(
|
||||||
random_state=self._random_state,
|
random_state=self._random_state,
|
||||||
n_classes=3,
|
n_classes=3,
|
||||||
@@ -508,6 +547,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
||||||
|
|
||||||
def test_score_multiclass_sigmoid(self):
|
def test_score_multiclass_sigmoid(self):
|
||||||
|
"""Test score for multiclass classification with sigmoid kernel."""
|
||||||
X, y = load_dataset(
|
X, y = load_dataset(
|
||||||
random_state=self._random_state,
|
random_state=self._random_state,
|
||||||
n_classes=3,
|
n_classes=3,
|
||||||
@@ -528,6 +568,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(0.9662921348314607, clf2.fit(X, y).score(X, y))
|
self.assertEqual(0.9662921348314607, clf2.fit(X, y).score(X, y))
|
||||||
|
|
||||||
def test_score_multiclass_linear(self):
|
def test_score_multiclass_linear(self):
|
||||||
|
"""Test score for multiclass classification with linear kernel."""
|
||||||
warnings.filterwarnings("ignore", category=ConvergenceWarning)
|
warnings.filterwarnings("ignore", category=ConvergenceWarning)
|
||||||
warnings.filterwarnings("ignore", category=RuntimeWarning)
|
warnings.filterwarnings("ignore", category=RuntimeWarning)
|
||||||
X, y = load_dataset(
|
X, y = load_dataset(
|
||||||
@@ -555,11 +596,13 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
|
||||||
|
|
||||||
def test_zero_all_sample_weights(self):
|
def test_zero_all_sample_weights(self):
|
||||||
|
"""Test exception raises when all sample weights are zero."""
|
||||||
X, y = load_dataset(self._random_state)
|
X, y = load_dataset(self._random_state)
|
||||||
with self.assertRaises(ValueError):
|
with self.assertRaises(ValueError):
|
||||||
Stree().fit(X, y, np.zeros(len(y)))
|
Stree().fit(X, y, np.zeros(len(y)))
|
||||||
|
|
||||||
def test_mask_samples_weighted_zero(self):
|
def test_mask_samples_weighted_zero(self):
|
||||||
|
"""Check that the weighted zero samples are masked."""
|
||||||
X = np.array(
|
X = np.array(
|
||||||
[
|
[
|
||||||
[1, 1],
|
[1, 1],
|
||||||
@@ -587,6 +630,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(model2.score(X, y, w), 1)
|
self.assertEqual(model2.score(X, y, w), 1)
|
||||||
|
|
||||||
def test_depth(self):
|
def test_depth(self):
|
||||||
|
"""Check depth of the tree."""
|
||||||
X, y = load_dataset(
|
X, y = load_dataset(
|
||||||
random_state=self._random_state,
|
random_state=self._random_state,
|
||||||
n_classes=3,
|
n_classes=3,
|
||||||
@@ -602,6 +646,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(4, clf.depth_)
|
self.assertEqual(4, clf.depth_)
|
||||||
|
|
||||||
def test_nodes_leaves(self):
|
def test_nodes_leaves(self):
|
||||||
|
"""Check number of nodes and leaves."""
|
||||||
X, y = load_dataset(
|
X, y = load_dataset(
|
||||||
random_state=self._random_state,
|
random_state=self._random_state,
|
||||||
n_classes=3,
|
n_classes=3,
|
||||||
@@ -621,6 +666,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(6, leaves)
|
self.assertEqual(6, leaves)
|
||||||
|
|
||||||
def test_nodes_leaves_artificial(self):
|
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")
|
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")
|
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")
|
n3 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test3")
|
||||||
@@ -639,12 +685,14 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(2, leaves)
|
self.assertEqual(2, leaves)
|
||||||
|
|
||||||
def test_bogus_multiclass_strategy(self):
|
def test_bogus_multiclass_strategy(self):
|
||||||
|
"""Check invalid multiclass strategy."""
|
||||||
clf = Stree(multiclass_strategy="other")
|
clf = Stree(multiclass_strategy="other")
|
||||||
X, y = load_wine(return_X_y=True)
|
X, y = load_wine(return_X_y=True)
|
||||||
with self.assertRaises(ValueError):
|
with self.assertRaises(ValueError):
|
||||||
clf.fit(X, y)
|
clf.fit(X, y)
|
||||||
|
|
||||||
def test_multiclass_strategy(self):
|
def test_multiclass_strategy(self):
|
||||||
|
"""Check multiclass strategy."""
|
||||||
X, y = load_wine(return_X_y=True)
|
X, y = load_wine(return_X_y=True)
|
||||||
clf_o = Stree(multiclass_strategy="ovo")
|
clf_o = Stree(multiclass_strategy="ovo")
|
||||||
clf_r = Stree(multiclass_strategy="ovr")
|
clf_r = Stree(multiclass_strategy="ovr")
|
||||||
@@ -654,6 +702,7 @@ class Stree_test(unittest.TestCase):
|
|||||||
self.assertEqual(0.9269662921348315, score_r)
|
self.assertEqual(0.9269662921348315, score_r)
|
||||||
|
|
||||||
def test_incompatible_hyperparameters(self):
|
def test_incompatible_hyperparameters(self):
|
||||||
|
"""Check incompatible hyperparameters."""
|
||||||
X, y = load_wine(return_X_y=True)
|
X, y = load_wine(return_X_y=True)
|
||||||
clf = Stree(kernel="liblinear", multiclass_strategy="ovo")
|
clf = Stree(kernel="liblinear", multiclass_strategy="ovo")
|
||||||
with self.assertRaises(ValueError):
|
with self.assertRaises(ValueError):
|
||||||
@@ -661,3 +710,50 @@ class Stree_test(unittest.TestCase):
|
|||||||
clf = Stree(multiclass_strategy="ovo", split_criteria="max_samples")
|
clf = Stree(multiclass_strategy="ovo", split_criteria="max_samples")
|
||||||
with self.assertRaises(ValueError):
|
with self.assertRaises(ValueError):
|
||||||
clf.fit(X, y)
|
clf.fit(X, y)
|
||||||
|
|
||||||
|
def test_version(self):
|
||||||
|
"""Check STree version."""
|
||||||
|
clf = Stree()
|
||||||
|
self.assertEqual(__version__, clf.version())
|
||||||
|
|
||||||
|
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