mirror of
https://github.com/Doctorado-ML/STree.git
synced 2025-08-18 00:46:02 +00:00
Compare commits
2 Commits
UpdateDocA
...
v1.3.1
| Author | SHA1 | Date | |
|---|---|---|---|
|
5b791bc5bf | ||
|
|
c37f044e3a |
@@ -50,7 +50,8 @@ Can be found in [stree.readthedocs.io](https://stree.readthedocs.io/en/stable/)
|
||||
| | criterion | {“gini”, “entropy”} | entropy | The function to measure the quality of a split (only used if max_features != num_features). <br>Supported criteria are “gini” for the Gini impurity and “entropy” for the information gain. |
|
||||
| | min_samples_split | \<int\> | 0 | The minimum number of samples required to split an internal node. 0 (default) for any |
|
||||
| | max_features | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. |
|
||||
| | splitter | {"best", "random", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random" | The strategy used to choose the feature set at each node (only used if max_features < num_features). Supported strategies are: **“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features. **“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them. **“trandom”**: The algorithm generates only one random combination. **"mutual"**: Chooses the best features w.r.t. their mutual info with the label. **"cfs"**: Apply Correlation-based Feature Selection. **"fcbf"**: Apply Fast Correlation-Based Filter. **"iwss"**: IWSS based algorithm |
|
||||
| | splitter | {"best", "random", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random" | The strategy used to choose the feature set at each node (only used if max_features < num_features).
|
||||
Supported strategies are: **“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features. **“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them. **“trandom”**: The algorithm generates only one random combination. **"mutual"**: Chooses the best features w.r.t. their mutual info with the label. **"cfs"**: Apply Correlation-based Feature Selection. **"fcbf"**: Apply Fast Correlation-Based Filter. **"iwss"**: IWSS based algorithm |
|
||||
| | normalize | \<bool\> | False | If standardization of features should be applied on each node with the samples that reach it |
|
||||
| \* | multiclass_strategy | {"ovo", "ovr"} | "ovo" | Strategy to use with multiclass datasets, **"ovo"**: one versus one. **"ovr"**: one versus rest |
|
||||
|
||||
|
||||
@@ -12,19 +12,18 @@
|
||||
#
|
||||
import os
|
||||
import sys
|
||||
import stree
|
||||
from stree._version import __version__
|
||||
|
||||
sys.path.insert(0, os.path.abspath("../../stree/"))
|
||||
|
||||
|
||||
# -- Project information -----------------------------------------------------
|
||||
|
||||
project = "STree"
|
||||
copyright = "2020 - 2021, Ricardo Montañana Gómez"
|
||||
copyright = "2020 - 2022, Ricardo Montañana Gómez"
|
||||
author = "Ricardo Montañana Gómez"
|
||||
|
||||
# The full version, including alpha/beta/rc tags
|
||||
version = stree.__version__
|
||||
version = __version__
|
||||
release = version
|
||||
|
||||
|
||||
|
||||
@@ -3,20 +3,20 @@
|
||||
| | **Hyperparameter** | **Type/Values** | **Default** | **Meaning** |
|
||||
| --- | ------------------- | -------------------------------------------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| \* | C | \<float\> | 1.0 | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. |
|
||||
| \* | kernel | {"liblinear", "linear", "poly", "rbf", "sigmoid"} | linear | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’. liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library |
|
||||
| \* | kernel | {"liblinear", "linear", "poly", "rbf", "sigmoid"} | linear | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’.<br>liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library |
|
||||
| \* | max_iter | \<int\> | 1e5 | Hard limit on iterations within solver, or -1 for no limit. |
|
||||
| \* | random_state | \<int\> | None | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls |
|
||||
| | max_depth | \<int\> | None | Specifies the maximum depth of the tree |
|
||||
| \* | tol | \<float\> | 1e-4 | Tolerance for stopping criterion. |
|
||||
| \* | degree | \<int\> | 3 | Degree of the polynomial kernel function (‘poly’). Ignored by all other kernels. |
|
||||
| \* | gamma | {"scale", "auto"} or \<float\> | scale | Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’.<br>if gamma='scale' (default) is passed then it uses 1 / (n_features \* X.var()) as value of gamma,<br>if ‘auto’, uses 1 / n_features. |
|
||||
| | split_criteria | {"impurity", "max_samples"} | impurity | Decides (just in case of a multi class classification) which column (class) use to split the dataset in a node\*\*. 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. |
|
||||
| | split_criteria | {"impurity", "max_samples"} | impurity | Decides (just in case of a multi class classification) which column (class) use to split the dataset in a node\*\*.<br>max_samples is incompatible with 'ovo' multiclass_strategy |
|
||||
| | criterion | {“gini”, “entropy”} | entropy | The function to measure the quality of a split (only used if max_features != num_features).<br>Supported criteria are “gini” for the Gini impurity and “entropy” for the information gain. |
|
||||
| | min_samples_split | \<int\> | 0 | The minimum number of samples required to split an internal node. 0 (default) for any |
|
||||
| | max_features | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. |
|
||||
| | splitter | {"best", "random", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random" | The strategy used to choose the feature set at each node (only used if max_features < num_features). 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 |
|
||||
| | splitter | {"best", "random", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random" | The strategy used to choose the feature set at each node (only used if max_features < num_features).<br>Supported strategies are:<br>**“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features.<br>**“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them.<br>**“trandom”**: The algorithm generates only one random combination.<br>**"mutual"**: Chooses the best features w.r.t. their mutual info with the label.<br>**"cfs"**: Apply Correlation-based Feature Selection.<br>**"fcbf"**: Apply Fast Correlation-Based Filter.<br>**"iwss"**: IWSS based algorithm |
|
||||
| | normalize | \<bool\> | False | If standardization of features should be applied on each node with the samples that reach it |
|
||||
| \* | multiclass_strategy | {"ovo", "ovr"} | "ovo" | Strategy to use with multiclass datasets, **"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
|
||||
|
||||
|
||||
@@ -133,33 +133,33 @@
|
||||
" '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",
|
||||
" '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",
|
||||
" '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",
|
||||
" '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",
|
||||
" '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",
|
||||
" '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",
|
||||
"}]"
|
||||
]
|
||||
},
|
||||
@@ -214,7 +214,7 @@
|
||||
" 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}"
|
||||
"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}"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
12
setup.py
12
setup.py
@@ -7,9 +7,8 @@ def readme():
|
||||
return f.read()
|
||||
|
||||
|
||||
def get_data(field):
|
||||
def get_data(field, file_name="__init__.py"):
|
||||
item = ""
|
||||
file_name = "_version.py" if field == "version" else "__init__.py"
|
||||
with open(os.path.join("stree", file_name)) as f:
|
||||
for line in f.readlines():
|
||||
if line.startswith(f"__{field}__"):
|
||||
@@ -21,9 +20,14 @@ def get_data(field):
|
||||
return item
|
||||
|
||||
|
||||
def get_requirements():
|
||||
with open("requirements.txt") as f:
|
||||
return f.read().splitlines()
|
||||
|
||||
|
||||
setuptools.setup(
|
||||
name="STree",
|
||||
version=get_data("version"),
|
||||
version=get_data("version", "_version.py"),
|
||||
license=get_data("license"),
|
||||
description="Oblique decision tree with svm nodes",
|
||||
long_description=readme(),
|
||||
@@ -46,7 +50,7 @@ setuptools.setup(
|
||||
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
||||
"Intended Audience :: Science/Research",
|
||||
],
|
||||
install_requires=["scikit-learn", "mufs"],
|
||||
install_requires=get_requirements(),
|
||||
test_suite="stree.tests",
|
||||
zip_safe=False,
|
||||
)
|
||||
|
||||
@@ -139,7 +139,7 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
self,
|
||||
C: float = 1.0,
|
||||
kernel: str = "linear",
|
||||
max_iter: int = 1e5,
|
||||
max_iter: int = int(1e5),
|
||||
random_state: int = None,
|
||||
max_depth: int = None,
|
||||
tol: float = 1e-4,
|
||||
@@ -368,6 +368,21 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
)
|
||||
|
||||
def __predict_class(self, X: np.array) -> np.array:
|
||||
"""Compute the predicted class for the samples in X. Returns the number
|
||||
of samples of each class in the corresponding leaf node.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
X : np.array
|
||||
Array of samples
|
||||
|
||||
Returns
|
||||
-------
|
||||
np.array
|
||||
Array of shape (n_samples, n_classes) with the number of samples
|
||||
of each class in the corresponding leaf node
|
||||
"""
|
||||
|
||||
def compute_prediction(xp, indices, node):
|
||||
if xp is None:
|
||||
return
|
||||
@@ -388,6 +403,25 @@ class Stree(BaseEstimator, ClassifierMixin):
|
||||
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)
|
||||
|
||||
@@ -1 +1 @@
|
||||
__version__ = "1.2.4"
|
||||
__version__ = "1.3.1"
|
||||
|
||||
@@ -306,7 +306,7 @@ class Stree_test(unittest.TestCase):
|
||||
for criteria in ["max_samples", "impurity"]:
|
||||
for kernel in self._kernels:
|
||||
clf = Stree(
|
||||
max_iter=1e4,
|
||||
max_iter=int(1e4),
|
||||
multiclass_strategy="ovr"
|
||||
if kernel == "liblinear"
|
||||
else "ovo",
|
||||
|
||||
Reference in New Issue
Block a user