diff options
Diffstat (limited to 'python-hpsklearn.spec')
| -rw-r--r-- | python-hpsklearn.spec | 780 |
1 files changed, 780 insertions, 0 deletions
diff --git a/python-hpsklearn.spec b/python-hpsklearn.spec new file mode 100644 index 0000000..2eb8cda --- /dev/null +++ b/python-hpsklearn.spec @@ -0,0 +1,780 @@ +%global _empty_manifest_terminate_build 0 +Name: python-hpsklearn +Version: 0.1.0 +Release: 1 +Summary: Hyperparameter Optimization for sklearn +License: BSD +URL: http://hyperopt.github.com/hyperopt-sklearn/ +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/ce/cb/61b99f73621e2692abd0e730f7888a9983d01f626868336fa1db1d57bc1e/hpsklearn-0.1.0.tar.gz +BuildArch: noarch + + +%description +# hyperopt-sklearn + +[Hyperopt-sklearn](http://hyperopt.github.com/hyperopt-sklearn/) is +[Hyperopt](http://hyperopt.github.com/hyperopt)-based model selection among machine learning algorithms in +[scikit-learn](http://scikit-learn.org/). + +See how to use hyperopt-sklearn through [examples](http://hyperopt.github.io/hyperopt-sklearn/#documentation) +or older +[notebooks](http://nbviewer.ipython.org/github/hyperopt/hyperopt-sklearn/tree/master/notebooks) + + +## Installation + +Installation from a git clone using pip is supported: + + git clone git@github.com:hyperopt/hyperopt-sklearn.git + (cd hyperopt-sklearn && pip install -e .) + +## Usage + +If you are familiar with sklearn, adding the hyperparameter search with hyperopt-sklearn is only a one line change from the standard pipeline. + +``` +from hpsklearn import HyperoptEstimator, svc +from sklearn import svm + +# Load Data +# ... + +if use_hpsklearn: + estim = HyperoptEstimator(classifier=svc('mySVC')) +else: + estim = svm.SVC() + +estim.fit(X_train, y_train) + +print(estim.score(X_test, y_test)) +# <<show score here>> +``` + +Complete example using the Iris dataset: + +``` +from hpsklearn import HyperoptEstimator, any_classifier +from sklearn.datasets import load_iris +from hyperopt import tpe +import numpy as np + +# Download the data and split into training and test sets + +iris = load_iris() + +X = iris.data +y = iris.target + +test_size = int(0.2 * len(y)) +np.random.seed(13) +indices = np.random.permutation(len(X)) +X_train = X[ indices[:-test_size]] +y_train = y[ indices[:-test_size]] +X_test = X[ indices[-test_size:]] +y_test = y[ indices[-test_size:]] + +# Instantiate a HyperoptEstimator with the search space and number of evaluations + +estim = HyperoptEstimator(classifier=any_classifier('my_clf'), + preprocessing=any_preprocessing('my_pre'), + algo=tpe.suggest, + max_evals=100, + trial_timeout=120) + +# Search the hyperparameter space based on the data + +estim.fit( X_train, y_train ) + +# Show the results + +print( estim.score( X_test, y_test ) ) +# 1.0 + +print( estim.best_model() ) +# {'learner': ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini', +# max_depth=3, max_features='log2', max_leaf_nodes=None, +# min_impurity_decrease=0.0, min_impurity_split=None, +# min_samples_leaf=1, min_samples_split=2, +# min_weight_fraction_leaf=0.0, n_estimators=13, n_jobs=1, +# oob_score=False, random_state=1, verbose=False, +# warm_start=False), 'preprocs': (), 'ex_preprocs': ()} +``` + +Here's an example using MNIST and being more specific on the classifier and preprocessing. + +``` +from hpsklearn import HyperoptEstimator, extra_trees +from sklearn.datasets import fetch_mldata +from hyperopt import tpe +import numpy as np + +# Download the data and split into training and test sets + +digits = fetch_mldata('MNIST original') + +X = digits.data +y = digits.target + +test_size = int(0.2 * len(y)) +np.random.seed(13) +indices = np.random.permutation(len(X)) +X_train = X[ indices[:-test_size]] +y_train = y[ indices[:-test_size]] +X_test = X[ indices[-test_size:]] +y_test = y[ indices[-test_size:]] + +# Instantiate a HyperoptEstimator with the search space and number of evaluations + +estim = HyperoptEstimator(classifier=extra_trees('my_clf'), + preprocessing=[], + algo=tpe.suggest, + max_evals=10, + trial_timeout=300) + +# Search the hyperparameter space based on the data + +estim.fit( X_train, y_train ) + +# Show the results + +print( estim.score( X_test, y_test ) ) +# 0.962785714286 + +print( estim.best_model() ) +# {'learner': ExtraTreesClassifier(bootstrap=True, class_weight=None, criterion='entropy', +# max_depth=None, max_features=0.959202875857, +# max_leaf_nodes=None, min_impurity_decrease=0.0, +# min_impurity_split=None, min_samples_leaf=1, +# min_samples_split=2, min_weight_fraction_leaf=0.0, +# n_estimators=20, n_jobs=1, oob_score=False, random_state=3, +# verbose=False, warm_start=False), 'preprocs': (), 'ex_preprocs': ()} +``` + +## Available Components + +Not all of the classifiers/regressors/preprocessing from sklearn have been implemented yet. +A list of those currently available is shown below. +If there is something you would like that is not on the list, feel free to make an issue or a pull request! +The source code for implementing these functions is found [here](https://github.com/hyperopt/hyperopt-sklearn/blob/master/hpsklearn/components.py) + +### Classifiers + +``` +svc +svc_linear +svc_rbf +svc_poly +svc_sigmoid +liblinear_svc + +knn + +ada_boost +gradient_boosting + +random_forest +extra_trees +decision_tree + +sgd + +xgboost_classification + +multinomial_nb +gaussian_nb + +passive_aggressive + +linear_discriminant_analysis +quadratic_discriminant_analysis + +rbm + +colkmeans + +one_vs_rest +one_vs_one +output_code + +``` + +For a simple generic search space across many classifiers, use `any_classifier`. If your data is in a sparse matrix format, use `any_sparse_classifier`. + +### Regressors + +``` +svr +svr_linear +svr_rbf +svr_poly +svr_sigmoid + +knn_regression + +ada_boost_regression +gradient_boosting_regression + +random_forest_regression +extra_trees_regression + +sgd_regression + +xgboost_regression +``` + +For a simple generic search space across many regressors, use `any_regressor`. If your data is in a sparse matrix format, use `any_sparse_regressor`. + +### Preprocessing + +``` +pca + +one_hot_encoder + +standard_scaler +min_max_scaler +normalizer + +ts_lagselector + +tfidf + +``` + +For a simple generic search space across many preprocessing algorithms, use `any_preprocessing`. +If you are working with raw text data, use `any_text_preprocessing`. +Currently only TFIDF is used for text, but more may be added in the future. +Note that the `preprocessing` parameter in `HyperoptEstimator` is expecting a list, since various preprocessing steps can be chained together. +The generic search space functions `any_preprocessing` and `any_text_preprocessing` already return a list, but the others do not so they should be wrapped in a list. +If you do not want to do any preprocessing, pass in an empty list `[]`. + +%package -n python3-hpsklearn +Summary: Hyperparameter Optimization for sklearn +Provides: python-hpsklearn +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-hpsklearn +# hyperopt-sklearn + +[Hyperopt-sklearn](http://hyperopt.github.com/hyperopt-sklearn/) is +[Hyperopt](http://hyperopt.github.com/hyperopt)-based model selection among machine learning algorithms in +[scikit-learn](http://scikit-learn.org/). + +See how to use hyperopt-sklearn through [examples](http://hyperopt.github.io/hyperopt-sklearn/#documentation) +or older +[notebooks](http://nbviewer.ipython.org/github/hyperopt/hyperopt-sklearn/tree/master/notebooks) + + +## Installation + +Installation from a git clone using pip is supported: + + git clone git@github.com:hyperopt/hyperopt-sklearn.git + (cd hyperopt-sklearn && pip install -e .) + +## Usage + +If you are familiar with sklearn, adding the hyperparameter search with hyperopt-sklearn is only a one line change from the standard pipeline. + +``` +from hpsklearn import HyperoptEstimator, svc +from sklearn import svm + +# Load Data +# ... + +if use_hpsklearn: + estim = HyperoptEstimator(classifier=svc('mySVC')) +else: + estim = svm.SVC() + +estim.fit(X_train, y_train) + +print(estim.score(X_test, y_test)) +# <<show score here>> +``` + +Complete example using the Iris dataset: + +``` +from hpsklearn import HyperoptEstimator, any_classifier +from sklearn.datasets import load_iris +from hyperopt import tpe +import numpy as np + +# Download the data and split into training and test sets + +iris = load_iris() + +X = iris.data +y = iris.target + +test_size = int(0.2 * len(y)) +np.random.seed(13) +indices = np.random.permutation(len(X)) +X_train = X[ indices[:-test_size]] +y_train = y[ indices[:-test_size]] +X_test = X[ indices[-test_size:]] +y_test = y[ indices[-test_size:]] + +# Instantiate a HyperoptEstimator with the search space and number of evaluations + +estim = HyperoptEstimator(classifier=any_classifier('my_clf'), + preprocessing=any_preprocessing('my_pre'), + algo=tpe.suggest, + max_evals=100, + trial_timeout=120) + +# Search the hyperparameter space based on the data + +estim.fit( X_train, y_train ) + +# Show the results + +print( estim.score( X_test, y_test ) ) +# 1.0 + +print( estim.best_model() ) +# {'learner': ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini', +# max_depth=3, max_features='log2', max_leaf_nodes=None, +# min_impurity_decrease=0.0, min_impurity_split=None, +# min_samples_leaf=1, min_samples_split=2, +# min_weight_fraction_leaf=0.0, n_estimators=13, n_jobs=1, +# oob_score=False, random_state=1, verbose=False, +# warm_start=False), 'preprocs': (), 'ex_preprocs': ()} +``` + +Here's an example using MNIST and being more specific on the classifier and preprocessing. + +``` +from hpsklearn import HyperoptEstimator, extra_trees +from sklearn.datasets import fetch_mldata +from hyperopt import tpe +import numpy as np + +# Download the data and split into training and test sets + +digits = fetch_mldata('MNIST original') + +X = digits.data +y = digits.target + +test_size = int(0.2 * len(y)) +np.random.seed(13) +indices = np.random.permutation(len(X)) +X_train = X[ indices[:-test_size]] +y_train = y[ indices[:-test_size]] +X_test = X[ indices[-test_size:]] +y_test = y[ indices[-test_size:]] + +# Instantiate a HyperoptEstimator with the search space and number of evaluations + +estim = HyperoptEstimator(classifier=extra_trees('my_clf'), + preprocessing=[], + algo=tpe.suggest, + max_evals=10, + trial_timeout=300) + +# Search the hyperparameter space based on the data + +estim.fit( X_train, y_train ) + +# Show the results + +print( estim.score( X_test, y_test ) ) +# 0.962785714286 + +print( estim.best_model() ) +# {'learner': ExtraTreesClassifier(bootstrap=True, class_weight=None, criterion='entropy', +# max_depth=None, max_features=0.959202875857, +# max_leaf_nodes=None, min_impurity_decrease=0.0, +# min_impurity_split=None, min_samples_leaf=1, +# min_samples_split=2, min_weight_fraction_leaf=0.0, +# n_estimators=20, n_jobs=1, oob_score=False, random_state=3, +# verbose=False, warm_start=False), 'preprocs': (), 'ex_preprocs': ()} +``` + +## Available Components + +Not all of the classifiers/regressors/preprocessing from sklearn have been implemented yet. +A list of those currently available is shown below. +If there is something you would like that is not on the list, feel free to make an issue or a pull request! +The source code for implementing these functions is found [here](https://github.com/hyperopt/hyperopt-sklearn/blob/master/hpsklearn/components.py) + +### Classifiers + +``` +svc +svc_linear +svc_rbf +svc_poly +svc_sigmoid +liblinear_svc + +knn + +ada_boost +gradient_boosting + +random_forest +extra_trees +decision_tree + +sgd + +xgboost_classification + +multinomial_nb +gaussian_nb + +passive_aggressive + +linear_discriminant_analysis +quadratic_discriminant_analysis + +rbm + +colkmeans + +one_vs_rest +one_vs_one +output_code + +``` + +For a simple generic search space across many classifiers, use `any_classifier`. If your data is in a sparse matrix format, use `any_sparse_classifier`. + +### Regressors + +``` +svr +svr_linear +svr_rbf +svr_poly +svr_sigmoid + +knn_regression + +ada_boost_regression +gradient_boosting_regression + +random_forest_regression +extra_trees_regression + +sgd_regression + +xgboost_regression +``` + +For a simple generic search space across many regressors, use `any_regressor`. If your data is in a sparse matrix format, use `any_sparse_regressor`. + +### Preprocessing + +``` +pca + +one_hot_encoder + +standard_scaler +min_max_scaler +normalizer + +ts_lagselector + +tfidf + +``` + +For a simple generic search space across many preprocessing algorithms, use `any_preprocessing`. +If you are working with raw text data, use `any_text_preprocessing`. +Currently only TFIDF is used for text, but more may be added in the future. +Note that the `preprocessing` parameter in `HyperoptEstimator` is expecting a list, since various preprocessing steps can be chained together. +The generic search space functions `any_preprocessing` and `any_text_preprocessing` already return a list, but the others do not so they should be wrapped in a list. +If you do not want to do any preprocessing, pass in an empty list `[]`. + +%package help +Summary: Development documents and examples for hpsklearn +Provides: python3-hpsklearn-doc +%description help +# hyperopt-sklearn + +[Hyperopt-sklearn](http://hyperopt.github.com/hyperopt-sklearn/) is +[Hyperopt](http://hyperopt.github.com/hyperopt)-based model selection among machine learning algorithms in +[scikit-learn](http://scikit-learn.org/). + +See how to use hyperopt-sklearn through [examples](http://hyperopt.github.io/hyperopt-sklearn/#documentation) +or older +[notebooks](http://nbviewer.ipython.org/github/hyperopt/hyperopt-sklearn/tree/master/notebooks) + + +## Installation + +Installation from a git clone using pip is supported: + + git clone git@github.com:hyperopt/hyperopt-sklearn.git + (cd hyperopt-sklearn && pip install -e .) + +## Usage + +If you are familiar with sklearn, adding the hyperparameter search with hyperopt-sklearn is only a one line change from the standard pipeline. + +``` +from hpsklearn import HyperoptEstimator, svc +from sklearn import svm + +# Load Data +# ... + +if use_hpsklearn: + estim = HyperoptEstimator(classifier=svc('mySVC')) +else: + estim = svm.SVC() + +estim.fit(X_train, y_train) + +print(estim.score(X_test, y_test)) +# <<show score here>> +``` + +Complete example using the Iris dataset: + +``` +from hpsklearn import HyperoptEstimator, any_classifier +from sklearn.datasets import load_iris +from hyperopt import tpe +import numpy as np + +# Download the data and split into training and test sets + +iris = load_iris() + +X = iris.data +y = iris.target + +test_size = int(0.2 * len(y)) +np.random.seed(13) +indices = np.random.permutation(len(X)) +X_train = X[ indices[:-test_size]] +y_train = y[ indices[:-test_size]] +X_test = X[ indices[-test_size:]] +y_test = y[ indices[-test_size:]] + +# Instantiate a HyperoptEstimator with the search space and number of evaluations + +estim = HyperoptEstimator(classifier=any_classifier('my_clf'), + preprocessing=any_preprocessing('my_pre'), + algo=tpe.suggest, + max_evals=100, + trial_timeout=120) + +# Search the hyperparameter space based on the data + +estim.fit( X_train, y_train ) + +# Show the results + +print( estim.score( X_test, y_test ) ) +# 1.0 + +print( estim.best_model() ) +# {'learner': ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini', +# max_depth=3, max_features='log2', max_leaf_nodes=None, +# min_impurity_decrease=0.0, min_impurity_split=None, +# min_samples_leaf=1, min_samples_split=2, +# min_weight_fraction_leaf=0.0, n_estimators=13, n_jobs=1, +# oob_score=False, random_state=1, verbose=False, +# warm_start=False), 'preprocs': (), 'ex_preprocs': ()} +``` + +Here's an example using MNIST and being more specific on the classifier and preprocessing. + +``` +from hpsklearn import HyperoptEstimator, extra_trees +from sklearn.datasets import fetch_mldata +from hyperopt import tpe +import numpy as np + +# Download the data and split into training and test sets + +digits = fetch_mldata('MNIST original') + +X = digits.data +y = digits.target + +test_size = int(0.2 * len(y)) +np.random.seed(13) +indices = np.random.permutation(len(X)) +X_train = X[ indices[:-test_size]] +y_train = y[ indices[:-test_size]] +X_test = X[ indices[-test_size:]] +y_test = y[ indices[-test_size:]] + +# Instantiate a HyperoptEstimator with the search space and number of evaluations + +estim = HyperoptEstimator(classifier=extra_trees('my_clf'), + preprocessing=[], + algo=tpe.suggest, + max_evals=10, + trial_timeout=300) + +# Search the hyperparameter space based on the data + +estim.fit( X_train, y_train ) + +# Show the results + +print( estim.score( X_test, y_test ) ) +# 0.962785714286 + +print( estim.best_model() ) +# {'learner': ExtraTreesClassifier(bootstrap=True, class_weight=None, criterion='entropy', +# max_depth=None, max_features=0.959202875857, +# max_leaf_nodes=None, min_impurity_decrease=0.0, +# min_impurity_split=None, min_samples_leaf=1, +# min_samples_split=2, min_weight_fraction_leaf=0.0, +# n_estimators=20, n_jobs=1, oob_score=False, random_state=3, +# verbose=False, warm_start=False), 'preprocs': (), 'ex_preprocs': ()} +``` + +## Available Components + +Not all of the classifiers/regressors/preprocessing from sklearn have been implemented yet. +A list of those currently available is shown below. +If there is something you would like that is not on the list, feel free to make an issue or a pull request! +The source code for implementing these functions is found [here](https://github.com/hyperopt/hyperopt-sklearn/blob/master/hpsklearn/components.py) + +### Classifiers + +``` +svc +svc_linear +svc_rbf +svc_poly +svc_sigmoid +liblinear_svc + +knn + +ada_boost +gradient_boosting + +random_forest +extra_trees +decision_tree + +sgd + +xgboost_classification + +multinomial_nb +gaussian_nb + +passive_aggressive + +linear_discriminant_analysis +quadratic_discriminant_analysis + +rbm + +colkmeans + +one_vs_rest +one_vs_one +output_code + +``` + +For a simple generic search space across many classifiers, use `any_classifier`. If your data is in a sparse matrix format, use `any_sparse_classifier`. + +### Regressors + +``` +svr +svr_linear +svr_rbf +svr_poly +svr_sigmoid + +knn_regression + +ada_boost_regression +gradient_boosting_regression + +random_forest_regression +extra_trees_regression + +sgd_regression + +xgboost_regression +``` + +For a simple generic search space across many regressors, use `any_regressor`. If your data is in a sparse matrix format, use `any_sparse_regressor`. + +### Preprocessing + +``` +pca + +one_hot_encoder + +standard_scaler +min_max_scaler +normalizer + +ts_lagselector + +tfidf + +``` + +For a simple generic search space across many preprocessing algorithms, use `any_preprocessing`. +If you are working with raw text data, use `any_text_preprocessing`. +Currently only TFIDF is used for text, but more may be added in the future. +Note that the `preprocessing` parameter in `HyperoptEstimator` is expecting a list, since various preprocessing steps can be chained together. +The generic search space functions `any_preprocessing` and `any_text_preprocessing` already return a list, but the others do not so they should be wrapped in a list. +If you do not want to do any preprocessing, pass in an empty list `[]`. + +%prep +%autosetup -n hpsklearn-0.1.0 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-hpsklearn -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Wed Apr 12 2023 Python_Bot <Python_Bot@openeuler.org> - 0.1.0-1 +- Package Spec generated |