import abess
import numpy as np

np.random.seed(1)
data = abess.make_glm_data(n=10000, p=5, k=3, family="gamma")

model1 = abess.GammaRegression(support_size = 3, approximate_Newton = False)
model1.fit(data.x, data.y)

model2 = abess.GammaRegression(support_size = 3, approximate_Newton = True)
model2.fit(data.x, data.y)

print("true_coef: ",data.coef_)
print("approx newton est_coef: ",model2.coef_)
print("exact newton est_coef: ",model1.coef_)

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_validate
from geomstats.geometry.hypersphere import Hypersphere
from abess import LogisticRegression

sphere = Hypersphere(dim=9)
labels = np.concatenate((np.zeros(1000),np.ones(1000)))
data0 = sphere.random_riemannian_normal(mean=np.array([1/3,0,2/3,0,2/3,0,0  ,0,0  ,0]), n_samples=1000, precision=5)
data1 = sphere.random_riemannian_normal(mean=np.array([0  ,0,0  ,0,2/3,0,2/3,0,1/3,0]), n_samples=1000, precision=5)
data = np.concatenate((data0,data1))
train_data, test_data, train_labels, test_labels = train_test_split(data, labels, test_size=0.33, random_state=0)
result = cross_validate(LogisticRegression(support_size=range(0, 11)), train_data, train_labels)
print(result)

{'fit_time': array([0.01018214, 0.0107348 , 0.00791812, 0.00899959, 0.00998664]), 'score_time': array([0.0010004, 0.       , 0.0010004, 0.       , 0.       ]), 'test_score': array([-96.61424923, -94.28383166, -91.52310614, -95.26857002,
       -87.02766473])}

from abess.linear import abessLogistic
from sklearn.datasets import load_breast_cancer
from sklearn.pipeline import Pipeline
from sklearn.metrics import make_scorer, roc_auc_score
from sklearn.preprocessing import PolynomialFeatures
from sklearn.model_selection import GridSearchCV
# combine feature transform and model:
pipe = Pipeline([('poly', PolynomialFeatures(include_bias=False)), ('alogistic', abessLogistic())])
param_grid = {'poly_interaction_only': [True, False],'poly_degree': [1, 2, 3]}
# Use cross validation to tune parameters:
scorer = make_scorer(roc_auc_score, greater_is_better=True)
grid_search = GridSearchCV(pipe, param_grid, scoring=scorer, cv=5)
# load and fitting example dataset:
X, y = load_breast_cancer(return_X_y=True)
grid_search.fit(X, y)
# print the best tuning parameter and associated AUC score:
print([grid_search.best_params_, grid_search.best_score_])

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/var/folders/pj/c4q3qfkx2119wyj2vbfr_yhr0000gn/T/ipykernel_28894/2314297278.py in <module>
     13 # load and fitting example dataset:
     14 X, y = load_breast_cancer(return_X_y=True)
---> 15 grid_search.fit(X, y)
     16 # print the best tuning parameter and associated AUC score:
     17 print([grid_search.best_params_, grid_search.best_score_])

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
     61             extra_args = len(args) - len(all_args)
     62             if extra_args <= 0:
---> 63                 return f(*args, **kwargs)
     64 
     65             # extra_args > 0

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
    839                 return results
    840 
--> 841             self._run_search(evaluate_candidates)
    842 
    843             # multimetric is determined here because in the case of a callable

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/model_selection/_search.py in _run_search(self, evaluate_candidates)
   1294     def _run_search(self, evaluate_candidates):
   1295         """Search all candidates in param_grid"""
-> 1296         evaluate_candidates(ParameterGrid(self.param_grid))
   1297 
   1298 

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/model_selection/_search.py in evaluate_candidates(candidate_params, cv, more_results)
    793                               n_splits, n_candidates, n_candidates * n_splits))
    794 
--> 795                 out = parallel(delayed(_fit_and_score)(clone(base_estimator),
    796                                                        X, y,
    797                                                        train=train, test=test,

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in __call__(self, iterable)
   1041             # remaining jobs.
   1042             self._iterating = False
-> 1043             if self.dispatch_one_batch(iterator):
   1044                 self._iterating = self._original_iterator is not None
   1045 

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
    859                 return False
    860             else:
--> 861                 self._dispatch(tasks)
    862                 return True
    863 

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in _dispatch(self, batch)
    777         with self._lock:
    778             job_idx = len(self._jobs)
--> 779             job = self._backend.apply_async(batch, callback=cb)
    780             # A job can complete so quickly than its callback is
    781             # called before we get here, causing self._jobs to

~/opt/anaconda3/lib/python3.9/site-packages/joblib/_parallel_backends.py in apply_async(self, func, callback)
    206     def apply_async(self, func, callback=None):
    207         """Schedule a func to be run"""
--> 208         result = ImmediateResult(func)
    209         if callback:
    210             callback(result)

~/opt/anaconda3/lib/python3.9/site-packages/joblib/_parallel_backends.py in __init__(self, batch)
    570         # Don't delay the application, to avoid keeping the input
    571         # arguments in memory
--> 572         self.results = batch()
    573 
    574     def get(self):

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in __call__(self)
    260         # change the default number of processes to -1
    261         with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262             return [func(*args, **kwargs)
    263                     for func, args, kwargs in self.items]
    264 

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in <listcomp>(.0)
    260         # change the default number of processes to -1
    261         with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262             return [func(*args, **kwargs)
    263                     for func, args, kwargs in self.items]
    264 

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/utils/fixes.py in __call__(self, *args, **kwargs)
    220     def __call__(self, *args, **kwargs):
    221         with config_context(**self.config):
--> 222             return self.function(*args, **kwargs)

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, split_progress, candidate_progress, error_score)
    584             cloned_parameters[k] = clone(v, safe=False)
    585 
--> 586         estimator = estimator.set_params(**cloned_parameters)
    587 
    588     start_time = time.time()

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/pipeline.py in set_params(self, **kwargs)
    148         self
    149         """
--> 150         self._set_params('steps', **kwargs)
    151         return self
    152 

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/utils/metaestimators.py in _set_params(self, attr, **params)
     52                 self._replace_estimator(attr, name, params.pop(name))
     53         # 3. Step parameters and other initialisation arguments
---> 54         super().set_params(**params)
     55         return self
     56 

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/base.py in set_params(self, **params)
    228             key, delim, sub_key = key.partition('__')
    229             if key not in valid_params:
--> 230                 raise ValueError('Invalid parameter %s for estimator %s. '
    231                                  'Check the list of available parameters '
    232                                  'with `estimator.get_params().keys()`.' %

ValueError: Invalid parameter poly_degree for estimator Pipeline(steps=[('poly', PolynomialFeatures(include_bias=False)),
                ('alogistic', abessLogistic())]). Check the list of available parameters with `estimator.get_params().keys()`.
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/var/folders/pj/c4q3qfkx2119wyj2vbfr_yhr0000gn/T/ipykernel_28894/2314297278.py in <module>
     13 # load and fitting example dataset:
     14 X, y = load_breast_cancer(return_X_y=True)
---> 15 grid_search.fit(X, y)
     16 # print the best tuning parameter and associated AUC score:
     17 print([grid_search.best_params_, grid_search.best_score_])

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
     61             extra_args = len(args) - len(all_args)
     62             if extra_args <= 0:
---> 63                 return f(*args, **kwargs)
     64 
     65             # extra_args > 0

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
    839                 return results
    840 
--> 841             self._run_search(evaluate_candidates)
    842 
    843             # multimetric is determined here because in the case of a callable

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/model_selection/_search.py in _run_search(self, evaluate_candidates)
   1294     def _run_search(self, evaluate_candidates):
   1295         """Search all candidates in param_grid"""
-> 1296         evaluate_candidates(ParameterGrid(self.param_grid))
   1297 
   1298 

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/model_selection/_search.py in evaluate_candidates(candidate_params, cv, more_results)
    793                               n_splits, n_candidates, n_candidates * n_splits))
    794 
--> 795                 out = parallel(delayed(_fit_and_score)(clone(base_estimator),
    796                                                        X, y,
    797                                                        train=train, test=test,

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in __call__(self, iterable)
   1041             # remaining jobs.
   1042             self._iterating = False
-> 1043             if self.dispatch_one_batch(iterator):
   1044                 self._iterating = self._original_iterator is not None
   1045 

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
    859                 return False
    860             else:
--> 861                 self._dispatch(tasks)
    862                 return True
    863 

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in _dispatch(self, batch)
    777         with self._lock:
    778             job_idx = len(self._jobs)
--> 779             job = self._backend.apply_async(batch, callback=cb)
    780             # A job can complete so quickly than its callback is
    781             # called before we get here, causing self._jobs to

~/opt/anaconda3/lib/python3.9/site-packages/joblib/_parallel_backends.py in apply_async(self, func, callback)
    206     def apply_async(self, func, callback=None):
    207         """Schedule a func to be run"""
--> 208         result = ImmediateResult(func)
    209         if callback:
    210             callback(result)

~/opt/anaconda3/lib/python3.9/site-packages/joblib/_parallel_backends.py in __init__(self, batch)
    570         # Don't delay the application, to avoid keeping the input
    571         # arguments in memory
--> 572         self.results = batch()
    573 
    574     def get(self):

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in __call__(self)
    260         # change the default number of processes to -1
    261         with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262             return [func(*args, **kwargs)
    263                     for func, args, kwargs in self.items]
    264 

~/opt/anaconda3/lib/python3.9/site-packages/joblib/parallel.py in <listcomp>(.0)
    260         # change the default number of processes to -1
    261         with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262             return [func(*args, **kwargs)
    263                     for func, args, kwargs in self.items]
    264 

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/utils/fixes.py in __call__(self, *args, **kwargs)
    220     def __call__(self, *args, **kwargs):
    221         with config_context(**self.config):
--> 222             return self.function(*args, **kwargs)

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, split_progress, candidate_progress, error_score)
    584             cloned_parameters[k] = clone(v, safe=False)
    585 
--> 586         estimator = estimator.set_params(**cloned_parameters)
    587 
    588     start_time = time.time()

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/pipeline.py in set_params(self, **kwargs)
    148         self
    149         """
--> 150         self._set_params('steps', **kwargs)
    151         return self
    152 

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/utils/metaestimators.py in _set_params(self, attr, **params)
     52                 self._replace_estimator(attr, name, params.pop(name))
     53         # 3. Step parameters and other initialisation arguments
---> 54         super().set_params(**params)
     55         return self
     56 

~/opt/anaconda3/lib/python3.9/site-packages/sklearn/base.py in set_params(self, **params)
    228             key, delim, sub_key = key.partition('__')
    229             if key not in valid_params:
--> 230                 raise ValueError('Invalid parameter %s for estimator %s. '
    231                                  'Check the list of available parameters '
    232                                  'with `estimator.get_params().keys()`.' %

ValueError: Invalid parameter poly_degree for estimator Pipeline(steps=[('poly', PolynomialFeatures(include_bias=False)),
                ('alogistic', abessLogistic())]). Check the list of available parameters with `estimator.get_params().keys()`.

import numpy as np
from abess.linear import MultinomialRegression
from abess.datasets import make_multivariate_glm_data

n, p = 100, 50
np.random.seed(12345)
data = make_multivariate_glm_data(n=n, p=p, k=10, M=3, family='multinomial')

# construct dataset1 with 100 samples
X1, y1 = data.x, data.y
w1 = np.ones(n)
model1 = MultinomialRegression(support_size=10)
model1.fit(X1, y1, weight=w1)
coef1 = model1.coef_

# construct dataset2 by adding 100 different samples to dataset1
# simultaneously set weight to 0 for these additional 100 samples
X2 = np.vstack([data.x, -data.x])
y2 = np.vstack([data.y, data.y])
w2 = np.ones(n * 2)
w2[n:] = 0
model2 = MultinomialRegression(support_size=10)
model2.fit(X2, y2, weight=w2)
coef2 = model2.coef_

Python 3.9.7 (default, Sep 16 2021, 08:50:36) 
[Clang 10.0.0 ] :: Anaconda, Inc. on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> from abess.linear import abessLogistic
>>> from sklearn.datasets import load_breast_cancer
>>> from sklearn.pipeline import Pipeline
>>> from sklearn.metrics import make_scorer, roc_auc_score
>>> from sklearn.preprocessing import PolynomialFeatures
>>> from sklearn.model_selection import GridSearchCV
>>> pipe = Pipeline([('poly', PolynomialFeatures(include_bias=False)), ('alogistic', abessLogistic())])
>>> param_grid = {'poly__interaction_only': [True, False],'poly__degree': [1, 2, 3]}
>>> scorer = make_scorer(roc_auc_score, greater_is_better=True)
>>> grid_search = GridSearchCV(pipe, param_grid, scoring=scorer, cv=5)
>>> X, y = load_breast_cancer(return_X_y=True)
>>> grid_search.fit(X, y)

elif family == "gamma":
            x = x / 16
            m = 5 * np.sqrt(2 * np.log(p) / n)
            if coef_ is None:
                Tbeta[nonzero] = np.random.uniform(m, 100 * m, k) * sign
            else:
                Tbeta = coef_
            # add noise
            eta = x @ Tbeta + np.random.normal(0, sigma, n)
            # set coef_0 to make eta<0
            eta = eta - np.abs(np.max(eta)) - 10
            eta = -1 / eta
            # set the shape para of gamma uniformly in [0.1,100.1]
            shape_para = 100 * np.random.uniform(0, 1, n) + 0.1
            y = np.random.gamma(
                shape=shape_para,
                scale=eta / shape_para,
                size=n)

Platform Version: Windows-10-10.0.22000-SP0, 64bit
Python Version: 3.7.4
'CPU info:  Intel64 Family 6 Model 85 Stepping 4, GenuineIntel'
Package Version: 0.4.0

model = abess.LinearRegression()
model.fit(np.random.rand(2,2), np.random.rand(2))

from pprint import pprint

from ConfigSpace.configuration_space import ConfigurationSpace
from ConfigSpace.hyperparameters import CategoricalHyperparameter, \
    UniformIntegerHyperparameter, UniformFloatHyperparameter

import sklearn.metrics
import autosklearn.classification
import autosklearn.pipeline.components.classification
from autosklearn.pipeline.components.base \
    import AutoSklearnClassificationAlgorithm
from autosklearn.pipeline.constants import DENSE, SIGNED_DATA, UNSIGNED_DATA, \
    PREDICTIONS

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
import openml
from abess import MultinomialRegression
from sklearn.ensemble import RandomForestClassifier
import numpy as np
import pandas as pd
from sklearn.datasets import fetch_openml
from sklearn import preprocessing
from sklearn.tree import DecisionTreeClassifier

import time
import matplotlib.pyplot as plt

import warnings
warnings.filterwarnings("ignore")

class AbessClassifier(AutoSklearnClassificationAlgorithm):

    def __init__(self, exchange_num, random_state=None):
        self.exchange_num = exchange_num
        self.random_state = random_state
        self.estimator = None

    def fit(self, X, y):
        from abess import MultinomialRegression
        self.estimator = MultinomialRegression()
        self.estimator.fit(X, y)
        return self

    def predict(self, X):
        if self.estimator is None:
            raise NotImplementedError
        return self.estimator.predict(X)
    
    def predict_proba(self, X):
        if self.estimator is None:
            raise NotImplementedError()
        return self.estimator.predict_proba(X)

    @staticmethod
    def get_properties(dataset_properties=None):
        return {
            'shortname': 'abess Classifier',
            'name': 'abess logistic Classifier',
            'handles_regression': False,
            'handles_classification': True,
            'handles_multiclass': True,
            'handles_multilabel': False,
            'handles_multioutput': False,
            'is_deterministic': False,
            # Both input and output must be tuple(iterable)
            'input': [DENSE, SIGNED_DATA, UNSIGNED_DATA],
            'output': [PREDICTIONS]
        }
    
    @staticmethod
    def get_hyperparameter_search_space(dataset_properties=None):
        cs = ConfigurationSpace() 
        exchange_num=UniformIntegerHyperparameter(
            name='exchange_num', lower=4, upper=6, default_value=5
        )
        cs.add_hyperparameters([exchange_num])
        return cs
    
# Add abess logistic classifier component to auto-sklearn.
autosklearn.pipeline.components.classification.add_classifier(AbessClassifier)
cs = AbessClassifier.get_hyperparameter_search_space()
print(cs)

dataset = fetch_openml(data_id = int(29),as_frame=True)#507,183,44136
X=dataset.data
y=dataset.target
X.replace([np.inf,-np.inf],np.NaN,inplace=True)
## Remove rows with NaN or Inf values
inx=X[X.isna().values==True].index.unique()
X.drop(inx,inplace=True)
y.drop(inx,inplace=True)
##use dummy variables to replace classification variables:
X = pd.get_dummies(X)
## Keep only numeric columns
X = X.select_dtypes(np.number)
## Remove columns with NaN or Inf values
nan = np.isnan(X).any()[np.isnan(X).any() == True]
inf = np.isinf(X).any()[np.isinf(X).any() == True]
X = X.drop(columns = list(nan.index))
X = X.drop(columns = list(inf.index))
##Encode target labels with value between 0 and 1
le = preprocessing.LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y)
print(X_train.shape) #number of initial features
print(X_test.shape) #number of initial features

cls = autosklearn.classification.AutoSklearnClassifier(
    time_left_for_this_task=60,
    per_run_time_limit=10,
    include={
            'classifier': ['AbessClassifier'],
            'feature_preprocessor': ['polynomial']
        },
    memory_limit=6144,
    ensemble_size=1,
)
cls.fit(X_train, y_train, X_test, y_test)
predictions = cls.predict(X_test)
print("Accuracy score", sklearn.metrics.accuracy_score(y_test, predictions))

# %%
from sklearn.model_selection import cross_validate
from abess import OrdinalRegression, make_glm_data
import numpy as np

np.random.seed(0)
data = make_glm_data(n=1000, p=200, k=30, family='ordinal')
model = OrdinalRegression()
result = cross_validate(model, data.x ,data.y)

from doubleml import DoubleMLData
from sklearn.base import clone
from abess.linear import LinearRegression    
n_obs = 500
n_vars = 100
theta = 3
X = np.random.normal(size=(n_obs, n_vars))
d = np.dot(X[:, :3], np.array([5, 5, 5])) + np.random.standard_normal(size=(n_obs,))
y = theta * d + np.dot(X[:, :3], np.array([5, 5, 5])) + np.random.standard_normal(size=(n_obs,))
dml_data_sim = DoubleMLData.from_arrays(X, y, d)
abess = LinearRegression(cv = 5)
ml_g_abess = clone(abess)
ml_m_abess = clone(abess)
ml_plr_abess = DoubleMLPLR(dml_data_sim, ml_g_abess, ml_m_abess)
dml_plr_abess.fit(); 

from abess.linear import LinearRegression
from abess.datasets import make_glm_data
import numpy as np
np.random.seed(12345)
data = make_glm_data(n = 100, p = 50, k = 10, family = 'gaussian')
model = LinearRegression(support_size = 10)
model.fit(data.x, data.y)

print(model.predict(data.x)[:4])