def __init__(self, estimator, param_grid, scoring=None, n_jobs=None, refit=True, verbose=0, cv=None, pre_dispatch='2*n_jobs', random_state=None, error_score=np.nan, return_train_score=True, max_budget='auto', budget_on='n_samples', ratio=3, r_min='auto', aggressive_elimination=False, force_exhaust_budget=False): super().__init__(estimator, scoring=scoring, n_jobs=n_jobs, verbose=verbose, cv=cv, pre_dispatch=pre_dispatch, random_state=random_state, error_score=error_score, return_train_score=return_train_score, max_budget=max_budget, budget_on=budget_on, ratio=ratio, r_min=r_min, aggressive_elimination=aggressive_elimination, force_exhaust_budget=force_exhaust_budget) self.param_grid = param_grid _check_param_grid(self.param_grid)
def __init__(self, estimator, param_grid, *, scoring=None, n_jobs=None, iid='deprecated', refit=True, cv=None, verbose=0, pre_dispatch='2*n_jobs', error_score=np.nan, return_train_score=False, active_trainer: trainer.Trainer = None): super().__init__(estimator=estimator, param_grid=param_grid, scoring=scoring, n_jobs=n_jobs, iid=iid, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score) self.param_grid = param_grid self.__active_trainer = active_trainer _check_param_grid(param_grid)
def __init__(self, estimator, param_grid, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=None, verbose=0, pre_dispatch='2*n_jobs', error_score='raise', return_train_score=True): super(GridSearchCVfastr, self).__init__(estimator=estimator, scoring=scoring, fit_params=fit_params, n_jobs=n_jobs, iid=iid, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score) self.param_grid = param_grid _check_param_grid(param_grid)
def __init__(self, estimator, param_grid, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=None, verbose=3, pre_dispatch='2*n_jobs', error_score='raise', return_train_score="warn", logger_level='notset', parallel_backend='threading'): super(GridSearchCVMultisignal, self).__init__(estimator=estimator, scoring=scoring, fit_params=fit_params, n_jobs=n_jobs, iid=iid, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score, logger_level=logger_level, parallel_backend=parallel_backend) self.param_grid = param_grid _check_param_grid(param_grid)
def __init__(self, estimator, param_grid, *, online_train_val_split=False, scoring=None, n_jobs=None, refit=True, cv=None, verbose=0, pre_dispatch='2*n_jobs', error_score=np.nan, return_train_score=False): super().__init__(estimator=estimator, scoring=scoring, online_train_val_split=online_train_val_split, n_jobs=n_jobs, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score) self.param_grid = param_grid _check_param_grid(param_grid)
def __init__(self, estimator, param_grid, early_stopping=None, scoring=None, n_jobs=None, cv=5, refit=True, verbose=0, error_score="raise", return_train_score=False, max_iters=10, use_gpu=False): super(TuneGridSearchCV, self).__init__(estimator=estimator, early_stopping=early_stopping, scoring=scoring, n_jobs=n_jobs, cv=cv, refit=refit, error_score=error_score, return_train_score=return_train_score, max_iters=max_iters, verbose=verbose, use_gpu=use_gpu) _check_param_grid(param_grid) self.param_grid = param_grid
def __init__(self, sc, estimator, param_grid, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=3, verbose=0, pre_dispatch='2*n_jobs', error_score='raise', return_train_score=True): super(GridSearchCV, self).__init__(estimator=estimator, scoring=scoring, n_jobs=n_jobs, iid=iid, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score) self.fit_params = fit_params if fit_params is not None else {} self.sc = sc self.param_grid = param_grid self.cv_results_ = None _check_param_grid(param_grid)
def __init__( self, estimator, param_grid, *, scoring=None, n_jobs=None, refit=True, cv=None, verbose=0, pre_dispatch="2*n_jobs", error_score=np.nan, return_train_score=False, ): super().__init__( estimator=estimator, scoring=scoring, n_jobs=n_jobs, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score, ) self.param_grid = param2grid(param_grid) _check_param_grid(param_grid)
def __init__( self, param_grid="tiny", scoring=None, iid=True, cv=None, refit=True, verbose=0, return_train_score=True, ): self.param_grid = param_grid if isinstance(self.param_grid, str): if self.param_grid == "tiny": self.param_grid = load_grid_tiny() elif self.param_grid == "small": self.param_grid = load_grid_small() elif self.param_grid == "full": self.param_grid = load_grid_full() else: raise ValueError("Unknown param grid %r" % self.param_grid) _check_param_grid(self.param_grid) _validate_param_grid(self.param_grid) self.scoring = scoring self.cv = 5 if cv is None else cv if isinstance(self.cv, ShuffleSplit) or isinstance( self.cv, StratifiedShuffleSplit): raise ValueError( "ShuffleSplit and StratifiedShuffleSplit are not supported at the moment. Please see the documentation for more info" ) self.refit = refit self.verbose = verbose self.return_train_score = return_train_score self.iid = iid
def __init__( self, estimator, param_grid, scheduler=None, scoring=None, n_jobs=None, cv=5, refit=True, verbose=0, error_score='raise', return_train_score=False, early_stopping=False, iters=1, ): super(TuneGridSearchCV, self).__init__( estimator=estimator, scheduler=scheduler, scoring=scoring, n_jobs=n_jobs, cv=cv, refit=refit, error_score=error_score, return_train_score=return_train_score, early_stopping=early_stopping, iters=iters, ) _check_param_grid(param_grid) self.param_grid = param_grid
def __init__( self, forecaster, cv, param_grid, scoring=None, n_jobs=None, refit=True, verbose=0, pre_dispatch="2*n_jobs", error_score=np.nan, return_train_score=False, ): super(ForecastingGridSearchCV, self).__init__( forecaster=forecaster, scoring=scoring, n_jobs=n_jobs, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score, ) self.param_grid = param_grid _check_param_grid(param_grid)
def __init__(self, estimator, param_grid, scoring=None, iid=True, refit=True, cv=None, error_score='raise', return_train_score=True, scheduler=None, n_jobs=-1, cache_cv=True): super(GridSearchCV, self).__init__(estimator=estimator, scoring=scoring, iid=iid, refit=refit, cv=cv, error_score=error_score, return_train_score=return_train_score, scheduler=scheduler, n_jobs=n_jobs, cache_cv=cache_cv) _check_param_grid(param_grid) self.param_grid = param_grid
def __init__(self, estimator, param_grid, scoring=None, fit_params=None, n_jobs=None, iid='warn', refit=True, cv='warn', verbose=0, pre_dispatch='2*n_jobs', error_score='raise-deprecating', return_train_score=False): super().__init__(estimator=estimator, scoring=scoring, fit_params=fit_params, n_jobs=n_jobs, iid=iid, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score) self.param_grid = param_grid _check_param_grid(param_grid)
def __init__(self, sc, estimator, param_grid, *args, **kwargs): self.sc = sc self.param_grid = param_grid self.estimator = estimator _check_param_grid(param_grid) super(SparkBaseSearchCV, self).__init__(estimator=self.estimator, *args, **kwargs)
def _normalize_param_grid(param_grid): """Normalize the parameter grid to use with parametrized estimators.""" _check_param_grid(param_grid) normalized_param_grid = param_grid.copy() est_name = list(set([param.split('__')[0] for param in param_grid.keys()])) normalized_param_grid.update({'est_name': est_name}) return normalized_param_grid
def fit(self, cvs, groups=None, **fit_params): self.best_estimator_ = None self.best_mem_score_ = float("-inf") self.best_mem_params_ = None for possible_params in self.possible_params: _check_param_grid(possible_params) self._fit(cvs, possible_params)
def __init__(self, estimator, param_grid, scoring=None, iid=True, refit=True, cv=None, error_score='raise', return_train_score=True, get=None): super(DaskGridSearchCV, self).__init__(estimator=estimator, scoring=scoring, iid=iid, refit=refit, cv=cv, error_score=error_score, return_train_score=return_train_score, get=get) _check_param_grid(param_grid) self.param_grid = param_grid
def __init__(self, sc, estimator, param_grid, scoring=None, iid='warn', refit=True, cv=None, verbose=0, error_score='raise-deprecating', return_train_score=False): super(GridSearchCV, self).__init__(estimator, scoring, iid, refit, cv, verbose, error_score, return_train_score) self.sc = sc self.param_grid = param_grid _check_param_grid(param_grid)
def __init__(self, estimator, param_grid, scoring=None, iid=True, refit=True, cv=None, error_score='raise', return_train_score=True, scheduler=None, n_jobs=-1, cache_cv=True): super(GridSearchCV, self).__init__(estimator=estimator, scoring=scoring, iid=iid, refit=refit, cv=cv, error_score=error_score, return_train_score=return_train_score, scheduler=scheduler, n_jobs=n_jobs, cache_cv=cache_cv) _check_param_grid(param_grid) self.param_grid = param_grid
def __init__(self, estimator, param_dict, scoring=None, n_jobs=1, cv=None, cv_exclude_first=0.0, verbose=0): self.estimator = estimator self.param_dict = param_dict self.scoring = scoring self.n_jobs = n_jobs self.cv = cv self.cv_exclude_first = cv_exclude_first self.verbose = verbose self.bayesian_optimizer = BayesianOptimization(self._evaluate, self.param_dict, verbose=verbose) self.scorer_ = check_scoring(self.estimator, scoring=self.scoring) _check_param_grid(self.param_dict)
def fit(self, X, y=None): self.best_estimator_ = None self.best_mem_score_ = float("-inf") self.best_mem_params_ = None for possible_params in self.possible_params: _check_param_grid(possible_params) self._fit(X, y, possible_params) if self.refit: self.best_estimator_ = clone(self.estimator) self.best_estimator_.set_params(**self.best_mem_params_) self.best_estimator_.fit(X, y)
def __init__(self, estimator, param_grid, scoring=None, n_jobs=None, refit=True, verbose=0, cv=None, pre_dispatch='2*n_jobs', random_state=None, error_score=np.nan, return_train_score=True): super().__init__(estimator, scoring=scoring, n_jobs=n_jobs, verbose=verbose, cv=cv, pre_dispatch=pre_dispatch, random_state=random_state, error_score=error_score, return_train_score=return_train_score) self.param_grid = param_grid _check_param_grid(self.param_grid)
def fit(self, X, y): self.best_estimator_ = None self.best_mem_score_ = float("-inf") self.best_mem_params_ = None _check_param_grid(self.params) self._fit(X, y, self.params) if self.refit: self.best_estimator_ = clone(self.estimator) self.best_estimator_.set_params(**self.best_mem_params_) if self.fit_params is not None: self.best_estimator_.fit(X, y, **self.fit_params) else: self.best_estimator_.fit(X, y)
def __init__(self, estimator, param_grid, n_iter, n_initial_points, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=None, verbose=0, pre_dispatch='2*n_jobs', error_score='raise'): #assert(n_jobs == 1) super(BayesianOptimizationSearchCV, self).__init__( estimator=estimator, scoring=scoring, fit_params=fit_params, n_jobs=n_jobs, iid=iid, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score) self.param_grid = param_grid assert(n_iter >= 0) self.n_iter = n_iter assert(n_initial_points > 0) self.n_initial_points = n_initial_points _search._check_param_grid(param_grid)
def __init__(self, sc, estimator, param_grid, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=3, verbose=0, pre_dispatch='2*n_jobs', error_score='raise', return_train_score=True): super(GridSearchCV, self).__init__( estimator=estimator, scoring=scoring, n_jobs=n_jobs, iid=iid, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score) self.fit_params = fit_params if fit_params is not None else {} self.sc = sc self.param_grid = param_grid self.cv_results_ = None _check_param_grid(param_grid)
def fit(self, X, y): self.best_estimator_ = None self.best_mem_score_ = float("-inf") self.best_mem_params_ = None _check_param_grid(self.params) self._fit(X, y, self.params) if self.refit: self.best_estimator_ = clone(self.estimator) self.best_estimator_.set_params(**self.best_mem_params_) if self.fit_params is not None: self.best_estimator_.fit(X, y, **self.fit_params) else: self.best_estimator_.fit(X, y) #print(self.cv_results_()) return self
def __init__(self, default_estimator, param_grid, cv, me, untrainable_param_grid=None, scoring_rank='f1_score', refit=False, iid=True, n_jobs=1, pre_dispatch='2*n_jobs', logger=StandardOutputLogger(Logger.INFO)): self.default_estimator = default_estimator self.param_grid = param_grid self.untrainable_param_grid = untrainable_param_grid self.cv = cv self.me = me self.scoring_rank = scoring_rank self.n_jobs = n_jobs self.pre_dispatch = pre_dispatch self.logger = logger self.refit = refit self.iid = iid _check_param_grid(param_grid) _check_param_grid(untrainable_param_grid)
def __init__(self, estimator, param_grid, scoring=None, fit_params=None, n_jobs=None, iid='warn', refit=True, cv='warn', verbose=0, pre_dispatch='2*n_jobs', error_score='raise-deprecating', return_train_score="warn", cachedir='./', return_estimator=False, client=None): super(PersGridSearchCV, self).__init__( estimator=estimator, scoring=scoring, fit_params=fit_params, n_jobs=n_jobs, iid=iid, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score) self.param_grid = param_grid self.cachedir = cachedir self.return_estimator = return_estimator self.client = client _check_param_grid(param_grid)
def fit(self, X, y): """Fit the model to the training data.""" X, y = check_X_y(X, y, force_all_finite=False, multi_output=self.multi_output) _check_param_grid(self.param_grid) # cv = _check_cv(self.cv, X, y, classifier=is_classifier(self.estimator)) cv = _check_cv(self.cv, y, classifier=is_classifier(self.estimator)) self.scorer_ = check_scoring(self.estimator, scoring=self.scoring) if comm_rank == 0: self._fit_master(X, y, cv) else: self._fit_slave() return self
def _normalize_param_grid(param_grid): """Normalize the parameter grid to use with parametrized estimators.""" # Check the parameters grid _check_param_grid(param_grid) # Copy the parameters grid normalized_param_grid = param_grid.copy() # Parse the estimator name est_name = list(set([param.split('__')[0] for param in param_grid.keys()])) # Update with the estimator name normalized_param_grid.update({'est_name': est_name}) return normalized_param_grid
def __init__(self, estimator, param_grid, known_triples=None, cv=None, n_jobs=1, refit=True, verbose=0): """ Initialise an object of the KGEGridSearch class Parameters ---------- estimator : estimator object. This is assumed to implement the scikit-learn estimator interface. param_grid : dict or list of dictionaries Dictionary with parameters names (string) as keys and lists of parameter settings to try as values, or a list of such dictionaries, in which case the grids spanned by each dictionary in the list are explored. This enables searching over any sequence of parameter settings. known_triples : np.ndarray array of known triples cv : int, cross-validation generator or an iterable, optional Determines the cross-validation splitting strategy. Possible inputs for cv are: - None, to use the default KGE train/valid gridsearch, - integer, to specify the number of folds in a scikit-learn `(Stratified)KFold`, - An object to be used as a cross-validation generator. - An iterable yielding train, test splits. n_jobs : int number of parallel jobs verbose : int level of logging verbosity """ super(KGEGridSearch, self).__init__(estimator=estimator, fit_params=None, n_jobs=n_jobs, iid=True, refit=refit, cv=cv, verbose=verbose, pre_dispatch='2*n_jobs', error_score='raise', return_train_score=False) self.cv = cv self.param_grid = param_grid self.valid_data = None self.known_triples = known_triples _check_param_grid(param_grid)
def fit(self, X, y): """Fit the model to the training data.""" X, y = check_X_y(X, y, force_all_finite=False, multi_output=self.multi_output) _check_param_grid(self.param_grid) # cv = _check_cv(self.cv, X, y, classifier=is_classifier(self.estimator)) cv = _check_cv(self.cv, y, classifier=is_classifier(self.estimator)) self.scorer_ = check_scoring(self.estimator, scoring=self.scoring) if comm_rank == 0: self._fit_master(X, y, cv) else: self._fit_slave() return self
def fit(self, cvs, groups=None, **fit_params): X = np.vstack((cvs[0][0], cvs[0][2], cvs[0][4])) if len(cvs[0][1].shape)==1 and len(cvs[0][5].shape)==1: y = np.hstack((cvs[0][1], cvs[0][3], cvs[0][5])) else: y = np.vstack((cvs[0][1], cvs[0][3], cvs[0][5])).ravel() self.best_estimator_ = None self.best_mem_score_ = float("-inf") self.best_mem_params_ = None for possible_params in self.possible_params: _check_param_grid(possible_params) self._fit(X, y, cvs, possible_params) if self.refit: self.best_estimator_ = clone(self.estimator) self.best_estimator_.set_params(**self.best_mem_params_) if self.fit_params is not None: self.best_estimator_.fit(X, y, **self.fit_params) else: self.best_estimator_.fit(X, y)
def __init__(self, estimator, param_grid, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=None, verbose=0, pre_dispatch='2*n_jobs', error_score='raise', return_train_score=True, client_kwargs=settings.DASK_SCHEDULER_PARAMS, uuid='', dataset=None, webserver_url='http://127.0.0.1:8000'): super(GridSearchCV, self).__init__(estimator=estimator, scoring=scoring, fit_params=fit_params, n_jobs=n_jobs, iid=iid, refit=refit, cv=cv, verbose=verbose, pre_dispatch=pre_dispatch, error_score=error_score, return_train_score=return_train_score) from AnyTimeGridSearchCV.grids.models import GridSearch, DataSet self.param_grid = param_grid _check_param_grid(param_grid) self.dask_client = Client(silence_logs=100, **client_kwargs) self.dask_client.upload_file(settings.SOURCE_PATH) self.dataset, _ = DataSet.objects.get_or_create( pk=dataset) if dataset is not None else (None, None) self._uuid = uuid if uuid else GridSearch.objects.create( classifier=type(estimator).__name__, dataset=self.dataset).uuid self.webserver_url = webserver_url