""" Class for parallelizing RandomizedSearchCV jobs in scikit-learn """ from sklearn.model_selection import ParameterSampler from spark_sklearn.base_search import SparkBaseSearchCV class RandomizedSearchCV(SparkBaseSearchCV): """Randomized search on hyper parameters. RandomizedSearchCV implements a "fit" and a "score" method. It also implements "predict", "predict_proba", "decision_function", "transform" and "inverse_transform" if they are implemented in the estimator used. The parameters of the estimator used to apply these methods are optimized by cross-validated search over parameter settings. In contrast to GridSearchCV, not all combinations of parameter values are tried out, but rather a fixed number of parameter settings is sampled from the specified distributions. The number of parameter settings that are tried is given by n_iter. If all parameters are presented as a list, sampling without replacement is performed. If at least one parameter is given as a distribution, sampling with replacement is used for all parameters. It is highly recommended to use continuous distributions for continuous parameters. Parameters ---------- estimator : estimator object. A object of that type is instantiated for each grid point. This is assumed to implement the scikit-learn estimator interface. Either estimator needs to provide a ``score`` function, or ``scoring`` must be passed. param_distributions : dict Dictionary with parameters names (string) as keys and distributions or lists of parameters to try. Distributions must provide a ``rvs`` method for sampling (such as those from scipy.stats.distributions). If a list is given, it is sampled uniformly. n_iter : int, default=10 Number of parameter settings that are sampled. n_iter trades off runtime vs quality of the solution. scoring : string, callable or None, default=None A string (see model evaluation documentation) or a scorer callable object / function with signature ``scorer(estimator, X, y)``. If ``None``, the ``score`` method of the estimator is used. fit_params : dict, optional Parameters to pass to the fit method. n_jobs : int, default=1 Number of jobs to run in parallel. pre_dispatch : int, or string, optional Not used; exists for scikit-learn compatibility. iid : boolean, default=True If True, the data is assumed to be identically distributed across the folds, and the loss minimized is the total loss per sample, and not the mean loss across the folds. 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 3-fold cross-validation, - integer, to specify the number of folds. - An object to be used as a cross-validation generator. - An iterable yielding train/test splits. For integer/None inputs, if the estimator is a classifier and ``y`` is either binary or multiclass, :class:`sklearn.model_selection.StratifiedKFold` is used. In all other cases, :class:`sklearn.model_selection.KFold` is used. refit : boolean, default=True Refit the best estimator with the entire dataset. If "False", it is impossible to make predictions using this RandomizedSearchCV instance after fitting. verbose : integer Controls the verbosity: the higher, the more messages. random_state : int, RandomState instance or None, optional, default=None Pseudo random number generator state used for random uniform sampling from lists of possible values instead of scipy.stats distributions. If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. error_score : 'raise' (default) or numeric Value to assign to the score if an error occurs in estimator fitting. If set to 'raise', the error is raised. If a numeric value is given, FitFailedWarning is raised. This parameter does not affect the refit step, which will always raise the error. Attributes ---------- cv_results_ : dict of numpy (masked) ndarrays A dict with keys as column headers and values as columns, that can be imported into a pandas ``DataFrame``. For instance the below given table +------------+-----------+------------+-----------------+---+---------+ |param_kernel|param_gamma|param_degree|split0_test_score|...|rank_....| +============+===========+============+=================+===+=========+ | 'poly' | -- | 2 | 0.8 |...| 2 | +------------+-----------+------------+-----------------+---+---------+ | 'poly' | -- | 3 | 0.7 |...| 4 | +------------+-----------+------------+-----------------+---+---------+ | 'rbf' | 0.1 | -- | 0.8 |...| 3 | +------------+-----------+------------+-----------------+---+---------+ | 'rbf' | 0.2 | -- | 0.9 |...| 1 | +------------+-----------+------------+-----------------+---+---------+ will be represented by a ``cv_results_`` dict of:: { 'param_kernel': masked_array(data = ['poly', 'poly', 'rbf', 'rbf'], mask = [False False False False]...) 'param_gamma': masked_array(data = [-- -- 0.1 0.2], mask = [ True True False False]...), 'param_degree': masked_array(data = [2.0 3.0 -- --], mask = [False False True True]...), 'split0_test_score' : [0.8, 0.7, 0.8, 0.9], 'split1_test_score' : [0.82, 0.5, 0.7, 0.78], 'mean_test_score' : [0.81, 0.60, 0.75, 0.82], 'std_test_score' : [0.02, 0.01, 0.03, 0.03], 'rank_test_score' : [2, 4, 3, 1], 'split0_train_score' : [0.8, 0.9, 0.7], 'split1_train_score' : [0.82, 0.5, 0.7], 'mean_train_score' : [0.81, 0.7, 0.7], 'std_train_score' : [0.03, 0.03, 0.04], 'mean_fit_time' : [0.73, 0.63, 0.43, 0.49], 'std_fit_time' : [0.01, 0.02, 0.01, 0.01], 'mean_score_time' : [0.007, 0.06, 0.04, 0.04], 'std_score_time' : [0.001, 0.002, 0.003, 0.005], 'params' : [{'kernel': 'poly', 'degree': 2}, ...], } NOTE that the key ``'params'`` is used to store a list of parameter settings dict for all the parameter candidates. The ``mean_fit_time``, ``std_fit_time``, ``mean_score_time`` and ``std_score_time`` are all in seconds. best_estimator_ : estimator Estimator that was chosen by the search, i.e. estimator which gave highest score (or smallest loss if specified) on the left out data. Not available if refit=False. best_score_ : float Score of best_estimator on the left out data. best_params_ : dict Parameter setting that gave the best results on the hold out data. best_index_ : int The index (of the ``cv_results_`` arrays) which corresponds to the best candidate parameter setting. The dict at ``search.cv_results_['params'][search.best_index_]`` gives the parameter setting for the best model, that gives the highest mean score (``search.best_score_``). Notes ----- The parameters selected are those that maximize the score of the held-out data, according to the scoring parameter. See Also -------- :class:`GridSearchCV`: Does exhaustive search over a grid of parameters. :class:`ParameterSampler`: A generator over parameter settings, constructed from param_distributions. """ def __init__(self, sc, estimator, param_distributions, n_iter=10, scoring=None, fit_params=None, n_jobs=1, iid=True, refit=True, cv=None, verbose=0, pre_dispatch='2*n_jobs', random_state=None, error_score='raise'): self.param_distributions = param_distributions self.n_iter = n_iter self.random_state = random_state super(RandomizedSearchCV, 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.fit_params = fit_params if fit_params is not None else {} self.sc = sc self.cv_results_ = None def fit(self, X, y=None, groups=None): """Run fit on the estimator with randomly drawn parameters. Parameters ---------- X : array-like, shape = [n_samples, n_features] Training vector, where n_samples in the number of samples and n_features is the number of features. y : array-like, shape = [n_samples] or [n_samples, n_output], optional Target relative to X for classification or regression; None for unsupervised learning. groups : array-like, with shape (n_samples,), optional Group labels for the samples used while splitting the dataset into train/test set. """ sampled_params = ParameterSampler(self.param_distributions, self.n_iter, random_state=self.random_state) return self._fit(X, y, groups, sampled_params)