Python scorer.check_scoring方法代码示例

# 需要导入模块: from sklearn.metrics import scorer [as 别名]
# 或者: from sklearn.metrics.scorer import check_scoring [as 别名]
def _optimize_n_neighbors(self, X, y):
        print('Auto optimizing n_neighbors using ' + str(self.n_neighbor_candidates))
        X_train, X_validate, y_train, y_validate = self._get_split(X, y)
        estimator = copy.copy(self)
        estimator.auto_optimize_k = False
        estimator.fit(X_train, y_train)
        scorer = check_scoring(estimator, scoring=self.scoring)
        configs = []
        for n_neighbors in self.n_neighbor_candidates:
            estimator.n_neighbors = n_neighbors
            score = scorer(estimator, X_validate, y_validate)
            print('N_neighbors = ' + str(n_neighbors) + ' score: ' + str(self.scoring) + ' ' + str(score))
            configs.append((n_neighbors, score))

        configs = sorted(configs, key=lambda i: i[1], reverse=True)
        print('Configs in order of score: ')
        pprint.pprint(configs)
        self.n_neighbors = configs[0][0] 

# 需要导入模块: from sklearn.metrics import scorer [as 别名]
# 或者: from sklearn.metrics.scorer import check_scoring [as 别名]
def test_cross_validate():
    # Compute train and test mse/r2 scores
    cv = KFold(n_splits=5)

    # Regression
    X_reg, y_reg = make_regression(n_samples=30, random_state=0)
    reg = Ridge(random_state=0)

    # Classification
    X_clf, y_clf = make_classification(n_samples=30, random_state=0)
    clf = SVC(kernel="linear", random_state=0)

    for X, y, est in ((X_reg, y_reg, reg), (X_clf, y_clf, clf)):
        # It's okay to evaluate regression metrics on classification too
        mse_scorer = check_scoring(est, 'neg_mean_squared_error')
        r2_scorer = check_scoring(est, 'r2')
        train_mse_scores = []
        test_mse_scores = []
        train_r2_scores = []
        test_r2_scores = []
        fitted_estimators = []
        for train, test in cv.split(X, y):
            est = clone(reg).fit(X[train], y[train])
            train_mse_scores.append(mse_scorer(est, X[train], y[train]))
            train_r2_scores.append(r2_scorer(est, X[train], y[train]))
            test_mse_scores.append(mse_scorer(est, X[test], y[test]))
            test_r2_scores.append(r2_scorer(est, X[test], y[test]))
            fitted_estimators.append(est)

        train_mse_scores = np.array(train_mse_scores)
        test_mse_scores = np.array(test_mse_scores)
        train_r2_scores = np.array(train_r2_scores)
        test_r2_scores = np.array(test_r2_scores)
        fitted_estimators = np.array(fitted_estimators)

        scores = (train_mse_scores, test_mse_scores, train_r2_scores,
                  test_r2_scores, fitted_estimators)

        check_cross_validate_single_metric(est, X, y, scores)
        check_cross_validate_multi_metric(est, X, y, scores) 

# 需要导入模块: from sklearn.metrics import scorer [as 别名]
# 或者: from sklearn.metrics.scorer import check_scoring [as 别名]
def cross_val_score(
    estimator,
    X,
    y=None,
    groups=None,
    scoring=None,
    cv=None,
    n_jobs=1,
    verbose=0,
    fit_params=None,
    pre_dispatch="2*n_jobs",
):
    """
    Evaluate a score by cross-validation
    """
    if not isinstance(scoring, (list, tuple)):
        scoring = [scoring]

    X, y, groups = indexable(X, y, groups)

    cv = check_cv(cv, y, classifier=is_classifier(estimator))
    splits = list(cv.split(X, y, groups))
    scorer = [check_scoring(estimator, scoring=s) for s in scoring]
    # We clone the estimator to make sure that all the folds are
    # independent, and that it is pickle-able.
    parallel = Parallel(n_jobs=n_jobs, verbose=verbose, pre_dispatch=pre_dispatch)
    scores = parallel(
        delayed(_fit_and_score)(
            clone(estimator), X, y, scorer, train, test, verbose, None, fit_params
        )
        for train, test in splits
    )

    group_order = []
    if hasattr(cv, "groups"):
        group_order = [np.array(cv.groups)[test].tolist()[0] for _, test in splits]
    return np.squeeze(np.array(scores)), group_order 

# 需要导入模块: from sklearn.metrics import scorer [as 别名]
# 或者: from sklearn.metrics.scorer import check_scoring [as 别名]
def _score(self, X, y, scoring=None, clf=None):
        from sklearn.model_selection._validation import _score

        if scoring is None:
            scoring = self._scorer

        if clf is None:
            clf = self._estimator

        return _score(clf, X, y, check_scoring(clf, scoring=scoring)) 

# 需要导入模块: from sklearn.metrics import scorer [as 别名]
# 或者: from sklearn.metrics.scorer import check_scoring [as 别名]
def test_cross_validate():
    # Compute train and test mse/r2 scores
    cv = KFold(n_splits=5)

    # Regression
    X_reg, y_reg = make_regression(n_samples=30, random_state=0)
    reg = Ridge(random_state=0)

    # Classification
    X_clf, y_clf = make_classification(n_samples=30, random_state=0)
    clf = SVC(kernel="linear", random_state=0)

    for X, y, est in ((X_reg, y_reg, reg), (X_clf, y_clf, clf)):
        # It's okay to evaluate regression metrics on classification too
        mse_scorer = check_scoring(est, 'neg_mean_squared_error')
        r2_scorer = check_scoring(est, 'r2')
        train_mse_scores = []
        test_mse_scores = []
        train_r2_scores = []
        test_r2_scores = []
        for train, test in cv.split(X, y):
            est = clone(reg).fit(X[train], y[train])
            train_mse_scores.append(mse_scorer(est, X[train], y[train]))
            train_r2_scores.append(r2_scorer(est, X[train], y[train]))
            test_mse_scores.append(mse_scorer(est, X[test], y[test]))
            test_r2_scores.append(r2_scorer(est, X[test], y[test]))

        train_mse_scores = np.array(train_mse_scores)
        test_mse_scores = np.array(test_mse_scores)
        train_r2_scores = np.array(train_r2_scores)
        test_r2_scores = np.array(test_r2_scores)

        scores = (train_mse_scores, test_mse_scores, train_r2_scores,
                  test_r2_scores)

        yield check_cross_validate_single_metric, est, X, y, scores
        yield check_cross_validate_multi_metric, est, X, y, scores 

# 需要导入模块: from sklearn.metrics import scorer [as 别名]
# 或者: from sklearn.metrics.scorer import check_scoring [as 别名]
def permutation_test_score(
    estimator,
    X,
    y,
    groups=None,
    cv=None,
    n_permutations=100,
    n_jobs=1,
    random_state=0,
    verbose=0,
    scoring=None,
):
    """
    Evaluate the significance of a cross-validated score with permutations,
    as in test 1 of [Ojala2010]_.

    A modification of original sklearn's permutation test score function
    to evaluate p-value outside this function, so that the score can be
    reused from outside.


    .. [Ojala2010] Ojala and Garriga. Permutation Tests for Studying Classifier
                   Performance.  The Journal of Machine Learning Research (2010)
                   vol. 11

    """
    X, y, groups = indexable(X, y, groups)

    cv = check_cv(cv, y, classifier=is_classifier(estimator))
    scorer = check_scoring(estimator, scoring=scoring)
    random_state = check_random_state(random_state)

    # We clone the estimator to make sure that all the folds are
    # independent, and that it is pickle-able.
    permutation_scores = Parallel(n_jobs=n_jobs, verbose=verbose)(
        delayed(_permutation_test_score)(
            clone(estimator), X, _shuffle(y, groups, random_state), groups, cv, scorer
        )
        for _ in range(n_permutations)
    )
    permutation_scores = np.array(permutation_scores)
    return permutation_scores 

# 需要导入模块: from sklearn.metrics import scorer [as 别名]
# 或者: from sklearn.metrics.scorer import check_scoring [as 别名]
def cross_val_score_track_trials(estimator, X, y=None, scoring=accuracy_score, cv=5, args_to_scorer=None):
    """
    Use the given estimator to perform fit and predict for splits defined by 'cv' and compute the given score on 
    each of the splits.

    Parameters
    ----------

    estimator: A valid sklearn_wrapper estimator
    X, y: Valid data and target values that work with the estimator
    scoring: string or a scorer object created using 
        https://scikit-learn.org/stable/modules/generated/sklearn.metrics.make_scorer.html#sklearn.metrics.make_scorer.
        A string from sklearn.metrics.SCORERS.keys() can be used or a scorer created from one of 
        sklearn.metrics (https://scikit-learn.org/stable/modules/classes.html#module-sklearn.metrics).
        A completely custom scorer object can be created from a python function following the example at 
        https://scikit-learn.org/stable/modules/model_evaluation.html
        The metric has to return a scalar value,
    cv: an integer or an object that has a split function as a generator yielding (train, test) splits as arrays of indices.
        Integer value is used as number of folds in sklearn.model_selection.StratifiedKFold, default is 5.
        Note that any of the iterators from https://scikit-learn.org/stable/modules/cross_validation.html#cross-validation-iterators can be used here.
    args_to_scorer: A dictionary of additional keyword arguments to pass to the scorer. 
                Used for cases where the scorer has a signature such as ``scorer(estimator, X, y, **kwargs)``.
    Returns
    -------
        cv_results: a list of scores corresponding to each cross validation fold
    """
    if isinstance(cv, int):
        cv = StratifiedKFold(cv)

    if args_to_scorer is None:
        args_to_scorer={}
    scorer = check_scoring(estimator, scoring=scoring)
    cv_results:List[float] = []
    log_loss_results = []
    time_results = []
    for train, test in cv.split(X, y):
        X_train, y_train = split_with_schemas(estimator, X, y, train)
        X_test, y_test = split_with_schemas(estimator, X, y, test, train)
        start = time.time()
        #Not calling sklearn.base.clone() here, because:
        #  (1) For Lale pipelines, clone() calls the pipeline constructor
        #      with edges=None, so the resulting topology is incorrect.
        #  (2) For Lale individual operators, the fit() method already
        #      clones the impl object, so cloning again is redundant.
        trained = estimator.fit(X_train, y_train)
        score_value  = scorer(trained, X_test, y_test, **args_to_scorer)
        execution_time = time.time() - start
        # not all estimators have predict probability
        try:
            y_pred_proba = trained.predict_proba(X_test)
            logloss = log_loss(y_true=y_test, y_pred=y_pred_proba)
            log_loss_results.append(logloss)
        except BaseException:
            logger.debug("Warning, log loss cannot be computed")
        cv_results.append(score_value)
        time_results.append(execution_time)
    result = np.array(cv_results).mean(), np.array(log_loss_results).mean(), np.array(execution_time).mean()
    return result 

# 需要导入模块: from sklearn.metrics import scorer [as 别名]
# 或者: from sklearn.metrics.scorer import check_scoring [as 别名]
def fit(self, X_train, y_train):
        self.cv = check_cv(self.cv, y = y_train, classifier=True) #TODO: Replace the classifier flag value by using tags?

        def smac_train_test(trainable, X_train, y_train):
            try:
                cv_score, logloss, execution_time = cross_val_score_track_trials(trainable, X_train, y_train, cv=self.cv, scoring=self.scoring)
                logger.debug("Successful trial of SMAC")
            except BaseException as e:
                #If there is any error in cross validation, use the score based on a random train-test split as the evaluation criterion
                if self.handle_cv_failure:
                    X_train_part, X_validation, y_train_part, y_validation = train_test_split(X_train, y_train, test_size=0.20)
                    start = time.time()
                    trained = trainable.fit(X_train_part, y_train_part)
                    scorer = check_scoring(trainable, scoring=self.scoring)
                    cv_score  = scorer(trained, X_validation, y_validation)
                    execution_time = time.time() - start
                    y_pred_proba = trained.predict_proba(X_validation)
                    try:
                        logloss = log_loss(y_true=y_validation, y_pred=y_pred_proba)
                    except BaseException:
                        logloss = 0
                        logger.debug("Warning, log loss cannot be computed")
                else:
                    logger.debug("Error {} with pipeline:{}".format(e, trainable.to_json()))
                    raise e
            return cv_score, logloss, execution_time

        def f(trainable):
            return_dict = {}
            try:
                score, logloss, execution_time = smac_train_test(trainable, X_train=X_train, y_train=y_train)
                return_dict = {
                    'loss': self.best_score - score,
                    'time': execution_time,
                    'log_loss': logloss
                }
            except BaseException as e:
                logger.warning(f"Exception caught in SMACCV:{type(e)}, {traceback.format_exc()}, SMAC will set a cost_for_crash to MAXINT.")
                raise e
            return return_dict['loss']

        try :
            smac = orig_SMAC(scenario=self.scenario, rng=np.random.RandomState(42),
                    tae_runner=lale_op_smac_tae(self.estimator, f))
            incumbent = smac.optimize()
            self.trials = smac.get_runhistory()
            trainable = lale_trainable_op_from_config(self.estimator, incumbent)
            #get the trainable corresponding to the best params and train it on the entire training dataset.
            trained = trainable.fit(X_train, y_train)
            self._best_estimator = trained
        except BudgetExhaustedException:
            logger.warning('Maximum alloted optimization time exceeded. Optimization exited prematurely')
        except BaseException as e:
            logger.warning('Error during optimization: {}'.format(e))
            self._best_estimator = None

        return self