Python sklearn.utils.validation 模块，_num_samples() 实例源码

def _do_n_samples(dsk, token, Xs, n_splits):
    name = 'n_samples-' + token
    n_samples = []
    n_samples_append = n_samples.append
    seen = {}
    m = 0
    for x in Xs:
        if x in seen:
            n_samples_append(seen[x])
        else:
            for n in range(n_splits):
                dsk[name, m, n] = (_num_samples, x + (n,))
            n_samples_append((name, m))
            seen[x] = (name, m)
            m += 1
    return n_samples

def check_cv_coverage(cv, X, y, labels, expected_n_iter=None):
    n_samples = _num_samples(X)
    # Check that a all the samples appear at least once in a test fold
    if expected_n_iter is not None:
        assert_equal(cv.get_n_splits(X, y, labels), expected_n_iter)
    else:
        expected_n_iter = cv.get_n_splits(X, y, labels)

    collected_test_samples = set()
    iterations = 0
    for train, test in cv.split(X, y, labels):
        check_valid_split(train, test, n_samples=n_samples)
        iterations += 1
        collected_test_samples.update(test)

    # Check that the accumulated test samples cover the whole dataset
    assert_equal(iterations, expected_n_iter)
    if n_samples is not None:
        assert_equal(collected_test_samples, set(range(n_samples)))

def predict(self, T):
        if self.check_X is not None:
            assert self.check_X(T)
        return self.classes_[np.zeros(_num_samples(T), dtype=np.int)]

def fit(self, X, y):
        """Actual fitting,  performing the search over parameters."""

        parameter_iterable = ParameterGrid(self.param_grid)

        estimator = self.estimator
        cv = self.cv

        n_samples = _num_samples(X)
        X, y = indexable(X, y)

        if y is not None:
            if len(y) != n_samples:
                raise ValueError('Target variable (y) has a different number '
                                 'of samples (%i) than data (X: %i samples)'
                                 % (len(y), n_samples))
        cv = check_cv(cv, X, y, classifier=is_classifier(estimator))

        if self.verbose > 0:
            if isinstance(parameter_iterable, Sized):
                n_candidates = len(parameter_iterable)
                print("Fitting {0} folds for each of {1} candidates, totalling"
                      " {2} fits".format(len(cv), n_candidates,
                                         n_candidates * len(cv)))

        base_estimator = clone(self.estimator)

        pre_dispatch = self.pre_dispatch

        out = Parallel(
            n_jobs=self.n_jobs, verbose=self.verbose,
            pre_dispatch=pre_dispatch
        )(delayed(cv_fit_and_score)(clone(base_estimator), X, y, self.scoring,
                                      parameters, cv=cv)
            for parameters in parameter_iterable)

        best = sorted(out, key=lambda x: x[0])[-1]
        self.best_params_ = best[1]
        self.best_score_ = best[0]

        if self.refit:
            # fit the best estimator using the entire dataset
            # clone first to work around broken estimators
            best_estimator = clone(base_estimator).set_params(
                **best[1])
            if y is not None:
                best_estimator.fit(X, y, **self.fit_params)
            else:
                best_estimator.fit(X, **self.fit_params)
            self.best_estimator_ = best_estimator

        return self

def fit(self, X, y):
        """Actual fitting,  performing the search over parameters."""

        parameter_iterable = ParameterSampler(self.param_distributions,
                                              self.n_iter,
                                              random_state=self.random_state)
        estimator = self.estimator
        cv = self.cv

        n_samples = _num_samples(X)
        X, y = indexable(X, y)

        if y is not None:
            if len(y) != n_samples:
                raise ValueError('Target variable (y) has a different number '
                                 'of samples (%i) than data (X: %i samples)'
                                 % (len(y), n_samples))
        cv = check_cv(cv, X, y, classifier=is_classifier(estimator))

        if self.verbose > 0:
            if isinstance(parameter_iterable, Sized):
                n_candidates = len(parameter_iterable)
                print("Fitting {0} folds for each of {1} candidates, totalling"
                      " {2} fits".format(len(cv), n_candidates,
                                         n_candidates * len(cv)))

        base_estimator = clone(self.estimator)

        pre_dispatch = self.pre_dispatch

        out = Parallel(
            n_jobs=self.n_jobs, verbose=self.verbose,
            pre_dispatch=pre_dispatch
        )(
            delayed(cv_fit_and_score)(clone(base_estimator), X, y, self.scoring,
                                      parameters, cv=cv)
            for parameters in parameter_iterable)

        best = sorted(out, reverse=True)[0]
        self.best_params_ = best[1]
        self.best_score_ = best[0]

        if self.refit:
            # fit the best estimator using the entire dataset
            # clone first to work around broken estimators
            best_estimator = clone(base_estimator).set_params(
                **best[1])
            if y is not None:
                best_estimator.fit(X, y, **self.fit_params)
            else:
                best_estimator.fit(X, **self.fit_params)
            self.best_estimator_ = best_estimator

        return self