Python base.clone函数代码示例

    def _fit_X_y(self, X_clf, y_clf, X_cal, y_cal):
        clf = clone(self.base_estimator)

        if isinstance(clf, RegressorMixin):
            clf = as_classifier(clf)

        clf.fit(X_clf, y_clf)

        if self.calibration is None:
            return clf, None, None

        else:
            if self.calibration == "kde":
                cal_num = KernelDensity()
                cal_den = KernelDensity()

            elif self.calibration == "histogram":
                cal_num = Histogram(bins=100, range=[(0.0, 1.0)])
                cal_den = Histogram(bins=100, range=[(0.0, 1.0)])

            else:
                cal_num = clone(self.calibration)
                cal_den = clone(self.calibration)

            X_num = clf.predict_proba(X_cal[y_cal == 0])[:, 0]
            X_den = clf.predict_proba(X_cal[y_cal == 1])[:, 0]
            cal_num.fit(X_num.reshape(-1, 1))
            cal_den.fit(X_den.reshape(-1, 1))

            return clf, cal_num, cal_den

def pool_entropy_h(X, y, candidate_mask, train_mask, classifier, n_candidates,
                   pool_n, n_jobs=-1, **kwargs):
    """ Return the candidate that will minimise the expected entropy of the predictions.

        Parameters
        ----------
        X_training_candidates : array
            The feature matrix of the potential training candidates.

        classes : int
            The name of classes.

        pool_n : int
            The size of the sampel pool used in estimating the entropy

        n_jobs : int
            The number of parallel jobs (-1 if want to use all cores)

        Returns
        -------
        best_candidate : int
            The index of the best candidate.
    """
    
    classes = classifier.classes_ # sorted lexicographically
    n_classes = len(classes)
    candidate_size = np.sum(train_mask)
    n_features = X.shape[1]
    entropy = np.empty(len(candidate_mask))
    entropy[:] = np.inf

    # the probabilities used to calculate expected value of pool
    probs = classifier.predict_proba(X[candidate_mask])

    # copy the classifier (avoid modifying the original classifier)
    classifier_plus = clone(classifier)

    # construct the sample pool (used to estimate the entropy)
    unlabelled_indices = np.where(-train_mask)[0]
    pool_indices = permutation(unlabelled_indices)[:pool_n]
    pool_mask = np.zeros(len(candidate_mask), dtype=bool)
    pool_mask[pool_indices] = True

    # let's look at each candidate
    candidate_indices = np.where(candidate_mask)[0]

    results = Parallel(n_jobs=n_jobs)(delayed(_parallel_entropy_estimate)(
        X, y.copy(), train_mask.copy(), pool_mask,
        clone(classifier_plus), classes, n_classes, probs, i, index)
        for i, index in enumerate(candidate_indices))

    indices, expected = zip(*results)
    indices, expected = np.asarray(indices), np.asarray(expected)
    assert not np.isnan(expected).any(), 'Some expected values are undefined.'

    entropy[indices] = expected

    # pick the candidate with the smallest expected entropy
    best_candidates = np.argsort(entropy)[:n_candidates]
    return best_candidates

def run_classifier(out_folder, trend_probs, referrers, y, train, test):

    F = referrers #static features
    etree = create_grid_search('lr', n_jobs = 1)
    
    y_pred = trend_probs[test].argmax(axis=1)
    save_results(out_folder, 'tl-base-lr', y_pred, y[test])

    aux = clone(etree)
    aux.fit(F[train], y[train])
    y_pred = aux.predict(F[test])
    save_results(out_folder, 'tree-feats', y_pred, y[test])
    
    aux = clone(etree)
    aux.fit(trend_probs[train], y[train])
    y_pred = aux.predict(trend_probs[test])
    save_results(out_folder, 'tree-probs', y_pred, y[test])
    
    C = np.hstack((F, trend_probs))
    aux = clone(etree)
    aux.fit(C[train], y[train])
    y_pred = aux.predict(C[test])
    save_results(out_folder, 'meta-combine', y_pred, y[test])

    #stack_clf = stacking.Stacking(3, [etree], 'tree')
    #stack_clf.fit(F[train], y[train], trend_probs[train])
    #y_pred = stack_clf.predict(F[test], trend_probs[test])
    #save_results(out_folder, 'meta-stack-tree', y_pred)
    
    stack_clf = stacking.Stacking(3, [etree], 'linear')
    stack_clf.fit(F[train], y[train], trend_probs[train])
    y_pred = stack_clf.predict(F[test], trend_probs[test])
    save_results(out_folder, 'meta-stack-linear', y_pred, y[test])

    def _validate_estimator(self):
        "Private function to validate SMOTE and ENN objects"
        if self.smote is not None:
            if isinstance(self.smote, SMOTE):
                self.smote_ = clone(self.smote)
            else:
                raise ValueError('smote needs to be a SMOTE object.'
                                 'Got {} instead.'.format(type(self.smote)))
        # Otherwise create a default SMOTE
        else:
            self.smote_ = SMOTE(
                sampling_strategy=self.sampling_strategy,
                random_state=self.random_state,
                n_jobs=self.n_jobs,
                ratio=self.ratio)

        if self.enn is not None:
            if isinstance(self.enn, EditedNearestNeighbours):
                self.enn_ = clone(self.enn)
            else:
                raise ValueError('enn needs to be an EditedNearestNeighbours.'
                                 ' Got {} instead.'.format(type(self.enn)))
        # Otherwise create a default EditedNearestNeighbours
        else:
            self.enn_ = EditedNearestNeighbours(
                            sampling_strategy='all',
                            n_jobs=self.n_jobs)

    def _validate_estimator(self):
        "Private function to validate SMOTE and ENN objects"

        if self.smote is not None:
            if isinstance(self.smote, SMOTE):
                self.smote_ = clone(self.smote)
            else:
                raise ValueError('smote needs to be a SMOTE object.'
                                 'Got {} instead.'.format(type(self.smote)))
        # Otherwise create a default SMOTE
        else:
            self.smote_ = SMOTE(
                sampling_strategy=self.sampling_strategy,
                random_state=self.random_state,
                ratio=self.ratio)

        if self.tomek is not None:
            if isinstance(self.tomek, TomekLinks):
                self.tomek_ = clone(self.tomek)
            else:
                raise ValueError('tomek needs to be a TomekLinks object.'
                                 'Got {} instead.'.format(type(self.tomek)))
        # Otherwise create a default TomekLinks
        else:
            self.tomek_ = TomekLinks(sampling_strategy='all')

def test_sklearn_clone():
    tm._skip_if_no_sklearn()
    from sklearn.base import clone

    clf = xgb.XGBClassifier(n_jobs=2, nthread=3)
    clf.n_jobs = -1
    clone(clf)

    def _fit_calibrators(self, df0, df1):
        df0 = df0.reshape(-1, 1)
        df1 = df1.reshape(-1, 1)

        if self.method == "kde":
            calibrator0 = KernelDensity()
            calibrator1 = KernelDensity()

        elif self.method == "histogram":
            eps = 0.05
            df_min = max(0, min(np.min(df0), np.min(df1)) - eps)
            df_max = min(1, max(np.max(df0), np.max(df1)) + eps)

            calibrator0 = Histogram(bins=10 + int(len(df0) ** (1. / 3.)),
                                    range=[(df_min, df_max)],
                                    interpolation="linear")
            calibrator1 = Histogram(bins=10 + int(len(df0) ** (1. / 3.)),
                                    range=[(df_min, df_max)],
                                    interpolation="linear")

        else:
            calibrator0 = clone(self.method)
            calibrator1 = clone(self.method)

        calibrator0.fit(df0)
        calibrator1.fit(df1)

        return calibrator0, calibrator1

def test_kernel_clone_after_set_params():
    # This test is to verify that using set_params does not
    # break clone on kernels.
    # This used to break because in kernels such as the RBF, non-trivial
    # logic that modified the length scale used to be in the constructor
    # See https://github.com/scikit-learn/scikit-learn/issues/6961
    # for more details.
    bounds = (1e-5, 1e5)
    for kernel in kernels:
        kernel_cloned = clone(kernel)
        params = kernel.get_params()
        # RationalQuadratic kernel is isotropic.
        isotropic_kernels = (ExpSineSquared, RationalQuadratic)
        if 'length_scale' in params and not isinstance(kernel,
                                                       isotropic_kernels):
            length_scale = params['length_scale']
            if np.iterable(length_scale):
                params['length_scale'] = length_scale[0]
                params['length_scale_bounds'] = bounds
            else:
                params['length_scale'] = [length_scale] * 2
                params['length_scale_bounds'] = bounds * 2
            kernel_cloned.set_params(**params)
            kernel_cloned_clone = clone(kernel_cloned)
            assert_equal(kernel_cloned_clone.get_params(),
                         kernel_cloned.get_params())
            assert_not_equal(id(kernel_cloned_clone), id(kernel_cloned))
            yield (check_hyperparameters_equal, kernel_cloned,
                   kernel_cloned_clone)

def nn_embedding_translate(words=en_2_es.keys(), embedding1=en_embedding, embedding2=es_embedding,
                           constraint=es_2_en.keys(), k=5,
                           pre_transform=None, log=False):
    if pre_transform is not None:
        pre_transform_1 = clone(pre_transform)
        pre_transform_2 = clone(pre_transform)
        embedding1 = transform(embedding1, pre_transform_1)
        embedding2 = transform(embedding2, pre_transform_2)

    if constraint is not None:
        embedding2 = sub_embedding(embedding2, constraint)

    in_vocab_words = [word for word in words if embedding1.normalize(word) is not None]
    if log:
        print "{} of {} words in vocab".format(len(in_vocab_words), len(words))

    output = {}
    for i, word in enumerate(in_vocab_words):
        if log and i % 100 == 0:
            print "{} of {} words".format(i, len(words))

        emb = embedding1.word_to_embedding(word)
        if emb is not None:
            trans = embedding2.words_closest_to_point(emb, k=k)
            trans = softmax(trans)
            output[word] = trans
    return output

def make_classifiers(method, balanced, labels, selectors=None, columns=None, random_state=None):
    estimators = {}
    class_weight = None
    if balanced:
        class_weight = 'balanced'

    # Make appropriate delegatation
    if 'lr' in method:
        estimator = LogisticRegression(n_jobs=1)
    elif 'svm' in method:
        estimator = SVC(probability=False)
    elif 'rf' in method:
        estimator = RandomForestClassifier(n_jobs=1)
    else:
        raise ValueError("Not implemented for method {}".format(method))

    estimator = estimator.set_params(**{'class_weight': class_weight, 'random_state': random_state})
    if hasattr(estimator, 'n_jobs'):
        estimator.set_params(**{'n_jobs': 1})

    if 'bagged' in method:
        for l in labels:
            named_estimators = zip(columns, [clone(estimator) for _ in columns])
            weights = [1] * len(columns)
            estimators[l] = HybridFeatureVotingClassifier(
                named_estimators, selectors, voting='soft', weights=weights, n_jobs=4
            )
    else:
        for l in labels:
            estimators[l] = clone(estimator)
    return estimators

def RunExp(StrModel:str, Param:str, FeaUsed:list, DataPath:str, Label:str, StrMeasure:str, std:bool = False, N:int = 0):
	Data = np.genfromtxt(DataPath + Label, delimiter = ',', dtype = int)
	Data = Data[:, np.newaxis]

	for f in FeaUsed:
		T = (np.genfromtxt(DataPath + Features[f], delimiter = ',' , dtype = float))
		if len(T.shape) < 2:
			T = T[:, np.newaxis]
		Data = np.concatenate((Data, T), axis = 1)

	if N > 0:
		Data = Data[:N, :]

	Lbl = Data[:, 0]
	Fea = Data[:,1:]
	if std:
		scaler = preprocessing.StandardScaler()
		Fea = scaler.fit_transform(Fea)

	Model = base.clone(Models[StrModel])
	SetParam(Model, Param)

	Model.fit(Fea, Lbl)
	Pred = Model.predict(Fea)
	st = Measures[StrMeasure](Lbl, Pred)
		
	sv = cross_validation.cross_val_score(base.clone(Models[StrModel]), Fea, Lbl, metrics.make_scorer(Measures[StrMeasure]), cv = 5, n_jobs = 5)

	return st, np.mean(sv)

    def fit(self, X):
        param_grid = list(ParameterGrid(self.param_grid))
        n_folds = len(self.cv)
        n_grid = len(param_grid)

        scores = np.zeros((n_folds, n_grid), dtype=np.float64)

        for i, (X_tr, X_te) in enumerate(self.cv.split(X)):
            for j, params in enumerate(param_grid):
                estimator = clone(self.estimator)
                estimator.set_params(**params)
                estimator.fit(X_tr)

                scores[i, j] = estimator.score(X_te)

        # FIXME: handle higher is better as well.
        best = scores.mean(axis=0).argmin()
        self.best_params_ = param_grid[best]

        # Refit
        if self.refit:
            self.best_estimator_ = clone(self.estimator)
            self.best_estimator_.set_params(**self.best_params_)
            self.best_estimator_.fit(X)

        return self

    def train(self,
              training_trackers,  # type: List[DialogueStateTracker]
              domain,  # type: Domain
              **kwargs  # type: **Any
              ):
        # type: (...) -> Dict[Text: Any]

        training_data = self.featurize_for_training(training_trackers,
                                                    domain,
                                                    **kwargs)

        X, y = self._extract_training_data(training_data)
        model = self.model_architecture(**kwargs)
        score = None
        # Note: clone is called throughout to avoid mutating default
        # arguments.
        self.label_encoder = clone(self.label_encoder).fit(y)
        Xt, yt = self._preprocess_data(X, y)

        if self.cv is None:
            model = clone(model).fit(Xt, yt)
        else:
            param_grid = self.param_grid or {}
            model, score = self._search_and_score(
                model, Xt, yt, param_grid)

        self.model = model
        logger.info("Done fitting sklearn policy model")
        if score is not None:
            logger.info("Cross validation score: {:.5f}".format(score))

def test_missing_value_handling(est, func, support_sparse):
    # check that the preprocessing method let pass nan
    rng = np.random.RandomState(42)
    X = iris.data.copy()
    n_missing = 50
    X[rng.randint(X.shape[0], size=n_missing),
      rng.randint(X.shape[1], size=n_missing)] = np.nan
    X_train, X_test = train_test_split(X, random_state=1)
    # sanity check
    assert not np.all(np.isnan(X_train), axis=0).any()
    assert np.any(np.isnan(X_train), axis=0).all()
    assert np.any(np.isnan(X_test), axis=0).all()
    X_test[:, 0] = np.nan  # make sure this boundary case is tested

    Xt = est.fit(X_train).transform(X_test)
    # missing values should still be missing, and only them
    assert_array_equal(np.isnan(Xt), np.isnan(X_test))

    # check that the function leads to the same results as the class
    Xt_class = est.transform(X_train)
    Xt_func = func(X_train, **est.get_params())
    assert_array_equal(np.isnan(Xt_func), np.isnan(Xt_class))
    assert_allclose(Xt_func[~np.isnan(Xt_func)], Xt_class[~np.isnan(Xt_class)])

    # check that the inverse transform keep NaN
    Xt_inv = est.inverse_transform(Xt)
    assert_array_equal(np.isnan(Xt_inv), np.isnan(X_test))
    # FIXME: we can introduce equal_nan=True in recent version of numpy.
    # For the moment which just check that non-NaN values are almost equal.
    assert_allclose(Xt_inv[~np.isnan(Xt_inv)], X_test[~np.isnan(X_test)])

    for i in range(X.shape[1]):
        # train only on non-NaN
        est.fit(_get_valid_samples_by_column(X_train, i))
        # check transforming with NaN works even when training without NaN
        Xt_col = est.transform(X_test[:, [i]])
        assert_array_equal(Xt_col, Xt[:, [i]])
        # check non-NaN is handled as before - the 1st column is all nan
        if not np.isnan(X_test[:, i]).all():
            Xt_col_nonan = est.transform(
                _get_valid_samples_by_column(X_test, i))
            assert_array_equal(Xt_col_nonan,
                               Xt_col[~np.isnan(Xt_col.squeeze())])

    if support_sparse:
        est_dense = clone(est)
        est_sparse = clone(est)

        Xt_dense = est_dense.fit(X_train).transform(X_test)
        Xt_inv_dense = est_dense.inverse_transform(Xt_dense)
        for sparse_constructor in (sparse.csr_matrix, sparse.csc_matrix,
                                   sparse.bsr_matrix, sparse.coo_matrix,
                                   sparse.dia_matrix, sparse.dok_matrix,
                                   sparse.lil_matrix):
            # check that the dense and sparse inputs lead to the same results
            Xt_sparse = (est_sparse.fit(sparse_constructor(X_train))
                         .transform(sparse_constructor(X_test)))
            assert_allclose(Xt_sparse.A, Xt_dense)
            Xt_inv_sparse = est_sparse.inverse_transform(Xt_sparse)
            assert_allclose(Xt_inv_sparse.A, Xt_inv_dense)

def RunExp(StrModel:str, Param:str, FeaUsed:list, DataPath:str, Label:str, std:bool = False, N:int = 0):
	Data = np.genfromtxt(DataPath + Label, delimiter = ',', dtype = int)
	Data = Data[:, np.newaxis]

	for f in FeaUsed:
		T = (np.genfromtxt(DataPath + Features[f], delimiter = ',' , dtype = float))
		if len(T.shape) < 2:
			T = T[:, np.newaxis]
		Data = np.concatenate((Data, T), axis = 1)
	
	if N > 0:
		Data = Data[:N, :]

	Lbl = Data[:, 0]
	Fea = Data[:,1:]
	if std:
		scaler = preprocessing.StandardScaler()
		Fea = scaler.fit_transform(Fea)

	Model = base.clone(Models[StrModel])
	SetParam(Model, Param)

	Model.fit(Fea, Lbl)
	Pred = Model.predict_proba(Fea)[:, 1]
	st = metrics.precision_recall_curve(Lbl, Pred)
		
	Folds = cross_validation.KFold(Fea.shape[0], n_folds = 5)
	for train, valid in Folds:
		Model = base.clone(Models[StrModel])
		SetParam(Model, Param)
		Model.fit(Fea[train], Lbl[train])
		Pred[valid] = Model.predict_proba(Fea[valid])[:, 1]
	
	sv = metrics.precision_recall_curve(Lbl, Pred)
	return st, sv