Python base.center_data函数代码示例

def test_center_data_weighted():
    n_samples = 200
    n_features = 2
    rng = check_random_state(0)
    X = rng.rand(n_samples, n_features)
    y = rng.rand(n_samples)
    sample_weight = rng.rand(n_samples)
    expected_X_mean = np.average(X, axis=0, weights=sample_weight)
    expected_y_mean = np.average(y, axis=0, weights=sample_weight)

    # XXX: if normalize=True, should we expect a weighted standard deviation?
    #      Currently not weighted, but calculated with respect to weighted mean
    # XXX: currently scaled to variance=n_samples
    expected_X_std = (np.sqrt(X.shape[0]) *
                      np.mean((X - expected_X_mean) ** 2, axis=0) ** .5)

    Xt, yt, X_mean, y_mean, X_std = center_data(X, y, fit_intercept=True,
                                                normalize=False,
                                                sample_weight=sample_weight)
    assert_array_almost_equal(X_mean, expected_X_mean)
    assert_array_almost_equal(y_mean, expected_y_mean)
    assert_array_almost_equal(X_std, np.ones(n_features))
    assert_array_almost_equal(Xt, X - expected_X_mean)
    assert_array_almost_equal(yt, y - expected_y_mean)

    Xt, yt, X_mean, y_mean, X_std = center_data(X, y, fit_intercept=True,
                                                normalize=True,
                                                sample_weight=sample_weight)
    assert_array_almost_equal(X_mean, expected_X_mean)
    assert_array_almost_equal(y_mean, expected_y_mean)
    assert_array_almost_equal(X_std, expected_X_std)
    assert_array_almost_equal(Xt, (X - expected_X_mean) / expected_X_std)
    assert_array_almost_equal(yt, y - expected_y_mean)

def test_center_data():
    n_samples = 200
    n_features = 2
    rng = check_random_state(0)
    X = rng.rand(n_samples, n_features)
    y = rng.rand(n_samples)
    expected_X_mean = np.mean(X, axis=0)
    # XXX: currently scaled to variance=n_samples
    expected_X_std = np.std(X, axis=0) * np.sqrt(X.shape[0])
    expected_y_mean = np.mean(y, axis=0)

    Xt, yt, X_mean, y_mean, X_std = center_data(X, y, fit_intercept=False,
                                                normalize=False)
    assert_array_almost_equal(X_mean, np.zeros(n_features))
    assert_array_almost_equal(y_mean, 0)
    assert_array_almost_equal(X_std, np.ones(n_features))
    assert_array_almost_equal(Xt, X)
    assert_array_almost_equal(yt, y)

    Xt, yt, X_mean, y_mean, X_std = center_data(X, y, fit_intercept=True,
                                                normalize=False)
    assert_array_almost_equal(X_mean, expected_X_mean)
    assert_array_almost_equal(y_mean, expected_y_mean)
    assert_array_almost_equal(X_std, np.ones(n_features))
    assert_array_almost_equal(Xt, X - expected_X_mean)
    assert_array_almost_equal(yt, y - expected_y_mean)

    Xt, yt, X_mean, y_mean, X_std = center_data(X, y, fit_intercept=True,
                                                normalize=True)
    assert_array_almost_equal(X_mean, expected_X_mean)
    assert_array_almost_equal(y_mean, expected_y_mean)
    assert_array_almost_equal(X_std, expected_X_std)
    assert_array_almost_equal(Xt, (X - expected_X_mean) / expected_X_std)
    assert_array_almost_equal(yt, y - expected_y_mean)

def test_randomized_logistic_sparse():
    """Check randomized sparse logistic regression on sparse data"""
    iris = load_iris()
    X = iris.data[:, [0, 2]]
    y = iris.target
    X = X[y != 2]
    y = y[y != 2]

    # center here because sparse matrices are usually not centered
    X, y, _, _, _ = center_data(X, y, True, True)

    X_sp = sparse.csr_matrix(X)

    F, _ = f_classif(X, y)

    scaling = 0.3
    clf = RandomizedLogisticRegression(verbose=False, C=1., random_state=42,
                                       scaling=scaling, n_resampling=50,
                                       tol=1e-3)
    feature_scores = clf.fit(X, y).scores_
    clf = RandomizedLogisticRegression(verbose=False, C=1., random_state=42,
                                       scaling=scaling, n_resampling=50,
                                       tol=1e-3)
    feature_scores_sp = clf.fit(X_sp, y).scores_
    assert_array_equal(feature_scores, feature_scores_sp)

    def fitting(self,XTrain, YTrain, XTest,YTest):

        YTrain_ = np.log(YTrain)
        if np.isnan(YTrain_).any():
            print("log y nan")
            return
        YTest_ = np.log(YTest)
        if np.isnan(YTest_).any():
            print("log y nan")
            return

        XTrain_transf = np.log(XTrain)
        if np.isnan(XTrain_transf):
            print("log x nan")
            return
        XTest_transf = np.log(XTest)
        if np.isnan(XTest_transf):
            print("log x nan")
            return

        ##centratura dei dati
        XTrain_transf, YTrain_, X_mean, y_mean, X_std = center_data(XTrain_transf, YTrain_, fit_intercept=True, normalize = True)
        XTest_transf, YTest_ = center_test(XTest_transf,YTest_,X_mean,y_mean,X_std)

        new_loss,_ = compute_lasso(XTrain_transf, YTrain_, XTest_transf, YTest_, score = "r2_score")

        print("loss log(y) e log(x) :", new_loss )

     def __init__(self, n_samples, n_features, interval, test_size = 0.33, normalize = True, centerdata = True, transformation=NullTransformation(), fit_intercept = True):
        self.n_samples = n_samples
        self.n_features = n_features
        self.transformation = transformation
        lower = interval[0]
        upper = interval[1]
        random.seed(1)
        data = [np.array([random.uniform(lower, upper) for j in range(n_features)]) for i in range(n_samples)]
        Y = map(lambda x : self.transformation.transform(x), data)

        self.X = np.row_stack(data)
        self.informative = Y[0][1]
        self.Y = map(itemgetter(0), Y)
        XTrain, XTest, YTrain, YTest = train_test_split(self.X, self.Y, test_size=test_size,random_state=0)
        self.XTrain_orig = XTrain
        self.XTest_orig = XTest
        self.YTrain_orig = YTrain
        self.YTest_orig = YTest
        if centerdata==True:
            self.XTrain, self.YTrain, X_mean, y_mean, X_std = center_data(XTrain, YTrain, fit_intercept=fit_intercept, normalize = normalize)
            self.XTest, self.YTest = self.center_test(XTest,YTest,X_mean,y_mean,X_std)
        else:
            self.XTrain = XTrain
            self.YTrain = YTrain
            self.XTest = XTest
            self.YTest = YTest

 def fit(self, X, y):
     X, _, self.X_mean, _, self.X_std = center_data(X, y, True, True, copy=False)
     X_t = self.pca.fit_transform(X)
     evr = numpy.cumsum(self.pca.explained_variance_ratio_)
     self.evr_idx = numpy.where(evr < self.explained_var)[0].max() + 1
     X_t = X_t[:,:(self.evr_idx+1)]
     print X.shape, X_t.shape, self.evr_idx
     self.svr.fit(X_t, y)

 def cross_val(self, X, y, n_fold, n_iter, lambd, model=None):
     """
     Perform general cross-validation
     :param X: Feature matrix
     :param y: Response
     :param n_fold: how many cross-val runs
     :param n_iter: training iterations
     :param lambd: reguralization parameter
     :param model: learning model *none* means current GraKeLasso
     :return:
     """
     X, y, X_mean, y_mean, X_std = center_data(X, y, fit_intercept=True, normalize=True)
     train_prct = 1 - (n_fold / 100.0)
     n_rows = np.floor(X.shape[0] * train_prct)
     index = np.ones(n_rows, dtype=bool)
     index = np.concatenate((index, np.zeros(X.shape[0] - n_rows - 1, dtype=bool)))
     avg_error = 0.0
     avg_theta = 0.0
     for i in xrange(n_fold):
         np.random.shuffle(index)
         new_index = 1-index
         new_index = np.array(new_index, dtype=bool)
         num_test_examples = sum(new_index)
         if model:
             model.l1_ratio_ = lambd # if model has this property, i.e. ElasticNet
             model.fit(X[index, :], y[index])
             theta = model.coef_
             y_temp = np.array(y[new_index])
             y_temp.shape = num_test_examples
         else:
             theta = self.train(X[index, :], y[index], lambd, n_iter)
             y_temp = np.array(y[new_index])
             y_temp.shape = (num_test_examples, 1)
             y_temp.shape = num_test_examples
         logging.info("Theta: %s", theta)
         predict = np.dot(X[new_index, :], theta)
         errors = y_temp - predict
         error = np.sqrt(1/(1.0*num_test_examples)*sum(np.square(errors)))
         avg_error += error
         avg_theta += 1.0 * (len([c for c in theta if c != 0])) / (1.0 * len(theta))
     avg_theta = avg_theta / (1.0 * n_fold)
     avg_error = avg_error / (1.0 * n_fold)
     return avg_error, avg_theta

print("transformation done")

X_transf, output_dict = enel_transf.transformPerTurbineLevel(
    dict_sample_turb, enel_dict, X, power_curve, X_transf, output_dict
)
print("transformation per turbine done")

XTrain_transf = X_transf[: XTrain.shape[0], :]
XTest_transf = X_transf[XTrain.shape[0] :, :]

##center data
XTrain_noCenter, XVal_noCenter, YTrain_noCenter, YVal_noCenter = train_test_split(
    XTrain_transf, YTrain, test_size=0.33, random_state=0
)
XTrain_, YTrain_, X_mean, y_mean, X_std = center_data(
    XTrain_noCenter, YTrain_noCenter, fit_intercept=True, normalize=True
)
XVal_, YVal_ = center_test(XVal_noCenter, YVal_noCenter, X_mean, y_mean, X_std)

values_TM = []
start_loss, _ = compute_lasso(XTrain_, YTrain_, XVal_, YVal_, score="mean_squared_error", values_TM=[])
print("loss", start_loss)

n_features_transf = XTrain_.shape[1]

####generation blocks
r = np.random.RandomState(11)
r1 = np.random.RandomState(12)
r2 = np.random.RandomState(13)
r4 = np.random.RandomState(15)

y_test[y_test=='scissors']=1
y_test[y_test=='scrambledpix']=-1
y_test=np.array(y_test.astype('double'))



masker = NiftiMasker(mask_strategy='epi',standardize=True)
                        
X_train = masker.fit_transform(X_train)
X_test  = masker.transform(X_test)

mask = masker.mask_img_.get_data().astype(np.bool)
mask= _crop_mask(mask)
background_img = mean_img(data_files.func[0])

X_train, y_train, _, y_train_mean, _ = center_data(X_train, y_train, fit_intercept=True, normalize=False,copy=False)
X_test-=X_train.mean(axis=0)
X_test/=np.std(X_train,axis=0)
alpha=1
ratio=0.5
k=200


solver_params = dict(tol=1e-6, max_iter=5000,prox_max_iter=100)

init=None
w,obj,init=tvksp_solver(X_train,y_train,alpha,ratio,k,mask=mask,init=init,loss="logistic",verbose=1,**solver_params)
coef=w[:-1]
intercept=w[-1]    
coef_img=masker.inverse_transform(coef)
y_pred=np.sign(X_test.dot(coef)+intercept)

def test_deprecation_center_data():
    n_samples = 200
    n_features = 2

    w = 1.0 + rng.rand(n_samples)
    X = rng.rand(n_samples, n_features)
    y = rng.rand(n_samples)

    param_grid = product([True, False], [True, False], [True, False],
                         [None, w])

    for (fit_intercept, normalize, copy, sample_weight) in param_grid:

        XX = X.copy()  # such that we can try copy=False as well

        X1, y1, X1_mean, X1_var, y1_mean = \
            center_data(XX, y, fit_intercept=fit_intercept,
                        normalize=normalize, copy=copy,
                        sample_weight=sample_weight)

        XX = X.copy()

        X2, y2, X2_mean, X2_var, y2_mean = \
            _preprocess_data(XX, y, fit_intercept=fit_intercept,
                             normalize=normalize, copy=copy,
                             sample_weight=sample_weight)

        assert_array_almost_equal(X1, X2)
        assert_array_almost_equal(y1, y2)
        assert_array_almost_equal(X1_mean, X2_mean)
        assert_array_almost_equal(X1_var, X2_var)
        assert_array_almost_equal(y1_mean, y2_mean)

    # Sparse cases
    X = sparse.csr_matrix(X)

    for (fit_intercept, normalize, copy, sample_weight) in param_grid:

        X1, y1, X1_mean, X1_var, y1_mean = \
            center_data(X, y, fit_intercept=fit_intercept, normalize=normalize,
                        copy=copy, sample_weight=sample_weight)

        X2, y2, X2_mean, X2_var, y2_mean = \
            _preprocess_data(X, y, fit_intercept=fit_intercept,
                             normalize=normalize, copy=copy,
                             sample_weight=sample_weight, return_mean=False)

        assert_array_almost_equal(X1.toarray(), X2.toarray())
        assert_array_almost_equal(y1, y2)
        assert_array_almost_equal(X1_mean, X2_mean)
        assert_array_almost_equal(X1_var, X2_var)
        assert_array_almost_equal(y1_mean, y2_mean)

    for (fit_intercept, normalize) in product([True, False], [True, False]):

        X1, y1, X1_mean, X1_var, y1_mean = \
            sparse_center_data(X, y, fit_intercept=fit_intercept,
                               normalize=normalize)

        X2, y2, X2_mean, X2_var, y2_mean = \
            _preprocess_data(X, y, fit_intercept=fit_intercept,
                             normalize=normalize, return_mean=True)

        assert_array_almost_equal(X1.toarray(), X2.toarray())
        assert_array_almost_equal(y1, y2)
        assert_array_almost_equal(X1_mean, X2_mean)
        assert_array_almost_equal(X1_var, X2_var)
        assert_array_almost_equal(y1_mean, y2_mean)

def path_scores(solver, X, y, mask, alphas, l1_ratios, train, test,
                solver_params, is_classif=False, n_alphas=10, eps=1E-3,
                key=None, debias=False, Xmean=None,
                screening_percentile=20., verbose=1):
    """Function to compute scores of different alphas in regression and
    classification used by CV objects

    Parameters
    ----------
    X : 2D array of shape (n_samples, n_features)
        Design matrix, one row per sample point.

    y : 1D array of length n_samples
        Response vector; one value per sample.

    mask : 3D arrays of boolean
        Mask defining brain regions that we work on.

    alphas : list of floats
        List of regularization parameters being considered.

    train : array or list of integers
        List of indices for the train samples.

    test : array or list of integers
        List of indices for the test samples.

    l1_ratio : float in the interval [0, 1]; optional (default .5)
        Constant that mixes L1 and TV (resp. Graph-Net) penalization.
        l1_ratio == 0: just smooth. l1_ratio == 1: just lasso.

    eps : float, optional (default 1e-3)
        Length of the path. For example, ``eps=1e-3`` means that
        ``alpha_min / alpha_max = 1e-3``.

    n_alphas : int, optional (default 10).
        Generate this number of alphas per regularization path.
        This parameter is mutually exclusive with the `alphas` parameter.

    solver : function handle
       See for example tv.TVl1Classifier documentation.

    solver_params: dict
       Dictionary of param-value pairs to be passed to solver.
    """
    if l1_ratios is None:
        raise ValueError("l1_ratios must be specified!")

    # misc
    _, n_features = X.shape
    verbose = int(verbose if verbose is not None else 0)

    # Univariate feature screening. Note that if we have only as few as 100
    # features in the mask's support, then we should use all of them to
    # learn the model i.e disable this screening)
    do_screening = (n_features > 100) and screening_percentile < 100.
    if do_screening:
        X, mask, support = _univariate_feature_screening(
            X, y, mask, is_classif, screening_percentile)

    # crop the mask to have a tighter bounding box
    mask = _crop_mask(mask)

    # get train and test data
    X_train, y_train = X[train].copy(), y[train].copy()
    X_test, y_test = X[test].copy(), y[test].copy()

    # it is essential to center the data in regression
    X_train, y_train, _, y_train_mean, _ = center_data(
        X_train, y_train, fit_intercept=True, normalize=False,
        copy=False)

    # misc
    if isinstance(l1_ratios, numbers.Number):
        l1_ratios = [l1_ratios]
    l1_ratios = sorted(l1_ratios)[::-1]  # from large to small l1_ratios
    best_score = -np.inf
    best_secondary_score = -np.inf
    best_l1_ratio = l1_ratios[0]
    best_alpha = None
    best_init = None
    all_test_scores = []
    if len(test) > 0.:
        # do l1_ratio path
        for l1_ratio in l1_ratios:
            this_test_scores = []

            # make alpha grid
            if alphas is None:
                alphas_ = _space_net_alpha_grid(
                    X_train, y_train, l1_ratio=l1_ratio, eps=eps,
                    n_alphas=n_alphas, logistic=is_classif)
            else:
                alphas_ = alphas
            alphas_ = sorted(alphas_)[::-1]  # from large to small l1_ratios

            # do alpha path
            if best_alpha is None:
                best_alpha = alphas_[0]
            init = None
#.........这里部分代码省略.........

    def _dense_fit(self, X, y, Xy=None, coef_init=None):

        # copy was done in fit if necessary
        X, y, X_mean, y_mean, X_std = center_data(
            X, y, self.fit_intercept, self.normalize, copy=False)

        if y.ndim == 1:
            y = y[:, np.newaxis]
        if Xy is not None and Xy.ndim == 1:
            Xy = Xy[:, np.newaxis]

        n_samples, n_features = X.shape
        n_targets = y.shape[1]
        
        precompute = self.precompute
        if hasattr(precompute, '__array__') \
                and not np.allclose(X_mean, np.zeros(n_features)) \
                and not np.allclose(X_std, np.ones(n_features)):
            # recompute Gram
            precompute = 'auto'
            Xy = None

        coef_ = self._init_coef(coef_init, n_features, n_targets)
        dual_gap_ = np.empty(n_targets)
        eps_ = np.empty(n_targets)

        l1_reg = self.alpha*self.l1_ratio * n_samples
        l2_reg = 0.0#self.alpha * (1.0 - self.l1_ratio) * n_samples

        # precompute if n_samples > n_features
        if hasattr(precompute, '__array__'):
            Gram = precompute
        elif precompute or (precompute == 'auto' and n_samples > n_features):
            Gram = np.dot(X.T, X)
        else:
            Gram = None
        
        for k in xrange(n_targets):
            if Gram is None:
                coef_[k, :], dual_gap_[k], eps_[k] = \
                    cd_fast.enet_coordinate_descent(
                        coef_[k, :], l1_reg, l2_reg, X, y[:, k], self.max_iter,
                        self.tol, True)
            else:
                Gram = Gram.copy()
                if Xy is None:
                    this_Xy = np.dot(X.T, y[:, k])
                else:
                    this_Xy = Xy[:, k]
                coef_[k, :], dual_gap_[k], eps_[k] = \
                    cd_fast.enet_coordinate_descent_gram(
                        coef_[k, :], l1_reg, l2_reg, Gram, this_Xy, y[:, k],
                        self.max_iter, self.tol, True)

            if dual_gap_[k] > eps_[k]:
                warnings.warn('Objective did not converge for ' +
                              'target %d, you might want' % k +
                              ' to increase the number of iterations')

        self.coef_, self.dual_gap_, self.eps_ = (np.squeeze(a) for a in
                                                 (coef_, dual_gap_, eps_))
        self._set_intercept(X_mean, y_mean, X_std)

        # return self for chaining fit and predict calls
        return self