Python validation.check_arrays函数代码示例

    def reduce_data(self, X, y):
        if self.classifier == None:
            self.classifier = KNeighborsClassifier(n_neighbors=self.n_neighbors)
        if self.classifier.n_neighbors != self.n_neighbors:
            self.classifier.n_neighbors = self.n_neighbors

        X, y = check_arrays(X, y, sparse_format="csr")

        classes = np.unique(y)
        self.classes_ = classes

        if self.n_neighbors >= len(X):
            self.X_ = np.array(X)
            self.y_ = np.array(y)
            self.reduction_ = 0.0

        mask = np.zeros(y.size, dtype=bool)

        tmp_m = np.ones(y.size, dtype=bool)
        for i in xrange(y.size):
            tmp_m[i] = not tmp_m[i]
            self.classifier.fit(X[tmp_m], y[tmp_m])
            sample, label = X[i], y[i]

            if self.classifier.predict(sample) == [label]:
                mask[i] = not mask[i]

            tmp_m[i] = not tmp_m[i]

        self.X_ = np.asarray(X[mask])
        self.y_ = np.asarray(y[mask])
        self.reduction_ = 1.0 - float(len(self.y_)) / len(y)
        return self.X_, self.y_

def _my_lrap(y_true, y_score):
    """Simple implementation of label ranking average precision"""
    y_true, y_score = check_arrays(y_true, y_score)
    n_samples, n_labels = y_true.shape
    score = np.empty((n_samples, ))
    for i in range(n_samples):
        # The best rank correspond to 1. Rank higher than 1 are worse.
        # The best inverse ranking correspond to n_labels.
        unique_rank, inv_rank = np.unique(y_score[i], return_inverse=True)
        n_ranks = unique_rank.size
        rank = n_ranks - inv_rank

        # Rank need to be corrected to take into account ties
        # ex: rank 1 ex aequo means that both label are rank 2.
        corr_rank = np.bincount(rank, minlength=n_ranks + 1).cumsum()
        rank = corr_rank[rank]

        relevant = y_true[i].nonzero()[0]
        if relevant.size == 0 or relevant.size == n_labels:
            score[i] = 1
            continue

        score[i] = 0.
        for label in relevant:
            # Let's count the number of relevant label with better rank
            # (smaller rank).
            n_ranked_above = sum(rank[r] <= rank[label] for r in relevant)

            # Weight by the rank of the actual label
            score[i] += n_ranked_above / rank[label]

        score[i] /= relevant.size

    return score.mean()

    def reduce_data(self, X, y):
        
        X, y = check_arrays(X, y, sparse_format="csr")

        if self.classifier == None:
            self.classifier = KNeighborsClassifier(n_neighbors=self.n_neighbors)

        prots_s = []
        labels_s = []

        classes = np.unique(y)
        self.classes_ = classes

        for cur_class in classes:
            mask = y == cur_class
            insts = X[mask]
            prots_s = prots_s + [insts[np.random.randint(0, insts.shape[0])]]
            labels_s = labels_s + [cur_class]


        self.classifier.fit(prots_s, labels_s)
        for sample, label in zip(X, y):
            if self.classifier.predict(sample) != [label]:
                prots_s = prots_s + [sample]
                labels_s = labels_s + [label]
                self.classifier.fit(prots_s, labels_s)
       
        self.X_ = np.asarray(prots_s)
        self.y_ = np.asarray(labels_s)
        self.reduction_ = 1.0 - float(len(self.y_))/len(y)
        return self.X_, self.y_

    def fit(self, X, y, sample_weight=None):
        X, y = check_arrays(X, y, dtype=DTYPE, sparse_format="dense", check_ccontiguous=True)
        sample_weight = check_sample_weight(y, sample_weight=sample_weight)
        sample_weight = normalize_weight(y, sample_weight, sig_weight=self.sig_weight)
        self.random_state = check_random_state(self.random_state)
        self.estimators = []
        score = numpy.zeros(len(X), dtype=float)
        y_signed = 2 * y - 1

        self.w_sig = []
        self.w_bck = []

        for _ in range(self.n_estimators):
            residual = y_signed
            # numpy.exp(- y_signed * score)
            # residual[y > 0.5] /= numpy.mean(residual[y > 0.5])
            # residual[y < 0.5] /= -numpy.mean(residual[y < 0.5])

            trainX, testX, trainY, testY, trainW, testW, trainR, testR, trainS, testS = \
                train_test_split(X, y, sample_weight, residual, score,
                                 train_size=self.train_part, test_size=self.test_size, random_state=self.random_state)

            tree = DecisionTreeRegressor(criterion=self.criterion, splitter=self.splitter,
                                         max_depth=self.max_depth, min_samples_leaf=self.min_samples_leaf,
                                         max_features=self.max_features, random_state=self.random_state)

            # fitting
            tree.fit(trainX, trainR, sample_weight=trainW, check_input=False)

            # post-pruning
            self.update_terminal_regions(tree.tree_, testX, testY, testW, testS)

            # updating score
            # score += self.learning_rate * tree.predict(X)
            self.estimators.append(tree)

def calc_hist_with_errors(x, weight=None, bins=60, normed=True, x_range=None, ignored_sideband=0.0):
    """
    Calculate data for error bar (for plot pdf with errors)

    :param x: data
    :type x: list or numpy.array
    :param weight: weights
    :type weight: None or list or numpy.array

    :return: tuple (x-points (list), y-points (list), y points errors (list), x points errors (list))
    """
    weight = numpy.ones(len(x)) if weight is None else weight
    x, weight = check_arrays(x, weight)

    if x_range is None:
        x_range = numpy.percentile(x, [100 * ignored_sideband, 100 * (1 - ignored_sideband)])

    ans, bins = numpy.histogram(x, bins=bins, normed=normed, weights=weight, range=x_range)
    yerr = []
    normalization = 1.0
    if normed:
        normalization = float(len(bins) - 1) / float(sum(weight)) / (x_range[1] - x_range[0])
    for i in range(len(bins) - 1):
        weight_bin = weight[(x > bins[i]) * (x <= bins[i + 1])]
        yerr.append(numpy.sqrt(sum(weight_bin * weight_bin)) * normalization)
    bins_mean = [0.5 * (bins[i] + bins[i + 1]) for i in range(len(ans))]
    xerr = [0.5 * (bins[i + 1] - bins[i]) for i in range(len(ans))]
    return bins_mean, ans, yerr, xerr

    def reduce_data(self, X, y):
        X, y = check_arrays(X, y, sparse_format="csr")

        if self.classifier == None:
            self.classifier = KNeighborsClassifier(n_neighbors=self.n_neighbors)
        if self.classifier.n_neighbors != self.n_neighbors:
            self.classifier.n_neighbors = self.n_neighbors

        classes = np.unique(y)
        self.classes_ = classes

        # loading inicial groups
        self.groups = []
        for label in classes:
            mask = y == label
            self.groups = self.groups + [_Group(X[mask], label)]

        self._main_loop()
        self._generalization_step()
        self._merge()
        self._pruning()
        self.X_ = np.asarray([g.rep_x for g in self.groups])
        self.y_ = np.asarray([g.label for g in self.groups])
        self.reduction_ = 1.0 - float(len(self.y_))/len(y)
        return self.X_, self.y_

def cvm_flatness(y, proba, X, uniform_variables, sample_weight=None, label=1, knn=30):
    """ The most simple way to compute Cramer-von Mises flatness, this is however very slow
    if you need to compute it many times
    :param y: real classes of events, shape = [n_samples]
    :param proba: predicted probabilities, shape = [n_samples, n_classes]
    :param X: pandas.DataFrame with uniform features (i.e. test dataset)
    :param uniform_variables: features, along which uniformity is desired, list of strings
    :param sample_weight: weights of events, shape = [n_samples]
    :param label: class, for which uniformity is measured (usually, 0 is bck, 1 is signal)
    :param knn: number of nearest neighbours used in knn

    Example of usage:
    proba = classifier.predict_proba(testX)
    cvm_flatness(testY, proba=proba, X=testX, uniform_variables=['mass'])
    """
    y, proba = check_arrays(y, proba)
    assert len(y) == len(proba) == len(X), 'Different lengths'
    y = column_or_1d(y)
    sample_weight = check_sample_weight(y, sample_weight=sample_weight)

    X = pandas.DataFrame(X)

    signal_mask = y == label
    groups_indices = computeSignalKnnIndices(uniform_variables=uniform_variables, dataframe=X,
                                             is_signal=signal_mask, n_neighbors=knn)
    groups_indices = groups_indices[signal_mask, :]

    return ut.group_based_cvm(proba[:, label], mask=signal_mask, groups_indices=groups_indices,
                              sample_weight=sample_weight)

def plot_score_variable_correlation(y_true, y_pred, correlation_values, cuts, sample_weight=None, classifier_name="",
                                    var_name="", score_function=efficiency_score, bins_number=20):
    """
    Different score functions available: Efficiency, Precision, Recall, F1Score, and other things from sklearn.metrics
    :param y_pred: numpy.array, of shape [n_samples]
    :param y_true: numpy.array, of shape [n_samples] with float predictions
    :param correlation_values: numpy.array of shape [n_samples], usually that is masses of events
    :param cuts: array-like of cuts, for each cut a separate
    :param sample_weight: numpy.array or None, shape = [n_samples]
    :param classifier_name: str, used only in label
    :param var_name: str, i.e. 'mass'
    :param score_function: any function with signature (y_true, y_pred, sample_weight=None)
    :param bins_number: int, the number of bins
    """
    y_true, y_pred, correlation_values = check_arrays(y_true, y_pred, correlation_values)
    sample_weight = check_sample_weight(y_true, sample_weight=sample_weight)

    binner = Binner(correlation_values, n_bins=bins_number)
    bins_data = binner.split_into_bins(correlation_values, y_true, y_pred, sample_weight)
    for cut in cuts:
        x_values = []
        y_values = []
        for bin_data in bins_data:
            bin_masses, bin_y_true, bin_proba, bin_weight = bin_data
            y_values.append(score_function(bin_y_true, bin_proba[:, 1] > cut, sample_weight=bin_weight))
            x_values.append(numpy.mean(bin_masses))
        pylab.plot(x_values, y_values, '.-', label="cut = %0.3f" % cut)

    pylab.title("Correlation with results of " + classifier_name)
    pylab.xlabel(var_name)
    pylab.ylabel(score_function.__name__)
    pylab.legend(loc="lower right")

    def transform(self, X, y=None):
        """Project the data by using matrix product with the random matrix

        Parameters
        ----------
        X : numpy array or scipy.sparse of shape [n_samples, n_features]
            The input data to project into a smaller dimensional space.

        y : is not used: placeholder to allow for usage in a Pipeline.

        Returns
        -------
        X_new : numpy array or scipy sparse of shape [n_samples, n_components]
            Projected array.

        """
        X, y = check_arrays(X, y)

        if self.components_ is None:
            raise ValueError('No random projection matrix had been fit.')

        if X.shape[1] != self.components_.shape[1]:
            raise ValueError(
                'Impossible to perform projection:'
                'X at fit stage had a different number of features.'
                '(%s != %s)' % (X.shape[1], self.components_.shape[1]))

        if not sp.issparse(X):
            X = np.atleast_2d(X)

        X_new = safe_sparse_dot(X, self.components_.T,
                                dense_output=self.dense_output)
        return X_new

def reorder_by_first(*arrays):
    """
    Applies the same permutation to all passed arrays,
    permutation sorts the first passed array
    """
    arrays = check_arrays(*arrays)
    order = numpy.argsort(arrays[0])
    return [arr[order] for arr in arrays]

    def fit(self, X, y, sample_weight=None):
        sample_weight = check_sample_weight(y, sample_weight=sample_weight)
        assert len(X) == len(y), 'Different lengths of X and y'
        X = pandas.DataFrame(X)
        y = numpy.array(column_or_1d(y), dtype=int)
        assert numpy.all(numpy.in1d(y, [0, 1])), 'Only two-class classification supported'
        self.check_params()

        self.estimators = []
        self.scores = []

        n_samples = len(X)
        n_inbag = int(self.subsample * len(X))
        self.loss = copy.copy(self.loss)
        self.loss.fit(X, y, sample_weight=sample_weight)

        # preparing for fitting in trees
        X = self.get_train_vars(X)
        self.n_features = X.shape[1]
        X, y = check_arrays(X, y, dtype=DTYPE, sparse_format="dense", check_ccontiguous=True)
        y_pred = numpy.zeros(len(X), dtype=float)

        if self.init_estimator is not None:
            y_signed = 2 * y - 1
            self.init_estimator.fit(X, y_signed, sample_weight=sample_weight)
            y_pred += numpy.ravel(self.init_estimator.predict(X))

        for stage in range(self.n_estimators):
            # tree creation
            tree = DecisionTreeRegressor(
                criterion=self.criterion,
                splitter=self.splitter,
                max_depth=self.max_depth,
                min_samples_split=self.min_samples_split,
                min_samples_leaf=self.min_samples_leaf,
                max_features=self.max_features,
                random_state=self.random_state,
                max_leaf_nodes=self.max_leaf_nodes)

            # tree learning
            residual = self.loss.negative_gradient(y_pred)
            train_indices = self.random_state.choice(n_samples, size=n_inbag, replace=False)

            tree.fit(X[train_indices], residual[train_indices],
                     sample_weight=sample_weight[train_indices], check_input=False)
            # update tree leaves
            if self.update_tree:
                self.loss.update_tree(tree.tree_, X=X, y=y, y_pred=y_pred, sample_weight=sample_weight,
                                      update_mask=numpy.ones(len(X), dtype=bool), residual=residual)

            y_pred += self.learning_rate * tree.predict(X)
            self.estimators.append(tree)
            self.scores.append(self.loss(y_pred))
        return self

def _log_loss(y_true, y_pred, eps=1e-10, sample_weight=None):
    """ This is shorter ans simpler version og log_loss, which supports sample_weight """
    sample_weight = check_sample_weight(y_true, sample_weight=sample_weight)
    y_true, y_pred, sample_weight = check_arrays(y_true, y_pred, sample_weight)
    y_true = column_or_1d(y_true)

    lb = LabelBinarizer()
    T = lb.fit_transform(y_true)
    if T.shape[1] == 1:
        T = numpy.append(1 - T, T, axis=1)

    # Clipping
    Y = numpy.clip(y_pred, eps, 1 - eps)

    # Check if dimensions are consistent.
    T, Y = check_arrays(T, Y)

    # Renormalize
    Y /= Y.sum(axis=1)[:, numpy.newaxis]
    loss = -(T * numpy.log(Y) * sample_weight[:, numpy.newaxis]).sum() / numpy.sum(sample_weight)
    return loss

    def fit(self, X):
        """Creates a biclustering for X.

        Parameters
        ----------
        X : array-like, shape (n_samples, n_features)

        """
        X, = check_arrays(X, sparse_format="csr", dtype=np.float64)
        check_array_ndim(X)
        self._check_parameters()
        self._fit(X)

def plot_roc(y_true, y_pred, sample_weight=None, classifier_name="", is_cut=False, mask=None):
    """Plots ROC curve in the way physicists like it
    :param y_true: numpy.array, shape=[n_samples]
    :param y_pred: numpy.array, shape=[n_samples]
    :param sample_weight: numpy.array | None, shape = [n_samples]
    :param classifier_name: str, the name of classifier for label
    :param is_cut: predictions are binary
    :param mask: plot ROC curve only for events that have mask=True
    """
    if is_cut:
        assert len(numpy.unique(y_pred)) == 2, 'Cut assumes that prediction are 0 and 1 (or True/False)'

    MAX_STEPS = 500
    y_true, y_pred = check_arrays(y_true, y_pred)
    if mask is not None:
        mask = numpy.array(mask, dtype=bool)  # converting to bool, just in case
        y_true = y_true[mask]
        y_pred = y_pred[mask]
        if sample_weight is not None:
            sample_weight = sample_weight[mask]

    fpr, tpr, thresholds = check_arrays(*roc_curve(y_true, y_pred, sample_weight=sample_weight))
    roc_auc = auc(fpr, tpr)
    # tpr = recall = isSasS / isS = signal efficiency
    # fpr = isBasS / isB = 1 - specificity = 1 - backgroundRejection
    bg_rejection = 1. - fpr

    if len(fpr) > MAX_STEPS:
        # decreasing the number of points in plot
        targets = numpy.linspace(0, 1, MAX_STEPS)
        x_ids = numpy.searchsorted(tpr, targets)
        y_ids = numpy.searchsorted(fpr, targets)
        indices = numpy.concatenate([x_ids, y_ids, [0, len(tpr) - 1]], )
        indices = numpy.unique(indices)
        tpr = tpr[indices]
        bg_rejection = bg_rejection[indices]
    if not is_cut:
        pylab.plot(tpr, bg_rejection, label='%s (area = %0.3f)' % (classifier_name, roc_auc))
    else:
        pylab.plot(tpr[1:2], bg_rejection[1:2], 'o', label='%s' % classifier_name)

def plot_roc(y_true, y_pred, sample_weight=None, classifier_name=""):
    """Plots ROC curve in the way physicist like it
    :param y_true: numpy.array, shape=[n_samples]
    :param y_pred: numpy.array, shape=[n_samples]
    :param sample_weight: numpy.array | None, shape = [n_samples]
    :param classifier_name: str, the name of classifier for label
    """
    y_true, y_pred = check_arrays(y_true, y_pred)
    fpr, tpr, thresholds = roc_curve(y_true, y_pred, sample_weight=sample_weight)
    # tpr = recall = isSasS / isS = signal efficiency
    # fpr = isBasS / isB = 1 - specificity ?=?  1 - backgroundRejection
    bg_rejection = 1. - numpy.array(fpr)
    roc_auc = auc(fpr, tpr)
    pylab.plot(tpr, bg_rejection, label='%s (area = %0.3f)' % (classifier_name, roc_auc))