Python numpy.mean() Examples

def get_graph_stats(graph_obj_handle, prop='degrees'):
    # if prop == 'degrees':
    num_cores = multiprocessing.cpu_count()
    inputs = [int(i*len(graph_obj_handle)/num_cores) for i in range(num_cores)] + [len(graph_obj_handle)]
    res = Parallel(n_jobs=num_cores)(delayed(get_values)(graph_obj_handle, inputs[i], inputs[i+1], prop) for i in range(num_cores))

    stat_dict = {}

    if 'degrees' in prop:
        stat_dict['degrees'] = list(set([d for core_res in res for file_res in core_res for d in file_res['degrees']]))
    if 'edge_labels' in prop:
        stat_dict['edge_labels'] = list(set([d for core_res in res for file_res in core_res for d in file_res['edge_labels']]))
    if 'target_mean' in prop or 'target_std' in prop:
        param = np.array([file_res['params'] for core_res in res for file_res in core_res])
    if 'target_mean' in prop:
        stat_dict['target_mean'] = np.mean(param, axis=0)
    if 'target_std' in prop:
        stat_dict['target_std'] = np.std(param, axis=0)

    return stat_dict 

def __init__(self, bam, keepReads=False):
        self.insertSizes = []
        self.readLengths = []
        self.orientations = []
        self._insertSizeKDE = None
        self.singleEnded = False

        self._insertSizeScores = {} # cache

        try:
            self.insertSizes, self.reads, self.orientations, self.readLengths = sampleInsertSizes(bam, keepReads=keepReads)
            if len(self.insertSizes) > 1:
                logging.info("  insert size mean: {:.2f} std: {:.2f}".format(numpy.mean(self.insertSizes), numpy.std(self.insertSizes)))
        except ValueError as e:
            print("*"*100, "here")
            print("ERROR:", e) 

def extract_sequence_and_score(graph=None):
    # make dict with positions as keys and lists of ids as values
    pos_to_ids = defaultdict(list)
    for u in graph.nodes():
        if 'position' not in graph.node[u]:  # no position attributes in graph, use the vertex id instead
            raise Exception('Missing "position" attribute in node:%s %s' % (u, graph.node[u]))
        else:
            pos = graph.node[u]['position']
        # accumulate all node ids
        pos_to_ids[pos] += [u]

    # extract sequence of labels and importances
    seq = [None] * len(pos_to_ids)
    score = [0] * len(pos_to_ids)
    for pos in sorted(pos_to_ids):
        ids = pos_to_ids[pos]
        labels = [graph.node[u].get('label', 'N/A') for u in ids]
        # check that all labels for the same position are identical
        assert(sum([1 for label in labels if label == labels[0]]) == len(labels)
               ), 'ERROR: non identical labels referring to same position: %s  %s' % (pos, labels)
        seq[pos] = labels[0]
        # average all importance score for the same position
        importances = [graph.node[u].get('importance', 0) for u in ids]
        score[pos] = np.mean(importances)
    return seq, score 

def train(self):
        while (self.epoch < self.option.max_epoch and not self.early_stopped):
            self.one_epoch_train()
            self.one_epoch_valid()
            self.one_epoch_test()
            self.epoch += 1
            model_path = self.saver.save(self.sess, 
                                         self.option.model_path,
                                         global_step=self.epoch)
            print("Model saved at %s" % model_path)
            
            if self.early_stop():
                self.early_stopped = True
                print("Early stopped at epoch %d" % (self.epoch))
        
        all_test_in_top = [np.mean(x[1]) for x in self.test_stats]
        best_test_epoch = np.argmax(all_test_in_top)
        best_test = all_test_in_top[best_test_epoch]
        
        msg = "Best test in top: %0.4f at epoch %d." % (best_test, best_test_epoch + 1)       
        print(msg)
        self.log_file.write(msg + "\n")
        pickle.dump([self.train_stats, self.valid_stats, self.test_stats],
                    open(os.path.join(self.option.this_expsdir, "results.pckl"), "w")) 

def _raise_on_mode(self, mode):
        """
        Checks that the provided query mode is one of the accepted values. If
        not, raises a :obj:`ValueError`.
        """
        valid_modes = [
            'random_sample',
            'random_sample_per_pix',
            'samples',
            'median',
            'mean',
            'best',
            'percentile']

        if mode not in valid_modes:
            raise ValueError(
                '"{}" is not a valid `mode`. Valid modes are:\n'
                '  {}'.format(mode, valid_modes)
            ) 

def __init__(self,node_i, node_j, node_k, node_l,t, E, mu, rho, name=None):
        #8-nodes
        self.__nodes.append(node_i)
        self.__nodes.append(node_j)
        self.__nodes.append(node_k)
        self.__nodes.append(node_l)

        self.__t=t
        
        center=np.mean([node_i,node_j,node_k,node_l])
#        self.local_csys = CoordinateSystem.cartisian(center,nodes[4],nodes[5])
        
        self.__alpha=[]#the angle between edge and local-x, to be added
        self.__alpha.append(self.angle(node_i,node_j,self.local_csys.x))
        self.__alpha.append(self.angle(node_j,node_k,self.local_csys.x))
        self.__alpha.append(self.angle(node_k,node_l,self.local_csys.x))
        self.__alpha.append(self.angle(node_l,node_i,self.local_csys.x))

        self.__K=np.zeros((24,24)) 

def _bbox_forward_train(self, x, sampling_results, gt_bboxes, gt_labels,
                            img_metas):
        num_imgs = len(img_metas)
        rois = bbox2roi([res.bboxes for res in sampling_results])
        bbox_results = self._bbox_forward(x, rois)

        bbox_targets = self.bbox_head.get_targets(sampling_results, gt_bboxes,
                                                  gt_labels, self.train_cfg)
        # record the `beta_topk`-th smallest target
        # `bbox_targets[2]` and `bbox_targets[3]` stand for bbox_targets
        # and bbox_weights, respectively
        pos_inds = bbox_targets[3][:, 0].nonzero().squeeze(1)
        num_pos = len(pos_inds)
        cur_target = bbox_targets[2][pos_inds, :2].abs().mean(dim=1)
        beta_topk = min(self.train_cfg.dynamic_rcnn.beta_topk * num_imgs,
                        num_pos)
        cur_target = torch.kthvalue(cur_target, beta_topk)[0].item()
        self.beta_history.append(cur_target)
        loss_bbox = self.bbox_head.loss(bbox_results['cls_score'],
                                        bbox_results['bbox_pred'], rois,
                                        *bbox_targets)

        bbox_results.update(loss_bbox=loss_bbox)
        return bbox_results 

def update_hyperparameters(self):
        """Update hyperparameters like IoU thresholds for assigner and beta for
        SmoothL1 loss based on the training statistics.

        Returns:
            tuple[float]: the updated ``iou_thr`` and ``beta``.
        """
        new_iou_thr = max(self.train_cfg.dynamic_rcnn.initial_iou,
                          np.mean(self.iou_history))
        self.iou_history = []
        self.bbox_assigner.pos_iou_thr = new_iou_thr
        self.bbox_assigner.neg_iou_thr = new_iou_thr
        self.bbox_assigner.min_pos_iou = new_iou_thr
        new_beta = min(self.train_cfg.dynamic_rcnn.initial_beta,
                       np.median(self.beta_history))
        self.beta_history = []
        self.bbox_head.loss_bbox.beta = new_beta
        return new_iou_thr, new_beta 

def fast_eval_recall(self, results, proposal_nums, iou_thrs, logger=None):
        gt_bboxes = []
        for i in range(len(self.img_ids)):
            ann_ids = self.coco.get_ann_ids(img_ids=self.img_ids[i])
            ann_info = self.coco.load_anns(ann_ids)
            if len(ann_info) == 0:
                gt_bboxes.append(np.zeros((0, 4)))
                continue
            bboxes = []
            for ann in ann_info:
                if ann.get('ignore', False) or ann['iscrowd']:
                    continue
                x1, y1, w, h = ann['bbox']
                bboxes.append([x1, y1, x1 + w, y1 + h])
            bboxes = np.array(bboxes, dtype=np.float32)
            if bboxes.shape[0] == 0:
                bboxes = np.zeros((0, 4))
            gt_bboxes.append(bboxes)

        recalls = eval_recalls(
            gt_bboxes, results, proposal_nums, iou_thrs, logger=logger)
        ar = recalls.mean(axis=1)
        return ar 

def cal_train_time(log_dicts, args):
    for i, log_dict in enumerate(log_dicts):
        print(f'{"-" * 5}Analyze train time of {args.json_logs[i]}{"-" * 5}')
        all_times = []
        for epoch in log_dict.keys():
            if args.include_outliers:
                all_times.append(log_dict[epoch]['time'])
            else:
                all_times.append(log_dict[epoch]['time'][1:])
        all_times = np.array(all_times)
        epoch_ave_time = all_times.mean(-1)
        slowest_epoch = epoch_ave_time.argmax()
        fastest_epoch = epoch_ave_time.argmin()
        std_over_epoch = epoch_ave_time.std()
        print(f'slowest epoch {slowest_epoch + 1}, '
              f'average time is {epoch_ave_time[slowest_epoch]:.4f}')
        print(f'fastest epoch {fastest_epoch + 1}, '
              f'average time is {epoch_ave_time[fastest_epoch]:.4f}')
        print(f'time std over epochs is {std_over_epoch:.4f}')
        print(f'average iter time: {np.mean(all_times):.4f} s/iter')
        print() 

def test_generate_np_targeted_gives_adversarial_example(self):
        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), np.random.randint(0, 1, 100)] = 1
        x_adv = self.attack.generate_np(x_val, max_iterations=100,
                                        binary_search_steps=3,
                                        initial_const=1,
                                        clip_min=-5, clip_max=5,
                                        batch_size=100, y_target=feed_labs)

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(np.argmax(feed_labs, axis=1) == new_labs)
                        > 0.9) 

def test_generate_gives_adversarial_example(self):

        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        orig_labs = np.argmax(self.sess.run(self.model(x_val)), axis=1)
        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), orig_labs] = 1
        x = tf.placeholder(tf.float32, x_val.shape)
        y = tf.placeholder(tf.float32, feed_labs.shape)

        x_adv_p = self.attack.generate(x, max_iterations=100,
                                       binary_search_steps=3,
                                       initial_const=1,
                                       clip_min=-5, clip_max=5,
                                       batch_size=100, y=y)
        self.assertEqual(x_val.shape, x_adv_p.shape)
        x_adv = self.sess.run(x_adv_p, {x: x_val, y: feed_labs})

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(orig_labs == new_labs) < 0.1) 

def test_generate_np_targeted_gives_adversarial_example(self):
        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), np.random.randint(0, 1, 100)] = 1
        x_adv = self.attack.generate_np(x_val, max_iterations=100,
                                        binary_search_steps=3,
                                        initial_const=1,
                                        clip_min=-5, clip_max=5,
                                        batch_size=100, y_target=feed_labs)

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(np.argmax(feed_labs, axis=1) == new_labs) >
                        0.9) 

def test_generate_gives_adversarial_example(self):

        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        orig_labs = np.argmax(self.sess.run(self.model(x_val)), axis=1)
        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), orig_labs] = 1
        x = tf.placeholder(tf.float32, x_val.shape)
        y = tf.placeholder(tf.float32, feed_labs.shape)

        x_adv_p = self.attack.generate(x, max_iterations=100,
                                       binary_search_steps=3,
                                       initial_const=1,
                                       clip_min=-5, clip_max=5,
                                       batch_size=100, y=y)
        self.assertEqual(x_val.shape, x_adv_p.shape)
        x_adv = self.sess.run(x_adv_p, {x: x_val, y: feed_labs})

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(orig_labs == new_labs) < 0.1) 

def test_generate_gives_adversarial_example(self):

        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        orig_labs = np.argmax(self.sess.run(self.model(x_val)), axis=1)
        x = tf.placeholder(tf.float32, x_val.shape)

        x_adv_p = self.attack.generate(x, over_shoot=0.02, max_iter=50,
                                       nb_candidate=2, clip_min=-5, clip_max=5)
        self.assertEqual(x_val.shape, x_adv_p.shape)
        x_adv = self.sess.run(x_adv_p, {x: x_val})

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(orig_labs == new_labs) < 0.1) 

def test_attack_strength(self):
        """
        If clipping is not done at each iteration (not using clip_min and
        clip_max), this attack fails by
        np.mean(orig_labels == new_labels) == .5
        """
        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        x_adv = self.attack.generate_np(x_val, eps=1.0, eps_iter=0.05,
                                        clip_min=0.5, clip_max=0.7,
                                        nb_iter=5)

        orig_labs = np.argmax(self.sess.run(self.model(x_val)), axis=1)
        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)
        self.assertTrue(np.mean(orig_labs == new_labs) < 0.1) 

def test_generate_np_targeted_gives_adversarial_example(self):
        x_val = np.random.rand(100, 2)
        x_val = np.array(x_val, dtype=np.float32)

        feed_labs = np.zeros((100, 2))
        feed_labs[np.arange(100), np.random.randint(0, 1, 100)] = 1
        x_adv = self.attack.generate_np(x_val, max_iterations=100,
                                        binary_search_steps=3,
                                        initial_const=1,
                                        clip_min=-5, clip_max=5,
                                        batch_size=100, y_target=feed_labs)

        new_labs = np.argmax(self.sess.run(self.model(x_adv)), axis=1)

        self.assertTrue(np.mean(np.argmax(feed_labs, axis=1) == new_labs)
                        > 0.9) 

def __forward(self, x, train_flg):
        if self.running_mean is None:
            N, D = x.shape
            self.running_mean = np.zeros(D)
            self.running_var = np.zeros(D)

        if train_flg:
            mu = x.mean(axis=0)
            xc = x - mu
            var = np.mean(xc ** 2, axis=0)
            std = np.sqrt(var + 10e-7)
            xn = xc / std

            self.batch_size = x.shape[0]
            self.xc = xc
            self.xn = xn
            self.std = std
            self.running_mean = self.momentum * self.running_mean + (1 - self.momentum) * mu
            self.running_var = self.momentum * self.running_var + (1 - self.momentum) * var
        else:
            xc = x - self.running_mean
            xn = xc / ((np.sqrt(self.running_var + 10e-7)))

        out = self.gamma * xn + self.beta
        return out 

def average_forest(forest):
    avg_forest = [[space for x in range(width)] for y in range(height)]

    for i, x in enumerate(range(1, forest_width, scale)):
        for j, y in enumerate(range(1, forest_height, scale)):
            neighbours = get_neighbours(x, y, avg_size)
            red = int(numpy.mean([forest[n[0]][n[1]][0] for n in neighbours]))
            green = int(numpy.mean([forest[n[0]][n[1]][1] for n in neighbours]))
            blue = int(numpy.mean([forest[n[0]][n[1]][2] for n in neighbours]))
            avg_forest[i][j] = [red, green, blue]

    return avg_forest 

def addVariantResults(self, dataHub):
        variant = str(dataHub.variant)
        for sampleName, sample in dataHub.samples.items():
            counts = collections.Counter()
            reasons = {}
            alnScores = collections.defaultdict(list)
            insertSizes = collections.defaultdict(list)

            # collect stats
            for alnCollection in sample.alnCollections:
                allele = alnCollection.choice
                counts[allele] += 1

                if not allele in reasons:
                    reasons[allele] = collections.Counter()

                reasons[allele][alnCollection.why] += 1
                alnScores[allele].append(sum(aln.score for aln in alnCollection.chosenSet().getAlignments()))
                insertSizes[allele].append(len(alnCollection.chosenSet()))



            # record stats
            for allele, count in counts.items():
                self.stats.append([variant, sampleName, allele, "count", count])

            for allele in reasons:
                for reason in reasons[allele]:
                    self.stats.append([variant, sampleName, allele, "reason_{}".format(reason), reasons[allele][reason]])

            for allele in alnScores:
                self.stats.append([variant, sampleName, allele, "alnScore_mean", numpy.mean(alnScores[allele])])
                self.stats.append([variant, sampleName, allele, "alnScore_std", numpy.std(alnScores[allele])])

            for allele in insertSizes:
                self.stats.append([variant, sampleName, allele, "insertSize_mean", numpy.mean(insertSizes[allele])])
                self.stats.append([variant, sampleName, allele, "insertSize_std", numpy.std(insertSizes[allele])]) 

def meanInsertSize(self):
        if self.hasInsertSizeDistribution():
            return mean(self.insertSizes)
        return None 

def meanReadLength(self):
        if self.hasReadLengthDistribution():
            return mean(self.readLengths)
        return None 

def risk(self, Z, theta, q):
        """
        Compute target contrastive pessimistic risk.

        Parameters
        ----------
        Z : array
            target samples (M samples by D features)
        theta : array
            classifier parameters (D features by K classes)
        q : array
            soft labels (M samples by K classes)

        Returns
        -------
        float
            Value of risk function.

        """
        # Number of classes
        K = q.shape[1]

        # Compute negative log-likelihood
        L = self.neg_log_likelihood(Z, theta)

        # Weight loss by soft labels
        for k in range(K):
            L[:, k] *= q[:, k]

        # Sum over weighted losses
        L = np.sum(L, axis=1)

        # Risk is average loss
        return np.mean(L, axis=0) 

def error_rate(self, preds, u_):
        """Compute classification error rate."""
        return np.mean(preds != u_, axis=0) 

def reg_cov(self, X):
        """
        Regularize covariance matrix until non-singular.

        Parameters
        ----------
        C : array
            square symmetric covariance matrix.

        Returns
        -------
        C : array
            regularized covariance matrix.

        """
        # Compute mean of data
        muX = np.mean(X, axis=0, keepdims=1)

        # Compute covariance matrix without regularization
        SX = np.cov((X - muX).T)

        # Initialize regularization parameter
        reg = 1e-6

        # Keep going until non-singular
        while not self.is_pos_def(SX):

            # Compute covariance matrix with regularization
            SX = np.cov((X - muX).T) + reg*np.eye(X.shape[1])

            # Increment reg
            reg *= 10

        # Report regularization
        print('Final regularization parameter = {}'.format(reg))

        return SX 

def score(self, Z, U, zscore=False):
        """
        Compute classification error on test set.

        Parameters
        ----------
        Z : array
            new data set (M samples x D features)
        zscore : boolean
            whether to transform the data using z-scoring (def: false)

        Returns
        -------
        preds : array
            label predictions (M samples x 1)

        """
        # If classifier is trained, check for same dimensionality
        if self.is_trained:
            if not self.train_data_dim == Z.shape[1]:
                raise ValueError("""Test data is of different dimensionality
                                 than training data.""")

        # Make predictions
        preds = self.predict(Z, zscore=zscore)

        # Compute error
        return np.mean(preds != U) 

def reg_cov(self, X):
        """
        Regularize covariance matrix until non-singular.

        Parameters
        ----------
        C : array
            square symmetric covariance matrix.

        Returns
        -------
        C : array
            regularized covariance matrix.

        """
        # Number of data points
        N = X.shape[0]

        # Compute mean of data
        muX = np.mean(X, axis=0, keepdims=1)

        # Compute covariance matrix without regularization
        SX = np.dot((X - muX).T, (X - muX)) / N

        # Initialize regularization parameter
        reg = 1e-6

        # Keep going until non-singular
        while not self.is_pos_def(SX):

            # Compute covariance matrix with regularization
            SX = np.dot((X - muX).T, (X - muX)) / N + reg*np.eye(X.shape[1])

            # Increment reg
            reg *= 10

        # Report regularization
        print('Final regularization parameter = {}'.format(reg))

        return SX 

def heatmap(values, xlabel, ylabel, xticklabels, yticklabels, cmap=None,
            vmin=None, vmax=None, ax=None, fmt="%0.2f"):
    """heatmap."""
    if ax is None:
        ax = plt.gca()
    # plot the mean cross-validation scores
    img = ax.pcolor(values, cmap=cmap, vmin=vmin, vmax=vmax)
    img.update_scalarmappable()
    ax.set_xlabel(xlabel)
    ax.set_ylabel(ylabel)
    ax.set_xticks(np.arange(len(xticklabels)) + .5)
    ax.set_yticks(np.arange(len(yticklabels)) + .5)
    ax.set_xticklabels(xticklabels)
    ax.set_yticklabels(yticklabels)
    ax.set_aspect(1)

    for p, color, value in zip(img.get_paths(),
                               img.get_facecolors(),
                               img.get_array()):
        x, y = p.vertices[:-2, :].mean(0)
        if np.mean(color[:3]) > 0.5:
            c = 'k'
        else:
            c = 'w'
        ax.text(x, y, fmt % value, color=c, ha="center", va="center")
    return img 

def bias_variance_decomposition(self, graphs, targets,
                                    cv=5, n_bootstraps=10):
        """bias_variance_decomposition."""
        x = self.transform(graphs)
        score_list = []
        for i in range(n_bootstraps):
            scores = cross_val_score(
                self.model, x, targets, cv=cv)
            score_list.append(scores)
        score_list = np.array(score_list)
        mean_scores = np.mean(score_list, axis=1)
        std_scores = np.std(score_list, axis=1)
        return mean_scores, std_scores 

def _eval_params(graphs, targets, param_distr):
    # sample parameters
    params = _sample_params(param_distr)
    # create model with those parameters
    est = EdenEstimator(**params)
    # run a cross_val_score
    scores = est.cross_val_score(graphs, targets)
    # return average
    return np.mean(scores), params