Python numpy.count_nonzero函数代码示例

    def verify(self, mask, exp):

        maxDiffRatio = 0.02
        expArea = np.count_nonzero(exp)
        nonIntersectArea = np.count_nonzero(mask != exp)
        curRatio = float(nonIntersectArea) / expArea
        return curRatio < maxDiffRatio

    def __init__(self, image, skin_mask, labeled_image, label_number,
                 rectangle_slices):
        """Creates a new skin region.

            image: The entire image in YCrCb mode.
            skin_mask: The entire image skin mask.
            labeled_image: A matrix of the size of the image with the region
                label in each position. See scipy.ndimage.measurements.label.
            label_number: The label number of this skin region.
            rectangle_slices: The slices to get the rectangle of the image in
                which the region fits as returned by
                scipy.ndimage.measurements.find_objects.
        """
        self.region_skin_pixels = np.count_nonzero(
            labeled_image[rectangle_slices] == label_number
        )

        self.bounding_rectangle_size = \
            (
                rectangle_slices[1].start - rectangle_slices[0].start
            ) * (
                rectangle_slices[1].stop - rectangle_slices[0].stop
            )

        self.bounding_rectangle_skin_pixels = np.count_nonzero(
            skin_mask[rectangle_slices]
        )

        self.bounding_rectangle_avarage_pixel_intensity = np.average(
            image[rectangle_slices].take([0], axis=2)
        )

def despike(self, n=3, recursive=False, verbose=False):
    """
    Replace spikes with np.NaN.
    Removing spikes that are >= n * std.
    default n = 3.

    """

    result = self.values.copy()
    outliers = (np.abs(self.values - nanmean(self.values)) >= n *
                nanstd(self.values))

    removed = np.count_nonzero(outliers)
    result[outliers] = np.NaN

    if verbose and not recursive:
        print("Removing from %s\n # removed: %s" % (self.name, removed))

    counter = 0
    if recursive:
        while outliers.any():
            result[outliers] = np.NaN
            outliers = np.abs(result - nanmean(result)) >= n * nanstd(result)
            counter += 1
            removed += np.count_nonzero(outliers)
        if verbose:
            print("Removing from %s\nNumber of iterations: %s # removed: %s" %
                  (self.name, counter, removed))
    return Series(result, index=self.index, name=self.name)

def cost_logit(X, A, R, lam, n, k):
    '''
    The cost function

    n is the number of examples
    k is the feature dimension
    R is the matrix indicating which entries of A are known.
    '''
    # get the matrices
    # U, V, beta, alpha
    U = X[:n*k]
    U = np.reshape(U, (n,k))
    V = X[n*k:2*n*k]
    V = np.reshape(V, (n,k))
    beta = X[2*n*k:2*n*k+n]
    beta = np.reshape(beta, (n,1))
    alpha = X[-1]
    num_knowns = np.count_nonzero(R)
    num_edges = np.count_nonzero(np.multiply(A, R))
    num_nonedges = num_knowns - num_edges
    h = alpha + np.dot(U, np.transpose(V))
    # add beta to every row, column
    for i in range(h.shape[0]):
        for j in range(h.shape[1]):
            h[i,j] += beta[i]+beta[j]
    sigH = sigmoid(h)
    J = ((-A/(2*num_edges))*np.log(sigH)) - (((1-A)/(2*num_nonedges))*np.log(1-sigH))
    J = J*R
    # regularizer
    for i in range(J.shape[0]):
        for j in range(J.shape[1]):
            J[i,j] += lam*( np.abs(beta[i])**2 + np.abs(beta[j])**2 + np.linalg.norm(U[i,:])**2 + np.linalg.norm(V[j,:])**2 )
    # sum over known values
    cost = sum(sum(J))
    return cost

def print_results(labels, predictions):
    total = len(labels)
    num_correct = total - np.count_nonzero(np.subtract(predictions,labels))
    print "\n***** ACCURACY *****"
    print "Overall Accuracy: %.3f percent\n" % ((float(num_correct)/float(total)) * 100.0)

    results = pd.DataFrame()
    results['real'] = labels
    results['predicted'] = predictions

    for label in np.unique(labels):
        data = results[results['real'] == label]
        num_correct = len(data) - np.count_nonzero(data['real'].sub(data['predicted']))
        acc = ((float(num_correct)/float(len(data))) * 100.0)
        print "Total class label '%s' accuracy: %f percent" % (label, acc)
    print ""

    # Distribution graphs
    utils.print_distribution_graph(labels, 'Actual Distribution of Classes')
    utils.print_distribution_graph(predictions, 'Distribution of Predictions')

    # Distribution graphs for each class label
    for label in np.unique(labels):
        data = results[results['predicted'] == label]['real'].tolist()
        title = "When class label '%s' was predicted, the actual class was:" % label
        utils.print_distribution_graph(data, title)

def norm_mean_cent(movies_np):
    mean_movie= []
    
    count_movie = []

    for row in movies_np:
        row_sum = np.sum(row)
        count = np.count_nonzero(row)
        count_movie.append(count)
        mean_movie.append(row_sum/count)
    
    count_user = []
    mean_user = []

    for row in movies_np.T:
        row_sum = np.sum(row)
        count = np.count_nonzero(row)
        count_user.append(count)
        mean_user.append(row_sum/count)

    movies_np[movies_np==0] = np.nan

    mean_cent = []
    i = 0
    for row in  movies_np:
        mean_cent.append(row - mean_movie[i]) 
        i += 1
    
    mean_cent = np.array(mean_cent)
    mean_cent = np.nan_to_num(mean_cent)
    
    return mean_cent

def analyze_param(net, layers):
#   plt.figure()
    print '\n=============analyze_param start==============='
    total_nonzero = 0
    total_allparam = 0
    percentage_list = []
    for i, layer in enumerate(layers):
        i += 1
        W = net.params[layer][0].data
        b = net.params[layer][1].data
#       plt.subplot(3, 1, i);
#       numBins = 2 ^ 8
#       plt.hist(W.flatten(), numBins, color='blue', alpha=0.8)
#       plt.show()
        print 'W(%d) range = [%f, %f]' % (i, min(W.flatten()), max(W.flatten()))
        print 'W(%d) mean = %f, std = %f' % (i, np.mean(W.flatten()), np.std(W.flatten()))
        non_zero = (np.count_nonzero(W.flatten()) + np.count_nonzero(b.flatten()))
        all_param = (np.prod(W.shape) + np.prod(b.shape))
        this_layer_percentage = non_zero / float(all_param)
        total_nonzero += non_zero
        total_allparam += all_param
        print 'non-zero W and b cnt = %d' % non_zero
        print 'total W and b cnt = %d' % all_param
        print 'percentage = %f\n' % (this_layer_percentage)
        percentage_list.append(this_layer_percentage)
    print '=====> summary:'
    print 'non-zero W and b cnt = %d' % total_nonzero
    print 'total W and b cnt = %d' % total_allparam
    print 'percentage = %f' % (total_nonzero / float(total_allparam))
    print '=============analyze_param ends ==============='
    return (total_nonzero / float(total_allparam), percentage_list)

def test_that_build_pyramid_relaxes_mask():
    from _stbt.match import _build_pyramid

    mask = numpy.ones((20, 20, 3), dtype=numpy.uint8) * 255
    mask[3:9, 3:9] = 0  # first 0 is an even row/col, last 0 is an odd row/col
    n = mask.size - numpy.count_nonzero(mask)
    assert n == 6 * 6 * 3
    cv2.imwrite("/tmp/dave1.png", mask)

    mask_pyramid = _build_pyramid(mask, 2, is_mask=True)
    assert numpy.all(mask_pyramid[0] == mask)

    downsampled = mask_pyramid[1]
    cv2.imwrite("/tmp/dave2.png", downsampled)
    assert downsampled.shape == (10, 10, 3)
    print downsampled[:, :, 0]  # pylint:disable=unsubscriptable-object
    n = downsampled.size - numpy.count_nonzero(downsampled)
    assert 3 * 3 * 3 <= n <= 6 * 6 * 3
    expected = [
        # pylint:disable=bad-whitespace
        [255, 255, 255, 255, 255, 255, 255, 255, 255, 255],
        [255,   0,   0,   0,   0,   0, 255, 255, 255, 255],
        [255,   0,   0,   0,   0,   0, 255, 255, 255, 255],
        [255,   0,   0,   0,   0,   0, 255, 255, 255, 255],
        [255,   0,   0,   0,   0,   0, 255, 255, 255, 255],
        [255,   0,   0,   0,   0,   0, 255, 255, 255, 255],
        [255, 255, 255, 255, 255, 255, 255, 255, 255, 255],
        [255, 255, 255, 255, 255, 255, 255, 255, 255, 255],
        [255, 255, 255, 255, 255, 255, 255, 255, 255, 255],
        [255, 255, 255, 255, 255, 255, 255, 255, 255, 255]]
    assert numpy.all(downsampled[:, :, 0] == expected)  # pylint:disable=unsubscriptable-object

    def __precision(self, y_test, Y_vote):
        """ precision extended to multi-class classification """
        # predicted classes
        y_hat = np.argmax(Y_vote, axis=1)

        if True or self.mode == "one-vs-one":
            # need confusion matrix
            conf = self.__confusion(y_test, Y_vote)

            # consider each class separately
            prec = np.zeros(self.numClasses)
            for c in xrange(self.numClasses):
                # true positives: label is c, classifier predicted c
                tp = conf[c,c]

                # false positives: label is c, classifier predicted not c
                fp = np.sum(conf[:,c]) - conf[c,c]

                # precision
                prec[c] = tp*1./(tp+fp)
        elif self.mode == "one-vs-rest":
            # consider each class separately
            prec = np.zeros(self.numClasses)
            for c in xrange(self.numClasses):
                # true positives: label is c, classifier predicted c
                tp = np.count_nonzero((y_test==c) * (y_hat==c))

                # false positives: label is c, classifier predicted not c
                fp = np.count_nonzero((y_test==c) * (y_hat!=c))

                prec[c] = tp*1./(tp+fp)
        return prec

 def testFeatureGenWithOnePoint(self):
   # ensure that the start and end datetimes are the same, since the average calculation uses
   # the total distance and the total duration
   ts = esta.TimeSeries.get_time_series(self.testUUID)
   trackpoint1 = ecwlo.Location({u'coordinates': [0,0], 'type': 'Point'})
   ts.insert_data(self.testUUID, "analysis/recreated_location", trackpoint1)
   testSeg = ecws.Section({"start_loc": trackpoint1,
               "end_loc": trackpoint1,
               "distance": 500,
               "sensed_mode": 1,
               "duration": 150,
               "start_ts": arrow.now().timestamp,
               "end_ts": arrow.now().timestamp,
               "_id": 2,
               "speeds":[],
               "distances":[],
               })
   testSegEntry = ecwe.Entry.create_entry(self.testUUID, "analysis/cleaned_section", testSeg)
   d = testSegEntry.data
   m = testSegEntry.metadata
   enufc.expand_start_end_data_times(d, m)
   testSegEntry["data"] = d
   testSegEntry["metadata"] = m
   inserted_id = ts.insert(testSegEntry)
   featureMatrix = np.zeros([1, len(self.pipeline.featureLabels)])
   resultVector = np.zeros(1)
   self.pipeline.updateFeatureMatrixRowWithSection(featureMatrix, 0, testSegEntry) 
   logging.debug("featureMatrix = %s" % featureMatrix)
   self.assertEqual(np.count_nonzero(featureMatrix[0][5:16]), 0)
   self.assertEqual(np.count_nonzero(featureMatrix[0][19:21]), 0)

    def corners(self, bandNames=None):
        "Return the corners of the tilted rectangle of valid image data as (x, y) pixel coordinates."
        alpha = self.mask(bandNames)
        alphaT = numpy.transpose(alpha)
        ysize, xsize = alpha.shape

        output = []
        for i in xrange(ysize):
            if numpy.count_nonzero(alpha[i]) > 0:
                break
        output.append((numpy.argwhere(alpha[i]).mean(), i))

        for i in xrange(xsize):
            if numpy.count_nonzero(alphaT[i]) > 0:
                break
        output.append((i, numpy.argwhere(alphaT[i]).mean()))

        for i in xrange(ysize - 1, 0, -1):
            if numpy.count_nonzero(alpha[i]) > 0:
                break
        output.append((numpy.argwhere(alpha[i]).mean(), i))

        for i in xrange(xsize - 1, 0, -1):
            if numpy.count_nonzero(alphaT[i]) > 0:
                break
        output.append((i, numpy.argwhere(alphaT[i]).mean()))

        return output

  def __init__(self,
               op_type,
               op_name,
               output_index,
               num_outputs,
               value):
    """Constructor of InfOrNanError.

    Args:
      op_type: Type name of the op that generated the tensor that generated the
        `inf`(s) or `nan`(s) (e.g., `Div`).
      op_name: Name of the op that generated the tensor with `inf`(s) or
        `nan`(s). This name is set by client and can be `None` if it is unset.
      output_index: The 0-based output index of the tensor that contains
        `inf`(s) or `nan`(s).
      num_outputs: Total number of outputs of the operation.
      value: The tensor value that contains `inf`(s) or `nan`(s).
    """
    self._op_type = op_type
    self._op_name = op_name
    self._output_index = output_index
    self._num_outputs = num_outputs
    self._value = value

    self._total_count = np.size(value)
    self._inf_count = np.count_nonzero(np.isinf(value))
    self._nan_count = np.count_nonzero(np.isnan(value))

    super(InfOrNanError, self).__init__(self._get_error_message())

def go(sltree, score, X_train, Y_train, X_test, Y_test):
    t_train_begin = time()
    sltree.train(X_train, Y_train)
    t_train_end = time()
    t_test_begin = time()
    Y_predict_train, AP_train, complexity_train, depths_train = sltree.test(X_train, Y_train, return_complexity=True, return_depth=True)
    Y_predict_test, AP_test, complexity_test, depths_test = sltree.test(X_test, Y_test, return_complexity=True, return_depth=True)
    t_test_end = time()
    n_acc_train = np.count_nonzero(Y_predict_train == Y_train)
    n_acc_test = np.count_nonzero(Y_predict_test == Y_test)

    score.update({'acc_train':float(n_acc_train)/Y_predict_train.shape[0],
                  'n_acc_train':n_acc_train,
                  'AP_train':AP_train,
                  'mAP_train':np.mean(AP_train),
                  'complexity_train':complexity_train,
                  'avg_complexity_train':np.mean(complexity_train),
                  'depths_train':depths_train,
                  'avg_depth_train':np.mean(depths_train),
                  'acc_test':float(n_acc_test)/Y_predict_test.shape[0],
                  'n_acc_test':n_acc_test,
                  'AP_test':AP_test,
                  'mAP_test':np.mean(AP_test),
                  'complexity_test':complexity_test,
                  'avg_complexity_test':np.mean(complexity_test),
                  'depths_test':depths_test,
                  'avg_depth_test':np.mean(depths_test),
                  'time_test':t_test_end-t_test_begin})

 def get_stats(self):
     # number of trades
     num_of_trades = self.record.shape[0] / 2
     # number of profit_lock_out
     num_of_profitlock = np.count_nonzero(np.where(self.record[:,2] == "profit_lock_out"))
     # number of stop_out
     num_of_stopout = np.count_nonzero(np.where(self.record[:,2] == "trailing_stop_out" ))
     num_of_stopout += np.count_nonzero(np.where(self.record[:,2] == "hard_stop_out" ))
     # number of reversed_out
     num_of_reversed_out = np.count_nonzero(np.where(self.record[:,2] == "reversed_out"))
     # number of time_out
     num_of_time_out = np.count_nonzero(np.where(self.record[:,2] == "time_out"))
     # PNL
     i = 1
     for i in range(1, num_of_trades * 2, 2):
         if self.record[i, 3] == "long":
             self.pnl = np.append(self.pnl,float(self.record[i,4])-float(self.record[i-1,4]))
         elif self.record[i, 3] == "short":
             self.pnl = np.append(self.pnl,float(self.record[i-1,4])-float(self.record[i,4]))
     lst.pnl = lst.pnl[1:]
     # output statistical results
     print "# trades", num_of_trades, "# profit_lock", num_of_profitlock,\
           "# stopout", num_of_stopout, "# reversed_out",\
           num_of_reversed_out, "# time_out", num_of_time_out
     print "P&L Summary Stats:", lst.pnl.__len__(), lst.pnl.mean()/tickBase, lst.pnl.std()/tickBase, lst.pnl.min()/tickBase, lst.pnl.max()/tickBase

 def relearn(self, test_size=0):
     samples, weights, targets = self.learning_component.get_training_set(const_weight=True)
     train_samples, test_samples, train_targets, test_targets = train_test_split(samples, targets, test_size=test_size, random_state=np.random.RandomState(0))
     count_positives = 1.0*np.count_nonzero(train_targets)
     count_negatives = 1.0*(len(train_targets) - count_positives)
     positive_weight = count_negatives/len(train_targets)
     negative_weight = count_positives/len(train_targets)
     weights = np.array([positive_weight if target == 1 else negative_weight for target in train_targets])
     self.classifier.fit(train_samples, train_targets, sample_weight=weights)
     self.learning_component.new_samples_count = 0
     if len(test_samples) > 0:
         test_result = [self.classifier.predict(sample) for sample in test_samples]
         true_positives = 0.0
         count_test_positives = 1.0*np.count_nonzero(test_targets)
         count_result_positives = 1.0*np.count_nonzero(test_result)
         for i in xrange(len(test_targets)):
             if test_targets[i] == test_result[i] and test_result[i] == 1:
                 true_positives += 1
         precision = true_positives / count_test_positives
         recall = true_positives / count_result_positives
         print "Precision:", precision
         print "Recall", recall
         if precision + recall != 0:
             print "F-score:", 2 * precision * recall / (precision + recall)
         else:
             print "F-score:", 0
     self.positive_class_index = 0
     for elem in self.classifier.classes_:
         if elem != 1.0:
             self.positive_class_index += 1
         else:
             break