如何将ggplot2的geom_dotplot（）与对称隔开的点一起使用

Question

当loss = tf.losses.sigmoid_cross_entropy(multi_class_labels=labels, logits=logits)大于1时，我在将点对称地放置在def read_dataset(filename, mode, batch_size = 512): def _input_fn(): def decode_csv(value_column): columns = tf.decode_csv(value_column, record_defaults = DEFAULTS) features = dict(zip(CSV_COLUMNS, columns)) label = features.pop(LABEL_COLUMS) return features, label # Create list of file names that match "glob" pattern (i.e. data_file_*.csv) filenames_dataset = tf.data.Dataset.list_files(filename) # Read lines from text files textlines_dataset = filenames_dataset.flat_map( lambda filename: ( tf.data.TextLineDataset(filename) .skip(1) )) # Parse text lines as comma-separated values (CSV) dataset = textlines_dataset.map(decode_csv) # Note: # use tf.data.Dataset.flat_map to apply one to many transformations (here: filename -> text lines) # use tf.data.Dataset.map to apply one to one transformations (here: text line -> feature list) if mode == tf.estimator.ModeKeys.TRAIN: num_epochs = None # indefinitely dataset = dataset.shuffle(buffer_size = 10 * batch_size) else: num_epochs = 1 # end-of-input after this dataset = dataset.repeat(num_epochs).batch(batch_size) batch_features, batch_labels = dataset.make_one_shot_iterator().get_next() return batch_features, batch_labels return _input_fn he_init = tf.keras.initializers.he_normal() def build_fully_connected(X, n_units=100, activation=tf.keras.activations.relu, initialization=he_init, batch_normalization=False, training=False, name=None): layer = tf.keras.layers.Dense(n_units, activation=None, kernel_initializer=he_init, name=name)(X) if batch_normalization: bn = tf.keras.layers.BatchNormalization(momentum=0.90) layer = bn(layer, training=training) return activation(layer) def output_layer(h, n_units, initialization=he_init, batch_normalization=False, training=False): logits = tf.keras.layers.Dense(n_units, activation=None)(h) if batch_normalization: bn = tf.keras.layers.BatchNormalization(momentum=0.90) logits = bn(logits, training=training) return logits # build model ACTIVATION = tf.keras.activations.relu BATCH_SIZE = 550 HIDDEN_UNITS = [256, 128, 16, 1] LEARNING_RATE = 0.01 NUM_STEPS = 10 USE_BATCH_NORMALIZATION = False def dnn_custom_estimator(features, labels, mode, params): in_training = mode == tf.estimator.ModeKeys.TRAIN use_batch_norm = params['batch_norm'] net = tf.feature_column.input_layer(features, params['features']) for i, n_units in enumerate(params['hidden_units']): net = build_fully_connected(net, n_units=n_units, training=in_training, batch_normalization=use_batch_norm, activation=params['activation'], name='hidden_layer'+str(i)) logits = output_layer(net, 1, batch_normalization=use_batch_norm, training=in_training) print (logits.get_shape()) print (labels.get_shape()) predicted_classes = tf.argmax(logits, 1) loss = tf.losses.sigmoid_cross_entropy(multi_class_labels=labels, logits=logits) accuracy = tf.metrics.accuracy(labels=tf.argmax(labels, 1), predictions=predicted_classes, name='acc_op') tf.summary.scalar('accuracy', accuracy[1]) # for visualizing in TensorBoard if mode == tf.estimator.ModeKeys.EVAL: return tf.estimator.EstimatorSpec(mode, loss=loss, eval_metric_ops={'accuracy': accuracy}) # Create training op. assert mode == tf.estimator.ModeKeys.TRAIN extra_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) optimizer = tf.train.AdamOptimizer(learning_rate=params['learning_rate']) with tf.control_dependencies(extra_ops): train_op = optimizer.minimize(loss, global_step=tf.train.get_global_step()) return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op) 中时遇到问题。对于<ipython-input-1-070ea24b3267> in dnn_custom_estimator(features, labels, mode, params) 198 199 --> 200 loss = tf.losses.sigmoid_cross_entropy(multi_class_labels=labels, logits=logits) 201 accuracy = tf.metrics.accuracy(labels=tf.argmax(labels, 1), 202 predictions=predicted_classes, ValueError: Shapes (?, 1) and (?,) are incompatible ，点被对称地放置在刻度线上方。使用geom_dotplot，点向左移动。有没有办法在点之间创建空间的同时使点对称放置？

stackratio

Answer 1

问题似乎出在makeContext.dotstackGrob函数中。它使用

来计算每个点的偏移量

xpos <- xmm + dotdiamm * (x$stackposition * x$stackratio + (1 - x$stackratio) / 2)

但是对于我的一生，我无法理解为什么(1 - x$stackratio) / 2部分在那里。没有它，一切似乎都可以。如果我将该行更改为

xpos <- xmm + dotdiamm * x$stackposition * x$stackratio

用示例数据进行测试，我得到

ggplot(data, aes(factor(x), y)) +
  geom_dotplot(binaxis = "y", stackdir = "center", stackratio = 1)

ggplot(data, aes(factor(x), y)) +
  geom_dotplot(binaxis = "y", stackdir = "center", stackratio = .5)

ggplot(data, aes(factor(x), y)) +
  geom_dotplot(binaxis = "y", stackdir = "center", stackratio = 2)

因此，这也许算是一个错误报告？不确定要测试什么