합성 그래프를 사용한, 감상 분류를 위한 그래프 정규화

pip install --quiet neural-structured-learning
pip install --quiet tensorflow-hub

import matplotlib.pyplot as plt
import numpy as np

import neural_structured_learning as nsl

import tensorflow as tf
import tensorflow_hub as hub

# Resets notebook state
tf.keras.backend.clear_session()

print("Version: ", tf.__version__)
print("Eager mode: ", tf.executing_eagerly())
print("Hub version: ", hub.__version__)
print(
    "GPU is",
    "available" if tf.config.list_physical_devices("GPU") else "NOT AVAILABLE")

Version:  2.6.0
Eager mode:  True
Hub version:  0.12.0
GPU is available

imdb = tf.keras.datasets.imdb
(pp_train_data, pp_train_labels), (pp_test_data, pp_test_labels) = (
    imdb.load_data(num_words=10000))

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb.npz
17465344/17464789 [==============================] - 0s 0us/step
17473536/17464789 [==============================] - 0s 0us/step

print('Training entries: {}, labels: {}'.format(
    len(pp_train_data), len(pp_train_labels)))
training_samples_count = len(pp_train_data)

Training entries: 25000, labels: 25000

print(pp_train_data[0])

[1, 14, 22, 16, 43, 530, 973, 1622, 1385, 65, 458, 4468, 66, 3941, 4, 173, 36, 256, 5, 25, 100, 43, 838, 112, 50, 670, 2, 9, 35, 480, 284, 5, 150, 4, 172, 112, 167, 2, 336, 385, 39, 4, 172, 4536, 1111, 17, 546, 38, 13, 447, 4, 192, 50, 16, 6, 147, 2025, 19, 14, 22, 4, 1920, 4613, 469, 4, 22, 71, 87, 12, 16, 43, 530, 38, 76, 15, 13, 1247, 4, 22, 17, 515, 17, 12, 16, 626, 18, 2, 5, 62, 386, 12, 8, 316, 8, 106, 5, 4, 2223, 5244, 16, 480, 66, 3785, 33, 4, 130, 12, 16, 38, 619, 5, 25, 124, 51, 36, 135, 48, 25, 1415, 33, 6, 22, 12, 215, 28, 77, 52, 5, 14, 407, 16, 82, 2, 8, 4, 107, 117, 5952, 15, 256, 4, 2, 7, 3766, 5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 2, 1029, 13, 104, 88, 4, 381, 15, 297, 98, 32, 2071, 56, 26, 141, 6, 194, 7486, 18, 4, 226, 22, 21, 134, 476, 26, 480, 5, 144, 30, 5535, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65, 16, 38, 1334, 88, 12, 16, 283, 5, 16, 4472, 113, 103, 32, 15, 16, 5345, 19, 178, 32]

len(pp_train_data[0]), len(pp_train_data[1])

(218, 189)

def build_reverse_word_index():
  # A dictionary mapping words to an integer index
  word_index = imdb.get_word_index()

  # The first indices are reserved
  word_index = {k: (v + 3) for k, v in word_index.items()}
  word_index['<PAD>'] = 0
  word_index['<START>'] = 1
  word_index['<UNK>'] = 2  # unknown
  word_index['<UNUSED>'] = 3
  return dict((value, key) for (key, value) in word_index.items())

reverse_word_index = build_reverse_word_index()

def decode_review(text):
  return ' '.join([reverse_word_index.get(i, '?') for i in text])

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb_word_index.json
1646592/1641221 [==============================] - 0s 0us/step
1654784/1641221 [==============================] - 0s 0us/step

decode_review(pp_train_data[0])

"<START> this film was just brilliant casting location scenery story direction everyone's really suited the part they played and you could just imagine being there robert <UNK> is an amazing actor and now the same being director <UNK> father came from the same scottish island as myself so i loved the fact there was a real connection with this film the witty remarks throughout the film were great it was just brilliant so much that i bought the film as soon as it was released for <UNK> and would recommend it to everyone to watch and the fly fishing was amazing really cried at the end it was so sad and you know what they say if you cry at a film it must have been good and this definitely was also <UNK> to the two little boy's that played the <UNK> of norman and paul they were just brilliant children are often left out of the <UNK> list i think because the stars that play them all grown up are such a big profile for the whole film but these children are amazing and should be praised for what they have done don't you think the whole story was so lovely because it was true and was someone's life after all that was shared with us all"

mkdir -p /tmp/imdb

pretrained_embedding = 'https://tfhub.dev/google/tf2-preview/gnews-swivel-20dim/1'

hub_layer = hub.KerasLayer(
    pretrained_embedding, input_shape=[], dtype=tf.string, trainable=True)

def _int64_feature(value):
  """Returns int64 tf.train.Feature."""
  return tf.train.Feature(int64_list=tf.train.Int64List(value=value.tolist()))


def _bytes_feature(value):
  """Returns bytes tf.train.Feature."""
  return tf.train.Feature(
      bytes_list=tf.train.BytesList(value=[value.encode('utf-8')]))


def _float_feature(value):
  """Returns float tf.train.Feature."""
  return tf.train.Feature(float_list=tf.train.FloatList(value=value.tolist()))


def create_embedding_example(word_vector, record_id):
  """Create tf.Example containing the sample's embedding and its ID."""

  text = decode_review(word_vector)

  # Shape = [batch_size,].
  sentence_embedding = hub_layer(tf.reshape(text, shape=[-1,]))

  # Flatten the sentence embedding back to 1-D.
  sentence_embedding = tf.reshape(sentence_embedding, shape=[-1])

  features = {
      'id': _bytes_feature(str(record_id)),
      'embedding': _float_feature(sentence_embedding.numpy())
  }
  return tf.train.Example(features=tf.train.Features(feature=features))


def create_embeddings(word_vectors, output_path, starting_record_id):
  record_id = int(starting_record_id)
  with tf.io.TFRecordWriter(output_path) as writer:
    for word_vector in word_vectors:
      example = create_embedding_example(word_vector, record_id)
      record_id = record_id + 1
      writer.write(example.SerializeToString())
  return record_id


# Persist TF.Example features containing embeddings for training data in
# TFRecord format.
create_embeddings(pp_train_data, '/tmp/imdb/embeddings.tfr', 0)

25000

graph_builder_config = nsl.configs.GraphBuilderConfig(
    similarity_threshold=0.99, lsh_splits=32, lsh_rounds=15, random_seed=12345)
nsl.tools.build_graph_from_config(['/tmp/imdb/embeddings.tfr'],
                                  '/tmp/imdb/graph_99.tsv',
                                  graph_builder_config)

wc -l /tmp/imdb/graph_99.tsv

858828 /tmp/imdb/graph_99.tsv

def create_example(word_vector, label, record_id):
  """Create tf.Example containing the sample's word vector, label, and ID."""
  features = {
      'id': _bytes_feature(str(record_id)),
      'words': _int64_feature(np.asarray(word_vector)),
      'label': _int64_feature(np.asarray([label])),
  }
  return tf.train.Example(features=tf.train.Features(feature=features))

def create_records(word_vectors, labels, record_path, starting_record_id):
  record_id = int(starting_record_id)
  with tf.io.TFRecordWriter(record_path) as writer:
    for word_vector, label in zip(word_vectors, labels):
      example = create_example(word_vector, label, record_id)
      record_id = record_id + 1
      writer.write(example.SerializeToString())
  return record_id

# Persist TF.Example features (word vectors and labels) for training and test
# data in TFRecord format.
next_record_id = create_records(pp_train_data, pp_train_labels,
                                '/tmp/imdb/train_data.tfr', 0)
create_records(pp_test_data, pp_test_labels, '/tmp/imdb/test_data.tfr',
               next_record_id)

50000

nsl.tools.pack_nbrs(
    '/tmp/imdb/train_data.tfr',
    '',
    '/tmp/imdb/graph_99.tsv',
    '/tmp/imdb/nsl_train_data.tfr',
    add_undirected_edges=True,
    max_nbrs=3)

NBR_FEATURE_PREFIX = 'NL_nbr_'
NBR_WEIGHT_SUFFIX = '_weight'

class HParams(object):
  """Hyperparameters used for training."""
  def __init__(self):
    ### dataset parameters
    self.num_classes = 2
    self.max_seq_length = 256
    self.vocab_size = 10000
    ### neural graph learning parameters
    self.distance_type = nsl.configs.DistanceType.L2
    self.graph_regularization_multiplier = 0.1
    self.num_neighbors = 2
    ### model architecture
    self.num_embedding_dims = 16
    self.num_lstm_dims = 64
    self.num_fc_units = 64
    ### training parameters
    self.train_epochs = 10
    self.batch_size = 128
    ### eval parameters
    self.eval_steps = None  # All instances in the test set are evaluated.

HPARAMS = HParams()

def make_dataset(file_path, training=False):
  """Creates a `tf.data.TFRecordDataset`.

  Args:
    file_path: Name of the file in the `.tfrecord` format containing
      `tf.train.Example` objects.
    training: Boolean indicating if we are in training mode.

  Returns:
    An instance of `tf.data.TFRecordDataset` containing the `tf.train.Example`
    objects.
  """

  def pad_sequence(sequence, max_seq_length):
    """Pads the input sequence (a `tf.SparseTensor`) to `max_seq_length`."""
    pad_size = tf.maximum([0], max_seq_length - tf.shape(sequence)[0])
    padded = tf.concat(
        [sequence.values,
         tf.fill((pad_size), tf.cast(0, sequence.dtype))],
        axis=0)
    # The input sequence may be larger than max_seq_length. Truncate down if
    # necessary.
    return tf.slice(padded, [0], [max_seq_length])

  def parse_example(example_proto):
    """Extracts relevant fields from the `example_proto`.

    Args:
      example_proto: An instance of `tf.train.Example`.

    Returns:
      A pair whose first value is a dictionary containing relevant features
      and whose second value contains the ground truth labels.
    """
    # The 'words' feature is a variable length word ID vector.
    feature_spec = {
        'words': tf.io.VarLenFeature(tf.int64),
        'label': tf.io.FixedLenFeature((), tf.int64, default_value=-1),
    }
    # We also extract corresponding neighbor features in a similar manner to
    # the features above during training.
    if training:
      for i in range(HPARAMS.num_neighbors):
        nbr_feature_key = '{}{}_{}'.format(NBR_FEATURE_PREFIX, i, 'words')
        nbr_weight_key = '{}{}{}'.format(NBR_FEATURE_PREFIX, i,
                                         NBR_WEIGHT_SUFFIX)
        feature_spec[nbr_feature_key] = tf.io.VarLenFeature(tf.int64)

        # We assign a default value of 0.0 for the neighbor weight so that
        # graph regularization is done on samples based on their exact number
        # of neighbors. In other words, non-existent neighbors are discounted.
        feature_spec[nbr_weight_key] = tf.io.FixedLenFeature(
            [1], tf.float32, default_value=tf.constant([0.0]))

    features = tf.io.parse_single_example(example_proto, feature_spec)

    # Since the 'words' feature is a variable length word vector, we pad it to a
    # constant maximum length based on HPARAMS.max_seq_length
    features['words'] = pad_sequence(features['words'], HPARAMS.max_seq_length)
    if training:
      for i in range(HPARAMS.num_neighbors):
        nbr_feature_key = '{}{}_{}'.format(NBR_FEATURE_PREFIX, i, 'words')
        features[nbr_feature_key] = pad_sequence(features[nbr_feature_key],
                                                 HPARAMS.max_seq_length)

    labels = features.pop('label')
    return features, labels

  dataset = tf.data.TFRecordDataset([file_path])
  if training:
    dataset = dataset.shuffle(10000)
  dataset = dataset.map(parse_example)
  dataset = dataset.batch(HPARAMS.batch_size)
  return dataset


train_dataset = make_dataset('/tmp/imdb/nsl_train_data.tfr', True)
test_dataset = make_dataset('/tmp/imdb/test_data.tfr')

# This function exists as an alternative to the bi-LSTM model used in this
# notebook.
def make_feed_forward_model():
  """Builds a simple 2 layer feed forward neural network."""
  inputs = tf.keras.Input(
      shape=(HPARAMS.max_seq_length,), dtype='int64', name='words')
  embedding_layer = tf.keras.layers.Embedding(HPARAMS.vocab_size, 16)(inputs)
  pooling_layer = tf.keras.layers.GlobalAveragePooling1D()(embedding_layer)
  dense_layer = tf.keras.layers.Dense(16, activation='relu')(pooling_layer)
  outputs = tf.keras.layers.Dense(1, activation='sigmoid')(dense_layer)
  return tf.keras.Model(inputs=inputs, outputs=outputs)


def make_bilstm_model():
  """Builds a bi-directional LSTM model."""
  inputs = tf.keras.Input(
      shape=(HPARAMS.max_seq_length,), dtype='int64', name='words')
  embedding_layer = tf.keras.layers.Embedding(HPARAMS.vocab_size,
                                              HPARAMS.num_embedding_dims)(
                                                  inputs)
  lstm_layer = tf.keras.layers.Bidirectional(
      tf.keras.layers.LSTM(HPARAMS.num_lstm_dims))(
          embedding_layer)
  dense_layer = tf.keras.layers.Dense(
      HPARAMS.num_fc_units, activation='relu')(
          lstm_layer)
  outputs = tf.keras.layers.Dense(1, activation='sigmoid')(dense_layer)
  return tf.keras.Model(inputs=inputs, outputs=outputs)


# Feel free to use an architecture of your choice.
model = make_bilstm_model()
model.summary()

Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
words (InputLayer)           [(None, 256)]             0         
_________________________________________________________________
embedding (Embedding)        (None, 256, 16)           160000    
_________________________________________________________________
bidirectional (Bidirectional (None, 128)               41472     
_________________________________________________________________
dense (Dense)                (None, 64)                8256      
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 65        
=================================================================
Total params: 209,793
Trainable params: 209,793
Non-trainable params: 0
_________________________________________________________________

model.compile(
    optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

validation_fraction = 0.9
validation_size = int(validation_fraction *
                      int(training_samples_count / HPARAMS.batch_size))
print(validation_size)
validation_dataset = train_dataset.take(validation_size)
train_dataset = train_dataset.skip(validation_size)

175

history = model.fit(
    train_dataset,
    validation_data=validation_dataset,
    epochs=HPARAMS.train_epochs,
    verbose=1)

Epoch 1/10
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/keras/engine/functional.py:585: UserWarning: Input dict contained keys ['NL_nbr_0_words', 'NL_nbr_1_words', 'NL_nbr_0_weight', 'NL_nbr_1_weight'] which did not match any model input. They will be ignored by the model.
  [n for n in tensors.keys() if n not in ref_input_names])
21/21 [==============================] - 8s 140ms/step - loss: 0.6930 - accuracy: 0.5069 - val_loss: 0.6928 - val_accuracy: 0.5019
Epoch 2/10
21/21 [==============================] - 3s 111ms/step - loss: 0.6923 - accuracy: 0.5119 - val_loss: 0.6917 - val_accuracy: 0.5317
Epoch 3/10
21/21 [==============================] - 3s 111ms/step - loss: 0.6827 - accuracy: 0.5892 - val_loss: 0.6899 - val_accuracy: 0.5424
Epoch 4/10
21/21 [==============================] - 3s 111ms/step - loss: 0.6589 - accuracy: 0.6550 - val_loss: 0.6445 - val_accuracy: 0.6614
Epoch 5/10
21/21 [==============================] - 3s 112ms/step - loss: 0.6446 - accuracy: 0.6654 - val_loss: 0.6356 - val_accuracy: 0.6889
Epoch 6/10
21/21 [==============================] - 3s 110ms/step - loss: 0.6146 - accuracy: 0.7035 - val_loss: 0.5842 - val_accuracy: 0.7102
Epoch 7/10
21/21 [==============================] - 3s 111ms/step - loss: 0.4995 - accuracy: 0.7665 - val_loss: 0.4513 - val_accuracy: 0.7982
Epoch 8/10
21/21 [==============================] - 3s 110ms/step - loss: 0.4300 - accuracy: 0.8150 - val_loss: 0.4427 - val_accuracy: 0.7969
Epoch 9/10
21/21 [==============================] - 3s 113ms/step - loss: 0.3854 - accuracy: 0.8342 - val_loss: 0.3523 - val_accuracy: 0.8530
Epoch 10/10
21/21 [==============================] - 3s 112ms/step - loss: 0.3240 - accuracy: 0.8754 - val_loss: 0.3240 - val_accuracy: 0.8708

results = model.evaluate(test_dataset, steps=HPARAMS.eval_steps)
print(results)

196/196 [==============================] - 3s 10ms/step - loss: 0.3884 - accuracy: 0.8370
[0.38840407133102417, 0.8370400071144104]

history_dict = history.history
history_dict.keys()

dict_keys(['loss', 'accuracy', 'val_loss', 'val_accuracy'])

acc = history_dict['accuracy']
val_acc = history_dict['val_accuracy']
loss = history_dict['loss']
val_loss = history_dict['val_loss']

epochs = range(1, len(acc) + 1)

# "-r^" is for solid red line with triangle markers.
plt.plot(epochs, loss, '-r^', label='Training loss')
# "-b0" is for solid blue line with circle markers.
plt.plot(epochs, val_loss, '-bo', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend(loc='best')

plt.show()

plt.clf()   # clear figure

plt.plot(epochs, acc, '-r^', label='Training acc')
plt.plot(epochs, val_acc, '-bo', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend(loc='best')

plt.show()

# Build a new base LSTM model.
base_reg_model = make_bilstm_model()

# Wrap the base model with graph regularization.
graph_reg_config = nsl.configs.make_graph_reg_config(
    max_neighbors=HPARAMS.num_neighbors,
    multiplier=HPARAMS.graph_regularization_multiplier,
    distance_type=HPARAMS.distance_type,
    sum_over_axis=-1)
graph_reg_model = nsl.keras.GraphRegularization(base_reg_model,
                                                graph_reg_config)
graph_reg_model.compile(
    optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

graph_reg_history = graph_reg_model.fit(
    train_dataset,
    validation_data=validation_dataset,
    epochs=HPARAMS.train_epochs,
    verbose=1)

Epoch 1/10
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/indexed_slices.py:449: UserWarning: Converting sparse IndexedSlices(IndexedSlices(indices=Tensor("gradient_tape/GraphRegularization/graph_loss/Reshape_1:0", shape=(None,), dtype=int32), values=Tensor("gradient_tape/GraphRegularization/graph_loss/Reshape:0", shape=(None, 1), dtype=float32), dense_shape=Tensor("gradient_tape/GraphRegularization/graph_loss/Cast:0", shape=(2,), dtype=int32))) to a dense Tensor of unknown shape. This may consume a large amount of memory.
  "shape. This may consume a large amount of memory." % value)
21/21 [==============================] - 10s 189ms/step - loss: 0.6931 - accuracy: 0.4988 - scaled_graph_loss: 1.1141e-06 - val_loss: 0.6926 - val_accuracy: 0.5004
Epoch 2/10
21/21 [==============================] - 3s 139ms/step - loss: 0.6899 - accuracy: 0.5327 - scaled_graph_loss: 2.0430e-05 - val_loss: 0.6844 - val_accuracy: 0.5194
Epoch 3/10
21/21 [==============================] - 3s 143ms/step - loss: 0.6527 - accuracy: 0.6362 - scaled_graph_loss: 9.6421e-04 - val_loss: 0.5461 - val_accuracy: 0.7525
Epoch 4/10
21/21 [==============================] - 3s 142ms/step - loss: 0.5031 - accuracy: 0.7715 - scaled_graph_loss: 0.0074 - val_loss: 0.4108 - val_accuracy: 0.8168
Epoch 5/10
21/21 [==============================] - 3s 143ms/step - loss: 0.3905 - accuracy: 0.8354 - scaled_graph_loss: 0.0158 - val_loss: 0.3452 - val_accuracy: 0.8580
Epoch 6/10
21/21 [==============================] - 3s 144ms/step - loss: 0.3623 - accuracy: 0.8596 - scaled_graph_loss: 0.0186 - val_loss: 0.3074 - val_accuracy: 0.8781
Epoch 7/10
21/21 [==============================] - 3s 144ms/step - loss: 0.3246 - accuracy: 0.8781 - scaled_graph_loss: 0.0201 - val_loss: 0.2957 - val_accuracy: 0.8838
Epoch 8/10
21/21 [==============================] - 3s 143ms/step - loss: 0.2915 - accuracy: 0.8946 - scaled_graph_loss: 0.0211 - val_loss: 0.2680 - val_accuracy: 0.8964
Epoch 9/10
21/21 [==============================] - 3s 146ms/step - loss: 0.2900 - accuracy: 0.8981 - scaled_graph_loss: 0.0236 - val_loss: 0.2595 - val_accuracy: 0.9022
Epoch 10/10
21/21 [==============================] - 3s 143ms/step - loss: 0.2721 - accuracy: 0.9115 - scaled_graph_loss: 0.0233 - val_loss: 0.2524 - val_accuracy: 0.9023

graph_reg_results = graph_reg_model.evaluate(test_dataset, steps=HPARAMS.eval_steps)
print(graph_reg_results)

196/196 [==============================] - 3s 10ms/step - loss: 0.3602 - accuracy: 0.8478
[0.36020034551620483, 0.8478400111198425]

graph_reg_history_dict = graph_reg_history.history
graph_reg_history_dict.keys()

dict_keys(['loss', 'accuracy', 'scaled_graph_loss', 'val_loss', 'val_accuracy'])

acc = graph_reg_history_dict['accuracy']
val_acc = graph_reg_history_dict['val_accuracy']
loss = graph_reg_history_dict['loss']
graph_loss = graph_reg_history_dict['scaled_graph_loss']
val_loss = graph_reg_history_dict['val_loss']

epochs = range(1, len(acc) + 1)

plt.clf()   # clear figure

# "-r^" is for solid red line with triangle markers.
plt.plot(epochs, loss, '-r^', label='Training loss')
# "-gD" is for solid green line with diamond markers.
plt.plot(epochs, graph_loss, '-gD', label='Training graph loss')
# "-b0" is for solid blue line with circle markers.
plt.plot(epochs, val_loss, '-bo', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend(loc='best')

plt.show()

plt.clf()   # clear figure

plt.plot(epochs, acc, '-r^', label='Training acc')
plt.plot(epochs, val_acc, '-bo', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend(loc='best')

plt.show()

# Accuracy values for both the Bi-LSTM model and the feed forward NN model have
# been precomputed for the following supervision ratios.

supervision_ratios = [0.3, 0.15, 0.05, 0.03, 0.02, 0.01, 0.005]

model_tags = ['Bi-LSTM model', 'Feed Forward NN model']
base_model_accs = [[84, 84, 83, 80, 65, 52, 50], [87, 86, 76, 74, 67, 52, 51]]
graph_reg_model_accs = [[84, 84, 83, 83, 65, 63, 50],
                        [87, 86, 80, 75, 67, 52, 50]]

plt.clf()  # clear figure

fig, axes = plt.subplots(1, 2)
fig.set_size_inches((12, 5))

for ax, model_tag, base_model_acc, graph_reg_model_acc in zip(
    axes, model_tags, base_model_accs, graph_reg_model_accs):

  # "-r^" is for solid red line with triangle markers.
  ax.plot(base_model_acc, '-r^', label='Base model')
  # "-gD" is for solid green line with diamond markers.
  ax.plot(graph_reg_model_acc, '-gD', label='Graph-regularized model')
  ax.set_title(model_tag)
  ax.set_xlabel('Supervision ratio')
  ax.set_ylabel('Accuracy(%)')
  ax.set_ylim((25, 100))
  ax.set_xticks(range(len(supervision_ratios)))
  ax.set_xticklabels(supervision_ratios)
  ax.legend(loc='best')

plt.show()

<Figure size 432x288 with 0 Axes>