映画レビューのテキスト分類

import matplotlib.pyplot as plt
import os
import re
import shutil
import string
import tensorflow as tf

from tensorflow.keras import layers
from tensorflow.keras import losses

2024-01-11 21:41:17.595673: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-01-11 21:41:17.595719: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-01-11 21:41:17.597304: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered

print(tf.__version__)

2.15.0

url = "https://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz"

dataset = tf.keras.utils.get_file("aclImdb_v1", url,
                                    untar=True, cache_dir='.',
                                    cache_subdir='')

dataset_dir = os.path.join(os.path.dirname(dataset), 'aclImdb')

Downloading data from https://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz
84125825/84125825 [==============================] - 4s 0us/step

os.listdir(dataset_dir)

['train', 'test', 'imdb.vocab', 'imdbEr.txt', 'README']

train_dir = os.path.join(dataset_dir, 'train')
os.listdir(train_dir)

['neg',
 'pos',
 'unsup',
 'urls_pos.txt',
 'labeledBow.feat',
 'unsupBow.feat',
 'urls_neg.txt',
 'urls_unsup.txt']

sample_file = os.path.join(train_dir, 'pos/1181_9.txt')
with open(sample_file) as f:
  print(f.read())

Rachel Griffiths writes and directs this award winning short film. A heartwarming story about coping with grief and cherishing the memory of those we've loved and lost. Although, only 15 minutes long, Griffiths manages to capture so much emotion and truth onto film in the short space of time. Bud Tingwell gives a touching performance as Will, a widower struggling to cope with his wife's death. Will is confronted by the harsh reality of loneliness and helplessness as he proceeds to take care of Ruth's pet cow, Tulip. The film displays the grief and responsibility one feels for those they have loved and lost. Good cinematography, great direction, and superbly acted. It will bring tears to all those who have lost a loved one, and survived.

main_directory/
...class_a/
......a_text_1.txt
......a_text_2.txt
...class_b/
......b_text_1.txt
......b_text_2.txt

remove_dir = os.path.join(train_dir, 'unsup')
shutil.rmtree(remove_dir)

batch_size = 32
seed = 42

raw_train_ds = tf.keras.utils.text_dataset_from_directory(
    'aclImdb/train', 
    batch_size=batch_size, 
    validation_split=0.2, 
    subset='training', 
    seed=seed)

Found 25000 files belonging to 2 classes.
Using 20000 files for training.

for text_batch, label_batch in raw_train_ds.take(1):
  for i in range(3):
    print("Review", text_batch.numpy()[i])
    print("Label", label_batch.numpy()[i])

Review b'"Pandemonium" is a horror movie spoof that comes off more stupid than funny. Believe me when I tell you, I love comedies. Especially comedy spoofs. "Airplane", "The Naked Gun" trilogy, "Blazing Saddles", "High Anxiety", and "Spaceballs" are some of my favorite comedies that spoof a particular genre. "Pandemonium" is not up there with those films. Most of the scenes in this movie had me sitting there in stunned silence because the movie wasn\'t all that funny. There are a few laughs in the film, but when you watch a comedy, you expect to laugh a lot more than a few times and that\'s all this film has going for it. Geez, "Scream" had more laughs than this film and that was more of a horror film. How bizarre is that?<br /><br />*1/2 (out of four)'
Label 0
Review b"David Mamet is a very interesting and a very un-equal director. His first movie 'House of Games' was the one I liked best, and it set a series of films with characters whose perspective of life changes as they get into complicated situations, and so does the perspective of the viewer.<br /><br />So is 'Homicide' which from the title tries to set the mind of the viewer to the usual crime drama. The principal characters are two cops, one Jewish and one Irish who deal with a racially charged area. The murder of an old Jewish shop owner who proves to be an ancient veteran of the Israeli Independence war triggers the Jewish identity in the mind and heart of the Jewish detective.<br /><br />This is were the flaws of the film are the more obvious. The process of awakening is theatrical and hard to believe, the group of Jewish militants is operatic, and the way the detective eventually walks to the final violent confrontation is pathetic. The end of the film itself is Mamet-like smart, but disappoints from a human emotional perspective.<br /><br />Joe Mantegna and William Macy give strong performances, but the flaws of the story are too evident to be easily compensated."
Label 0
Review b'Great documentary about the lives of NY firefighters during the worst terrorist attack of all time.. That reason alone is why this should be a must see collectors item.. What shocked me was not only the attacks, but the"High Fat Diet" and physical appearance of some of these firefighters. I think a lot of Doctors would agree with me that,in the physical shape they were in, some of these firefighters would NOT of made it to the 79th floor carrying over 60 lbs of gear. Having said that i now have a greater respect for firefighters and i realize becoming a firefighter is a life altering job. The French have a history of making great documentary\'s and that is what this is, a Great Documentary.....'
Label 1

print("Label 0 corresponds to", raw_train_ds.class_names[0])
print("Label 1 corresponds to", raw_train_ds.class_names[1])

Label 0 corresponds to neg
Label 1 corresponds to pos

raw_val_ds = tf.keras.utils.text_dataset_from_directory(
    'aclImdb/train', 
    batch_size=batch_size, 
    validation_split=0.2, 
    subset='validation', 
    seed=seed)

Found 25000 files belonging to 2 classes.
Using 5000 files for validation.

raw_test_ds = tf.keras.utils.text_dataset_from_directory(
    'aclImdb/test', 
    batch_size=batch_size)

Found 25000 files belonging to 2 classes.

def custom_standardization(input_data):
  lowercase = tf.strings.lower(input_data)
  stripped_html = tf.strings.regex_replace(lowercase, '<br />', ' ')
  return tf.strings.regex_replace(stripped_html,
                                  '[%s]' % re.escape(string.punctuation),
                                  '')

max_features = 10000
sequence_length = 250

vectorize_layer = layers.TextVectorization(
    standardize=custom_standardization,
    max_tokens=max_features,
    output_mode='int',
    output_sequence_length=sequence_length)

# Make a text-only dataset (without labels), then call adapt
train_text = raw_train_ds.map(lambda x, y: x)
vectorize_layer.adapt(train_text)

def vectorize_text(text, label):
  text = tf.expand_dims(text, -1)
  return vectorize_layer(text), label

# retrieve a batch (of 32 reviews and labels) from the dataset
text_batch, label_batch = next(iter(raw_train_ds))
first_review, first_label = text_batch[0], label_batch[0]
print("Review", first_review)
print("Label", raw_train_ds.class_names[first_label])
print("Vectorized review", vectorize_text(first_review, first_label))

Review tf.Tensor(b'Great movie - especially the music - Etta James - "At Last". This speaks volumes when you have finally found that special someone.', shape=(), dtype=string)
Label neg
Vectorized review (<tf.Tensor: shape=(1, 250), dtype=int64, numpy=
array([[  86,   17,  260,    2,  222,    1,  571,   31,  229,   11, 2418,
           1,   51,   22,   25,  404,  251,   12,  306,  282,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
           0,    0,    0,    0,    0,    0,    0,    0]])>, <tf.Tensor: shape=(), dtype=int32, numpy=0>)

print("1287 ---> ",vectorize_layer.get_vocabulary()[1287])
print(" 313 ---> ",vectorize_layer.get_vocabulary()[313])
print('Vocabulary size: {}'.format(len(vectorize_layer.get_vocabulary())))

1287 --->  silent
 313 --->  night
Vocabulary size: 10000

train_ds = raw_train_ds.map(vectorize_text)
val_ds = raw_val_ds.map(vectorize_text)
test_ds = raw_test_ds.map(vectorize_text)

AUTOTUNE = tf.data.AUTOTUNE

train_ds = train_ds.cache().prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
test_ds = test_ds.cache().prefetch(buffer_size=AUTOTUNE)

embedding_dim = 16

model = tf.keras.Sequential([
  layers.Embedding(max_features + 1, embedding_dim),
  layers.Dropout(0.2),
  layers.GlobalAveragePooling1D(),
  layers.Dropout(0.2),
  layers.Dense(1)])

model.summary()

Model: "sequential"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 embedding (Embedding)       (None, None, 16)          160016    
                                                                 
 dropout (Dropout)           (None, None, 16)          0         
                                                                 
 global_average_pooling1d (  (None, 16)                0         
 GlobalAveragePooling1D)                                         
                                                                 
 dropout_1 (Dropout)         (None, 16)                0         
                                                                 
 dense (Dense)               (None, 1)                 17        
                                                                 
=================================================================
Total params: 160033 (625.13 KB)
Trainable params: 160033 (625.13 KB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

model.compile(loss=losses.BinaryCrossentropy(from_logits=True),
              optimizer='adam',
              metrics=tf.metrics.BinaryAccuracy(threshold=0.0))

epochs = 10
history = model.fit(
    train_ds,
    validation_data=val_ds,
    epochs=epochs)

Epoch 1/10
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1705009314.868632  943769 device_compiler.h:186] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.
625/625 [==============================] - 45s 68ms/step - loss: 0.6607 - binary_accuracy: 0.7017 - val_loss: 0.6116 - val_binary_accuracy: 0.7732
Epoch 2/10
625/625 [==============================] - 2s 3ms/step - loss: 0.5469 - binary_accuracy: 0.8013 - val_loss: 0.4977 - val_binary_accuracy: 0.8236
Epoch 3/10
625/625 [==============================] - 2s 3ms/step - loss: 0.4439 - binary_accuracy: 0.8446 - val_loss: 0.4197 - val_binary_accuracy: 0.8464
Epoch 4/10
625/625 [==============================] - 2s 3ms/step - loss: 0.3783 - binary_accuracy: 0.8665 - val_loss: 0.3731 - val_binary_accuracy: 0.8622
Epoch 5/10
625/625 [==============================] - 2s 3ms/step - loss: 0.3352 - binary_accuracy: 0.8788 - val_loss: 0.3443 - val_binary_accuracy: 0.8686
Epoch 6/10
625/625 [==============================] - 2s 3ms/step - loss: 0.3045 - binary_accuracy: 0.8884 - val_loss: 0.3255 - val_binary_accuracy: 0.8710
Epoch 7/10
625/625 [==============================] - 2s 3ms/step - loss: 0.2804 - binary_accuracy: 0.8972 - val_loss: 0.3119 - val_binary_accuracy: 0.8748
Epoch 8/10
625/625 [==============================] - 2s 3ms/step - loss: 0.2612 - binary_accuracy: 0.9036 - val_loss: 0.3025 - val_binary_accuracy: 0.8776
Epoch 9/10
625/625 [==============================] - 2s 3ms/step - loss: 0.2440 - binary_accuracy: 0.9125 - val_loss: 0.2958 - val_binary_accuracy: 0.8790
Epoch 10/10
625/625 [==============================] - 2s 3ms/step - loss: 0.2297 - binary_accuracy: 0.9165 - val_loss: 0.2910 - val_binary_accuracy: 0.8802

loss, accuracy = model.evaluate(test_ds)

print("Loss: ", loss)
print("Accuracy: ", accuracy)

782/782 [==============================] - 2s 2ms/step - loss: 0.3099 - binary_accuracy: 0.8734
Loss:  0.30990463495254517
Accuracy:  0.8733999729156494

history_dict = history.history
history_dict.keys()

dict_keys(['loss', 'binary_accuracy', 'val_loss', 'val_binary_accuracy'])

acc = history_dict['binary_accuracy']
val_acc = history_dict['val_binary_accuracy']
loss = history_dict['loss']
val_loss = history_dict['val_loss']

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

# "bo" is for "blue dot"
plt.plot(epochs, loss, 'bo', label='Training loss')
# b is for "solid blue line"
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()

plt.show()

plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend(loc='lower right')

plt.show()

export_model = tf.keras.Sequential([
  vectorize_layer,
  model,
  layers.Activation('sigmoid')
])

export_model.compile(
    loss=losses.BinaryCrossentropy(from_logits=False), optimizer="adam", metrics=['accuracy']
)

# Test it with `raw_test_ds`, which yields raw strings
loss, accuracy = export_model.evaluate(raw_test_ds)
print(accuracy)

782/782 [==============================] - 3s 4ms/step - loss: 0.3099 - accuracy: 0.8734
0.8733999729156494

examples = [
  "The movie was great!",
  "The movie was okay.",
  "The movie was terrible..."
]

export_model.predict(examples)

1/1 [==============================] - 0s 175ms/step
array([[0.61918825],
       [0.44328377],
       [0.3598296 ]], dtype=float32)

train/
...python/
......0.txt
......1.txt
...javascript/
......0.txt
......1.txt
...csharp/
......0.txt
......1.txt
...java/
......0.txt
......1.txt

# MIT License
#
# Copyright (c) 2017 François Chollet
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.