Classifying newswires: a multiclass classification example
"""
@Date: 2018/10/6
@Author: dreamhomes
@Summary:
"""
from keras.datasets import reuters
from keras.utils.np_utils import to_categorical
from keras import models
from keras import layers
import numpy as np
import matplotlib.pyplot as plt
(train_data, train_labels), (test_data,
test_labels) = reuters.load_data(num_words=10000)
word_index = reuters.get_word_index()
reverse_word_index = dict([(value, key)
for (key, value) in word_index.items()])
def vectorize_sequences(sequences, dimension=10000):
"""
one hot encoding - Turn lists to vectors/tensors
:param sequences:
:param dimension:
:return:
"""
results = np.zeros((len(sequences), dimension))
for i, sequence in enumerate(sequences):
results[i, sequence] = 1.
return results
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
one_hot_train_labels = to_categorical(train_labels)
one_hot_test_labels = to_categorical(test_labels)
model = models.Sequential()
model.add(layers.Dense(64, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(46, activation='softmax'))
model.compile(
optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
x_val = x_train[:1000]
partial_x_train = x_train[1000:]
y_val = one_hot_train_labels[:1000]
partial_y_train = one_hot_train_labels[1000:]
history = model.fit(
partial_x_train,
partial_y_train,
epochs=20,
batch_size=512,
validation_data=(
x_val,
y_val))
history_dict = history.history
loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']
acc_values = history_dict['acc']
val_acc_values = history_dict['val_acc']
epochs = range(1, len(history_dict['acc']) + 1)
plt.figure()
plt.plot(epochs, loss_values, 'bo', label='Training loss')
plt.plot(epochs, val_loss_values, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.figure()
plt.plot(epochs, acc_values, 'bo', label='Training acc')
plt.plot(epochs, val_acc_values, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()
result = model.evaluate(x_test, one_hot_test_labels)
print(model.metrics_names)
print(result)