# -*- coding: utf-8 -*-

"""

Simple example using LSTM recurrent neural network to classify IMDB

sentiment dataset.

References:

    - Long Short Term Memory, Sepp Hochreiter & Jurgen Schmidhuber, Neural

    Computation 9(8): 1735-1780, 1997.

    - Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng,

    and Christopher Potts. (2011). Learning Word Vectors for Sentiment

    Analysis. The 49th Annual Meeting of the Association for Computational

    Linguistics (ACL 2011).

Links:

    - http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf

    - http://ai.stanford.edu/~amaas/data/sentiment/

"""

from __future__ import division, print_function, absolute_import

import tflearn

from tflearn.data_utils import to_categorical, pad_sequences

from tflearn.datasets import imdb

# IMDB Dataset loading

train, test, _ = imdb.load_data(path='imdb.pkl', n_words=10000,

                                valid_portion=0.1)

trainX, trainY = train

testX, testY = test

# Data preprocessing

# Sequence padding

trainX = pad_sequences(trainX, maxlen=100, value=0.)

testX = pad_sequences(testX, maxlen=100, value=0.)

# Converting labels to binary vectors

trainY = to_categorical(trainY)

testY = to_categorical(testY)

# Network building

net = tflearn.input_data([None, 100])

net = tflearn.embedding(net, input_dim=10000, output_dim=128)

net = tflearn.lstm(net, 128, dropout=0.8)

net = tflearn.fully_connected(net, 2, activation='softmax')

net = tflearn.regression(net, optimizer='adam', learning_rate=0.001,

                         loss='categorical_crossentropy')

# Training

model = tflearn.DNN(net, tensorboard_verbose=0)

model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,

batch_size=32)

# -*- coding: utf-8 -*-

"""

Simple example using a Dynamic RNN (LSTM) to classify IMDB sentiment dataset.

Dynamic computation are performed over sequences with variable length.

References:

    - Long Short Term Memory, Sepp Hochreiter & Jurgen Schmidhuber, Neural

    Computation 9(8): 1735-1780, 1997.

    - Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng,

    and Christopher Potts. (2011). Learning Word Vectors for Sentiment

    Analysis. The 49th Annual Meeting of the Association for Computational

    Linguistics (ACL 2011).

Links:

    - http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf

    - http://ai.stanford.edu/~amaas/data/sentiment/

"""

from __future__ import division, print_function, absolute_import

import tflearn

from tflearn.data_utils import to_categorical, pad_sequences

from tflearn.datasets import imdb

# IMDB Dataset loading

train, test, _ = imdb.load_data(path='imdb.pkl', n_words=10000,

                                valid_portion=0.1)

trainX, trainY = train

testX, testY = test

# Data preprocessing

# NOTE: Padding is required for dimension consistency. This will pad sequences

# with 0 at the end, until it reaches the max sequence length. 0 is used as a

# masking value by dynamic RNNs in TFLearn; a sequence length will be

# retrieved by counting non zero elements in a sequence. Then dynamic RNN step

# computation is performed according to that length.

trainX = pad_sequences(trainX, maxlen=100, value=0.)

testX = pad_sequences(testX, maxlen=100, value=0.)

# Converting labels to binary vectors

trainY = to_categorical(trainY)

testY = to_categorical(testY)

# Network building

net = tflearn.input_data([None, 100])

# Masking is not required for embedding, sequence length is computed prior to

# the embedding op and assigned as 'seq_length' attribute to the returned Tensor.

net = tflearn.embedding(net, input_dim=10000, output_dim=128)

net = tflearn.lstm(net, 128, dropout=0.8, dynamic=True)

net = tflearn.fully_connected(net, 2, activation='softmax')

net = tflearn.regression(net, optimizer='adam', learning_rate=0.001,

                         loss='categorical_crossentropy')

# Training

model = tflearn.DNN(net, tensorboard_verbose=0)

model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,

batch_size=32)

# -*- coding: utf-8 -*-

"""

Simple example using LSTM recurrent neural network to classify IMDB

sentiment dataset.

References:

    - Long Short Term Memory, Sepp Hochreiter & Jurgen Schmidhuber, Neural

    Computation 9(8): 1735-1780, 1997.

    - Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng,

    and Christopher Potts. (2011). Learning Word Vectors for Sentiment

    Analysis. The 49th Annual Meeting of the Association for Computational

    Linguistics (ACL 2011).

Links:

    - http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf

    - http://ai.stanford.edu/~amaas/data/sentiment/

"""

from __future__ import division, print_function, absolute_import

import tflearn

from tflearn.data_utils import to_categorical, pad_sequences

from tflearn.datasets import imdb

from tflearn.layers.core import input_data, dropout, fully_connected

from tflearn.layers.embedding_ops import embedding

from tflearn.layers.recurrent import bidirectional_rnn, BasicLSTMCell

from tflearn.layers.estimator import regression

# IMDB Dataset loading

train, test, _ = imdb.load_data(path='imdb.pkl', n_words=10000,

                                valid_portion=0.1)

trainX, trainY = train

testX, testY = test

# Data preprocessing

# Sequence padding

trainX = pad_sequences(trainX, maxlen=200, value=0.)

testX = pad_sequences(testX, maxlen=200, value=0.)

# Converting labels to binary vectors

trainY = to_categorical(trainY)

testY = to_categorical(testY)

# Network building

net = input_data(shape=[None, 200])

net = embedding(net, input_dim=20000, output_dim=128)

net = bidirectional_rnn(net, BasicLSTMCell(128), BasicLSTMCell(128))

net = dropout(net, 0.5)

net = fully_connected(net, 2, activation='softmax')

net = regression(net, optimizer='adam', loss='categorical_crossentropy')

# Training

model = tflearn.DNN(net, clip_gradients=0., tensorboard_verbose=2)

model.fit(trainX, trainY, validation_set=0.1, show_metric=True, batch_size=64)

# -*- coding: utf-8 -*-

"""

Simple example using convolutional neural network to classify IMDB

sentiment dataset.

References:

    - Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng,

    and Christopher Potts. (2011). Learning Word Vectors for Sentiment

    Analysis. The 49th Annual Meeting of the Association for Computational

    Linguistics (ACL 2011).

    - Kim Y. Convolutional Neural Networks for Sentence Classification[C].

    Empirical Methods in Natural Language Processing, 2014.

Links:

    - http://ai.stanford.edu/~amaas/data/sentiment/

    - http://emnlp2014.org/papers/pdf/EMNLP2014181.pdf

"""

from __future__ import division, print_function, absolute_import

import tensorflow as tf

import tflearn

from tflearn.layers.core import input_data, dropout, fully_connected

from tflearn.layers.conv import conv_1d, global_max_pool

from tflearn.layers.merge_ops import merge

from tflearn.layers.estimator import regression

from tflearn.data_utils import to_categorical, pad_sequences

from tflearn.datasets import imdb

# IMDB Dataset loading

train, test, _ = imdb.load_data(path='imdb.pkl', n_words=10000,

                                valid_portion=0.1)

trainX, trainY = train

testX, testY = test

# Data preprocessing

# Sequence padding

trainX = pad_sequences(trainX, maxlen=100, value=0.)

testX = pad_sequences(testX, maxlen=100, value=0.)

# Converting labels to binary vectors

trainY = to_categorical(trainY)

testY = to_categorical(testY)

# Building convolutional network

network = input_data(shape=[None, 100], name='input')

network = tflearn.embedding(network, input_dim=10000, output_dim=128)

branch1 = conv_1d(network, 128, 3, padding='valid', activation='relu', regularizer="L2")

branch2 = conv_1d(network, 128, 4, padding='valid', activation='relu', regularizer="L2")

branch3 = conv_1d(network, 128, 5, padding='valid', activation='relu', regularizer="L2")

network = merge([branch1, branch2, branch3], mode='concat', axis=1)

network = tf.expand_dims(network, 2)

network = global_max_pool(network)

network = dropout(network, 0.5)

network = fully_connected(network, 2, activation='softmax')

network = regression(network, optimizer='adam', learning_rate=0.001,

                     loss='categorical_crossentropy', name='target')

# Training

model = tflearn.DNN(network, tensorboard_verbose=0)

model.fit(trainX, trainY, n_epoch = 5, shuffle=True, validation_set=(testX, testY), show_metric=True, batch_size=32)