Ch-11: Text classification using Long Short-Term Memory Network

# IMDB data
library(keras)
imdb <- dataset_imdb(num_words = 500) 
c(c(train_x, train_y), c(test_x, test_y)) %<-% imdb
train_x <- pad_sequences(train_x, maxlen = 200) 
test_x <- pad_sequences(test_x, maxlen = 200)

# Model architecture
model <- keras_model_sequential() %>%
         layer_embedding(input_dim = 500, output_dim = 32) %>%
         layer_lstm(units = 32) %>%
         layer_dense(units = 1, activation = "sigmoid")
model

# Compile
model %>% compile(optimizer = "rmsprop",  
         loss = "binary_crossentropy",
         metrics = c("acc"))
         
# Fit model
model_one <- model %>% fit(train_x, train_y,
         epochs = 10,
         batch_size = 128,
         validation_split = 0.2)
plot(model_one)

# Evaluate
model %>% evaluate(train_x, train_y)

# Confusion Matrix
pred <- model %>% predict_classes(train_x)
table(Predicted=pred, Actual=imdb$train$y)

# Evaluate
model %>% evaluate(test_x, test_y)

# Confusion Matrix
pred1 <- model %>$ predict_classes(text_x)
table(Predicted=pred1, Actual=imdb$test$y)

# Model architecture
model <- keras_model_sequential() %>%
         layer_embedding(input_dim = 500, output_dim = 32) %>%
         layer_lstm(units = 32) %>%
         layer_dense(units = 1, activation = "sigmoid")

# Compile
model %>% compile(optimizer = "adam",  
         loss = "binary_crossentropy",
         metrics = c("acc"))

# Fit model
model_two <- model %>% fit(train_x, train_y,
         epochs = 10,
         batch_size = 128,
         validation_split = 0.2)
plot(model_two)

# Loss and accuracy
model %>% evaluate(train_x, train_y)

# Confusion Matrix
pred <- model %>%   predict_classes(train_x)
table(Predicted=pred, Actual=imdb$train$y)

# Loss and accuracy
model %>% evaluate(test_x, test_y)

# Confusion Matrix
pred1 <- model %>%   predict_classes(test_x)
table(Predicted=pred1, Actual=imdb$test$y)

# Number of positive and negative reviews in the train data
table(train_y)

# Number of positive and negative review in the test data
table(test_y)

# Model architecture
model <- keras_model_sequential() %>%
         layer_embedding(input_dim = 500, output_dim = 32) %>%
         layer_lstm(units = 32,
                    return_sequences = TRUE) %>%
         layer_lstm(units = 32) %>%
         layer_dense(units = 1, activation = "sigmoid")

# Compiling model
model %>% compile(optimizer = "adam",   
         loss = "binary_crossentropy",
         metrics = c("acc"))

# Fitting model
model_three <- model %>% fit(train_x, train_y,
         epochs = 10,
         batch_size = 128,
         validation_split = 0.2)

# Loss and accuracy plot
plot(model_three)

# Loss and accuracy
model %>% evaluate(train_x, train_y)

# Confusion Matrix
pred <- model %>%   predict_classes(train_x)
table(Predicted=pred, Actual=imdb$train$y) 

# Loss and accuracy
model %>% evaluate(test_x, test_y)

# Confusion Matrix
pred1 <- model %>%   predict_classes(test_x)
table(Predicted=pred1, Actual=imdb$test$y)

# Model architecture
model <- keras_model_sequential() %>%
          layer_embedding(input_dim = 500, output_dim = 32) %>%
          bidirectional(layer_lstm(units = 32)) %>%
          layer_dense(units = 1, activation = "sigmoid")
# Model summary
summary(model)

# Compiling model
model %>% compile(optimizer = "adam",   
          loss = "binary_crossentropy",
          metrics = c("acc"))

# Fitting model
 model_four <- model %>% fit(train_x, train_y,
          epochs = 10,
          batch_size = 128,
          validation_split = 0.2)

# Loss and accuracy plot
plot(model_four)

# Loss and accuracy
model %>% evaluate(train_x, train_y)

# Confusion Matrix
pred <- model %>%   predict_classes(train_x)
table(Predicted=pred, Actual=imdb$train$y)

# Loss and accuracy
model %>% evaluate(test_x, test_y)

#Confusion Matrix
pred1 <- model %>%   predict_classes(test_x)
table(Predicted=pred1, Actual=imdb$test$y)