Train LSTM model

Source: R/train_lstm.R

Train LSTM model using keras on the given dataset

Arguments

data

the sentiment140 train dataset with text for text of the tweet and polarity for polarity.
max_words

Maximum number of words to consider using word frequency measure.
maxlen

Maximum length of a sequence.
embedding_dim

Output dimension of the embedding layer.
epochs

Number of epochs to run the training for.
batch_size

Batch Size for model fitting.
validation_split

Split ratio for validation
lstm_units

Number of units i.e. output dimension of lstm layer.
seed

Seed for shuffling training data.
model_save_path

File path location for saving model.

Value

plot of the training operation showing train vs validation loss and accuracy.

Examples

# NOT RUN {
  data(sentiment140_train)
  train_lstm(model_save_path = "./train_no_glove_lstm.h5")
# }