Create vectors of sentences and next characters

This exercise aims to emphasize more the value of data preparation. You will use texts containing phrases of the character Sheldon from The Big Bang Theory TV show as input and will create vectors of sentence indexes and next characters that are needed before creating a text generation model.

The text is available in the sheldon variable, as well as the vocabulary (characters) on the vocabulary variable and the hyperparameters chars_window and step defined with values 20 and 3. This means that a sequence of 20 characters will be used to predict the next one, and the window will shift 3 characters on every iteration.

Also, the package pandas as pd is loaded in the environment.

Diese Übung ist Teil des Kurses

Recurrent Neural Networks (RNNs) for Language Modeling with Keras

Anleitung zur Übung

Split the text by line break to loop through sentences.
Loop until the end of the sentence minus chars_window.
Append the portion of the sentence that has chars_window characters to the sentences variable and append the next character to the next_chars variable.
Use the obtained vectors to create a pd.DataFrame() and print its first rows.

Interaktive Übung

Vervollständige den Beispielcode, um diese Übung erfolgreich abzuschließen.

# Instantiate the vectors
sentences = []
next_chars = []
# Loop for every sentence
for sentence in sheldon.____:
    # Get 20 previous chars and next char; then shift by step
    for i in range(0, len(sentence) - ____, step):
        sentences.append(sentence[i:i + ____])
        next_chars.append(sentence[____ + chars_window])

# Define a Data Frame with the vectors
df = pd.DataFrame({'sentence': ____, 'next_char': ____})

# Print the initial rows
print(df.head())

Code bearbeiten und ausführen

Diese Übung ist Teil des Kurses

Recurrent Neural Networks (RNNs) for Language Modeling with Keras

Hohe SchwierigkeitSchwierigkeitsgrad

4.8+

Kurs kostenlos starten

In this chapter, you will learn the foundations of Recurrent Neural Networks (RNN). Starting with some prerequisites, continuing to understanding how information flows through the network and finally seeing how to implement such models with Keras in the sentiment classification task.

Exercise 1: Introduction to the course Exercise 2: Comparing the number of parameter of RNN and ANN Exercise 3: Sentiment analysis Exercise 4: Sequence to sequence models Exercise 5: Introduction to language models Exercise 6: Getting used to text data Exercise 7: Preparing text data for model input Exercise 8: Transforming new text Exercise 9: Introduction to RNN inside Keras Exercise 10: Keras models Exercise 11: Keras preprocessing Exercise 12: Your first RNN model

You will learn about the vanishing and exploding gradient problems, often occurring in RNNs, and how to deal with them with the GRU and LSTM cells. Furthermore, you'll create embedding layers for language models and revisit the sentiment classification task.

Exercise 1: Vanishing and exploding gradients Exercise 2: Exploding gradient problem Exercise 3: Vanishing gradient problem Exercise 4: GRU and LSTM cells Exercise 5: GRU cells are better than simpleRNN Exercise 6: Stacking RNN layers Exercise 7: The Embedding layer Exercise 8: Number of parameters comparison Exercise 9: Transfer learning Exercise 10: Embeddings improves performance Exercise 11: Sentiment classification revisited Exercise 12: Better sentiment classification Exercise 13: Using the CNN layer

Next, in this chapter you will learn how to prepare data for the multi-class classification task, as well as the differences between multi-class classification and binary classification (sentiment analysis). Finally, you will learn how to create models and measure their performance with Keras.

Exercise 1: Data pre-processing Exercise 2: Prepare label vectors Exercise 3: Pre-process data Exercise 4: Transfer learning for language models Exercise 5: Transfer learning starting point Exercise 6: Word2Vec Exercise 7: Multi-class classification models Exercise 8: Exploring 20 News Groups dataset Exercise 9: Classifying news articles Exercise 10: Assessing the model's performance Exercise 11: Precision-Recall trade-off Exercise 12: Precision or Recall, that is the question Exercise 13: Performance on multi-class classification

This chapter introduces you to two applications of RNN models: Text Generation and Neural Machine Translation. You will learn how to prepare the text data to the format needed by the models. The Text Generation model is used for replicating a character's way of speech and will have some fun mimicking Sheldon from The Big Bang Theory. Neural Machine Translation is used for example by Google Translate in a much more complex model. In this chapter, you will create a model that translates Portuguese small phrases into English.

Exercise 1: Sequence to Sequence Models Exercise 2: Text generation examples Exercise 3: NMT example Exercise 4: The Text Generating Function Exercise 5: Predict next character Exercise 6: Generate sentence with context Exercise 7: Change the probability scale Exercise 8: Text Generation Models Exercise 9: Create vectors of sentences and next characters

Aktuelle Übung

Exercise 10: Preparing the data for training Exercise 11: Creating the text generation model Exercise 12: Neural Machine Translation Exercise 13: Preparing the input text Exercise 14: Preparing the output text Exercise 15: Translate Portuguese to English Exercise 16: Congratulations!