Utilized by https://austingwalters.com/fasttext-for-sentence-classification/

fasttest_data_formatting.py

max_words, batch_size, maxlen, epochs, ngram_range = 10000, 32, 500, 5, 2

# Determine the number of categories + default(i.e. sentence types)
num_classes = np.max(y_train) + 1

# Vectorize the output sentence type classifcations to Keras readable format
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

if ngram_range > 1:

    # Create set of unique n-gram from the training set    
    ngram_set = set()
    for input_list in x_train:
        for i in range(2, ngram_range + 1):
            set_of_ngram = create_ngram_set(input_list, ngram_value=i)
            ngram_set.update(set_of_ngram)

    # Dictionary mapping n-gram token to a unique integer
    # Integer values are greater than max_words in order
    # to avoid collision with existing features
    start_index = max_words + 1
    token_indice = {v: k + start_index for k, v in enumerate(ngram_set)}
    indice_token = {token_indice[k]: k for k in token_indice}

    # max_words is the highest integer that could be found in the dataset
    max_words = np.max(list(indice_token.keys())) + 1

    # Augmenting x_train and x_test with n-grams features
    x_train = add_ngram(x_train, token_indice, ngram_range)
    x_test = add_ngram(x_test, token_indice, ngram_range)

# Pad the input vectors to ensure a consistent length
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)