Use Tensorflow to detect sarcasm in sentences

sarcasm.py

# Colab -> https://goo.gle/tfw-sarcembed
# GitHub -> https://goo.gle/2PH90ea
import json

with open("sarcasm.json", "r") as f:
    datastore = json.load(f)

sentences = []
labels = []
for item in datastore:
    sentences.append(item["headline"])
    labels.append(item["is_sarcastic"])

import tensorflow as tf
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

vocab_size = 10000
embedding_dim = 16
max_length = 100
trunc_type= "post"
padding_type= "post"
oov_tok = "<OOV>"
training_size = 20000

training_sentences = sentences[0:training_size]
testing_sentences = sentences[training_size:]
training_labels = labels[0:training_size]
testing_labels = labels[training_size:]

tokenizer = Tokenizer(num_words=vocab_size, oov_token=oov_tok)
tokenizer.fit_on_texts(training_sentences)

word_index = tokenizer.word_index

training_sequences = tokenizer.texts_to_sequences(training_sentences)
training_padded = pad_sequences(training_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

testing_sequences = tokenizer.texts_to_sequences(testing_sentences)
testing_padded = pad_sequences(testing_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

# Need this block to get it to work with TensorFlow 2.x
import numpy as np

training_padded = np.array(training_padded)
training_labels = np.array(training_labels)
testing_padded = np.array(testing_padded)
testing_labels = np.array(testing_labels)

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),
    tf.keras.layers.GlobalAveragePooling1D(),
    tf.keras.layers.Dense(24, activation="relu"),
    tf.keras.layers.Dense(1, activation="sigmoid")
])
model.compile(loss="binary_crossentropy",optimizer="adam",metrics=["accuracy"])
model.summary()

num_epochs = 30
history = model.fit(
    training_padded, training_labels,
    epochs=num_epochs, validation_data=(testing_padded, testing_labels), verbose=2,
)

import matplotlib.pyplot as plt


def plot_graphs(history, string):
    plt.close()
    plt.plot(history.history[string])
    plt.plot(history.history["val_" + string])
    plt.xlabel("Epochs")
    plt.ylabel(string)
    plt.legend([string, "val_" + string])
    plt.savefig(f"plot_{string}.png")


plot_graphs(history, "accuracy")
plot_graphs(history, "loss")

new_sentence = [
    "granny starting to fear spiders in the garden might be real",
    "game of thrones season finale showing this sunday night",
    "kitty wants sushi really bad",
]
new_sequences = tokenizer.texts_to_sequences(new_sentence)
new_padded = pad_sequences(new_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
print(model.predict(new_padded))