Implementing an RNN for spam prediction

In this section, we will see how to implement an RNN in TensorFlow to predict spam/ham from texts.

Data description and preprocessing

The popular spam dataset from the UCI ML repository will be used, which can be downloaded from http://archive.ics.uci.edu/ml/machine-learning-databases/00228/smssp amcollection.zip.

The dataset contains texts from several emails, some of which were marked as spam. Here we will train a model that will learn to distinguish between spam and non-spam emails using only the text of the email. Let's get started by importing the required libraries and model:

import os
import re
import io
import requests
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from zipfile import ZipFile
from tensorflow.python.framework import ops
import warnings

Additionally, we can stop printing the warning produced by TensorFlow if you want:

warnings.filterwarnings("ignore")
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
ops.reset_default_graph...