用dynamic_rnn来进行垃圾邮件分类

#implementing an rnn in tensorflow
#
#we implement an RNN intensorflow to predict spam/ham from texts
#

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
ops.reset_default_graph()

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

#start a graph
sess=tf.Session()

#set rnn parameters
epochs=20
batch_size=250
max_sequence_length=25     #短信最大长度为25个单词，超过部分会被截取掉，不够的部分用0填充
rnn_size=10            #rnn模型由10个单元组成,一个cell中神经元的个数
embedding_size=50         #每个单词会被嵌套在长度为50的词向量中
min_word_frequency=10         #词频超过10的单词
learning_rate=0.0005
dropout_keep_prob=tf.placeholder(tf.float32)

# Download or open data
data_dir = 'temp'
data_file = 'text_data.txt'
if not os.path.exists(data_dir):
    os.makedirs(data_dir)

if not os.path.isfile(os.path.join(data_dir, data_file)):
    zip_url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00228/smsspamcollection.zip'
    r = requests.get(zip_url)
    z = ZipFile(io.BytesIO(r.content))
    file = z.read('SMSSpamCollection')