求文章的段落的句子个数，句子平均数以及句子的标准差

先用划分段落的办法把每一个段落存进一个列的表里面，再遍历每个段落，求出句子个数

具体代码如下：

# -*-coding:utf-8 -*-
import nltk
# nltk.download()
import sys
import numpy
import re
import os
from scipy.stats import pearsonr
reload(sys)
sys.setdefaultencoding('utf8')
n = 0
while n < 5:
    n += 1
    url = '/home/zheng/firstproject2/essay/' + str(n)
    file_name = os.listdir(url)
    print  str(n) + '分下文章'
    number = 0
    for single_file in file_name:
        number += 1
        with open(url + '/' + single_file, 'r') as essay:
            content = essay.read()
            essay_list=re.split('[\n]+[\s]{2,}', content)
            num=0
            new_list = []
            for single_paragraph in essay_list:
                num += 1
                sentences_num=re.findall('(.*?[A-Za-z]+.*?[\.\!\?])',single_paragraph)
                new_list.append(len(sentences_num))
                N = len(new_list)
                sum1 = 0.0
                sum2 = 0.0
                for i in range(N):
                    sum1 += new_list[i]
                    sum2 += new_list[i] ** 2
                    mean = sum1 / N
                    var = sum2 / N - mean ** 2
                    var = sum2 / N - mean ** 2
                    biaozhuncha=var **0.5
            print '第' + str(number) + '篇文章的段落句子平均数：' +str(float(sum(new_list))/len(new_list))
            print '第' + str(number) + '篇文章的段落句子数的方差为：' + str(var)
            print '第' + str(number) + '篇文章的段落句子数的标准差为：' +str(biaozhuncha)