基本统计量计算和文本词频统计

一、基本统计量计算

#CalStatisticsV1.py
def getNum():       #获取用户不定长度的输入
    nums = []
    iNumStr = input("请输入数字(回车退出): ")
    while iNumStr != "":
        nums.append(eval(iNumStr))
        iNumStr = input("请输入数字(回车退出): ")
    return nums

def mean(numbers):  #计算平均值
    s = 0.0
    for num in numbers:
        s = s + num
    return s / len(numbers)

def dev(numbers, mean): #计算方差
    sdev = 0.0
    for num in numbers:
        sdev = sdev + (num - mean)**2
    return pow(sdev / (len(numbers)-1), 0.5)

def median(numbers):    #计算中位数
    sorted(numbers)
    size = len(numbers)
    if size % 2 == 0:
        med = (numbers[size//2-1] + numbers[size//2])/2
    else:
        med = numbers[size//2]
    return med

n =  getNum() #主体函数
m =  mean(n)
print("平均值:{},方差:{:.2},中位数:{}.".format(m, dev(n,m),median(n)))

二、文本词频统计
（1）Hamlet词频统计（含Hamlet原文文本）

#CalHamletV1.py
def getText():
    txt = open("hamlet.txt", "r").read()
    txt = txt.lower()
    for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
        txt = txt.replace(ch, " ")   #将文本中特殊字符替换为空格
    return txt

hamletTxt = getText()
words  = hamletTxt.split()
counts = {}
for word in words:			
    counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(10):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

（2）《三国演义》人物出场统计（上）

#CalThreeKingdomsV1.py
import jieba
txt = open("threekingdoms.txt", "r", encoding='utf-8').read()
words  = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    else:
        counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(15):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

（3）《三国演义》人物出场统计（下）

#CalThreeKingdomsV2.py
import jieba
excludes = {"将军","却说","荆州","二人","不可","不能","如此"}
txt = open("threekingdoms.txt", "r", encoding='utf-8').read()
words  = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word == "诸葛亮" or word == "孔明曰":
        rword = "孔明"
    elif word == "关公" or word == "云长":
        rword = "关羽"
    elif word == "玄德" or word == "玄德曰":
        rword = "刘备"
    elif word == "孟德" or word == "丞相":
        rword = "曹操"
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1
for word in excludes:
    del counts[word]
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(10):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))