统计值计算实例、Hamlet词频统计、三国词频统计

统计值计算实例

#CalStatisticsV1.py

def getnum():    #获得用户一连串数字输入
    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+=num
    return s/len(numbers)

def dev(numbers,mean):      #计算方差
    sdev = 0.0
    for num in numbers:
        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()
m=mean(n)
print('平均值：{},方差：{},中位数：{}.'.format(m,dev(n,m),median(n)))

文本词频统计

Hamlet词频统计

#CalHamletV1.py

def gettext():
    txt = open('D://TXT2019//Hamlet.txt','r').read()     #用\或者//代替/，python中/为转字符
    txt = txt.lower()        #将所有大写字符串转换为小写
    for ch in '!"#$%()*+,-./:;<=>?@[\\]^_‘{|}~':
        txt = txt.replace(ch,'')
    return txt

HT = gettext()
words = HT.split()
counts = {}
for word in words:
    counts[word] = counts.get(word,0)+1
items = list(counts.items()) #items()以列表返回可遍历的(键, 值)元组数组[(,),(,),(,)]；list()转换为列表类型
items.sort(key=lambda x:x[1],reverse=True)   #sort()用于排序，根据iems的第二个值进行从大到小的排序
for i in range(15):
    word,count = items[i]              #items的形式应该是[(,),(,),(,),(,)]
    print('{:<10}{:>5}'.format(word,count))

运行效果如下：

D:\Anaconda3\python.exe D:/Python_pycharm_projects/yuyanseji_examples(20190404)/CalHamletV1.py
the        1137
and         963
to          736
of          669
you         546
i           540
a           527
my          513
hamlet      459
in          435
it          415
that        389
is          340
not         312
lord        308

Process finished with exit code 0

三国词频统计

#CalThreeKingdomsV1.py

import jieba as t
txt = open('D:\TXT2019\Threekingdoms.txt','r',encoding='utf-8').read()
words = t.lcut(txt)   #返回的是中文分词列表
counts = {}    #建立空字典类型，用于统计分词与数量
for word in words:       #遍历列表中每个中文分词
    if len(word)==1:
        continue
    else:
        counts[word]=counts.get(word,0)+1   #统计分词和数量
items=list(counts.items())   #将统计完成的字典类型转换成元组数组，再转换成列表
items.sort(key=lambda x:x[1],reverse=True)   #然后对列表中的元组元素第二个从大到小进行排序
for i in range(10):   #遍历输出列表中前10个元组元素
    word,count=items[i]
    print('{:<10}{:>5}'.format(word,count))

运行效果如下：

D:\Anaconda3\python.exe D:/Python_pycharm_projects/yuyanseji_examples(20190404)/CalThreeKingdomsV1.py
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\Public\Documents\iSkysoft\CreatorTemp\jieba.cache
Loading model cost 1.128 seconds.
Prefix dict has been built succesfully.
曹操          953
孔明          836
将军          772
却说          656
玄德          585
关公          510
丞相          491
二人          469
不可          440
荆州          425

Process finished with exit code 0

#CalThreekingdomsV2.py

import jieba
excludes={'将军','却说','荆州','二人','不可','不能','如此'}
txt = open('D:\TXT2019\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(15):
    word , count=items[i]
    print('{:<10}{:>5}'.format(word ,count))

运行效果如下：

D:\Anaconda3\python.exe D:/Python_pycharm_projects/yuyanseji_examples(20190404)/CalThreeKingdomsV2.py
Building prefix dict from the default dictionary ...
Dumping model to file cache C:\Users\Public\Documents\iSkysoft\CreatorTemp\jieba.cache
Loading model cost 1.944 seconds.
Prefix dict has been built succesfully.
孔明         1386
刘备         1254
曹操          953
关羽          786
张飞          358
商议          345
如何          339
主公          331
军士          317
吕布          300
左右          296
军马          293
赵云          279
引兵          276
次日          271

Process finished with exit code 0