Python123第六周（实例）

1，求解基本统计值

#calstistics.py
def getNum(): #获取多个输入值
    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）：") #此处无法忽略，否则输入无法跳出
    return nums
    
def mean(numbers): #求解平均值
    s = 0.0
    for num in numbers:
        s = s + num
    return s / len(numbers)

def dev(numbers,mean): #求解方差
    sdev = 0.0
    for num in numbers:
        sdev = sdev + (num - mean)**2
    return pow(sdev/len(numbers),0.5) #此处视频中为len(numbers)-1

def median(numbers): #求解中位数
    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 #之前忘记了返回值，导致输出为None

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

2, jieba库的安装与使用指令

在cmd命令行中输入
pip install jieba
若报错存在延时，也可输入
pip --default-timeout=100 install -U jieba
若仍然报错，则需要手动安装
（1）下载地址https://pypi.org/project/jieba/#files
（2）cmd进入jieba的文件python setup.py install

jieba的常用函数


3，文本词频分析

# #dpcq.txt
import jieba
excludes = {"便是","之中","能够","旋即","之上","却是","有些","有着","这种","然后"}
txt = open("dpcq.txt","r",encoding="ANSI").read()
words = jieba.lcut(txt) #切分文章
counts = {} #创建字典类型
for word in words:
    if len(word) == 1:
        continue
    #可以添加elif
    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(30):
    word, count = items[i]
    print("{0:<10}{1:>15}".format(word,count))

吐槽：斗破苍穹词汇实在是太贫瘠了