Python-统计值计算、词频统计

一、统计值计算

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:#遍历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)))

统计值计算

 二、词频统计

def getText():
    txt = open("Text.txt", "r").read()
    txt = txt.lower()#字母变小写
    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))

词频统计