Python入门学习笔记三

1.组合数据类型

实例：基本统计值计算

#CalStatisticsV1.py
def getNum():
    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(number):
    s=0.0
    for num in number:
        s=s+num
    return s/len(number)
def dev(numbers,mean):
    sdev=0.0
    for num in numbers:
        sdev=sdev+(num-mean)**2
    return pow(sdev/(len(numbers)-1),0.5)
def median(numbers):
    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("平均数{},方差：{:.2}，中位数：{}".format(m,dev(n,m),median(n)))

实例：文本词频统计

#CalHamletV1.py
def getText():
    txt=open("hamlet.txt","r").read()
    txt=txt.lower()
    for ch in '!"#$&()*+,=./:;<>=?@[\\]^_{|}~':
        txt=txt.replace(cj," ")
    return txt
hamletTxt=getText()
words=hamletText.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))

#CalThreeKindomsV2
import jieba
txt=open("threekingkoms.txt","r",encoding="utf-8").read()
excludes={"将军","却说","荆州","二人","不可","不能","如此"}
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=="丞相曰":
        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))

2.文件和数据格式化

实例：自动轨迹绘制

#AutoTranceDraw.py
import turtle as t
t.title("自动绘制轨迹")
t.setup(800,600,0,0)
t.pencolor("red")
t.pensize(5)
#数据读取
datals=[]
f.open("data.txt")
for line in f:
    line=line.replace("\n","")
    datals.append(list(map(eval,line.split(","))))
f.close()
#自动绘制
for i in range(len(datals)):
    t.pencolor(datals[i][3],datals[i][4],datals[i][5])
    t.fd(datals[i][0])
    if datals[i][1]:
        t.right(datals[i][2])
    else:
        t.right(datals[i][2])

实例：政府工作词云报告

#GovRpWordCloudv1.py
import jieba
import wordcloud
f=open("新时代中国特色社会主义.txt","r",encoding="utf-8")
t=f.read()
f.close()
txt=" ".join(jieba.lcut(t))
w=wordcloud.WordCloud(font_path="msyh.ttc"\
width=1000,height=700,background_color="white",\
                     max_words=15)
w,generate(txt)