具体操作步骤如下:
#统计词频
#1 输入文章
#2 建立统计词频的空字典
#3 对文本的一行统计词频
#4 获取字典数据对
#5 对数据对进行排序
#6 输出结果
#7 用Turtle库绘制词频结果图表
实现效果如下:
实现代码如下:
import turtle
##全局变量##
count = 10
data = []
words = []
yScale = 6
xScale = 30
###################
#################Turtle Start #############
#绘制线段(x1,y1)到(x2,y2)
def drawLine(t,x1,y1,x2,y2):
t.penup()
t.goto(x1,y1)
t.pendown()
t.goto(x2,y2)
#在坐标(x,y)处写文字
def drawText(t,x,y,text):
t.penup()
t.goto(x,y)
t.pendown()
t.write(text)
#绘制图表
def drawGraph(t):
#绘制x/y轴线
drawLine(t,0,0,360,0)
drawLine(t,0,300,0,0)
#x轴:坐标以及描述
for x in range(count):
x = x+1 #右移一位,不在原点
drawText(t,x*xScale-4,-20,words[x-1])
drawText(t,x*xScale-4,data[x-1]*yScale+10,data[x-1])
drawBar(t)
#绘制一个柱体
def drawRectangle(t,x,y):
x = x * xScale
y = y * yScale
drawLine(t, x - 5, 0, x - 5, y)
drawLine(t, x - 5, y, x + 5, y)
drawLine(t, x + 5, y, x + 5, 0)
drawLine(t, x + 5, 0, x - 5, 0)
#绘制多个柱体
def drawBar(t):
for i in range(count):
drawRectangle(t,i+1,data[i])
###################### Turtle end ##############
#对文本的每一行计算统计词频的函数
def processLine(line,wordCounts): #wordCounts空字典
#用空格代替标点符号
line = replacePunctuations(line)
#从每一行获取每个词
words = line.split()
for word in words:
if word in wordCounts:
wordCounts[word] += 1
else:
wordCounts[word] = 1
#空格替换标点的函数
def replacePunctuations(line):
for ch in "~@#$%^&*()_-+=<>?/,.:;{}[]|\'""":
line = line.replace(ch," ")
return line
def main():
#用户输入文件名
filename = raw_input("enter a filename: ").strip()
infile = open(filename,"r")
#建立用于计算词频的字典
wordCounts = {}
for line in infile:
processLine(line.lower(),wordCounts)
#从字典获取数据对
pairs = list(wordCounts.items())
# #列表中的数据对交换位置,数据对排序
items = [[x,y] for [y,x] in pairs]
items.sort()
# 输出count个数词频结果
for i in range(len(items)-1,len(items)-count-1,-1):
print(items[i][1]+"\t"+str(items[i][0]))
data.append(items[i][0])
words.append(items[i][1])
infile.close()
# 根据词频结果绘制柱状图
turtle.title("词频结果柱状图")
turtle.setup(900,750,0,0)
t= turtle.Turtle()
t.hideturtle()
t.width(3)
drawGraph(t)
turtle.done()
if __name__ == '__main__':
main()