python學習筆記2詞頻統計
對英文文字中的英文單詞進行詞頻統計:
程式碼如下:
# -*- coding: utf-8 -*-
"""
Created on Thu Apr 5 20:07:09 2018
@author: Administrator
"""
import turtle
count=5
data=[]
words=[]
yScale=10
xScale=30
#點連成線
def drawLine(t,x1,y1,x2,y2):
t.penup()
t.goto(x1,y1)
t.pendown()
t.goto(x2,y2)
#寫入文字
def drawText(t,x,y,text):
t.penup()
t.goto(x,y)
t.pendown()
t.write(text)
#繪圖
def drawGraph(t):
drawLine(t,0,0,400,0)
drawLine(t,0,400,0,0)
for x in range(count):
x=x+1
drawText(t,x*xScale-4,-20,(words[x-1]))
drawText(t,x*xScale-4,data[x-1]*yScale+10,data[x-1])
drawBar(t)
#繪製直方圖
def drawRectangle(t,x,y):
x=x*xScale
y=y*yScale
drawLine(t,x-10,0,x-10,y)
drawLine(t,x-10,y,x+10,y)
drawLine(t,x+10,y,x+10,0)
drawLine(t,x+10,0,x-10,0)
#繪製多個直方圖
def drawBar(t):
for i in range(count):
drawRectangle(t,i+1,data[i])
#處理文字
def processLine(line,wordCounts):
line=replacePunctuations(line)
#從每一行獲取每個詞
words=line.split()
for word in words:
if word in wordCounts:
wordCounts[word] +=1
else:
wordCounts[word] =1
#用空格替換標點符號
def replacePunctuations(line):
for ch in line:
if ch in "/
line =line.replace(ch,"")
return line
def main():
#使用者輸入一個檔名
filename=input("enter a filename:").strip()
infile=open(filename,"r")
#建立用於計算詞頻的空字典
wordCounts={}
for line in infile:
processLine(line.lower(),wordCounts)
#從字典中獲取資料對
pairs=list(wordCounts.items())
#列表中的資料對交換位置,資料對排序
items=[[x,y]for (y,x) in pairs]
items.sort()
#輸出count個數詞頻結果
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])
#根據詞頻結果繪製柱狀圖
turtle.title('詞頻結果柱狀圖')
turtle.setup(900,750,0,0)
t=turtle.Turtle()
t.hideturtle()
t.width(3)
drawGraph(t)
#呼叫main()函式
if __name__=='__main__':
main()
輸出顯示: