python统计小说人物出现次数_使用python统计《三国演义》小说里人物出现次数前十名，并实现可视化。...

一、安装所需要的第三方库

jieba (jieba是优秀的中文分词第三分库)

pyecharts (一个优秀的数据可视化库)

使用pycharm安装库

打开Pycharm选择【File】下的Settings

出现下面页面,

选择右边的【+】出现下面页面，在此页面顶端搜索想要的库，然后安装就可以了

二、编写代码

import jieba #导入库

import os

print("人物出现次数前十名：")

txt = open('三国演义.txt', 'r' ,encoding='gb18030').read()

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":

rword = "曹操" # 把相同意思的名字归为一个人

else:

rword = word

counts[rword] = counts.get(rword, 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("{}:{}".format(word, count)) # 打印前十名名单

结果如下图：

可以看到这里面有很多不是人物的名字，所以咱们要把这些删掉。更改代码如下

import jieba #导入库

import os

print("人物出现次数前十名：")

txt = open('三国演义.txt', 'r' ,encoding='gb18030').read()

remove = {"将军", "却说", "不能", "后主", "上马", "不知", "天子", "大叫", "众将", "不可",

"主公", "蜀兵", "只见", "如何", "商议", "都督", "一人", "汉中", "人马",

"陛下", "魏兵", "天下", "今日", "左右", "东吴", "于是", "荆州", "不能", "如此",

"大喜", "引兵", "次日", "军士", "军马","二人","不敢"} # 这些文字是要排出掉的，多次运行程序所得到的

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":

rword = "曹操" # 把相同意思的名字归为一个人

else:

rword = word

counts[rword] = counts.get(rword, 0) + 1

for word in remove:

del counts[word] #匹配文字相等就删除

items = list(counts.items())

items.sort(key=lambda x: x[1], reverse=True)

for i in range(10):

word, count=items[i]

print("{}:{}".format(word, count)) # 打印前十名名单

运行结果如下图

可以看到现在都是人物名称了

导出数据，代码如下

import jieba #导入库

import os

print("人物出现次数前十名：")

txt = open('三国演义.txt', 'r' ,encoding='gb18030').read()

remove = {"将军", "却说", "不能", "后主", "上马", "不知", "天子", "大叫", "众将", "不可",

"主公", "蜀兵", "只见", "如何", "商议", "都督", "一人", "汉中", "人马",

"陛下", "魏兵", "天下", "今日", "左右", "东吴", "于是", "荆州", "不能", "如此",

"大喜", "引兵", "次日", "军士", "军马","二人","不敢"} # 这些文字是要排出掉的，多次运行程序所得到的

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":

rword = "曹操" # 把相同意思的名字归为一个人

else:

rword = word

counts[rword] = counts.get(rword, 0) + 1

for word in remove:

del counts[word] #匹配文字相等就删除

items = list(counts.items())

items.sort(key=lambda x: x[1], reverse=True)

#导出数据

fo = open("三国人物出场次数.txt", "a", encoding='utf-8')

for i in range(10):

word, count=items[i]

word = str(word)

count = str(count)

fo.write(word)

fo.write(':') #使用冒号分开

fo.write(count)

fo.write('\n') #换行

fo.close() #关闭文件

现在咱们运行看是否导出，运行结果如下图。

可以看到已经生成一个名为三国人物出场次数.txt的文件，而文件里的内容就是咱们刚才的数据。

三、数据可视化

想要可视化首先咱们要有数据，咱们把刚才导出的数据转换为字典形式。代码如下

#将txt文本里的数据转换为字典形式

fr = open('三国人物出场次数.txt', 'r', encoding='utf-8')

dic = {}

keys = [] # 用来存储读取的顺序

for line in fr:

v = line.strip().split(':')

dic[v[0]] = v[1]

keys.append(v[0])

fr.close()

print(dic)

-运行结果如下

使用pyecharts绘图

先倒入模块

from pyecharts import options as opts

from pyecharts.charts import Bar

代码如下

# 绘图

list1=list(dic.keys())

list2=list(dic.values()) #提取字典里的数据作为绘图数据

c = (

Bar()

.add_xaxis(list1)

.add_yaxis("人物出场次数",list2)

.set_global_opts(

xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),

)

.render("人物出场次数可视化图.html")

)

运行程序看到目录下会生成一个名为人物出场次数可视化图.html的文件，如下图

使用浏览器打开，就可以看到数据以图形的方式呈现出来。

三、全部代码呈现

#《三国演义》的人物出场次数Python代码：

import jieba #导入库

import os

from pyecharts import options as opts

from pyecharts.charts import Bar

print("人物出现次数前十名：")

txt = open('三国演义.txt', 'r' ,encoding='gb18030').read()

remove = {"将军", "却说", "不能", "后主", "上马", "不知", "天子", "大叫", "众将", "不可",

"主公", "蜀兵", "只见", "如何", "商议", "都督", "一人", "汉中", "人马",

"陛下", "魏兵", "天下", "今日", "左右", "东吴", "于是", "荆州", "不能", "如此",

"大喜", "引兵", "次日", "军士", "军马","二人","不敢"} # 这些文字是要排出掉的，多次运行程序所得到的

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":

rword = "曹操" # 把相同意思的名字归为一个人

else:

rword = word

counts[rword] = counts.get(rword, 0) + 1

for word in remove:

del counts[word] #匹配文字相等就删除

items = list(counts.items())

items.sort(key=lambda x: x[1], reverse=True)

#导出数据

fo = open("三国人物出场次数.txt", "a", encoding='utf-8')

for i in range(10):

word, count=items[i]

word = str(word)

count = str(count)

fo.write(word)

fo.write(':') #使用冒号分开

fo.write(count)

fo.write('\n') #换行

fo.close() #关闭文件

#将txt文本里的数据转换为字典形式

fr = open('三国人物出场次数.txt', 'r',encoding='utf-8' )

dic = {}

keys = [] # 用来存储读取的顺序

for line in fr:

v = line.strip().split(':')

dic[v[0]] = v[1]

keys.append(v[0])

fr.close()

print(dic)

# 绘图

list1=list(dic.keys())

list2=list(dic.values()) #提取字典里的数据作为绘图数据

c = (

Bar()

.add_xaxis(list1)

.add_yaxis("人物出场次数",list2)

.set_global_opts(

xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),

)

.render("人物出场次数可视化图.html")

)