使用python統計《三國演義》小說里人物出現次數前十名，並實現可視化。

一、安裝所需要的第三方庫

jieba （jieba是優秀的中文分詞第三分庫）
pyecharts （一個優秀的數據可視化庫）

《三國演義》.txt下載地址（提取碼：kist ）

使用pycharm安裝庫

  • 打開Pycharm選擇【File】下的Settings
  • 出現下面頁面,
  • 選擇右邊的【+】出現下面頁面，在此頁面頂端搜索想要的庫，然後安裝就可以了

二、編寫代碼

import jieba  #導入庫
import os
print("人物出現次數前十名：")
txt = open('三國演義.txt', 'r' ,encoding='gb18030').read()
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word == "諸葛亮" or word == "孔明曰":
        rword = "孔明"
    elif word == "關公" or word == "雲長":
        rword = "關羽"
    elif word == "玄德" or word == "玄德曰":
        rword = "劉備"
    elif word == "孟德" or word == "丞相":
        rword = "曹操"  # 把相同意思的名字歸為一個人
    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))  # 打印前十名名單
  • 結果如下圖：
  • 可以看到這裏面有很多不是人物的名字，所以咱們要把這些刪掉。更改代碼如下
import jieba  #導入庫
import os
print("人物出現次數前十名：")
txt = open('三國演義.txt', 'r' ,encoding='gb18030').read()
remove = {"將軍", "卻說", "不能", "後主", "上馬", "不知", "天子", "大叫", "眾將", "不可",
            "主公", "蜀兵", "只見", "如何", "商議", "都督", "一人", "漢中", "人馬",
            "陛下", "魏兵", "天下", "今日", "左右", "東吳", "於是", "荊州", "不能", "如此",
            "大喜", "引兵", "次日", "軍士", "軍馬","二人","不敢"}  # 這些文字是要排出掉的，多次運行程序所得到的
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word == "諸葛亮" or word == "孔明曰":
        rword = "孔明"
    elif word == "關公" or word == "雲長":
        rword = "關羽"
    elif word == "玄德" or word == "玄德曰":
        rword = "劉備"
    elif word == "孟德" or word == "丞相":
        rword = "曹操"  # 把相同意思的名字歸為一個人
    else:
        rword = word
    counts[rword] = counts.get(rword, 0) + 1
for word in remove:
    del counts[word]  #匹配文字相等就刪除

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))  # 打印前十名名單
  • 運行結果如下圖

可以看到現在都是人物名稱了

  • 導出數據，代碼如下
import jieba  #導入庫
import os
print("人物出現次數前十名：")
txt = open('三國演義.txt', 'r' ,encoding='gb18030').read()
remove = {"將軍", "卻說", "不能", "後主", "上馬", "不知", "天子", "大叫", "眾將", "不可",
            "主公", "蜀兵", "只見", "如何", "商議", "都督", "一人", "漢中", "人馬",
            "陛下", "魏兵", "天下", "今日", "左右", "東吳", "於是", "荊州", "不能", "如此",
            "大喜", "引兵", "次日", "軍士", "軍馬","二人","不敢"}  # 這些文字是要排出掉的，多次運行程序所得到的
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word == "諸葛亮" or word == "孔明曰":
        rword = "孔明"
    elif word == "關公" or word == "雲長":
        rword = "關羽"
    elif word == "玄德" or word == "玄德曰":
        rword = "劉備"
    elif word == "孟德" or word == "丞相":
        rword = "曹操"  # 把相同意思的名字歸為一個人
    else:
        rword = word
    counts[rword] = counts.get(rword, 0) + 1
for word in remove:
    del counts[word]  #匹配文字相等就刪除

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

#導出數據

fo = open("三國人物出場次數.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(':') #使用冒號分開
   fo.write(count)
   fo.write('\n') #換行 
fo.close() #關閉文件
  • 現在咱們運行看是否導出，運行結果如下圖。

可以看到已經生成一個名為三國人物出場次數.txt的文件，而文件里的內容就是咱們剛才的數據。

三、數據可視化

  • 想要可視化首先咱們要有數據，咱們把剛才導出的數據轉換為字典形式。代碼如下
#將txt文本里的數據轉換為字典形式
fr = open('三國人物出場次數.txt', 'r', encoding='utf-8')
dic = {}
keys = [] # 用來存儲讀取的順序
for line in fr:
  v = line.strip().split(':')
  dic[v[0]] = v[1]
  keys.append(v[0])
fr.close()
print(dic)

-運行結果如下

  • 使用pyecharts繪圖
  • 先倒入模塊
from pyecharts import options as opts
from pyecharts.charts import Bar
  • 代碼如下
#　繪圖
list1=list(dic.keys())
list2=list(dic.values())  #提取字典里的數據作為繪圖數據
c = (
    Bar()
    .add_xaxis(list1)
    .add_yaxis("人物出場次數",list2)
    .set_global_opts(
        xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),
    )
    .render("人物出場次數可視化圖.html")
)
  • 運行程序看到目錄下會生成一個名為人物出場次數可視化圖.html的文件，如下圖
  • 使用瀏覽器打開，就可以看到數據以圖形的方式呈現出來。

三、全部代碼呈現

#《三國演義》的人物出場次數Python代碼：


import jieba  #導入庫
import os
from pyecharts import options as opts
from pyecharts.charts import Bar

print("人物出現次數前十名：")
txt = open('三國演義.txt', 'r' ,encoding='gb18030').read()
remove = {"將軍", "卻說", "不能", "後主", "上馬", "不知", "天子", "大叫", "眾將", "不可",
            "主公", "蜀兵", "只見", "如何", "商議", "都督", "一人", "漢中", "人馬",
            "陛下", "魏兵", "天下", "今日", "左右", "東吳", "於是", "荊州", "不能", "如此",
            "大喜", "引兵", "次日", "軍士", "軍馬","二人","不敢"}  # 這些文字是要排出掉的，多次運行程序所得到的
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word == "諸葛亮" or word == "孔明曰":
        rword = "孔明"
    elif word == "關公" or word == "雲長":
        rword = "關羽"
    elif word == "玄德" or word == "玄德曰":
        rword = "劉備"
    elif word == "孟德" or word == "丞相":
        rword = "曹操"  # 把相同意思的名字歸為一個人
    else:
        rword = word
    counts[rword] = counts.get(rword, 0) + 1
for word in remove:
    del counts[word]  #匹配文字相等就刪除

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

#導出數據

fo = open("三國人物出場次數.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(':') #使用冒號分開
   fo.write(count)
   fo.write('\n') #換行
fo.close() #關閉文件

#將txt文本里的數據轉換為字典形式
fr = open('三國人物出場次數.txt', 'r',encoding='utf-8' )
dic = {}
keys = [] # 用來存儲讀取的順序
for line in fr:
  v = line.strip().split(':')
  dic[v[0]] = v[1]
  keys.append(v[0])
fr.close()
print(dic)


#　繪圖
list1=list(dic.keys())
list2=list(dic.values())  #提取字典里的數據作為繪圖數據
c = (
    Bar()
    .add_xaxis(list1)
    .add_yaxis("人物出場次數",list2)
    .set_global_opts(
        xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),
    )
    .render("人物出場次數可視化圖.html")
)
Tags:

VirMach 便宜 VPS

QNews

QNews