準備工作

matplotlib庫

三體.txt（utf-8編碼）

三體主要人物.txt（utf-8編碼）

大綱

匯入matplotlib.pyplot方法，建立1個Novel類，包含2個屬性和4個方法。

import matplotlib.pyplot as plt

class Novel():
    """建立一個小說的類"""
    
    def __init__(self, novel_name, roles_name):
        """初始化類的屬性"""
　　
　　def one_role_nums(self, role_name):
        
 
"""統計一個人物名字出現的次數"""

　　def main_roles_nums(self):
        """統計主要人物名字出現的次數"""

　　def show_datas(self):
        """輸出人物名字及出現次數"""

　　def draw_picture(self, title = ""):
        """視覺化資料"""      

 初始化

類包含兩個屬性，小說名字和主要人物名字。

主要人物來源於《三體》百度百科，以每行一個名字的格式儲存於txt文件，如下圖。

注：艾aa的名字採用aa，因小說中多稱呼aa。

def __init__
 
(self, novel_name, roles_name):
    """初始化類的屬性"""

    self.novel_name = novel_name
    self.roles_name = roles_name

one_role_nums方法

預設名字為2-4個字，否則不計數。

def one_role_nums(self, role_name):
    """統計一個人物名字出現的次數"""

    with open(self.novel_name, encoding = 'utf-8') as f:
        content 
 
= f.read()

    count = 0
    if len(role_name) < 2 or len(role_name) > 4:
        return 0
    if len(role_name) == 2:
        for i in range(len(content) - 1):
            if content[i] + content[i + 1] == role_name:
                count += 1
    if len(role_name) == 3:
        for i in range(len(content) - 2):
            if content[i] + content[i + 1]  + content[i + 2]== role_name:
                count += 1
    if len(role_name) == 4:
        for i in range(len(content) - 3):
            if content[i] + content[i + 1]  + content[i + 2] + content[i + 3] == role_name:
                count += 1
    return count

main_roles_nums方法

返回一個列表，列表元素為字典中的鍵值對且按value降序排列。

def main_roles_nums(self):
    """統計主要人物名字出現的次數"""

    with open(self.roles_name, encoding = 'utf-8') as f:
        names = [line.strip() for line in f.readlines()]

    dic = {}                    
    for name in names:
        num = self.one_role_nums(name)
        if num:
            dic[name] = num
    dic = sorted(dic.items(), key = lambda k : k[1], reverse = True)
    return dic

show_datas方法

def show_datas(self):
    """輸出人物名字及出現次數"""

    dic = self.main_roles_nums()
    for x in dic:
        print(x[0], x[1])

draw_picture方法

運用matplotlib庫將所得資料視覺化。

呼叫方法時可賦予一個標題，預設為空。

def draw_picture(self, title = ""):
    """視覺化資料"""

    dic = self.main_roles_nums()
    names, nums = [], []
    for x in dic:
        names.append(x[0])
        nums.append(x[1])

    n = list(range(len(names)))
    plt.figure(figsize=(10, 6))    
    plt.bar(n, nums, alpha=0.5)
    plt.xlim((0, len(names)))
    plt.xticks(n, names, rotation = 30, fontproperties = "SimHei", fontsize = 24)
    plt.title(title, fontproperties = "SimHei", fontsize = 40)

    plt.show()

建立物件並呼叫方法

建立一個物件，賦予兩個屬性。

novel = Novel("三體.txt", "三體主要人物.txt")   

呼叫方法show_datas()

novel.show_datas()

呼叫方法draw_picture()並賦予一個標題

novel.draw_picture("三體主要人物名字出現次數")

結果符合預期，汪淼、羅輯和程心是當之無愧的三大主角，且隨著《三體I》《三體II》《三體III》小說的篇幅增多而名字出現次數增多。

其他人物名字出現的次數基本與觀感相符合。

全部程式碼

import matplotlib.pyplot as plt

class Novel():
    """建立一個小說的類"""
    
    def __init__(self, novel_name, roles_name):
        """初始化類的屬性"""
        
        self.novel_name = novel_name
        self.roles_name = roles_name
        
    def one_role_nums(self, role_name):
        """統計一個人物名字出現的次數"""
        
        with open(self.novel_name, encoding = 'utf-8') as f:
            content = f.read()
            
        count = 0
        if len(role_name) < 2 or len(role_name) > 4:
            return 0
        if len(role_name) == 2:
            for i in range(len(content) - 1):
                if content[i] + content[i + 1] == role_name:
                    count += 1
        if len(role_name) == 3:
            for i in range(len(content) - 2):
                if content[i] + content[i + 1]  + content[i + 2]== role_name:
                    count += 1
        if len(role_name) == 4:
            for i in range(len(content) - 3):
                if content[i] + content[i + 1]  + content[i + 2] + content[i + 3] == role_name:
                    count += 1
        return count
        
    def main_roles_nums(self):
        """統計主要人物名字出現的次數"""
        
        with open(self.roles_name, encoding = 'utf-8') as f:
            names = [line.strip() for line in f.readlines()]
            
        dic = {}                    
        for name in names:
            num = self.one_role_nums(name)
            if num:
                dic[name] = num
        dic = sorted(dic.items(), key = lambda k : k[1], reverse = True)
        return dic
    
    def show_datas(self):
        """輸出人物名字及出現次數"""
        
        dic = self.main_roles_nums()
        for x in dic:
            print(x[0], x[1])
        
    def draw_picture(self, title = ""):
        """視覺化資料"""
        
        dic = self.main_roles_nums()
        names, nums = [], []
        for x in dic:
            names.append(x[0])
            nums.append(x[1])

        n = list(range(len(names)))
        plt.figure(figsize=(12, 9))    
        plt.bar(n, nums, alpha=0.5)
        plt.xlim((0, len(names)))
        plt.xticks(n, names, rotation = 30, fontproperties = "SimHei", fontsize = 24)
        plt.title(title, fontproperties = "SimHei", fontsize = 40)

        plt.show()
        
novel = Novel("三體.txt", "三體主要人物.txt")   
novel.show_datas()
novel.draw_picture("三體主要人物名字出現次數")