python學(xué)習(xí) - day3

1、三國(guó)演義Top10人物分析

import jieba
from wordcloud import WordCloud
import imageio
# 1.讀取小說(shuō)內(nèi)容
with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
    words = f.read()
    counts = {} # counts = {'姓名':出現(xiàn)頻率}
    excludes = {"將軍", "卻說(shuō)", "丞相", "二人", "不可", "荊州", "不能", "如此", "商議",
                "如何", "主公", "軍士", "軍馬", "左右", "次日", "引兵", "大喜", "天下",
                "東吳", "于是", "今日", "不敢", "魏兵", "陛下", "都督", "人馬", "不知",
                "孔明曰", "玄德曰", "劉備", "云長(zhǎng)"}
    # 2.分詞
    words_list = jieba.lcut(words)
    print(words_list)
    for word in words_list:
            if len(word) <= 1:
                continue
            else:
                # 更新字典中的值
                # counts[word] = 取出字典中原來(lái)鍵對(duì)應(yīng)的值 ＋ 1
                # counts[word] = counts[word] + 1
                # 字典.get(k)  如果字典中沒(méi)有這個(gè)鍵 ，(返回NONE)添加一個(gè)默認(rèn)值：0
                counts[word] = counts.get(word, 0) + 1
    print(counts)
    # 3.詞語(yǔ)過(guò)濾，刪除無(wú)關(guān)詞，重復(fù)詞
    counts['孔明'] = counts['孔明'] + counts['孔明曰']
    counts['玄德'] = counts['玄德'] + counts['玄德曰'] + counts['劉備']
    counts['關(guān)公'] = counts['關(guān)公'] + counts['云長(zhǎng)']
    for word in excludes:
        del counts[word]
    # 4.排序[(), ()]
    items = list(counts.items())
    print(items)

    # def sort_by_count(x):
    #     return x[1]
    # items.sort(key=sort_by_count, reverse=True)
    # 用列表解析排序
    items.sort(key=lambda x: x[1], reverse=True)
    # print(items)
    li = []  # ['孔明', '孔明', '孔明',..., '曹操'...]
    for i in range(10):
        # 序列解包
        role, count = items[i]
        print(role, count)
        # _ 是告訴看代碼的人，循環(huán)里面不需要使用臨時(shí)變量
        for _ in range(count):
            li.append(role)
        # 得出結(jié)論
        # 繪制中文詞云，在WordCloud()里面設(shè)置參數(shù)
        text = ' '.join(li)
        wc = WordCloud(
            font_path='msyh.ttc',
            background_color='white',
            width=800,
            height=600,
            # 相鄰兩個(gè)重復(fù)詞之間的匹配，關(guān)掉
            collocations=False
        ).generate(text)
        wc.to_file('三國(guó)TOP10人物詞云.png')

結(jié)果：
Top10人物

2、匿名函數(shù) lambda

  • 結(jié)構(gòu)： lambda x1, x2, ...xn: 表達(dá)式
    eg：
sum_num = lambda x1, x2: x1+x2
print(sum_num(2, 3))
# 結(jié)果：5
  • 參數(shù)可以是無(wú)限多個(gè)，但是表達(dá)式只有一個(gè)
    eg1：從大到小排序
name_info_list = [
    ('張三', 4500),
    ('李四', 9500),
    ('王五', 2000),
    ('趙六', 5500),
]
name_info_list.sort(key=lambda x: x[1], reverse=True)
print(name_info_list)
# 結(jié)果：[('李四', 9500), ('趙六', 5500), ('張三', 4500), ('王五', 2000)]

eg2：從小到大排序

stu_info = [
    {"name": 'zhangsan', "age": 18},
    {"name": 'lisi', "age": 30},
    {"name": 'wangwu', "age": 99},
    {"name": 'tianqi', "age": 3},
]
stu_info.sort(key=lambda i: i['age'])
print(stu_info)
# 結(jié)果：[{'name': 'tianqi', 'age': 3}, {'name': 'zhangsan', 'age': 18}, {'name': 'lisi', 'age': 30}, {'name': 'wangwu', 'age': 99}]

3、列表推導(dǎo)式，列表解析和字典解析

1、列表推導(dǎo)式

  • 之前用普通for 創(chuàng)建列表
li = []
for i in range(10):
    li.append(i)
print(li)
# 結(jié)果：[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
  • 使用列表推導(dǎo)式創(chuàng)建列表
    結(jié)構(gòu)：[表達(dá)式 for 臨時(shí)變量 in 可迭代對(duì)象 可以追加條件]
print([i for i in range(10)])
# 結(jié)果：[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]

2、 列表解析

  • 普通篩選出列表中所有的偶數(shù)
# 篩選出列表中所有的偶數(shù)
li = []
for i in range(10):
    if i % 2 == 0:
        li.append(i)
print(li)
# 結(jié)果：[0, 2, 4, 6, 8]
  • 使用列表解析篩選偶數(shù)
print([i for i in range(10) if i % 2 == 0])
# 結(jié)果：[0, 2, 4, 6, 8]
  • 篩選出列表中 大于0 的數(shù)
# 隨機(jī)生成(-10, 10)的10個(gè)數(shù)
from random import randint
num_list = [randint(-10, 10) for _ in range(10)]
print(num_list)
# 輸出num_list中 大于0 的數(shù)
print([i for i in num_list if i > 0])
# 結(jié)果：[-5, -1, -4, -8, -8, -1, -8, 7, 10, -4]
#      [7, 10]

3、字典解析

from random import randint
stu_grades = {'student{}'.format(i): randint(50, 100) for i in range(1, 101)}
print(stu_grades)

# 篩選 大于60 分的所有學(xué)生
print({k: v for k, v in stu_grades.items() if v > 60})

結(jié)果：
結(jié)果

4、Matplotlib

  • 導(dǎo)入
from matplotlib import pyplot as plt
  • 使用100個(gè)點(diǎn) 繪制[0, 2π]正余弦曲線圖
from matplotlib import pyplot as plt
import numpy as np
# 處理中文亂碼
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

# 使用100個(gè)點(diǎn)  繪制[0, 2π]正弦曲線圖
# .linspace 左閉右閉區(qū)間的等差數(shù)列
x = np.linspace(0, 2*np.pi, num=100)
print(x)
y = np.sin(x)
# 正弦和余弦在同一坐標(biāo)系下
cosy = np.cos(x)
plt.plot(x, y, color='g', linestyle='--')
plt.plot(x, cosy, color='r')
plt.xlabel('時(shí)間（s）')
plt.ylabel('電壓（v）')
plt.title('歡迎來(lái)到python世界')
# 圖例
plt.legend()
plt.show()

結(jié)果：
正余弦圖
  • 柱狀圖
# 切片
# print(string.ascii_uppercase[0: 6])
# 結(jié)果：ABCDEF

# 柱狀圖
from matplotlib import pyplot as plt
# 處理中文亂碼
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
x = ['口紅{}'.format() for x in string.ascii_uppercase[:5]]
y = [randint(200, 500) for _ in range(5)]
print(x)
print(y)
plt.xlabel('口紅品牌')
plt.ylabel('價(jià)格（元）')
plt.bar(x, y)
plt.show()

結(jié)果：
柱狀圖
  • 餅圖
# 餅圖
from matplotlib import pyplot as plt
# 處理中文亂碼
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
from random import randint
counts = [randint(3500, 9000) for _ in range(6)]
labels = ['員工{}'.format(x) for x in string.ascii_lowercase[:6]]
# 距離圓心點(diǎn)距離
explode = [0.1, 0, 0, 0, 0, 0]
color = ['red', 'purple', 'blue', 'yellow', 'gray', 'green']
plt.pie(counts, explode=explode, shadow=True, labels=labels, autopct='%1.1f%%', colors=color)
plt.axis('equal')
plt.legend(loc=2)
plt.show()

結(jié)果：
餅圖
  • 散點(diǎn)圖
from matplotlib import pyplot as plt
import numpy as np
# 均值為 0 標(biāo)準(zhǔn)差為 1 的正態(tài)分布數(shù)據(jù)
x = np.random.normal(0, 1, 100)
y = np.random.normal(0, 1, 100)
plt.scatter(x, y)
plt.show()

結(jié)果：
散點(diǎn)圖
  • 有透明度的散點(diǎn)圖
from matplotlib import pyplot as plt
import numpy as np
x = np.random.normal(0, 1, 100)
y = np.random.normal(0, 1, 100)
# alpha透明度
plt.scatter(x, y, alpha=0.1)
plt.show()

結(jié)果：
有透明度的散點(diǎn)圖

5、繪制 三國(guó)top10人物 餅圖

with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
    words = f.read()
    counts = {} # counts = {'姓名':出現(xiàn)頻率}
    excludes = {"將軍", "卻說(shuō)", "丞相", "二人", "不可", "荊州", "不能", "如此", "商議",
                "如何", "主公", "軍士", "軍馬", "左右", "次日", "引兵", "大喜", "天下",
                "東吳", "于是", "今日", "不敢", "魏兵", "陛下", "都督", "人馬", "不知",
                "孔明曰", "玄德曰", "劉備", "云長(zhǎng)"}
    # 2.分詞
    words_list = jieba.lcut(words)
    print(words_list)
    for word in words_list:
            if len(word) <= 1:
                continue
            else:
                # 字典.get(k)  如果字典中沒(méi)有這個(gè)鍵 ，(返回NONE)添加一個(gè)默認(rèn)值：0
                counts[word] = counts.get(word, 0) + 1
    print(counts)
    # 3.詞語(yǔ)過(guò)濾，刪除無(wú)關(guān)詞，重復(fù)詞
    counts['孔明'] = counts['孔明'] + counts['孔明曰']
    counts['玄德'] = counts['玄德'] + counts['玄德曰'] + counts['劉備']
    counts['關(guān)公'] = counts['關(guān)公'] + counts['云長(zhǎng)']
    for word in excludes:
        del counts[word]
    # 4.排序[(), ()]
    items = list(counts.items())
    # print(items)
    # 普通排序
    # def sort_by_count(x):
    #     return x[1]
    # items.sort(key=sort_by_count, reverse=True)
    # 用列表解析排序
    items.sort(key=lambda x: x[1], reverse=True)
    # print(items)
    li = []  # ['孔明', '孔明', '孔明',..., '曹操'...]
    counts = [] # 人物名
    labels = [] # 次數(shù)
    for i in range(10):
        # 序列解包
        role, count = items[i]
        counts.append(count)
        labels.append(role)
# 距離圓心點(diǎn)距離
explode = [0.1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
color = ['red', 'purple', 'blue', 'yellow', 'gray', 'green', 'pink']
plt.pie(counts, explode=explode, shadow=True, labels=labels, autopct='%1.1f%%')
plt.axis('equal')
plt.legend(loc=2)
plt.show()

結(jié)果：
三國(guó)Top10人物餅圖

6、紅樓夢(mèng) Top10 人物分析

import jieba
from wordcloud import WordCloud
import imageio
# 1.讀取小說(shuō)內(nèi)容
with open('./novel/all.txt', 'r', encoding='utf-8') as f:
    words = f.read()
    counts = {} # counts = {'姓名':出現(xiàn)頻率}
    excludes = {"什么", "一個(gè)", "我們", "你們", "如今", "說(shuō)道", "太太", "知道", "姑娘",
                "起來(lái)", "這里", "出來(lái)", "眾人", "那里", "自己", "一面", "只見(jiàn)", "兩個(gè)",
                "沒(méi)有", "怎么", "不是", "不知", "這個(gè)", "聽(tīng)見(jiàn)", "奶奶", "老太太", "不知",
                "這樣", "進(jìn)來(lái)", "咱們", "就是", "東西", "告訴", "回來(lái)", "只是", "大家",
                "老爺", "只得", "丫頭", "這些", "他們", "不敢", "出去", "所以", "賈寶玉",
                "林黛玉", "薛寶釵", "鳳姐兒", "王熙鳳"}
    # 2.分詞
    words_list = jieba.lcut(words)
    print(words_list)
    for word in words_list:
            if len(word) <= 1:
                continue
            else:
                # 更新字典中的值
                # counts[word] = 取出字典中原來(lái)鍵對(duì)應(yīng)的值 ＋ 1
                # counts[word] = counts[word] + 1
                # 字典.get(k)  如果字典中沒(méi)有這個(gè)鍵 ，(返回NONE)添加一個(gè)默認(rèn)值：0
                counts[word] = counts.get(word, 0) + 1
    print(counts)
    # 3.詞語(yǔ)過(guò)濾，刪除無(wú)關(guān)詞，重復(fù)詞
    counts['寶玉'] = counts['寶玉'] + counts['賈寶玉']
    counts['黛玉'] = counts['黛玉'] + counts['林黛玉']
    counts['寶釵'] = counts['寶釵'] + counts['薛寶釵']
    counts['賈母'] = counts['賈母'] + counts['老太太']
    counts['鳳姐'] = counts['鳳姐'] + counts['鳳姐兒'] + counts['王熙鳳']
    for word in excludes:
        del counts[word]
    # 4.排序[(), ()]
    items = list(counts.items())
    print(items)

    # def sort_by_count(x):
    #     return x[1]
    # items.sort(key=sort_by_count, reverse=True)
    # 用列表解析排序
    items.sort(key=lambda x: x[1], reverse=True)
    # print(items)
    li = []  # ['孔明', '孔明', '孔明',..., '曹操'...]
    for i in range(10):
        # 序列解包
        role, count = items[i]
        print(role, count)
        # _ 是告訴看代碼的人，循環(huán)里面不需要使用臨時(shí)變量
        for _ in range(count):
            li.append(role)
        # 得出結(jié)論
        # 繪制中文詞云，在WordCloud()里面設(shè)置參數(shù)
        text = ' '.join(li)
        wc = WordCloud(
            font_path='msyh.ttc',
            background_color='white',
            width=800,
            height=600,
            # 相鄰兩個(gè)重復(fù)詞之間的匹配，關(guān)掉
            collocations=False
        ).generate(text)
        wc.to_file('紅樓夢(mèng)TOP10人物詞云.png')

結(jié)果：
紅樓夢(mèng)TOP10人物詞云
?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請(qǐng)聯(lián)系作者
【社區(qū)內(nèi)容提示】社區(qū)部分內(nèi)容疑似由AI輔助生成，瀏覽時(shí)請(qǐng)結(jié)合常識(shí)與多方信息審慎甄別。
平臺(tái)聲明：文章內(nèi)容（如有圖片或視頻亦包括在內(nèi)）由作者上傳并發(fā)布，文章內(nèi)容僅代表作者本人觀點(diǎn)，簡(jiǎn)書(shū)系信息發(fā)布平臺(tái)，僅提供信息存儲(chǔ)服務(wù)。

相關(guān)閱讀更多精彩內(nèi)容

  • 好像第三天的學(xué)習(xí)筆記忘寫了，直接合并到一起來(lái)，學(xué)的貌似都是函數(shù)的相關(guān)知識(shí) 1.變長(zhǎng)參數(shù) ‘ * ’ 將參數(shù)都放到一...
    Heller_J閱讀 287評(píng)論 0贊 0
  • 實(shí)現(xiàn)詞云的繪制 步驟： 1.繪制詞云的形狀 2.讀取小說(shuō)內(nèi)容 3.分詞 4.詞語(yǔ)過(guò)濾,刪除無(wú)關(guān)詞，重復(fù)詞 5.排序...
    小頴子閱讀 454評(píng)論 0贊 0
  • 一、繪制詞云 導(dǎo)入包 讀取小說(shuō)內(nèi)容 分詞 詞語(yǔ)過(guò)濾,刪除無(wú)關(guān)詞，重復(fù)詞 排序 序列解包 結(jié)論 二、匿名函數(shù) 匿名函...
    喵青禾閱讀 365評(píng)論 0贊 0
  • 三國(guó)人物分析圖 匿名函數(shù) lambda lambda x1, x2, ...xn: 表達(dá)式sum_num = la...
    ___a67c閱讀 513評(píng)論 0贊 0
  • 首先要解決昨天安裝詞云失敗的問(wèn)題 安裝失敗會(huì)報(bào)詳情，原來(lái)是我選擇錯(cuò)誤，應(yīng)該選擇32位，而自己錯(cuò)裝成64位卸載重裝后...
    小海綿ball閱讀 611評(píng)論 0贊 0

友情鏈接更多精彩內(nèi)容