python學(xué)習(xí)的第三天

1.三國TOP10人物分析

1.讀取小說內(nèi)容
2.分詞
3.詞語過濾，刪除無關(guān)詞、重復(fù)分詞
4.排序
5.得出結(jié)論

import jieba
# 1. 讀取小說內(nèi)容
with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
    words = f.read()
    counts = {} #{'曹操': 234, '回寨': 56}
# 2.分詞
    words_list = jieba.lcut(words)
    for word in words_list:
        if len(word) <= 1:
            continue
        else:
            #向字典中更新字典中的值
            #counts[word] = 取出字典中原來鍵對應(yīng)的值 + 1
            # counts[word] = counts[word] + 1  counts[word]沒有就會報錯
            #字典.get(k) 如果字典中沒有這個鍵 返回 none
            counts[word] = counts.get(word, 0) + 1
    print(counts)
# 3.詞語過濾，刪除無關(guān)詞、重復(fù)分詞
    # 4.排序 [(), ()]
    items = list(counts.items())
    print('排序前的列表', items)
    def sort_by_count(x):
        return x[1]
    items.sort(key=sort_by_count, reverse=True)
    for i in range(20):
        #序列解包
        role, count = items[i]
        print(role, count)

排除不是人名的分詞，合并人名，然后排出top10

exclude = {"將軍", "卻說", "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"}

   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']
   for word in exclude:
       del counts[word]

最終代碼：（其中collocations=False ：取消相鄰兩個重復(fù)詞之間的匹配)

import jieba
from wordcloud import WordCloud
import imageio
# 1. 讀取小說內(nèi)容
with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
    words = f.read()
    counts = {} #{'曹操': 234, '回寨': 56}
    exclude = {"將軍", "卻說", "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"}

    # 2.分詞
    words_list = jieba.lcut(words)
    for word in words_list:
        if len(word) <= 1:
            continue
        else:
            #向字典中更新字典中的值
            #counts[word] = 取出字典中原來鍵對應(yīng)的值 + 1
            # counts[word] = counts[word] + 1  counts[word]沒有就會報錯
            #字典.get(k) 如果字典中沒有這個鍵 返回 none
            counts[word] = counts.get(word, 0) + 1
    print(counts)
    # 3.詞語過濾，刪除無關(guān)詞、重復(fù)分詞
    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']
    for word in exclude:
        del counts[word]
    # 4.排序 [(), ()]
    items = list(counts.items())
    print('排序前的列表', items)
    def sort_by_count(x):
        return x[1]
    items.sort(key=sort_by_count, reverse=True)

    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變量
        for _ in range(count):
            li.append(role)
    # 5.得出結(jié)論
    mask = imageio.imread('./china.jpg')
    text = ' '.join(li)
    WordCloud(
        font_path='msyh.ttc',
        background_color='white',
        width=800,
        height=600,
        mask=mask,
        # 相鄰兩個重復(fù)詞之間的匹配
        collocations=False
    ).generate(text).to_file('top10.png')

2.匿名函數(shù)

# 匿名函數(shù)
# 結(jié)構(gòu)
# lambda x1, x2....xn: 表達式
sum_num = lambda x1, x2: x1+x2
print(sum_num(2, 3))
# # 參數(shù)可以是無限多個，但是表達式只有一個
name_info_list = [
    ('張三',4500),
    ('李四',9900),
    ('王五',2000),
    ('趙六',5500),
]
name_info_list.sort(key=lambda x:x[1], reverse=True)
print(name_info_list)
stu_info = [
    {"name":'zhangsan', "age":18},
    {"name":'lisi', "age":30},
    {"name":'wangwu', "age":99},
    {"name":'tiaqi', "age":3},
]
stu_info.sort(key=lambda i:i['age'])
print(stu_info)
# 列表推導(dǎo)式，列表解析個字典解析
# 之前我們使用普通for 創(chuàng)建列表
li = []
for i in range(10):
    li.append(i)
print(li)
# # 使用列表推導(dǎo)式
# # [表達式 for 臨時變量 in 可迭代對象 可以追加條件]
print([i for i in range(10)])
# 列表解析
# # 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)
# # 使用列表解析
print([i for i in range(10) if i%2 == 0])
# 篩選出列表中 大于0 的數(shù)
from random import randint
num_list = [randint(-10, 10) for _ in range(10)]
print(num_list)
print([i for i in num_list if i>0])

# 字典解析

# 生成100個學(xué)生的成績
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})

3. Matplotlib

Matplotlib 是一個Python的2D繪圖庫，它以各種硬拷貝格式和跨平臺的交互式環(huán)境生成出版質(zhì)量級別的圖形 。
通過 Matplotlib，開發(fā)者可以僅需要幾行代碼，便可以生成繪圖，直方圖，功率譜，條形圖，錯誤圖，散點圖等。

繪制圖形

# matplotlib
#  導(dǎo)入
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import numpy as np

# #  使用100個點 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系下
cosy = np.cos(x)
plt.plot(x, y, color='g', linestyle='--',label='sin(x)')
plt.plot(x, cosy, color='r',label='cos(x)')
plt.xlabel('時間（s）')
plt.ylabel('電壓（V）')
plt.title('歡迎來到python世界')
# # 圖例
plt.legend()
plt.show()

# 繪制柱狀圖
import string
from random import randint
# print(string.ascii_uppercase[0:6])
# ['A', 'B', 'C'...]
x = ['口紅{}'.format(x) 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('價格（元）')
plt.bar(x, y)
plt.show()

#繪制餅圖
from random import randint
import string
counts = [randint(3500, 9000) for _ in range(6)]
labels = ['員工{}'.format(x) for x in string.ascii_lowercase[:6] ]
# # 距離圓心點距離
explode = [0.1,0,0, 0, 0,0]
colors = ['red', 'purple','blue', 'yellow','gray','green']
plt.pie(counts,explode = explode,shadow=True, labels=labels, autopct = '%1.1f%%',colors=colors)
plt.legend(loc=2)
plt.axis('equal')
plt.show()

# 繪制散點圖
# 均值為 0 標準差為1 的正太分布數(shù)據(jù)
x = np.random.normal(0, 1, 100)
y = np.random.normal(0, 1, 100)
plt.scatter(x, y)
plt.show()
x = np.random.normal(0, 1, 1000000)
y = np.random.normal(0, 1, 1000000)
# alpha透明度
plt.scatter(x, y, alpha=0.1)
plt.show()

4.練習(xí)

4.1 紅樓夢TOP10人物分析

import jieba
from wordcloud import WordCloud
# 1.讀取小說內(nèi)容
with open('./all.txt', 'r', encoding='utf-8') as f:
    words = f.read()

    counts = {}
    excludes = {"什么", "一個", "我們", "你們", "如今", "說道", "知道", "起來", "這里",
               "出來", "眾人", "那里", "自己", "一面", "只見", "太太", "兩個", "沒有",
               "怎么", "不是", "不知", "這個", "聽見", "這樣", "進來", "咱們", "就是",
               "老太太", "東西", "告訴", "回來", "只是", "大家", "姑娘", "奶奶", "鳳姐兒"}
    # 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] = 取出字典中原來鍵對應(yīng)的值 + 1
            # counts[word] = counts[word] + 1  # counts[word]如果沒有就要報錯
            # 字典。get（k） 如果字典中沒有這個鍵 返回 NONE
            counts[word] = counts.get(word, 0) + 1

    print(len(counts))
    # 3. 詞語過濾,刪除無關(guān)詞，重復(fù)詞
    counts['賈母'] = counts['老太太'] + counts['賈母']
    counts['林黛玉'] = counts['林妹妹'] + counts['黛玉']
    counts['賈寶玉'] = counts['寶玉'] +counts['賈寶玉']
    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)

    li = []  
    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變量
        for _ in range(count):
            li.append(role)

    # 5得出結(jié)論

    text = ' '.join(li)
    WordCloud(
        font_path='msyh.ttc',
        background_color='black',
        width=800,
        height=600,
        # 相鄰兩個重復(fù)詞之間的匹配
        collocations=False
    ).generate(text).to_file('top10.png')

紅樓夢人物分析

4.2 繪制三國top10人物餅圖

#繪制三國人物TOP10餅圖
import jieba
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# 1.讀取小說內(nèi)容
with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
    words = f.read()
    counts = {}  # {‘曹操’:234，‘回寨’:56}
    excludes = {"將軍", "卻說", "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"}
    # 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] = 取出字典中原來鍵對應(yīng)的值 + 1
            # counts[word] = counts[word] + 1  # counts[word]如果沒有就要報錯
            # 字典。get（k） 如果字典中沒有這個鍵 返回 NONE
            counts[word] = counts.get(word, 0) + 1

    print(len(counts))
    # 3. 詞語過濾,刪除無關(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']
    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)
    counthtml=[]
    sanguo=[]
    li = []  # ['孔明'， 孔明， 孔明，孔明...., '曹操'。。。。。]
    for i in range(10):
        # 序列解包
        role, count = items[i]
        print(role, count)
        counthtml.append(count)
        sanguo.append(role)
   #5.繪圖
  plt.pie(counthtml,shadow=True, labels=sanguo, autopct = '%1.1f%%')
  plt.legend(loc=2)
  plt.axis('equal')
  plt.show()

三國演義人物餅圖