学习python的第三天

import jieba

1.读取小说内容

with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
words = f.read()

counts = {}  # {‘曹操’:234，‘回寨’:56}
excludes = {"将军", "却说", "丞相", "二人", "不可", "荆州", "不能", "如此", "商议",
            "如何", "主公", "军士", "军马", "左右", "次日", "引兵", "大喜", "天下",
            "东吴", "于是", "今日", "不敢", "魏兵", "陛下", "都督", "人马", "不知",
            "孔明曰","玄德曰","刘备","云长"}
# 2. 分词
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] = 取出字典中原来键对应的值 + 1
        # counts[word] = counts[word] + 1  # counts[word]如果没有就要报错
        # 字典。get（k） 如果字典中没有这个键 返回 NONE
        counts[word] = counts.get(word, 0) + 1

print(len(counts))
# 3. 词语过滤,删除无关词，重复词
counts['孔明'] =  counts['孔明'] +  counts['孔明曰']
counts['玄德'] = counts['玄德'] + counts['玄德曰'] +counts['刘备']
counts['关公'] = counts['关公'] +counts['云长']
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)


for i in range(10):
    # 序列解包
    role, count = items[i]
    print(role, count)

# 5得出结论

matplotlib

导入

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个点 绘制 [0 , 2π]正弦曲线图

.linspace 左闭右闭区间的等差数列

x = np.linspace(0, 2*np.pi, num=100)
print(x)
y = np.sin(x)

正弦和余弦在同一坐标系下

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('时间（s）')
plt.ylabel('电压（V）')
plt.title('欢迎来到python世界')

图例

plt.legend()
plt.show()

红楼梦 top1o人物分析

import jieba
from wordcloud import WordCloud
# 1.读取小说内容
with open('./novel/all.txt','r',encoding='utf-8') as f:
    words = f.read()
    counts = {}
    excludes =  {'什么','我们','你们','如今','说道','知道','姑娘','起来','这里','出来','众人','那里','奶奶',
                 '自己','太太','一面','只见','两个','没有','怎么','不是','不知','这个','听见','这样','进来',
                 '咱们','就是','东西','告诉','回来','回来','只是','大家','老爷','只得','丫头','这些','他们',
                 '不敢','出去','所以','一个','贾宝玉','王熙凤','老太太','凤姐儿','林黛玉','薛宝钗'}
    # 2.分词
    words_list = jieba.lcut(words)
    print(words_list)
    for word in words_list:
        if len(word) <= 1:
            continue
        else:
            counts[word] = counts.get(word, 0) + 1
    print(counts)
    # 3.词语过滤重复词
    counts['宝玉'] = counts['宝玉'] + counts['贾宝玉']
    counts['黛玉'] = counts['黛玉'] + counts['林黛玉']
    counts['宝钗'] = counts['宝钗'] + counts['薛宝钗']
    counts['贾母'] = counts['老太太'] + counts['贾母']
    counts['凤姐'] = counts['凤姐'] + counts['王熙凤']+ counts['凤姐儿']
    #删除无关词
    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)
    items.sort(key=lambda i:i[1],reverse=True)
    li = []
    # 遍历
    for i in range(10):
        # 序列解包
        role, count = items[i]
        print(role, count)
        # _ 是告诉看代码的人，循环里面不需要临时变量
        for _ in range(count):
            li.append(role)
        # 5.得出结论
        text = ' '.join(li)
        WordCloud(
            font_path='msyh.ttc',
            background_color='white',
            width=880,
            height=600,
            # 两个相邻重复词之间的匹配
            collocations=False
        ).generate(text).to_file 
.png')