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}
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)


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

# 5得出結(jié)論

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()

紅樓夢 top1o人物分析

import jieba
from wordcloud import WordCloud
# 1.讀取小說內(nèi)容
with open('./novel/all.txt','r',encoding='utf-8') as f:
    words = f.read()
    counts = {}
    excludes =  {'什么','我們','你們','如今','說道','知道','姑娘','起來','這里','出來','眾人','那里','奶奶',
                 '自己','太太','一面','只見','兩個','沒有','怎么','不是','不知','這個','聽見','這樣','進來',
                 '咱們','就是','東西','告訴','回來','回來','只是','大家','老爺','只得','丫頭','這些','他們',
                 '不敢','出去','所以','一個','賈寶玉','王熙鳳','老太太','鳳姐兒','林黛玉','薛寶釵'}
    # 2.分詞
    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.詞語過濾重復(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['老太太'] + counts['賈母']
    counts['鳳姐'] = counts['鳳姐'] + counts['王熙鳳']+ counts['鳳姐兒']
    #刪除無關(guān)詞
    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 = []
    # 遍歷
    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='white',
            width=880,
            height=600,
            # 兩個相鄰重復(fù)詞之間的匹配
            collocations=False
        ).generate(text).to_file 
.png')