三國人物top10分析
讀取小說內(nèi)容
with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
words = f.read()
分詞
words_list = jieba.lcut(words)
每個詞出現(xiàn)的次數(shù)
for word in words_list:
if len(word) <= 1: #如果詞的長度小于等于1不計入計算
continue
else:
counts[word] = counts.get(word, 0) + 1 #詞計數(shù)器,每次出現(xiàn),該詞+1
Python 字典(Dictionary) get() 函數(shù)返回指定鍵的值,如果值不在字典中返回默認(rèn)值。
詞語過濾,刪除無關(guān)詞,重復(fù)詞
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"}
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]
從counts中刪掉與excludes中相同的詞
匿名函數(shù)
結(jié)構(gòu)
lambda x1,x2,....xn:表達(dá)式
sum_num = lambda x1,x2:x1+x2
print(sum_num(2,3))
注意 參數(shù)可以是無限多個,但是表達(dá)式只有一個
實例
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)
使用列表推導(dǎo)式
[表達(dá)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)])
實例
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
from random import randint
stu_grades = {
'student{}'.format(i):randint(50,100) for i in range(1,101)
}
print(stu_grades)
#篩選出大于60分的學(xué)生
print({k:v for k,v in stu_grades() if v > 60})
圖形
正弦、余弦曲線圖
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import numpy as np
x = np.linspace(0,2*np.pi,num=100)
print(x)
y = np.sin(x)
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('hello Python')
plt.legend()
plt.show()
柱狀圖
import string
from random import randint
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()
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_uppercase[:6]]
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()