三国演义Top10 人物词云绘制
import jieba
from wordcloud import WordCloud
import imageio
# 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，'回家':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词 返回none
counts[word] = counts.get(word, 0) + 1
print(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 [(),()]
# 字典转换为列表
items = list(counts.items())
print(items)
def sort_by_counts(x):
return x[1]
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)
# _告诉看代码的人，循环里面不需要使用临时变量
for _ in range(count):
li.append(role)
# 5.得出结论
text = ' '.join(li)
mask = imageio.imread('./image/china.jpg')
WordCloud(
font_path='msyh.ttc',
background_color='white',
width=800,
height=600,
mask=mask,
# 相邻两个重复值之间的匹配
collocations=False
).generate(text).to_file('TOP10.png')
词云截图
红楼梦 Top10 人物词云绘制
import jieba
from wordcloud import WordCloud
import imageio
# 读取红楼梦小说
with open('./novel/all.txt', 'r', encoding='utf-8') as f:
words = f.read()
counts = {}
excludes = {"什么", "一个", "我们", "你们", "如今", "说道", "知道", "起来", "这里",
"出来", "众人", "那里", "自己", "一面", "只见", "太太", "两个", "没有",
"怎么", "不是", "不知", "这个", "听见", "这样", "进来", "咱们", "就是",
"老太太", "东西", "告诉", "回来", "只是", "大家", "姑娘", "奶奶", "凤姐儿", "王夫人", "太太"}
# 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词 返回none
counts[word] = counts.get(word, 0) + 1
print(counts)
# 3.词语过滤，删除无关词，重复词
counts['贾母'] = counts['贾母'] + counts['老太太']
counts['黛玉'] = counts['黛玉'] + counts['林黛玉']
counts['宝玉'] = counts['宝玉'] + counts['贾宝玉']
counts['宝钗'] = counts['宝钗'] + counts['薛宝钗']
counts['贾政'] = counts['老爷'] + counts['贾政']
counts['王熙凤'] = counts['凤姐儿'] + counts['凤姐'] + counts['王熙凤']
for word in excludes:
del counts[word]
# 4.排序 [(),()]
# 字典转换为列表
items = list(counts.items())
print(items)
items.sort(key=lambda x:x[1], reverse=True)
print(items)
li = []
for i in range(10):
# 序列解包
role, count = items[i]
print(role, count)
# _告诉看代码的人，循环里面不需要使用临时变量
for _ in range(count):
li.append(role)
# 5.得出结论
text = ' '.join(li)
mask = imageio.imread('./image/china.jpg')
WordCloud(
font_path='msyh.ttc',
background_color='white',
width=800,
height=600,
mask=mask,
# 相邻两个重复值之间的匹配
collocations=False
).generate(text).to_file('TOP10.png')
词云截图
匿名函数
- 结构： lambda x1, x2, x3, ....., xn: 表达式
sum_num = lambda x1, x2: x1+x2
print(sum_num(2, 3))
# 参数可以是无限多个，但是表达式只有一个
- 实例
name_info_list = [
("张三",5465),
("李四",6545),
("王五",5674),
("赵六",9676),
]
name_info_list.sort(key=lambda x:x[1], reverse=True)
print(name_info_list)
str_info = [
{"name":"zhangsan","age":18},
{"name":"lisi","age":32},
{"name":"wangwu","age":2},
{"name":"zhaoliu","age":45},
]
str_info.sort(key=lambda x:x['age'], reverse=True)
print(str_info)
列表推导式: 列表解析与字典解析
- 普通for循环创建列表
li = []
for i in range(10):
li.append(i)
print(li)
- 列表推导式创建列表
# [表达式 for 临时变量 in 可迭代对象 可以增加条件]
print([i for i in range(10)])
- 列表解析—筛选出列表中所有的偶数
# 普通方法
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])
- 随机生成，筛选出列表中大于0的数
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个学生的成绩
str_grades = {'student{}'.format(i):randint(50,100) for i in range(1,101)}
print(str_grades)
# 筛选大于60分的所有学生
print({k : v for k, v in str_grades.items() if v > 60})
matplotlib
- 导入
from matplotlib import pyplot as plt
import numpy as np
- 解决中文乱码
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
- 使用100个点 绘制{0 , 2pi}正弦、余弦曲线图
# .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)
plt.plot(x, y, color='g', linestyle='--',label='sinx')
# 正弦和余弦在同一坐标系下
cosy = np.cos(x)
plt.plot(x, cosy, color='r',label='cosx')
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()
正弦、余弦曲线图
- 柱状图
import string
from random import randint
# print(string.ascii_uppercase[0:6])
# ['A','B','C',.....]
x = ['口红{}'.format(x) for x in string.ascii_uppercase[0:5]]
y = [randint(200, 500) for _ in range(5)]
print(x)
print(y)
plt.xlabel("口红价格")
plt.ylabel('价格（元）')
plt.bar(x, y)
plt.show()
柱状图
- 饼图
from random import randint
counts = [randint(3500, 9000) for _ in range(6)]
labels = ['员工{}'.format(x) for x in string.ascii_uppercase[0:6]]
# 距离圆心点距离
explode = [0.1,0,0,0,0,0]
colors = ['red','purple','blue','yellow','gray','green']
plt.pie(counts, explode=explode, labels = labels, shadow=True, autopct='%1.1f%%', colors=colors)
plt.legend(loc = 2)
# plt.axis('equal')
plt.show()
饼图
- 散点图
# 均值为0 标准差为1 的正太分布数据
x = np.random.normal(0, 1, 100000)
y = np.random.normal(0, 1, 100000)
# alpha透明度
plt.scatter(x, y, alpha=0.1)
plt.show()
散点图
绘制三国Top10人物饼图
import jieba
from wordcloud import WordCloud
with open('./novel/threekingdom.txt','r',encoding='utf-8') as f:
words = f.read()
counts = {} # {'曹操'：234，'回家':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词 返回none
counts[word] = counts.get(word, 0) + 1
# 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 [(),()]
# 字典转换为列表
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)
names = []
number = []
for i in range(10):
# 序列解包
role, count = items[i]
names.append(role)
number.append(count)
# 5.得出结论
# 距离圆心点距离
explode = [0.1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
plt.pie(number, explode=explode, labels=names, shadow=True, autopct='%1.1f%%')
plt.axis('equal')
plt.legend(loc=2)
plt.show()
三国Top10人物饼图