图形绘制
1.正弦余弦图
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, 2∏]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的世界')
image.png
2.柱状图
# 导入
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import numpy as np
# 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[:5]]
y = [randint(200, 500) for _ in range(5)]
print(x)
print(y)
plt.xlabel('口红品牌')
plt.ylabel('价格(元)')
plt.bar(x,y)
plt.show()
image.png
3.饼状图
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import numpy as np
# # 饼图
from random import randint
import string
counts = [randint(3500,9000) for _ in range(6)]
labels = ['员工{}'.format(x) for x in string.ascii_lowercase[: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,shadow=True,labels=labels,autopct='%1.1f%%',colors=colors)
plt.legend(loc=2)
plt.axis('equal')
plt.show()
image.png
4.散点图
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import numpy as np
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()
image.png
小作业
1.三国top10人物分析饼状图
import jieba
from wordcloud import WordCloud
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import string
# 1.读取小说
with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
words = f.read()
counts = {}
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] = counts[word] + 1
# 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['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)
items.sort(key=lambda x: x[1], reverse=True)
li = [] # ['孔明',...'曹操',...]
count1 = []
count2 = []
for i in range(10):
# 序列解包
role, count = items[i]
print(role, count)
count1.append(role)
count2.append(count)
# _是告诉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)
WordCloud(
font_path='msyh.ttc',
background_color='white',
width=800,
height=600,
# 相邻两个重复词之间的匹配
collocations=False
).generate(text).to_file('./TOP10.png')
# 6.绘制三国TOP10饼图
plt.pie(count2, shadow=True, labels=count1, autopct='%1.lf%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()
image.png
2.红楼梦top10人物分析
import jieba
with open("./novel/all.txt",'r',encoding='utf-8') as f:
words = f.read()
count = {}
words_list = jieba.lcut(words) #精确分词
for i in words_list:
if len(i) <= 1:
continue
else:
count[i] = count.get(i, 0)+1
print(count)
excludes = {'什么', '一个', '我们', '你们', '如今', '说道', '老太太', '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', '袭人', '回来', '就是', '只是', '大家', '老爷', '只得', '丫头',
'这些', '他们', '不敢', '出去', '所以', '不过', '不好', '姐姐', '探春', '一时', '的话', '鸳鸯','凤姐'
,'过来','不能','心里','她们','如此','今日','二人','答应','几个','这么','还有','只管','说话'}
count['凤姐儿'] = count['凤姐儿'] = count['凤姐']
for i in excludes:
del count[i] # 删除不是人名的高频词汇
items = list(count.items()) #将字典转换为列表
items.sort(key=lambda x: x[1], reverse=True) #使用匿名函数从大到小排序
# print(items)
li = []
lii = [] # 装人物
lli = [] # 装人物出现的次数
for i in range(10):
role, count = items[i] #序列解包
lli.append(count)
lii.append(role)
for _ in range(count):
li.append(role) # 在li里循环写入 count个 role(人名)
text = ' '.join(li) #将li转换为字符串
from wordcloud import WordCloud
import imageio
mask = imageio.imread('./image/china.jpg')
WordCloud(
font_path='msyh.ttc',
background_color='black',
width=800,
height=600,
collocations=False, #相邻两个重复词之间的匹配
mask=mask
).generate(text).to_file('红楼梦.png')
image.png