数据可视化
对应教学日历：讲次 13
一、Matplotlib 基础
import matplotlib.pyplot as plt常用函数
| 函数 | 作用 |
|---|---|
plt.figure(figsize=(w, h)) | 创建绘图对象 |
plt.plot(x, y, s) | 绘制折线图 |
plt.bar(x, y) | 绘制垂直条形图 |
plt.barh(x, y) | 绘制水平条形图 |
plt.pie(x) | 绘制饼图 |
plt.scatter(x, y) | 绘制散点图 |
plt.subplot(nrows, ncols, index) | 绘制子图 |
plt.show() | 显示图形 |
plt.title() | 添加标题 |
plt.xlabel() / plt.ylabel() | 添加轴名称 |
plt.xlim() / plt.ylim() | 设置轴范围 |
plt.xticks() / plt.yticks() | 设置刻度 |
plt.legend() | 显示图例 |
中文显示
plt.rcParams['font.sans-serif'] = ['SimHei'] # 显示中文
plt.rcParams['axes.unicode_minus'] = False # 显示负号plot() 参数
- 颜色：
'r'红、'g'绿、'b'蓝、'y'黄 - 线型：
'-'实线、'--'虚线、':'点线 - 标记：
'o'圆圈、's'方块、'^'三角形
plt.plot(x, y, 'r', label='cos(x)+1') # 红色实线
plt.plot(x, z, 'b--', label='sin(x^2)+1') # 蓝色虚线二、折线图
import matplotlib.pyplot as plt
import numpy as np
x = np.arange(0, 1, 0.01)
y = x ** 2
plt.plot(x, y, 'b')
plt.plot(x, x ** 3)
plt.title('math example')
plt.xlim(0, 1)
plt.ylim(0, 1)
plt.ylabel('Y')
plt.legend(['y=x^2', 'y=x^3'])
plt.show()三、条形图
import matplotlib.pyplot as plt
name = ["张三", "李四", "王五"]
score = [85, 95, 75]
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.bar(name, score) # 垂直条形图
plt.show()
plt.barh(name, score) # 水平条形图
plt.show()四、饼图
import matplotlib.pyplot as plt
labels = ['吃饭', '日用品', '学习用具', '其它']
sizes = [1200, 300, 200, 500]
explodes = (0, 0, 0, 0.2) # 第4块突出
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.pie(sizes, explode=explodes, labels=labels,
autopct='%.1f%%', shadow=True)
plt.title("4月份个人消费分析")
plt.show()五、散点图
import matplotlib.pyplot as plt
name = ["张三", "李四", "王五"]
score = [85, 95, 75]
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.scatter(name, score)
plt.show()六、子图
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
p1 = plt.subplot(121) # 1行2列第1个
p2 = plt.subplot(122) # 1行2列第2个
sizes1 = [1200, 300, 200, 500]
sizes2 = [1100, 400, 300, 800]
p1.pie(sizes1)
p2.pie(sizes2)
plt.suptitle("3、4月份个人消费分析")
plt.show()七、NumPy 基础
import numpy as np
a = np.arange(0, 10, 0.1) # [0, 10)，步长0.1
b = np.linspace(0, 10, 100) # [0, 10]，分成100份常用函数
np.sin(x) # 正弦
np.cos(x) # 余弦
np.sqrt(x) # 平方根
np.pi # 圆周率
np.exp(x) # 指数作业示例
正态分布密度函数
import matplotlib.pyplot as plt
from numpy import *
plt.figure(figsize=(4, 3))
x = linspace(-5, 5, 100)
y = (1 / (sqrt(2 * pi))) * exp(-(x * x) / 2)
plt.plot(x, y, '-b')
plt.show()参数方程绘图
from numpy import *
import matplotlib.pyplot as plt
plt.figure(figsize=(6, 6))
plt.plot([-3, 3], [0, 0], "r")
plt.plot([0, 0], [-3, 3], "r")
t = arange(0, 2 * pi, 0.01)
x = -2 * sin(2 * t) + sin(t)
y = -2 * cos(2 * t) + cos(t)
plt.plot(x, y, 'b')
plt.show()坐标轴+函数曲线
import matplotlib.pyplot as plt
from numpy import *
plt.figure(figsize=(6, 6))
wh = hh = 6 / 2
plt.plot([-3, 3], [0, 0], c='r')
plt.plot([0, 0], [-3, 3], c='r')
t = linspace(0, 4 * pi, 100)
x = (wh / 4) * (sin(2 * t) + 2 * cos(t))
y = (hh / 4) * (cos(2 * t) + 2 * sin(t))
plt.plot(x, y, c='b')
plt.show()词云生成
import matplotlib.pyplot as plt
from wordcloud import WordCloud
from imageio.v2 import imread
import jieba
with open("二十大报告.txt", "r", encoding="utf-8") as fobj:
txt = fobj.read()
words = jieba.lcut(txt)
pic = imread('cloud.jpg')
counts = {}
excludes = set()
with open("中文停用词.txt", "r", encoding="utf-8") as fobj:
for i in fobj:
i = i.strip()
excludes.add(i)
for word in words:
if len(word) == 1:
continue
elif word in excludes:
continue
else:
counts[word] = counts.get(word, 0) + 1
wc = WordCloud(mask=pic, font_path='msyh.ttc',
repeat=False, background_color='white',
max_words=110, max_font_size=120,
min_font_size=10, random_state=50, scale=10)
wc.generate_from_frequencies(counts)
plt.imshow(wc)
plt.show()作业重点
plt.rcParams['font.sans-serif']=['SimHei']显示中文plot(x, y, 'r')绘制红色折线图bar()条形图、pie()饼图、scatter()散点图subplot(行,列,位置)绘制子图- NumPy：
arange()生成等差序列，linspace()等分区间 - 词云：
jieba.lcut()分词 → 字典统计 →WordCloud生成 - 停用词过滤：
excludes集合，len(word)==1过滤单字