[Python] Visualization of Wuhu Air Quality Index
This article is for learning reference only, if there is any mistake, please correct me!
1. Introduction
The air quality index (Air Quality Index, AQI) is simply the data that can quantitatively describe the air quality. The quality of air quality (Air Quality) reflects the degree of air pollution, which is judged according to the concentration of pollutants in the air. Air pollution is a complex phenomenon. At a specific time and place, the concentration of air pollutants is affected by many factors.
The figure below shows part of the air quality index data of Wuhu City, Anhui Province in 2020. Please use the given data to complete the following tasks.
2. Topic requirements
(1) Use the pandas library to read the air quality index statistics of Wuhu City in 2020.
(2) Draw a scatter diagram of the relationship between AQI and PM2.5.
(3) Draw a scatter diagram of air quality classification.
(4) Draw the univariate distribution map of the air quality level.
(5) Draw the linear regression fitting graph of PM2.5 and AQI.
(6) Calculate the correlation coefficient.
(7) Draw a feature correlation heat map.
3. Output result
Scatter diagram of the relationship between AQI and PM2.5
Draw air quality classification scatter diagram
Draw a univariate distribution map of air quality levels
Draw the linear regression fitting graph of PM2.5 and AQI
Calculate the correlation coefficient
Plotting Feature Correlation Heatmaps
4. Source code
# 何壮壮 20302211009
import pandas as pd
import seaborn as sn
import matplotlib.pyplot as plt
# 正常显示中文标签
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['font.family'] = 'sans-serif'
# 1、读取数据
aqi = pd.read_csv('aqi.csv', encoding='gbk')
# ['日期', 'AQI', '质量等级', 'PM2.5含量（ppm）', 'PM10含量（ppm）', 'SO2含量（ppm）',
# 'CO含量（ppm）', 'NO2含量（ppm）', 'O3_8h含量（ppm）']
# 绘制 aqi 和 pm2.5 的关系散点图
# 设置图像尺寸
plt.figure(figsize=(15, 10))
# 绘制散点图，横坐标为aqi数据的第二列，纵坐标为aqi数据的第四列
plt.scatter(aqi[aqi.columns[1]], aqi[aqi.columns[3]])
# 设置横轴标签为'AQI'，字体大小为20
plt.xlabel('AQI', fontsize=20)
# 设置纵轴标签为'PM2.5'，字体大小为20
plt.ylabel('PM2.5', fontsize=20)
# 设置图像标题为'芜湖市AQI和PM2.5的关系散点图'，字体大小为25
plt.title('芜湖市AQI和PM2.5的关系散点图', fontsize=25)
# 显示图像
plt.show()
# 绘制空气质量等级分类散点图
# 设定画布大小
plt.figure(figsize=(15, 10))
# 绘制散点图，x轴：AQI数据，y轴：空气等级数据
sn.stripplot(x=aqi[aqi.columns[2]], y=aqi[aqi.columns[1]], data=aqi, jitter=True)
# 设定x轴标签和字体大小
plt.xlabel('AQI', fontsize=20)
# 设定y轴标签和字体大小
plt.ylabel('空气等级', fontsize=20)
# 设定标题和字体大小
plt.title('芜湖市空气质量等级分类散点图', fontsize=25)
# 显示图形
plt.show()
# 绘制空气质量等级单变量分布图
# 绘制以第三列为 x 轴，数据来源为 aqi 的计数图
sn.countplot(x=aqi.columns[2], data=aqi)
# 设置标题为“空气质量等级单变量分布图”
plt.title("空气质量等级单变量分布图")
# 设置 x 轴标签为“质量等级”
plt.xlabel("质量等级")
# 设置 y 轴标签为“频数”
plt.ylabel("频数")
# 显示图像
plt.show()
# 绘制PM2.5与AQI的线性回归拟合图
# 调用seaborn库的regplot函数，将PM2.5含量（ppm）作为x轴，AQI作为y轴，数据源为aqi
sn.regplot(x='PM2.5含量（ppm）', y='AQI', data=aqi)
# 设定图表标题为 'PM2.5与AQI的线性回归拟合图'
plt.title('PM2.5与AQI的线性回归拟合图')
# 设定图表x轴标签为'PM2.5含量（ppm）'
plt.xlabel('PM2.5含量（ppm）')
# 设定图表y轴标签为'AQI'
plt.ylabel('AQI')
# 显示图表
plt.show()
# 计算相关系数
# 计算相关系数并赋值给变量 corr
corr = aqi[['AQI', 'PM2.5含量（ppm）', 'PM10含量（ppm）', 'SO2含量（ppm）', 'CO含量（ppm）', 'NO2含量（ppm）', 'O3_8h含量（ppm）']].corr()
print("AQI与其他因素的相关系数如下：\n", corr)
# 绘制特征相关性热力图
# 设置画布大小
plt.figure(figsize=(17, 14))
# 计算相关系数并赋值给变量 corr
corr = aqi[['AQI', 'PM2.5含量（ppm）', 'PM10含量（ppm）', 'SO2含量（ppm）', 'CO含量（ppm）', 'NO2含量（ppm）', 'O3_8h含量（ppm）']].corr()
# 以热图的形式展示相关性，并用蓝红色调表示，同时在每个方格中显示数值，并设置线宽为1
sn.heatmap(corr, cmap='RdBu_r', annot=True, linewidths=1)
# 设置热图的标题，并设置字体大小为25
plt.title("各污染物之间的特征相关性热力分布图", fontsize=25)
# 设置x轴标签字体大小为15
plt.xticks(fontsize=15)
# 设置y轴标签字体大小为15
plt.yticks(fontsize=15)
# 展示画布
plt.show()