Python爬虫课程设计

import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns # 解决中文乱码问题 plt.rcParams["font.sans-serif"] = ["SimHei"] # 设置字体 plt.rcParams["axes.unicode_minus"] = False # 该语句解决图像中的“-”负号的乱码问题 # AQI指数数据处理 def aqi(data1,data2,data3): # 全部AQI数据 aqi_data1 = data1['AQI'] describe1 = aqi_data1.describe() writer1 = pd.ExcelWriter('aqi.xlsx') describe1.to_excel(writer1, 'Sheet1') writer1.save() # 柱状图 fig1 = plt.figure() ax1 = fig1.add_subplot(1, 1, 1) ax1.hist(aqi_data1, bins=50) ax1.set_xlabel('AQI指数') ax1.set_ylabel('频率') ax1.set_title('AQI指数柱状图') # 散点图 fig1_1 = plt.figure() ax1_1 = fig1_1.add_subplot(1, 1, 1) ax1_1.scatter(aqi_data1,aqi_data1) ax1_1.set_xlabel('AQI指数') ax1_1.set_ylabel('AQI指数') ax1_1.set_title('AQI指数散点图') # 密度图 fig1_2 = plt.figure() ax1_2 = fig1_2.add_subplot(1, 1, 1) aqi_data1.plot.density() ax1_2.set_xlabel('AQI指数') ax1_2.set_title('AQI指数密度图') # # 空气质量优AQI数据 aqi_data2 = data2['AQI'] describe2 = aqi_data2.describe() writer2 = pd.ExcelWriter('aqi(优).xlsx') describe2.to_excel(writer2, 'Sheet1') writer2.save() # 柱状图 fig2 = plt.figure() ax2 = fig2.add_subplot(1, 1, 1) ax2.hist(aqi_data2, bins=50) ax2.set_xlabel('AQI指数') ax2.set_ylabel('频率') ax2.set_title('AQI指数柱状图（优）') # #散点图 fig2_1 = plt.figure() ax2_1 = fig2_1.add_subplot(1, 1, 1) ax2_1.scatter(aqi_data2,aqi_data2) ax2_1.set_xlabel('AQI指数(优)') ax2_1.set_ylabel('AQI指数(优)') ax2_1.set_title('AQI指数散点图(优)') # 密度图 fig2_2 = plt.figure() ax2_2 = fig2_2.add_subplot(1, 1, 1) aqi_data2.plot.density() ax2_2.set_xlabel('AQI指数(优)') ax2_2.set_title('AQI指数密度图(优)') # # 空气质量非优AQI数据 aqi_data3 = data3['AQI'] describe3 = aqi_data3.describe() writer3 = pd.ExcelWriter('aqi(良).xlsx') describe3.to_excel(writer3, 'Sheet1') writer3.save() # 柱状图 fig3 = plt.figure() ax3 = fig3.add_subplot(1, 1, 1) ax3.hist(aqi_data3, bins=50) ax3.set_xlabel('AQI指数') ax3.set_ylabel('频率') ax3.set_title('AQI指数柱状图（良）') # # 散点图 fig3_1 = plt.figure() ax3_1 = fig3_1.add_subplot(1, 1, 1) ax3_1.scatter(aqi_data3,aqi_data3) ax3_1.set_xlabel('AQI指数(良)') ax3_1.set_ylabel('AQI指数(良)') ax3_1.set_title('AQI指数散点图(良)') # 密度图 fig3_2 = plt.figure() ax3_2 = fig3_2.add_subplot(1, 1, 1) aqi_data3.plot.density() ax3_2.set_xlabel('AQI指数(良)') ax3_2.set_title('AQI指数密度图(良)') plt.show() if __name__ == '__main__': # 数据源文件路径 xlsx = pd.ExcelFile('d:/xvb/data.xlsx') # 读取数据 excel = pd.read_excel(xlsx, 'Sheet1') # 获取所有数值数据 data1 = excel.drop(['城市', '首要污染物', '空气质量'], axis=1) # 获取空气质量为优的数据 you=excel[excel['首要污染物']=='—'] # 获取数值数据 data2=you.drop(['城市', '首要污染物', '空气质量'], axis=1) #获取空气质量非优的数据 liang = excel[excel['首要污染物'] != '—'] # 获取数值数据 data3 = liang.drop(['城市', '首要污染物', '空气质量'], axis=1) aqi(data1,data2,data3)