Python||五城P.M.2.5数据分析与可视化_使用华夫图分析各个城市的情况（下）

目录

沈阳市的空气质量

华夫图

柱状图

总结

---

五城P.M.2.5数据分析与可视化——北京市、上海市、广州市、沈阳市、成都市，使用华夫图和柱状图分析各个城市的情况

沈阳市的空气质量

华夫图

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pywaffle import Waffle
#读入文件
sy = pd.read_csv('./Shenyang.csv')
fig = plt.figure(dpi=100,figsize=(5,5))

def good(pm):
    #优
    degree = []
    for i in pm:
        if 0 < i <= 35:
            degree.append(i)
    return degree
def moderate(pm):
    #良
    degree = []
    for i in pm:
        if 35 < i <= 75:
            degree.append(i)
    return degree
def lightlyP(pm):
    #轻度污染
    degree = []
    for i in pm:
        if 75 < i <= 115:
            degree.append(i)
    return degree
def moderatelyP(pm):
    #中度污染
    degree = []
    for i in pm:
        if 115 < i <= 150:
            degree.append(i)
    return degree
def heavilyP(pm):
    #重度污染
    degree = []
    for i in pm:
        if 150 < i <= 250:
            degree.append(i)
    return degree
def severelyP(pm):
    #严重污染
    degree = []
    for i in pm:
        if 250 < i:
            degree.append(i)
    return degree

def PM(sy,str3):
    sy_dist_pm = sy.loc[:, [str3]]
    sy_dist1_pm = sy_dist_pm.dropna(axis=0, subset=[str3])
    sy_dist1_pm = np.array(sy_dist1_pm[str3])
    sy_good_count = len(good(sy_dist1_pm))
    sy_moderate_count = len(moderate(sy_dist1_pm))
    sy_lightlyP_count = len(lightlyP(sy_dist1_pm))
    sy_moderatelyP_count = len(moderatelyP(sy_dist1_pm))
    sy_heavilyP_count = len(heavilyP(sy_dist1_pm))
    sy_severelyP_count = len(severelyP(sy_dist1_pm))
    a = {'优':sy_good_count,'良':sy_moderate_count,'轻度污染':sy_lightlyP_count,'中度污染':sy_moderatelyP_count,'重度污染':sy_heavilyP_count,'严重污染':sy_severelyP_count}
    pm = pd.DataFrame(pd.Series(a),columns=['daysum'])
    pm = pm.reset_index().rename(columns={'index':'level'})
    return pm
#沈阳
#PM_Taiyuanjie列
sy_tyj = PM(sy,'PM_Taiyuanjie')
PMday_Taiyuanjie = np.array(sy_tyj['daysum'])
#PM_Xiaoheyan列
sy_xhy = PM(sy,'PM_Xiaoheyan')
PMday_Xiaoheyan = np.array(sy_xhy['daysum'])
sy_pm_daysum = (PMday_Xiaoheyan+PMday_Taiyuanjie)/2
sum = 0
for i in sy_pm_daysum:
    sum += i
sy_pm_daysum1 = np.array(sy_pm_daysum)
data = {'优':int((sy_pm_daysum[0]/sum)*100), '良':int((sy_pm_daysum[1]/sum)*100), '轻度污染': int(sy_pm_daysum[2]/sum*100),'中度污染':int((sy_pm_daysum[3]/sum)*100),'重度污染':int((sy_pm_daysum[4]/sum)*100),'严重污染':int((sy_pm_daysum[5]/sum)*100)}
total = np.sum(list(data.values()))
plt.figure(
    FigureClass=Waffle,
    rows = 5,   # 列数自动调整
    values = data,
    # 设置title
    title = {
        'label': "沈阳市污染情况",
        'loc': 'center',
        'fontdict':{
            'fontsize': 13,
        }
    },
    labels = ['{} {:.1f}%'.format(k, (v/total*100)) for k, v in data.items()],
    # 设置标签图例的样式
    legend = {
        'loc': 'lower left',
        'bbox_to_anchor': (0, -0.4),
        'ncol': len(data),
        'framealpha': 0,
        'fontsize': 6
    },
    dpi=120
)
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']
plt.show()

柱状图

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

#读入文件
sy = pd.read_csv('./Shenyang.csv')
fig = plt.figure(dpi=100,figsize=(5,5))

def good(pm):
    #优
    degree = []
    for i in pm:
        if 0 < i <= 35:
            degree.append(i)
    return degree
def moderate(pm):
    #良
    degree = []
    for i in pm:
        if 35 < i <= 75:
            degree.append(i)
    return degree
def lightlyP(pm):
    #轻度污染
    degree = []
    for i in pm:
        if 75 < i <= 115:
            degree.append(i)
    return degree
def moderatelyP(pm):
    #中度污染
    degree = []
    for i in pm:
        if 115 < i <= 150:
            degree.append(i)
    return degree
def heavilyP(pm):
    #重度污染
    degree = []
    for i in pm:
        if 150 < i <= 250:
            degree.append(i)
    return degree
def severelyP(pm):
    #严重污染
    degree = []
    for i in pm:
        if 250 < i:
            degree.append(i)
    return degree

def PM(sy,str3):
    sy_dist_pm = sy.loc[:, [str3]]
    sy_dist1_pm = sy_dist_pm.dropna(axis=0, subset=[str3])
    sy_dist1_pm = np.array(sy_dist1_pm[str3])
    sy_good_count = len(good(sy_dist1_pm))
    sy_moderate_count = len(moderate(sy_dist1_pm))
    sy_lightlyP_count = len(lightlyP(sy_dist1_pm))
    sy_moderatelyP_count = len(moderatelyP(sy_dist1_pm))
    sy_heavilyP_count = len(heavilyP(sy_dist1_pm))
    sy_severelyP_count = len(severelyP(sy_dist1_pm))
    a = {'优':sy_good_count,'良':sy_moderate_count,'轻度污染':sy_lightlyP_count,'中度污染':sy_moderatelyP_count,'重度污染':sy_heavilyP_count,'严重污染':sy_severelyP_count}
    pm = pd.DataFrame(pd.Series(a),columns=['daysum'])
    pm = pm.reset_index().rename(columns={'index':'level'})
    return pm
#沈阳
#PM_Taiyuanjie列
sy_tyj = PM(sy,'PM_Taiyuanjie')
PMday_Taiyuanjie = np.array(sy_tyj['daysum'])
#PM_Xiaoheyan列
sy_xhy = PM(sy,'PM_Xiaoheyan')
PMday_Xiaoheyan = np.array(sy_xhy['daysum'])
sy_pm_daysum = (PMday_Xiaoheyan+PMday_Taiyuanjie)/2
sum = 0
for i in sy_pm_daysum:
    sum += i
sy_pm_daysum1 = np.array(sy_pm_daysum)
#图像
bar_width = 0.1
plt.bar(0.2,sy_pm_daysum[0]/sum,width=bar_width,color='aqua',label='优')
plt.bar(0.4,sy_pm_daysum[1]/sum,width=bar_width,color='deepskyblue',label='良')
plt.bar(0.6,sy_pm_daysum[2]/sum,width=bar_width,color='cornflowerblue',label='轻度污染')
plt.bar(0.8,sy_pm_daysum[3]/sum,width=bar_width,color='skyblue',label='中度污染')
plt.bar(1,sy_pm_daysum[4]/sum,width=bar_width,color='lightsteelblue',label='重度污染')
plt.bar(1.2,sy_pm_daysum[5]/sum,width=bar_width,color='silver',label='严重污染')
x = [0.2,0.4,0.6,0.8,1,1.2]
for a,b in zip(x,sy_pm_daysum):
    plt.text(a, (b/sum) + 0.02,'%.1f'%(b/sum*100)+'%', ha='center', va='bottom', fontsize=10)
plt.xticks([0.2,0.4,0.6,0.8,1,1.2])
plt.xlabel(['优','良','轻度污染','中度污染','重度污染','严重污染'])
plt.yticks([0.2,0.4,0.6,0.8,1])
plt.ylabel(['20%','40%','60%','80%','100%'])
plt.ylabel(u'百分比',fontsize=12,rotation='horizontal',verticalalignment='top',horizontalalignment='left', x=2,y=1.1)
plt.xlabel(u'污染程度',fontsize=12,verticalalignment='top',horizontalalignment='left',x=0.9, y=1.2)
plt.legend()
fig.suptitle('沈阳市污染情况',fontsize=15,x=0.5,y=1)
plt.grid(alpha=0.4)
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']
plt.show()

沈阳市总体空气质量较差，空气污染程度占比超过35%——其中轻度污染占比约16%，中度污染占比约7%，重度污染占比约8%，严重污染占比约3%。

总结

总体来讲，广州市的空气质量最好，上海次之；北京市的空气质量最差，严重污染占比远远超过其他四座城市。