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（中）

目录

1.上海市的空气质量

2.成都市的空气质量

【沈阳市空气质量情况详见下期】

---

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

1.上海市的空气质量

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pywaffle import Waffle
import math
#读入文件
sh = pd.read_csv('./Shanghai.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(sh,str3):
    sh_dist_pm = sh.loc[:, [str3]]
    sh_dist1_pm = sh_dist_pm.dropna(axis=0, subset=[str3])
    sh_dist1_pm = np.array(sh_dist1_pm[str3])
    sh_good_count = len(good(sh_dist1_pm))
    sh_moderate_count = len(moderate(sh_dist1_pm))
    sh_lightlyP_count = len(lightlyP(sh_dist1_pm))
    sh_moderatelyP_count = len(moderatelyP(sh_dist1_pm))
    sh_heavilyP_count = len(heavilyP(sh_dist1_pm))
    sh_severelyP_count = len(severelyP(sh_dist1_pm))
    a = {'优':sh_good_count,'良':sh_moderate_count,'轻度污染':sh_lightlyP_count,'中度污染':sh_moderatelyP_count,'重度污染':sh_heavilyP_count,'严重污染':sh_severelyP_count}
    pm = pd.DataFrame(pd.Series(a),columns=['daysum'])
    pm = pm.reset_index().rename(columns={'index':'level'})
    return pm
#上海
#PM_Jingan列
sh_jg = PM(sh,'PM_Jingan')
PMday_Jingan = np.array(sh_jg['daysum'])
#PM_Xuhui列
sh_xh = PM(sh,'PM_Xuhui')
PMday_Xuhui = np.array(sh_xh['daysum'])
sh_pm_daysum = (PMday_Jingan+PMday_Xuhui)/2
sum = 0
for i in sh_pm_daysum:
    sum += i
sh_pm_daysum1 = np.array(sh_pm_daysum)

data = {'优':int((sh_pm_daysum[0]/sum)*100), '良':int((sh_pm_daysum[1]/sum)*100), '轻度污染': int(sh_pm_daysum[2]/sum*100),'中度污染':int((sh_pm_daysum[3]/sum)*100),'重度污染':int((sh_pm_daysum[4]/sum)*100),'严重污染':int((sh_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': "上海市污染情况",
        '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()

上海市总体空气质量良好，优和良的空气质量占比超过70%，只有不到1%的严重污染，中度污染和重度污染占比总和不超过10%。

2.成都市的空气质量

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pywaffle import Waffle

#读入文件
cd = pd.read_csv('./Chengdu.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(cd,str3):
    cd_dist_pm = cd.loc[:, [str3]]
    cd_dist1_pm = cd_dist_pm.dropna(axis=0, subset=[str3])
    cd_dist1_pm = np.array(cd_dist1_pm[str3])
    cd_good_count = len(good(cd_dist1_pm))
    cd_moderate_count = len(moderate(cd_dist1_pm))
    cd_lightlyP_count = len(lightlyP(cd_dist1_pm))
    cd_moderatelyP_count = len(moderatelyP(cd_dist1_pm))
    cd_heavilyP_count = len(heavilyP(cd_dist1_pm))
    cd_severelyP_count = len(severelyP(cd_dist1_pm))
    a = {'优':cd_good_count,'良':cd_moderate_count,'轻度污染':cd_lightlyP_count,'中度污染':cd_moderatelyP_count,'重度污染':cd_heavilyP_count,'严重污染':cd_severelyP_count}
    pm = pd.DataFrame(pd.Series(a),columns=['daysum'])
    pm = pm.reset_index().rename(columns={'index':'level'})
    return pm
#成都
#PM_Caotangsi列
cd_cts = PM(cd,'PM_Caotangsi')
PMday_Caotangsi = np.array(cd_cts['daysum'])
#PM_Shahepu列
cd_shp = PM(cd,'PM_Shahepu')
PMday_Shahepu = np.array(cd_shp['daysum'])
cd_pm_daysum = (PMday_Shahepu+PMday_Caotangsi)/2
sum = 0
for i in cd_pm_daysum:
    sum += i
cd_pm_daysum1 = np.array(cd_pm_daysum)

data = {'优':int((cd_pm_daysum[0]/sum)*100), '良':int((cd_pm_daysum[1]/sum)*100), '轻度污染': int(cd_pm_daysum[2]/sum*100),'中度污染':int((cd_pm_daysum[3]/sum)*100),'重度污染':int((cd_pm_daysum[4]/sum)*100),'严重污染':int((cd_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': "成都市污染情况",
        '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()

成都市总体空气质量较差，空气污染程度占比约35%——其中轻度污染占比约17%，中度污染占比约8%，重度污染占比约8%，严重污染占比约2%。

【沈阳市空气质量情况详见下期】