数据可视化（pyecharts 1.7.1）学习笔记——系列笔记（9）

九、空间数据可视化

1、地理坐标系-Geo

1）地理坐标系-散点图

2、地理坐标系-Geolines

3、实际案例

1）各省份城市空气质量

2）北京起飞航班的航线

4、空间数据可视化实验

实验环境

• pyecharts=1.7.2

各城市最低气温可视化

All_Data = []
ua = UserAgent(use_cache_server=False)
# 网页的解析函数
def parse_page(url):
    headers = {
        'User-Agent': ua.random
    }
    response = requests.get(url, headers=headers)
    text = response.content.decode('utf-8')
    soup = BeautifulSoup(text, 'lxml')
    conMidtab = soup.find('div', {'class': 'conMidtab'})
    tables = conMidtab.find_all('table')
#     查看是否拿到了每个城市的天气
    for table in tables:
        trs = table.find_all('tr')[2:]
        for index, tr in enumerate(trs):
            tds = tr.find_all('td')
            if len(tds) >= 8:
                city_td = tds[0]
                if index == 0:
                    city_td = tds[1]
    #             获取标签里面的字符串属性返回一个生成器，因此要转化为一个列表
                city = city_td.get_text()
                temp_td = tds[-2]
                min_temp = temp_td.get_text()
    #             将数据添加到列表
                All_Data.append({'城市': city, '最低气温': int(min_temp)})
def main():
    urls = [
        'http://www.weather.com.cn/textFC/hb.shtml',
        'http://www.weather.com.cn/textFC/db.shtml',
        'http://www.weather.com.cn/textFC/hz.shtml',
        'http://www.weather.com.cn/textFC/hn.shtml',
        'http://www.weather.com.cn/textFC/hd.shtml',
        'http://www.weather.com.cn/textFC/xb.shtml',
        'http://www.weather.com.cn/textFC/xn.shtml',
        'http://www.weather.com.cn/textFC/gat.shtml'
    ]
    for url in urls:
        parse_page(url)
    # 分析数据，根据最低气温进行排序
    All_Data.sort(key=lambda data: data['最低气温'])
    data = All_Data[0:10]  # 取出前10的最低气温及其城市
    return data
if __name__ == '__main__':
    datas = main()
    city = []
    temp = []
    plt.figure(figsize=(15, 9.27))
    plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
    plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
    for data in datas:
        city.append(data['城市'])
        temp.append(data['最低气温'])
    plt.bar(range(len(city)), temp, tick_label=city)
    plt.show()

import pandas as pd

def main():
    aqi_data = pd.read_csv('data/china_city_AQI.csv')
    print('基本信息：')
    print(aqi_data.info())

    print('数据预览：')
    print(aqi_data.head())

    # 基本统计
    print('AQI最大值:', aqi_data['AQI'].max())
    print('AQI最小值：', aqi_data['AQI'].min())
    print('AQI均值：', aqi_data['AQI'].mean())

    # top10
    top10_cities = aqi_data.sort_values(by=['AQI']).head(10)
    print('空气质量最好的10个城市：')
    print(top10_cities)

    # bottom10
    # bottom10_cities = aqi_data.sort_values(by=['AQI']).tail(10)
    bottom10_cities = aqi_data.sort_values(by=['AQI'], ascending=False).head(10)
    print('空气质量最差的10个城市：')
    print(bottom10_cities)

    # 保存csv文件
    top10_cities.to_csv('data/top10_aqi.csv', index=False)
    bottom10_cities.to_csv('data/bottom10_aqi.csv', index=False)


if __name__ == '__main__':
    main()

def main():
    aqi_data = pd.read_csv('data/china_city_AQI.csv')
    print('基本信息：')
    print(aqi_data.info())

    print('数据预览：')
    print(aqi_data.head())

    # 数据清洗
    # 只保留AQI>0的数据
    # filter_condition = aqi_data['AQI'] > 0
    # clean_aqi_data = aqi_data[filter_condition]

    clean_aqi_data = aqi_data[aqi_data['AQI'] > 0]

    # 基本统计
    print('AQI最大值:', clean_aqi_data['AQI'].max())
    print('AQI最小值：', clean_aqi_data['AQI'].min())
    print('AQI均值：', clean_aqi_data['AQI'].mean())

    # top50
    top50_cities = clean_aqi_data.sort_values(by=['AQI']).head(50)
    print(top50_cities)
    top50_cities.plot(kind='bar', x='City', y='AQI', title='空气质量最好的50个城市',
                      figsize=(20, 10))
    plt.figure(figsize=(15, 9.27))
    plt.savefig('data/top50_aqi_bar.png')
    plt.show()


if __name__ == '__main__':
    main()

from pyecharts.globals import CurrentConfig, NotebookType
CurrentConfig.NOTEBOOK_TYPE = NotebookType.JUPYTER_LAB
from pyecharts.globals import ThemeType
from pyecharts.charts import Bar
import pyecharts.options as opts

aqi_data = pd.read_csv('data/china_city_AQI.csv')
print('基本信息: ')
print(aqi_data.info())

print('数据预览: ')
print(aqi_data.head())

#     数据清洗
#     只保留AQI>0的数据
clean_aqi_data = aqi_data[aqi_data['AQI']  > 0]

#     基本统计
print('AQI最大值：{}'.format(clean_aqi_data['AQI'].max()))
print('AQI最小值：{}'.format(clean_aqi_data['AQI'].min()))
print('AQI均值：{}'.format(clean_aqi_data['AQI'].mean()))

top50_cities = clean_aqi_data.sort_values(by=['AQI']).head(50)
bar = (
    Bar(init_opts=opts.InitOpts(theme=ThemeType.DARK))
    .add_xaxis(top50_cities['City'].tolist())
    .add_yaxis('', top50_cities['AQI'].tolist(), label_opts=opts.LabelOpts(is_show=False), category_gap='50%')
    .set_global_opts(title_opts=opts.TitleOpts(title='空气质量指数最优TOP50城市'),
                     xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=30, interval=0)),
                     datazoom_opts=[opts.DataZoomOpts(), opts.DataZoomOpts(type_='inside')]
                    )
)
bar.load_javascript()

bar.render_notebook()