def locate_on_map(addr, longtitude, latitude):
g = Geo().add_schema(maptype="上海")
g.add_coordinate(addr, longtitude, latitude)
data_pair = [(addr, 1)]
g.add('', data_pair, type_=GeoType.EFFECT_SCATTER, symbol_size=20)
g.set_series_opts(label_opts=options.LabelOpts(is_show=False))
g.set_global_opts(title_opts=options.TitleOpts(title="地图标点测试"))
g.render_notebook()
print("process finished")
def quakes():
# 对地震数据进行绘图
quakes_data = pd.read_csv("quakes.csv")
latitude = quakes_data['lat'].values
longitude = quakes_data['long'].values
mag = quakes_data['mag'].values
index = list(range(len(mag)))
#可视化
geo = Geo()
geo.add_schema(maptype='world')
for i in range(len(index)):
geo.add_coordinate(index[i], longitude[i], latitude[i])
data_pair = [list(z) for z in zip(index, mag)]
# 将数据添加进图中
geo.add('震源', data_pair, symbol_size=3)
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
# 设置显示区间
pieces = [
{
'max': 4,
'label': '4级以下',
'color': '#50A3BA'
},
{
'min': 4,
'max': 5,
'label': '4-5级',
'color': '#E2C568'
},
{
'min': 5,
'max': 6,
'label': '5-6级',
'color': '#D94E5D'
},
{
'min': 6,
'max': 7,
'label': '6-7级',
'color': '#3700A4'
},
{
'min': 7,
'label': '7级以上',
'color': '#81AE9F'
},
]
geo.set_global_opts(visualmap_opts=opts.VisualMapOpts(is_piecewise=True,
pieces=pieces),
title_opts=opts.TitleOpts(title="震源分布"))
#导出图像
geo.render('地震地点分布.html')
def base_info():
geo = Geo()
geo.add_schema(maptype="河南") # 加入自定义的点，格式为
# 地图形式 type_=ChartType.HEATMAP
geo.add("geo", data, type_=ChartType.EFFECT_SCATTER)
# is_show：是否显示经纬度
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
geo.set_global_opts(visualmap_opts=opts.VisualMapOpts(max_=10),
title_opts=opts.TitleOpts(title="Geo-河南省地图"))
return geo
def out_data(date_number):
city_list = ('南宁市', '柳州市', '桂林市', '梧州市', '北海市', '防城港市', '钦州市', '贵港市',
'玉林市', '百色市', '贺州市', '河池市', '来宾市', '崇左市')
city_od_list_pro = []
city_od_values_pro = []
for i in city_list:
city = i
workbook = xlrd.open_workbook(f'.\\{path}\\{city}-迁入来源地规模指数.xlsx')
sheet = workbook.sheet_by_index(0)
city_od_list = []
city_od_values = []
a = 0
cols = sheet.col_values(1)[1:]
cols_date = sheet.col_values(date_number + 1)[1:]
for j in cols:
city_od = (city, j)
city_od_v = (j, cols_date[a])
city_od_list.append(city_od)
city_od_values.append(city_od_v)
a += 1
city_od_list_pro.append(city_od_list)
city_od_values_pro.append(city_od_values)
od_list = []
os_values = []
for i in range(14):
for j in range(14):
od_list.append(city_od_list_pro[i][j])
os_values.append(city_od_values_pro[i][j])
# print(od_list)
# print(os_values)
geo = Geo()
# 地图类型，世界地图可换为world
geo.add_schema(maptype="广西")
# 添加数据点
geo.add("%", os_values, type_=ChartType.EFFECT_SCATTER)
# 添加流向，type_设置为LINES，涟漪配置为箭头，提供的标记类型包括 'circle', 'rect', 'roundRect', 'triangle',
# 'diamond', 'pin', 'arrow', 'none'
geo.add("迁出城市",
od_list,
type_=ChartType.LINES,
effect_opts=opts.EffectOpts(symbol=SymbolType.ARROW,
symbol_size=5,
color="yellow"),
linestyle_opts=opts.LineStyleOpts(curve=0.2),
is_large=True)
# 不显示标签
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
# 设置图标标题，visualmap_opts=opts.VisualMapOpts()为左下角的视觉映射配置项
geo.set_global_opts(visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title="广西地市迁徙数据"))
# 直接在notebook里显示图表
geo.render_notebook()
# 生成html文件，可传入位置参数
geo.render(f".\\out_od\\广西-2020.10.{date_number}迁出OD图.html")
def drawGeoMap(excel_path, mtype='china'):
data = xlrd.open_workbook(excel_path)
table = data.sheet_by_index(0)
nrow = table.nrows
dates = table.row_values(0)
# print(dates)
allData = {}
for i in range(1, nrow):
aNameData = {}
sname = f"{table.cell(i,0).value} {table.cell(i,1).value}"
for j in range(2, len(dates)):
value = table.cell(i,j).value
try:
value = json.loads(value)
value = value[1:4]
except Exception as e:
print(f"error: {e}")
pass
aNameData[dates[j]] = value
allData[sname] = aNameData
# print(f'学生数：{len(allData)}')
title = '2021年1月21日能仔位置'
geo = Geo(init_opts=opts.InitOpts(width='1000px', height='580px', page_title=title, theme=ThemeType.LIGHT))
geo.add_schema(maptype=mtype)
for name, data in allData.items():
for date, location in data.items():
aNameLocation = []
try:
longitude, latitude, address = location
except Exception as e:
print(f"Error: {e}")
longitude, latitude, address = DEFAULT_Location
# aNameLocation.append(('%s %s\n' % (name, date), address))
# geo.add_coordinate('%s %s' % (name, date), longitude, latitude)
sno, sname = name.split(' ')
# print(sno, sname)
aNameLocation.append(('%s %s' % (sno, sname), date))
geo.add_coordinate('%s %s' % (sno, sname), longitude, latitude)
geo.add(name, aNameLocation, type_=ChartType.EFFECT_SCATTER)
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
geo.set_global_opts(legend_opts=opts.LegendOpts(type_='scroll', orient='vertical', pos_left='left', pos_top='10%', is_show=False), title_opts=opts.TitleOpts(title=title))
map_path = os.path.join(dir_path, '2021年1月21日能仔位置地图.html')
geo.render(map_path)
# os.system(f'"C:\Program Files (x86)\Google\Chrome\Application\chrome.exe" {os.path.abspath(map_path)}')
print('done.')
def draw_map(data_pair, data_coordinate) -> Geo: # ->常常出现在python函数定义的函数名后面，为函数添加元数据,描述函数的返回类型，从而方便开发人员使用。
g = Geo()
# 选择要显示的地图
g.add_schema(maptype="重庆", center=[106.531638,29.561081], itemstyle_opts=opts.ItemStyleOpts(color="#575D57"))
# 使用add_coordinate(name, lng, lat)添加坐标点和坐标名称
for item in data_coordinate:
g.add_coordinate(item['name'], item['lng'], item['lat'])
# 将数据添加到定义的地图上
g.add('', data_pair, type_=GeoType.EFFECT_SCATTER, symbol_size=5) # type_=ChartType.HEATMAP
# 设置样式
g.set_series_opts(label_opts=opts.LabelOpts(is_show=False))\
.set_global_opts(visualmap_opts=opts.VisualMapOpts(min_=60, max_ = 200, is_piecewise=True),title_opts=opts.TitleOpts(title="重庆房源分布图"))
return g
def base_info():
print(data)
geo = Geo()
geo.add_schema(maptype="china") # 加入自定义的点，格式为
# geo.add_coordinate("自定义点", 80.39770014211535,39.90779994986951)
# 地图形式 type_=ChartType.HEATMAP
geo.add("geo", data, type_=ChartType.EFFECT_SCATTER)
# is_show：是否显示经纬度
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
geo.set_global_opts(visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title="Geo-基本示例"))
return geo
def insert_loc():
g = Geo()
data_pair = []
g.add_schema(maptype='china')
airport_df = pd.read_excel('CN_airport_info.xlsx', usecols='B,D,E,F,S')
for i in range(len(airport_df)):
g.add_coordinate(airport_df.iloc[i, 1], float(airport_df.iloc[i, 3]),
float(airport_df.iloc[i, 2]))
data_pair.append((airport_df.iloc[i, 1], int(airport_df.iloc[i, 4])))
g.add('', data_pair, type_=GeoType.EFFECT_SCATTER, symbol_size=7)
g.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
g.set_global_opts(
visualmap_opts=opts.VisualMapOpts(is_piecewise=False),
title_opts=opts.TitleOpts(title="全国机场分布图"),
)
return g
def base_info():
geo = Geo()
geo.width = "1440px"
geo.height = "680px"
geo.add_schema(maptype="china")
geo.add("确诊人数", confirmed, type_=ChartType.EFFECT_SCATTER)
geo.add("疑似人数", suspect, type_=ChartType.EFFECT_SCATTER)
geo.add("死亡人数", dead, type_=ChartType.EFFECT_SCATTER)
geo.add("治愈人数", healed, type_=ChartType.EFFECT_SCATTER)
geo.set_series_opts(
label_opts=opts.LabelOpts(is_show=False, background_color='#61a0a8'))
geo.set_global_opts(visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(
title="中国ncov-2019疫情动态\n上一次数据更新时间：\n" + time))
return geo
def geo_base():
city_data = get_data()
print(city_data)
geo = Geo(init_opts=opts.InitOpts(theme="vintage"))
for city in city_data:
try:
geo.add_schema(maptype="china",
itemstyle_opts=opts.ItemStyleOpts(color="gray"))
geo.add("微信好友分布地图", [city], type_="effectScatter", symbol_size=10)
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
geo.set_global_opts(
visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title="来自中南海的瓶子"),
)
except Exception as e:
print(city)
pass
geo.render("ms_geo.html")
def draw_with_echarts_scatter():
'''使用pyecharts画散点图'''
try:
device_csv_dir = r'E:/test_opencv/车辆经常停留位置/all_device_data_csv/'
pyecharts_device_html_dir = r'E:/test_opencv/车辆经常停留位置/pyecharts_device_html/'
if not os.path.exists(device_csv_dir):
os.makedirs(device_csv_dir)
if not os.path.exists(pyecharts_device_html_dir):
os.makedirs(pyecharts_device_html_dir)
for item in os.listdir(device_csv_dir):
csvlName = device_csv_dir + item
df = pd.read_csv(csvlName, encoding='utf-8', low_memory=False)
# X = df.drop_duplicates(subset=['longitude', 'latitude'])
X = df
device_id = X['device_id'].iloc[0] # 取组内第一个device_id用于存csv用
staff_id = X['staff_id'].iloc[0] # 取组内第一个staff_id用于存csv用
staff_name = X['staff_name'].iloc[0] # 取组内第一个staff_name用于存csv用
car_id = X['car_id'].iloc[0] # 取组内第一个car_id用于存csv用
car_num = X['car_num'].iloc[0] # 取组内第一个car_num用于存csv用
create_time_1 = X['create_time_1'].iloc[0] # 取组内第一个create_time_1用于存csv用
g = Geo()
g.add_schema(maptype="china")
# 给所有点附上标签 'create_time'
for index, row in X.iterrows():
g.add_coordinate(row['create_time'], row['remain_longitude'], row['remain_latitude'])
create_time = X.create_time.values.tolist()
# 给每个点的值赋为 1
data_list = [[item, 1] for item in create_time]
# 画图
# g.add('', data_list, type_=GeoType.HEATMAP, symbol_size=2)
g.add('', data_list, type_=GeoType.EFFECT_SCATTER, symbol_size=2)
g.set_series_opts(label_opts=options.LabelOpts(is_show=False))
#heatmap
# g.set_global_opts(visualmap_opts=options.VisualMapOpts(), title_opts=options.TitleOpts(title=staff_name+"_" + str(car_num) + '_' + str(create_time_1) +'_heatmap' ,pos_left='50%',pos_top='20'))
#scatter
g.set_global_opts(title_opts=options.TitleOpts(title=staff_name+"_" + str(car_num) + '_' + str(create_time_1) +'_scatter' ,pos_left='50%',pos_top='20'))
# 保存结果到 html
result = g.render(pyecharts_device_html_dir + str(staff_name) + '_' +str(car_num) + '_' + str(create_time_1) + '.html')
except Exception as ex:
logger.error("Call method draw_with_echarts_scatter() error!")
logger.error("Exception:" + str(ex))
raise ex
def geo_heatmap(k, v) -> Geo:
try:
c = Geo()
c.add_schema(maptype="china")
c.add(
"ratio",
[list(z) for z in zip(k, v)],
type_=ChartType.HEATMAP,
)
except TypeError:
print("地址有误，开始排错......")
with open("place.txt", mode="a") as f:
i = 0
c = Geo()
c.add_schema(maptype="china")
while i < len(k):
try:
c.add(
"ratio",
[list(z) for z in zip(k[:i], v[:i])],
type_=ChartType.HEATMAP,
)
except:
print(k[i - 1])
f.writelines(k[i - 1])
f.writelines('\n')
del k[i - 1]
del v[i - 1]
i -= 1
continue
else:
i += 1
geo_heatmap(k, v)
else:
c.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
timen = datetime.datetime.now().strftime('%Y-%m-%d')
timea = datetime.datetime.now().strftime('%Y-%m-%d %H.%M.%S')
c.set_global_opts(
visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title="2019nCoV{} BY PZW".format(timen)))
Geo.render(c, path='{}HEATMAP.html'.format(timea))
print('渲染完毕')
def get_company_city(self):
sql = """
select city,count(distinct url) as company_count from lagou_company GROUP BY city
"""
result = cursor.execute(sql)
key = []
values = []
for info in cursor.fetchall():
if info[0] != '海外' and re.match('[\u4e00-\u9fa5]', info[0]):
key.append(info[0])
values.append(info[1])
geo = Geo(init_opts=opts.InitOpts(width="1600px", height="1000px"))
geo.add_schema(maptype="china")
geo.add("公司分布", [list(z) for z in zip(key, values)], type_="heatmap")
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
geo.set_global_opts(visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title="各城市公司分布"))
file = data_store + "\\" + "company.html"
check_path(file)
geo.render(file)
def plot():
# 初始化图表信息
geo = Geo(init_opts=opts.InitOpts(width="96vw",
height="96vh",
page_title="教育网拓扑图",
animation_opts=opts.AnimationOpts(
animation=False)))
# 添加地图
geo.add_schema(maptype="china")
# 添加所有点的地理信息
geo.add_coordinate_json("./data/data.json")
# 画中间节点
geo.add("Route", [(i, "Route") for i in Nodes_Route],
color="Red",
point_size=4,
symbol_size=4,
effect_opts=opts.EffectOpts(is_show=False))
# 画目的节点
geo.add("Dst", [(i, "Dst") for i in Nodes_Dst],
color="SeaGreen",
point_size=4,
symbol_size=4,
effect_opts=opts.EffectOpts(is_show=False))
# 画线 展示拓扑信息
geo.add("",
list(Trace),
type_=ChartType.LINES,
effect_opts=opts.EffectOpts(is_show=False, symbol_size=2),
linestyle_opts=opts.LineStyleOpts(curve=0.1))
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
geo.set_global_opts(title_opts=opts.TitleOpts(title="教育网拓扑图"))
# 生成图表到指定文件
geo.render("./dist/render.html")
def get_geo_base(self, _data):
'''
plot geo-HeatMap
:param _data: gps对应的城市分布(dataframe)
:return: geo城市分布图
'''
register_url(self.echarts_url)
geo = Geo(init_opts=opts.InitOpts(width="1000px",
height="600px",
page_title=self.country,
bg_color=''))
geo.add_schema(maptype=self.country)
for _city, _gps in self.geo_dict.items():
geo.add_coordinate(name=_city, longitude=_gps[0], latitude=_gps[1])
geo.add(series_name=self.series_name,
data_pair=_data,
type_=ChartType.HEATMAP)
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
geo.set_global_opts(
visualmap_opts=opts.VisualMapOpts(max_=self.threshold_plot),
title_opts=opts.TitleOpts(title="Geo-HeatMap"))
return geo
def country_job_num(self):
df = pd.read_csv(
"D:\PythonFile\LagouSpider\imags\CsvFile\LagouPosition.csv")
citys = df.city
count = Counter(citys)
# count = count.most_common(len(count))
city_list = []
for city in count:
city_list.append([city, count[city]])
map = Geo()
map.add_schema("china")
map.add("geo", city_list, type_=ChartType.EFFECT_SCATTER)
map.set_series_opts(label_opts=opt.LabelOpts(is_show=False))
map.set_global_opts(
visualmap_opts=opt.VisualMapOpts(),
title_opts=opt.TitleOpts(title="Python开发工程师分布情况"),
)
map.render(
path="D:\PythonFile\LagouSpider\imags\pic/Python开发工程师分布情况.html")
def plot_geo_heatmap(all_df):
"""画热力图
Args:
all_df (dataframe): 每日数据图
"""
def valid_area(x, v):
if x.get_coordinate(v) is not None:
return 'Y'
else:
return 'N'
c = Geo(init_opts=opts.InitOpts(width='800px', height='600px'))
all_df['valid'] = all_df['name'].apply(lambda x: valid_area(c, x))
all_df['plot_v'] = np.log2(all_df['confirm_all'] / 50 + 1) * 10
c.add_schema(maptype="china")
c.add(
"ratio",
all_df.loc[all_df['valid'] == 'Y', ['name', 'plot_v']].values,
type_=ChartType.HEATMAP,
)
c.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
c.set_global_opts(
visualmap_opts=opts.VisualMapOpts(),
legend_opts=opts.LegendOpts(is_show=False),
title_opts=opts.TitleOpts(
pos_left='center',
title='2020 Novel coronavirus pneumonia (NCP) ',
title_link=
'https://news.qq.com/zt2020/page/feiyan.htm?from=timeline&isappinstalled=0'
))
# map_p = Map()
# map_p.set_global_opts(title_opts=opts.TitleOpts(title="实时疫情图"), visualmap_opts=opts.VisualMapOpts(max_=100))
# map_p.add("确诊", data, maptype="china")
Geo.render(c, path='E:/HEATMAP.html')
def in_data(city, date_number):
workbook = xlrd.open_workbook(f'.\\{path}\\{city}-迁入来源地规模指数.xlsx')
sheet = workbook.sheet_by_index(0)
city_od_list = []
city_od_values = []
a = 0
cols = sheet.col_values(1)[1:]
cols_date = sheet.col_values(date_number + 1)[1:]
for j in cols:
city_od = (j, city)
city_od_v = (j, cols_date[a])
city_od_list.append(city_od)
city_od_values.append(city_od_v)
a += 1
geo = Geo()
# 地图类型，世界地图可换为world
geo.add_schema(maptype="广西")
# 添加数据点
geo.add("%", city_od_values, type_=ChartType.EFFECT_SCATTER)
# 添加流向，type_设置为LINES，涟漪配置为箭头，提供的标记类型包括 'circle', 'rect', 'roundRect', 'triangle',
# 'diamond', 'pin', 'arrow', 'none'
geo.add("迁入城市",
city_od_list,
type_=ChartType.LINES,
effect_opts=opts.EffectOpts(symbol=SymbolType.ARROW,
symbol_size=5,
color="yellow"),
linestyle_opts=opts.LineStyleOpts(curve=0.2),
is_large=True)
# 不显示标签
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
# 设置图标标题，visualmap_opts=opts.VisualMapOpts()为左下角的视觉映射配置项
geo.set_global_opts(visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title=f"{city}迁入数据"))
# 直接在notebook里显示图表
geo.render_notebook()
# 生成html文件，可传入位置参数
geo.render(f".\\in_od\\{city}-2020.10.{date_number}迁入OD图.html")
def generate_geo_png(geodata, geomax, geomin, geotitle, display_id,
map_data_title):
from pyecharts import options as opts
from pyecharts.charts import Map, Geo
from pyecharts.render import make_snapshot
# from pyecharts_snapshot.main import make_a_snapshot
from snapshot_selenium import snapshot
geo = Geo()
geo.add_coordinate_json(
'/home/CitizenScience/backend/backend/geoCoordJson.js')
geo.add_schema(maptype="china")
print(geodata)
print(map_data_title)
geo.add(" ", geodata, symbol_size=10)
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
geo.set_global_opts(
visualmap_opts=opts.VisualMapOpts(max_=geomax, min_=geomin))
figure_url = "/home/CitizenScience/file/visualization/" + str(
display_id) + '_geo.png'
# figure_url = str(display_id) + '_geo.png'
make_snapshot(snapshot, geo.render(), figure_url, 2)
# geo.render(path='render.html')
# cmd = "snapshot render.html png"
# try:
# isRun = os.system(cmd)
# print("截图完成")
# except:
# print("截图失败")
# cmd = "mv output.png ../file/visualization/{}".format(figure_url)
# try:
# isRun = os.system(cmd)
# print("移动完成")
# except:
# print("移动失败")
# make_a_snapshot('geo2.html', 'geo3.png')
return figure_url
("黄埔",1),
("秦皇岛",1),
("南通",1),
("杭州",1),
("上海",1),
("香港",1),
("澳门",1),
("深圳",1),
("汕头",1),
("烟台",1),
("威海",1),
("芜湖",1),
("南京",1),
("温州",1),
("嘉兴",1),
],type_=ChartType.EFFECT_SCATTER,color="gold")
c.add("机场",
[("北京",6),
("呼和浩特",4),
("南昌",4),
("贵州",4),
("成都",4),
("哈尔滨",2),
("乌鲁木齐",1),
("郑州",1),
("沈阳",2),
("长春",1),
],type_=ChartType.EFFECT_SCATTER,color="deepskyblue")
c.set_series_opts(label_opts=opts.LabelOpts(is_show=False)).set_global_opts(title_opts=opts.TitleOpts(title="港口机场分布图"))
c.render_notebook()
def city_distribution(df):
df['city'] = df.city.replace(re.compile(r'[a-zA-Z]+'), '国外')
# 筛选国外城市
df_city1 = []
for i in df['city']:
i = str(i)
if '国外' in i:
df_city1.append('国外')
else:
df_city1.append(i)
df['city'] = df_city1
# 提取城市名
df_city2 = []
for i in df['city']:
i = str(i)
# 处理形如 县级市,地级市 数据
if ',' in i:
i = i.split(',')[1].strip()
elif len(i) == 4:
i = i[2:]
elif len(i) > 4:
if '中国台湾' in i:
i = i[4:]
elif '内蒙古' in i or '黑龙江' in i:
i = i[3:]
else:
i = i[2:]
df_city2.append(i)
df['city'] = df_city2
# 筛选出国内城市Top10
city_top = df.city.value_counts()
if '国外' in city_top.index:
city_top.drop('国外', inplace=True)
if '未知' in city_top.index:
city_top.drop('未知', inplace=True)
if city_top.count() > 10:
city_top = city_top[:10]
print('Top10 cities:')
print(city_top)
# 绘制条形图
bar = Bar(init_opts=opts.InitOpts(width='1350px', height='750px'))
bar.add_xaxis(city_top.index.tolist())
bar.add_yaxis('评论人次', city_top.values.tolist())
bar.set_global_opts(title_opts=opts.TitleOpts(title='评论者Top10城市分布'),
toolbox_opts=opts.ToolboxOpts())
# 绘制Top30城市分布地理图（国内）
city_num = df.city.value_counts()
if '国外' in city_num.index:
city_num.drop('国外', inplace=True)
if '未知' in city_num.index:
city_num.drop('未知', inplace=True)
if city_num.count() > 30:
city_num = city_num[:30]
print('Top30 cities:')
print(city_num)
geo = Geo(init_opts=opts.InitOpts(width='1350px', height='750px'))
geo.add_schema(maptype='china')
geo.add(
'',
[list(z) for z in zip(city_num.index, city_num.values.astype('str'))],
type_=GeoType.EFFECT_SCATTER)
geo.set_global_opts(visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title='评论者城市分布'),
toolbox_opts=opts.ToolboxOpts())
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
return bar, geo
"color": "cyan"
}, {
"value": "7",
"label": "G",
"color": "purple"
}
],
),
legend_opts=opts.LegendOpts( # 设置图例配置项
pos_right="right",
pos_top="top",
orient="vertical",
),
)
geo.set_series_opts(label_opts=opts.LabelOpts( # 设置标签配置项
is_show=False # 设置不显示Label
))
geo.render("demo03.html") # 生成名为"demo03"的本地html文件
# customMap = (
# Map()
# .add("商家A", # 图例
# [list(z) for z in zip(Faker.provinces, Faker.values())], # 数据项
# "china" # 地图
# )
# .set_global_opts( # 设置全局项
# title_opts=opts.TitleOpts( # 设置标题项
# title="中国地图" # 设置标题名称
# )
# )
def test_geo():
city = '长沙'
g = Geo()
g.add_schema(maptype='河南')
# 定义坐标对应的名称，添加到坐标库中 add_coordinate(name, lng, lat)
# g.add_coordinate('湖南省长沙市宁乡市横市镇藕塘', 112.21369756169062, 28.211359706637378)
# g.add_coordinate('湖南省长沙市雨花区跳马镇仙峰岭', 113.16921879037058, 28.039877432448428)
# g.add_coordinate('湖南省长沙市长沙县黄花镇新塘铺长沙黄花国际机场', 113.23212337884058, 28.19327497825815)
# 定义数据对，
# data_pair = [('湖南省长沙市雨花区跳马镇仙峰岭', 10), ('湖南省长沙市宁乡市横市镇藕塘', 5), ('湖南省长沙市长沙县黄花镇新塘铺长沙黄花国际机场', 20)]
data_pair = list(temp_d.items())
# Geo 图类型，有 scatter, effectScatter, heatmap, lines 4 种，建议使用
# from pyecharts.globals import GeoType
# GeoType.GeoType.EFFECT_SCATTER，GeoType.HEATMAP，GeoType.LINES
# 将数据添加到地图上
g.add('', data_pair, type_=GeoType.EFFECT_SCATTER, symbol_size=15)
# 设置样式
g.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
# 自定义分段 color 可以用取色器取色
# pieces = [
# {'max': 1, 'label': '0以下', 'color': '#50A3BA'},
# {'min': 1, 'max': 10, 'label': '1-10', 'color': '#3700A4'},
# {'min': 10, 'max': 20, 'label': '10-20', 'color': '#81AE9F'},
# {'min': 20, 'max': 30, 'label': '20-30', 'color': '#E2C568'},
# {'min': 30, 'max': 50, 'label': '30-50', 'color': '#FCF84D'},
# {'min': 50, 'max': 100, 'label': '50-100', 'color': '#DD0200'},
# {'min': 100, 'max': 200, 'label': '100-200', 'color': '#DD675E'},
# {'min': 200, 'label': '200以上', 'color': '#D94E5D'} # 有下限无上限
# ]
pieces = [
{
'min': 0,
'max': 3,
'label': '类别1',
'color': '#50A3BA'
}, #有上限无下限，label和color自定义
{
'min': 4,
'max': 6,
'label': '类别2',
'color': '#81AE9F'
},
{
'min': 7,
'max': 8,
'label': '类别3',
'color': '#E2C568'
},
# {'min': 150, 'max': 300,'label': '150-300','color':'#FCF84D'},
# {'min': 300, 'label': '300以上','color':'#D94E5D'}#有下限无上限
]
# is_piecewise 是否自定义分段， 变为true 才能生效
g.set_global_opts(
visualmap_opts=opts.VisualMapOpts(is_piecewise=True, pieces=pieces),
title_opts=opts.TitleOpts(title="城市聚类"),
)
return g
data = pd.read_excel("D:\数有引力\魔都商圈\办公项目.xlsx") # 读取数据
geo_sight_coord = {
data['项目名称'][i].strip(): [data['经度'][i], data['纬度'][i]]
for i in range(len(data))
} # 构造位置字典数据
data_pair = [(data['项目名称'][i].strip(), data['日租金'][i])
for i in range(len(data))] # 构造项目租金数据
g = Geo() # 地理初始化
g.add_schema(maptype="上海") # 限定上海市范围
for key, value in geo_sight_coord.items(): # 对地理点循环
g.add_coordinate(key, value[0], value[1]) # 追加点位置
g.add("", data_pair, symbol_size=2) # 追加项目名称和租金
g.set_series_opts(label_opts=opts.LabelOpts(is_show=False),
type='scatter') # 星散点图scatter
pieces = [
{
'max': 3,
'label': '<3',
'color': '#00B2EE'
},
{
'min': 3,
'max': 6,
'3~6': 'love',
'color': '#71C671'
},
{
'min': 6,
avg_salary_by_loc = salary_data.groupby(loc_data).mean() \
.sort_values(ascending=False)
avg_salary_by_loc.plot.bar()
for i, v in enumerate(avg_salary_by_loc):
plt.text(i, v, round(v, 2), ha='center', va='bottom')
plt.title('不同区域平均工资柱状图', fontproperties=font_zh)
plt.xticks(range(len(avg_salary_by_loc)),
avg_salary_by_loc.index,
fontproperties=font_zh)
plt.xlabel('区域', fontproperties=font_zh)
plt.ylabel('平均工资（千/年）', fontproperties=font_zh)
loc_list = [[i, loc_counts[i]] for i in loc_counts.index]
geo = Geo().add_schema(maptype='成都')
geo.add('区域分布热度图', loc_list, type_=ChartType.HEATMAP) # 设置名称和数据
geo.set_series_opts(label_opts=opts.LabelOpts(is_show=True)) # 设置标签是否可见
geo.set_global_opts(visualmap_opts=opts.VisualMapOpts()) # 视觉映射配置
geo.render('./loc_heatmap.html') # 保存为网页
os.system('"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"\
./loc_heatmap.html') # 打开网页
# 工作经验分析
exp_data = data['job_exp']
exp_des = exp_data.describe() # 工作经验基本数据描述，包括平均数、中位数等
exp_counts = exp_data.value_counts().sort_index() # 按实际值进行频率统计
fig = plt.figure('平均工作经验统计详情', figsize=[16, 5])
plt.subplots_adjust(left=0.03, bottom=0.15, right=0.97, top=0.9, wspace=0.25)
ax1 = fig.add_subplot(161)
plt.title('平均工作经验年限详情描述', fontproperties=font_zh)
city2 = sheet.col_values(8)#降落城市
speed = sheet.col_values(22)#飞机速度
vspeed = sheet.col_values(23)#垂直速度
height = sheet.col_values(24)#飞行高度
uptime = sheet.col_values(26)#时间
c = Geo()
# 加载图表模型中的中国地图
c.add_schema(maptype="china")
i = 1
for i in range(1,10):
c.add_coordinate("航班号" + flightnumber_list[i], long_list[i], lat_list[i])
# 为自定义的点添加属性
c.add("geo", [("航班号" + flightnumber_list[i], "航空公司："+aircname[i]+" "+city1[i]+"飞往"+city2[i]+" 飞行速度："+str(speed[i])+" 垂直速度："+str(vspeed[i])+" 高度："+str(height[i])+" 时间"+uptime[i])])
# 设置坐标属性
c.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
# 设置全局属性
c.set_global_opts(
visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title="航班信息可视化"),
)
# 在 html(浏览器) 中渲染图表
c.render()
# 在 Jupyter Notebook 中渲染图表
c.render_notebook()
addr_dic[provice] = 0
addr_dic[provice] += 1
# print(addr_dic)
# print(addr_dic.items())
sort_addr = sorted(addr_dic.items(), key=lambda item: item[1],
reverse=True)[0:10]
print(sort_addr)
# addr_names = [item[0] for item in sort_addr]
# addr_counts = [item[1] for item in sort_addr]
# print(addr_names, addr_counts)
from pyecharts.charts import Geo
from pyecharts.options import LabelOpts, VisualMapOpts, TitleOpts
from pyecharts.globals import ChartType
geo = Geo()
geo.add_schema(maptype="china")
geo.add("地点统计", sort_addr, type_=ChartType.EFFECT_SCATTER)
geo.set_series_opts(label_opts=LabelOpts(is_show=False))
geo.set_global_opts(
visualmap_opts=VisualMapOpts(is_piecewise=True, max_=sort_addr[0][1]),
title_opts=TitleOpts(title="撩课Python统计"),
)
geo.render("地点统计-geo图.html")
def geo():
place_avaliable = passenger_spider(None, all=True)
place_no_weather = passenger_spider_no_weather()
city = '上海'
g = Geo(init_opts=opts.InitOpts(
width="100%", height="100%", bg_color="#12406d"))
g.add_schema(maptype=city,
itemstyle_opts=opts.ItemStyleOpts(color="#135dbe",
border_color="#fff"),
zoom=1.2)
# 定义坐标对应的名称，添加到坐标库中 add_coordinate(name, lng, lat)
for k, v in jingwei_dict.items():
g.add_coordinate(k, float(v[1]), float(v[0]))
for item in place_no_weather:
g.add_coordinate(item["NAME"], float(item["LOCATION_X"]),
float(item["LOCATION_Y"]))
coordinates = []
for k in jingwei_dict.keys():
data_pairs = []
data_pairs.append(k)
for p in place_avaliable:
if k == p["NAME"]:
if not p.get("MAX_NUM"):
data_pairs.append(0.0)
else:
data_pairs.append(
round(int(p["NUM"]) / int(p["MAX_NUM"]), 2))
break
if len(data_pairs) == 1:
data_pairs.append(0.0)
data_pairs = tuple(data_pairs)
coordinates.append(data_pairs)
for item in place_no_weather:
data_pairs = []
data_pairs.append(item["NAME"])
if (not item["MAX_NUM"]) or (item["MAX_NUM"] == ""):
data_pairs.append(0)
else:
data_pairs.append(round(
int(item["NUM"]) / int(item["MAX_NUM"]), 2))
data_pairs = tuple(data_pairs)
coordinates.append(data_pairs)
# 定义数据对，
# data_pair = [
# ('湖南省长沙市雨花区跳马镇仙峰岭', 25),
# ('湖南省长沙市宁乡市横市镇藕塘', 5),
# ('湖南省长沙市长沙县黄花镇新塘铺长沙黄花国际机场', 20)
# ]
data_pair = coordinates
# Geo 图类型，有 scatter, effectScatter, heatmap, lines 4 种，建议使用
# from pyecharts.globals import GeoType
# GeoType.GeoType.EFFECT_SCATTER，GeoType.HEATMAP，GeoType.LINES
# 将数据添加到地图上
g.add('', data_pair, type_=ChartType.EFFECT_SCATTER)
# 设置样式
g.set_series_opts(
label_opts=opts.LabelOpts(is_show=False, formatter="{b}:{c}"))
# 自定义分段 color 可以用取色器取色
pieces = [
{
'max': 0.1,
'label': '10%以下',
'color': '#98F5FF'
},
{
'min': 0.1,
'max': 0.3,
'label': '10%-30%',
'color': '#0f0'
},
{
'min': 0.3,
'max': 0.5,
'label': '30%-50%',
'color': 'orange'
},
{
'min': 0.5,
'max': 0.7,
'label': '50%-70%',
'color': '#E2C568'
},
{
'min': 0.7,
'max': 0.8,
'label': '70%-80%',
'color': '#FCF84D'
},
{
'min': 0.8,
'max': 0.9,
'label': '80%-90%',
'color': '#3700A4'
},
{
'min': 0.9,
'max': 1,
'label': '90%-100%',
'color': '#DD675E'
},
{
'min': 1,
'label': '100%以上',
'color': '#f00'
} # 有下限无上限
]
# is_piecewise 是否自定义分段， 变为true 才能生效
g.set_global_opts(
visualmap_opts=opts.VisualMapOpts(is_piecewise=True,
pieces=pieces,
textstyle_opts=opts.TextStyleOpts(
color="#fff")))
return g
("深圳", 1),
("汕头", 1),
("烟台", 1),
("威海", 1),
("芜湖", 1),
("南京", 1),
("温州", 1),
("嘉兴", 1),
],
type_=ChartType.EFFECT_SCATTER)
c.add(
"机场",
[
("北京", 6),
("呼和浩特", 4),
("南昌", 4),
("贵州", 4),
("成都", 4),
("哈尔滨", 2),
("乌鲁木齐", 1),
("郑州", 1),
("沈阳", 2),
("长春", 1),
],
type_=ChartType.EFFECT_SCATTER,
)
c.set_series_opts(label_opts=opts.LabelOpts(is_show=False)).set_global_opts(
title_opts=opts.TitleOpts(title="港口机场分布图"),
visualmap_opts=opts.VisualMapOpts(max_=30))
c.render_notebook()
def _cluster(self,
up_2,
class_upper,
plot_matplotlib=False,
plot_echarts=False) -> (list, list, list):
'''对某个部分进行聚类
class_upper:
表示是否是在所有点的 y 均值之上的点
key: city_index value: 0 or 1
:return 聚好的2类城市的列表 class_0, class_1 另一边的城市列表 (都是不包含起始点的)
'''
if up_2:
# 找出上面的点进行聚类
cities = [key for key, value in class_upper.items() if value == 1]
else:
cities = [key for key, value in class_upper.items() if value == 0]
try:
cities.remove(self.city_start) # 去除起始点
except:
pass
# todo 将与此部分的点没有联通，但是与另一部分的点有联通的归为另一边(这些点会影响聚类结果，并且不符合业务)
should_cluster = deepcopy(self.init_data) # 新的要聚两类中的点组成的无向图
should_not_cluster = dict()
other_cities = [] # 另一边的城市
# 分开两边的点
for k, v in class_upper.items():
if k not in cities:
other_cities.append(k)
should_cluster.pop(k)
should_not_cluster[k] = v
# 如果一个点的!!所有子结点!!都不在这一部分里，在无向图中删除，并放到另一边
for k, v in list(should_cluster.items()):
not_in_sum = 0
for next_node in v:
if next_node not in cities:
not_in_sum += 1
if not_in_sum == len(v):
other_cities.append(k)
cities.remove(k)
should_cluster.pop(k)
should_not_cluster[k] = v
arr = []
# 构建二维的数据矩阵
for c in cities:
arr.append([*self.map_dict[c]])
data = pd.DataFrame(arr)
n_cluster = 2
# km = DBSCAN(eps=1.2, min_samples=3).fit(data)
km = KMeans(n_clusters=n_cluster, random_state=6).fit(data)
y_pred_ = km.labels_ # 类别预测
print(cities)
print(y_pred_)
print(other_cities)
centroid = km.cluster_centers_ # 聚类中心
# city_class = {i:y_pred_[j] for i, j in zip(data.index, range(0, len(cities)))}
# todo 将与自己的类里面无联通，但是与另一个类的点有联通的归为那一类
class_1 = [cities[index] for index, j in enumerate(y_pred_) if j == 1]
class_0 = [cities[index] for index, j in enumerate(y_pred_) if j == 0]
for c in cities:
_sum = 0
out_sum = 0
if c in class_0:
c_mark = 0 # c_mark 当前点的类别
else:
c_mark = 1
c_list = should_cluster[c] # 单点点对应的子结点列表
for node in c_list:
if node not in cities:
out_sum += 1
continue
node_mark = 0 if node in class_0 else 1
if c_mark != node_mark:
_sum += 1
if len(c_list) == _sum + out_sum:
if c_mark == 0:
class_0.remove(c)
class_1.append(c)
else:
class_1.remove(c)
class_0.append(c)
if plot_matplotlib:
color = ['red', 'blue']
fig, ax1 = plt.subplots(1)
y_pred = km.labels_
for i in range(n_cluster):
ax1.scatter(data.iloc[y_pred == i, 0],
data.iloc[y_pred == i, 1],
marker='o',
s=50,
c=color[i])
ax1.scatter(centroid[:, 0],
centroid[:, 1],
marker='x',
s=50,
c='black')
plt.savefig('./ttesst.jpg')
plt.show()
# 不需要聚类那一边的点
# class_another = [x for x in range(0, 17) if x not in class_0
# and x not in class_1].remove(self.city_start) 注意这个列表推导式有毒！
# 另一边的点
class_another = []
for x in range(0, 17):
if x not in class_0:
if x not in class_1:
class_another.append(x)
# fp = open('./地图可视化.pk', 'wb')
# pickle.dump({2:class_0, 5: class_1, 8:class_another}, fp)
# f = open('./城市经纬度.pk', 'wb')
# pickle.dump(self.map_dict, f)
# ff = open('./m_list.pk', 'wb')
# pickle.dump(self.m_list, ff)
# fp.close()
# f.close()
# ff.close()
if plot_echarts:
temp_d = {}
d = {2: class_0, 5: class_1, 8: class_another}
for key, value in d.items():
for v in value:
if v == self.city_start:
continue
temp_d[self.m_list[v]] = key
temp_d[self.m_list[self.city_start]] = 11
g = Geo()
g.add_schema(maptype='河南')
data_pair = list(temp_d.items())
g.add('', data_pair, type_=GeoType.EFFECT_SCATTER, symbol_size=15)
g.set_series_opts(label_opts=opts.LabelOpts(is_show=False))
pieces = [
{
'min': 0,
'max': 3,
'label': '类别1',
'color': '#50A3BA'
}, # blue
{
'min': 4,
'max': 6,
'label': '类别2',
'color': '#81AE9F'
}, # green
{
'min': 7,
'max': 8,
'label': '类别3',
'color': '#E2C568'
}, # yellow
{
'min': 10,
'max': 12,
'label': '起始点',
'color': '#FF8C00'
} # orange
]
g.set_global_opts(
visualmap_opts=opts.VisualMapOpts(is_piecewise=True,
pieces=pieces),
title_opts=opts.TitleOpts(
title=f"物流路径规划-城市聚类-起始点{self.m_list[self.city_start]}"),
)
g.render(f'物流路径规划之城市聚类-{self.m_list[self.city_start]}.html')
# self.fix_cluster_graph(class_0, class_1, class_another)
return class_0, class_1, class_another
