def countStatistics():
# 读取数据文件
my_file = ReadCsv("directory.csv").readCsv()
# 清洗数据-处理缺省值
my_file = my_file.fillna("None")
timeZone = my_file["Timezone"]
# 处理重复数据并排序
timeZoneSort = sorted(set(timeZone))
# 根据 TImeZone 重新排列
group_by_time_zone = my_file.groupby(timeZone)
# 计算相同时区出现的次数
time_zone_count = dict(group_by_time_zone["Timezone"].value_counts())
# 计算星巴克的总数
store_sum = sum(time_zone_count.values())
# 每个时区的星巴克的比例
rate_text = [(value / store_sum) for value in time_zone_count.values()]
length = len(timeZoneSort)
values_list = list(time_zone_count.values())
# 把时区的相关信息写入文件
with open("timeZone.csv", "w") as csvFile:
writer = csv.writer(csvFile)
writer.writerow(["Timezone", "Amount", "Rate"])
for x in range(length):
writer.writerow([timeZoneSort[x], values_list[x], rate_text[x]])
file = ReadCsv("timeZone.csv").readCsv()
table = FF.create_table(file)
py.offline.plot(table, filename='countStatistics.html')
def timeZoneDistribution():
# 读取文件
file = ReadCsv("directory.csv")
my_file = file.readCsv()
lat, lon, store_number, store_name, address, postcode, phone_number = file.getCsvData(
)
time_zone = my_file["Timezone"]
# 显示文本
my_text = ("StoreNum: " + store_number + '</br>' + "store_name: " +
store_name + '</br>' + "StreetAddress: " + address + '</br>' +
"Postcode: " + postcode + '</br>' + "phone_number: " +
phone_number + '</br>')
# 添加数据到源文件
my_file['Text'] = my_text
# 处理重复数据
time_zone_set = set(time_zone)
# 根据 TimeZone 重新排列文件
group_by_time_zone = my_file.groupby(time_zone)
# 存放Scattermapbox
messages = []
for sub_time_zone in time_zone_set:
new_time_zone_group = group_by_time_zone.get_group(sub_time_zone)
data_temp = setLoopData(new_time_zone_group, sub_time_zone,
randomColor())
messages.append(data_temp)
data = Data(messages)
layout = setLoopDataLayout(title="Timezone Distribution Map")
fig = dict(data=data, layout=layout)
py.offline.plot(fig, validate=False, filename='timeZoneDistribution.html')
def init():
data = ReadCsv("directory.csv").readCsv()
grouped = data.groupby('Country').size() # series 类型，国家星巴克数量
# 创建关于国家名字数组
country = []
return country, grouped
def readFile():
file = ReadCsv("directory.csv")
lat, lon, store_number, store_name, address, postcode, phone_number = file.getCsvData()
list_semblance = [0] * len(lat)
list_datas = [" "] * len(lat)
result_list = [[a, b, c, d, e, f, g, h, i] for a, b, c, d, e, f, g, h, i in
zip(lon, lat, store_number, store_name, address, postcode, phone_number, list_semblance,
list_datas)]
return result_list
def solveKMapData():
file = ReadCsv("directory.csv")
lat, lon, store_number, store_name, store_address, postcode, phone_number = file.getCsvData(
)
datas = []
i = 0
while i <= lat.__len__() - 1:
c = store_number[i]
d = store_name[i]
f = store_address[i]
g = postcode[i]
h = phone_number[i]
data = 'store_number:' + c + '</br>' + 'store_name:' + d + '</br>' + 'Postcode:' + g + '</br>' + 'phone_number:' + h + '</br>' + 'store_address:' + f
datas.append(data)
i = i + 1
return lat, lon, datas
def radiusTimeChange(la, lo):
# 按照距离筛选数据
#读取表格数据
file = ReadCsv("directory.csv")
lat, lon, store_number, store_name, store_address, postcode, phone_number = file.getCsvData(
)
result_list = [[
a, b, c, d, e, f, g
] for a, b, c, d, e, f, g in zip(lat, lon, store_number, store_name,
store_address, postcode, phone_number)]
rlist = [1, 20, 100, 500, 2000, 10000, 40076]
runTime = []
for i in rlist:
start = time.clock()
filter(la, lo, i, result_list)
end = time.clock()
runTime.append(end - start)
trace = go.Scatter(x=rlist,
y=runTime,
name='RunTime Trace',
line=dict(color=('rgb(22, 96, 167)'),
width=4,
dash='dot'))
data = [trace]
# Edit the layout
layout = dict(
title='随着r的增长查询时延的变化',
xaxis=dict(title='r'),
yaxis=dict(title='查询时延'),
)
fig = dict(data=data, layout=layout)
py.plot(fig, filename='styled-line')
def districtAmount():
# 把两位国家代码转换成三位代码
with open("CountryTwoLettersToThree.pickle", "rb") as file:
three_country_code = pickle.load(file)
from Configuration.ReadCsv import ReadCsv
my_file = ReadCsv('directory.csv').readCsv()
# 计算相同国家的次数
country_count = dict(my_file["Country"].value_counts())
# 存放每个国家的星巴克数量
country_num = [country_count[key] for key in country_count]
# 转换国家代码
country_of_three_lettters_list = [
three_country_code[key] for key in country_count
]
data = [
dict(
type='choropleth',
Colorscale=[[0, "rgb (255, 255，255)"], [0.3, "rgb(255，80，80)"],
[0.35, "rgb(255, 160，160) "], [1, "rgb(255, 0，0) "]],
z=country_num,
reversescale=False,
autocolorscale=False,
locations=country_of_three_lettters_list,
locationmode="ISO-3",
colorbar=dict(autotick=False, title='星巴克<br>商店数量'),
)
]
layout = dict(
title="National Distribution Map",
autosize=True,
hovemode='closest',
mapbox=dict(
accesstoken=
"pk.eyJ1IjoibW9oYWlsYW5nIiwiYSI6ImNqZm93cGs5bDF3OXMyeG1zdGhuejBoNTIifQ.fouiU5hKtls0ohPA7LHJEA",
bearing=0,
pitch=0,
zoom=1,
))
fig = dict(data=data, layout=layout)
py.offline.plot(fig, validate=False, filename='distrinctAmount.html')
def topKSearch(latitude, longitude, k):
file = ReadCsv("directory.csv")
lat, lon, store_number, store_name, address, postcode, phone_number = file.getCsvData(
)
# 初始半径
initial_x = 5
initial_y = 5
list_x = [10] * len(lon)
list_y = [5] * len(lat)
result_list = [[a, b, c, d, e, f, g, h, i]
for a, b, c, d, e, f, g, h, i in zip(
lon, lat, store_number, store_name, address, postcode,
phone_number, list_x, list_y)]
# 输入数据
input_x = latitude
input_y = longitude
input_k = k
def haveRSine(x): # 经度1，纬度1，经度2，纬度2 （十进制度数）
# 将十进制度数转化为弧度
lon1, lat1, lon2, lat2 = map(radians, [x[0], x[1], input_x, input_y])
# haversine公式
d_lon = lon2 - lon1
d_lat = lat2 - lat1
a = sin(d_lat / 2)**2 + cos(lat1) * cos(lat2) * sin(d_lon / 2)**2
c = 2 * asin(sqrt(a))
r = 6371 # 地球平均半径，单位为公里
return c * r * 1000
# 处理筛选特殊情况
def sovleFilter(x):
if input_x + x[-2] > 180:
return input_y - x[-1] <= x[1] <= input_y + x[-1] and (input_x - x[-2]) < x[0] < 180 or \
-180 < x[0] < -(180 - (input_x + x[-2] - 180))
elif input_x - x[-2] < -180:
return input_y - x[-1] <= x[1] <= input_y + x[-1] and (
-180 < x[0] < (x[-2] + input_x) or (180 - abs(
(input_x - x[-2] + 180)) < x[0] < -180))
return input_y - x[-1] <= x[1] <= input_y + x[-1] and input_x - x[
-2] <= x[0] <= input_x + x[-2]
# 按照距离筛选数据
temp_list = result_list
def new_filter(x1, y1):
for x in temp_list:
x[-2] = x1
x[-1] = y1
data = list(filter(sovleFilter, temp_list))
return data
result = [] #存储所有符合条件的店铺信息
# 根据搜索到的数量逐步扩大半径
start = time.clock()
while result.__len__() < input_k:
result = new_filter(initial_x, initial_y)
# 增大半径
initial_x += 5
initial_y += 5
final_result = sorted(result, key=haveRSine)[:input_k] # 取最近的前k项为最终结果
lat_result = [] #存储符合要求的纬度信息
lon_result = [] #存储符合要求的经度信息
for x in final_result:
lon_result.append(x[0])
lat_result.append(x[1])
end = time.clock()
return lon_result, lat_result, final_result, end - start
def timeZoneMap():
file = ReadCsv("directory.csv")
df = file.readCsv()
drawTimezoneMap(df, "draw")