用K-Means、Foursquare和Folium聚集村庄，在大马尼拉寻找新鲜农产品供应商

# 获取北格林希尔的经纬度

address = 'North Greenhills, Metro Manila'

geolocator = Nominatim(user_agent="gh_agent")
location = geolocator.geocode(address)
latitude = location.latitude
longitude = location.longitude
print(latitude, longitude)

import requests # 处理请求
import pandas as pd # 数据分析
import numpy as np # 以矢量化的方式处理数据

import json # 将json文件解析为Python字典或列表

import matplotlib.cm as cm # 绘制点
import matplotlib.colors as colors # 绘制点

from pandas.io.json import json_normalize # 将json文件转换为pandas数据框

!python3 -m pip install folium
import folium # 创建地图
from geopy.geocoders import Nominatim # 对需要的不同区域的经度和纬度进行地理编码

from sklearn.cluster import KMeans # 用于创建k-means模型

print('Libraries imported.')

#Foursquare credentials (hidden cell)

# @hidden_cell

CLIENT_ID = '[insert Foursquare ID here]' 
CLIENT_SECRET = '[insert Foursquare Secret here]' 
ACCESS_TOKEN = '[insert Access Token here]'
VERSION = '20180605' # Foursquare API version
LIMIT = 100 # A default Foursquare API limit value

# 获取马尼拉的纬度和经度

address = 'Metro Manila'

geolocator = Nominatim(user_agent="mm_agent")
location = geolocator.geocode(address)
latitude = location.latitude
longitude = location.longitude

# 生成大马尼拉的村庄地图

village_map = folium.Map(location=[latitude, longitude], zoom_start=13)

# 将村庄设置为蓝色圆圈标记
for Latitude, Longitude, label in zip(df_villages.Latitude, df_villages.Longitude, df_villages.Village):
    folium.CircleMarker(
        [Latitude, Longitude],
        radius=5,
        color='blue',
        popup=label,
        fill = True,
        fill_color='blue',
        fill_opacity=0.6
    ).add_to(village_map)

# 显示地图
village_map

#获取k-means 大马尼拉村庄簇
#6个簇，每个簇对应一个工作日

kclusters = 6
kmeans = KMeans(n_clusters=kclusters, random_state=0).fit(df_villages[["Latitude", "Longitude"]])

# 为数据帧添加簇标签

df_villages.insert(0, 'Cluster Labels', kmeans.labels_)

# 显示数据帧的前5行

df_villages.head()

# 地图簇
cluster_map = folium.Map(location=[latitude, longitude], zoom_start=12)

# 设置簇的颜色
x = np.arange(kclusters)
ys = [i + x + (i*x)**2 for i in range(kclusters)]
colors_array = cm.rainbow(np.linspace(0, 1, len(ys)))
rainbow = [colors.rgb2hex(i) for i in colors_array]
centers = kmeans.cluster_centers_

# 设置markers
cluster_markers = []
for lat, lon, village, cluster in zip(df_villages['Latitude'], df_villages['Longitude'], df_villages['Village'], df_villages['Cluster Labels']):
    label = folium.Popup(str(village) + ' Cluster ' + str(cluster), parse_html=True)
    folium.CircleMarker(
        [lat, lon],
        radius=5,
        popup=label,
        color=rainbow[cluster-1],
        fill=True,
        fill_color=rainbow[cluster-1],
        fill_opacity=0.7).add_to(cluster_map)

cluster_map

# 获取Ayala Alabang村的经纬度
address_1 = 'Ayala Alabang, Metro Manila'
geolocator_1 = Nominatim(user_agent="1_agent")
location_1 = geolocator_1.geocode(address_1)
latitude_1 = location_1.latitude
longitude_1 = location_1.longitude

# 搜索每个选定的地址附近的菜市场
search_query = 'wet market'
radius = 2000
print(search_query)

# 获取簇1附近菜市场的结果
url_1 = 'https://api.foursquare.com/v2/venues/search?client_id={}&client_secret={}&ll={},{}&oauth_token={}&v={}&query={}&radius={}&limit={}'.format(CLIENT_ID, CLIENT_SECRET, latitude_1, longitude_1,ACCESS_TOKEN, VERSION, search_query, radius, LIMIT)

# 获取簇1附近菜市场的结果
results_1 = requests.get(url_1).json()

# 将JSON的相关部分分配给场馆
venues_1 = results_1['response']['venues']

# 将场馆转换为数据帧
df_results_1 = json_normalize(venues_1)
df_results_1

# 只保留包括场地名称和任何与地点相关的列
filtered_columns_1 = ['name', 'categories'] + [col for col in df_results_1.columns if col.startswith('location.')] + ['id']
df_markets_1 = df_results_1.loc[:, filtered_columns_1]

# 提取场地类别的函数
def get_category_type(row):
    try:
        categories_list = row['categories']
    except:
        categories_list = row['venue.categories']

    if len(categories_list) == 0:
        return None
    else:
        return categories_list[0]['name']

# 为每一行筛选类别
df_markets_1['categories'] = df_markets_1.apply(get_category_type, axis=1)

# 清理列名，只保留最后一个项
df_markets_1.columns = [column.split('.')[-1] for column in df_markets_1.columns]

df_markets_1

# 将菜市场用黄色的圆圈标记在地图上
for lat, lng, label in zip(df_markets_1.lat, df_markets_1.lng, df_markets_1.name):
    folium.CircleMarker(
        [lat, lng],
        radius=5,
        color='yellow',
        popup=label,
        fill = True,
        fill_color='yellow',
        fill_opacity=0.6
    ).add_to(cluster_map)

# 显示地图
cluster_map

# 查看大学街周六市场的评分。

venue_id_SMUA = '4b9c7413f964a520d96936e3' # Saturday Market on University Ave.
url_SMUA = 'https://api.foursquare.com/v2/venues/{}?client_id={}&client_secret={}&oauth_token={}&v={}'.format(venue_id_SMUA, CLIENT_ID, CLIENT_SECRET,ACCESS_TOKEN, VERSION)

result_SMUA = requests.get(url_SMUA).json()

try:
    print(result_SMUA['response']['venue']['rating'])
except:
    print('This venue has not been rated yet.')

url_SMUA_photo = 'https://api.foursquare.com/v2/photos/{}?client_id={}&client_secret={}&oauth_token={}&v={}'.format(venue_id_SMUA, CLIENT_ID, CLIENT_SECRET,ACCESS_TOKEN, VERSION)
result_SMUA_photo = requests.get(url_SMUA_photo).json()

result_SMUA_photo

## MMFM 技巧
limit_MMFM = 15 # set limit to be greater than or equal to the total number of tips
tips_MMFM = 'https://api.foursquare.com/v2/venues/{}/tips?client_id={}&client_secret={}&oauth_token={}&v={}&limit={}'.format(venue_id_MMFM, CLIENT_ID, CLIENT_SECRET,ACCESS_TOKEN, VERSION, limit_MMFM)

results_MMFM = requests.get(tips_MMFM).json()
results_MMFM