Segmentation of Neighborhood of Toronto and New York using Foursquare API and Clustering

a = pd.read_csv('https://cocl.us/Geospatial_data')
gdf = pd.DataFrame(a)

!wget -q -O 'newyork_data.json' https://cocl.us/new_york_dataset

with open('newyork_data.json') as json_data:
    newyork_nigh = json.load(json_data)
ny_neigh = newyork_nigh['features']

# define the dataframe columns
ny_nighcolumn = ['Borough', 'Neighborhood', 'Latitude', 'Longitude'] 

# instantiate the dataframe
ny_neighborhoods = pd.DataFrame(columns=ny_nighcolumn)

for data in ny_neigh:
    borough = neighborhood_name = data['properties']['borough'] 
    neighborhood_name = data['properties']['name']
        
    neighborhood_latlon = data['geometry']['coordinates']
    neighborhood_lat = neighborhood_latlon[1]
    neighborhood_lon = neighborhood_latlon[0]
    
    ny_neighborhoods = ny_neighborhoods.append({'Borough': borough,
                                          'Neighborhood': neighborhood_name,
                                          'Latitude': neighborhood_lat,
                                          'Longitude': neighborhood_lon}, ignore_index=True)

CLIENT_ID = "Your Foursquare client ID"
CLIENT_SECRET = "Your Foursquare Client Secret"
VERSION = '20180605'

print('My credentails:')
print('CLIENT_ID: ' + CLIENT_ID)
print('CLIENT_SECRET:' + CLIENT_SECRET)def getNearbyVenues(names, latitudes, longitudes, radius, LIMIT):
    
    venues_list=[]
    for name, lat, lng in zip(names, latitudes, longitudes):
        print(name)
           ....
......
 # create the API request URL
        url = 'https://api.foursquare.com/v2/venues/explore?&client_id={}&client_secret={}&v={}&ll={},{}&radius={}&limit={}'.format(
            CLIENT_ID, 
            CLIENT_SECRET, 
            VERSION, 
            lat, 
            lng, 
            radius, 
            LIMIT)

    ...#some code here
    return(nearby_venues)

# set number of clusters
t_kclusters = 5

toronto_grouped_clustering = toronto_grouped.drop('Neighborhood', 1)

# run k-means clustering
kmeans_tor = KMeans(n_clusters=t_kclusters, random_state=0).fit(toronto_grouped_clustering)

# check cluster labels generated for each row in the dataframe
kmeans_tor.labels_[0:10]

Now, the labelled neighborhood data was plotted in a map using folium package.
example code:

#create map
ny_map_clusters = folium.Map(location=[ny_latitude, ny_longitude], zoom_start=10.25)

# set color scheme for the clusters
x = np.arange(ny_kclusters)
ys = [i + x + (i*x)**2 for i in range(ny_kclusters)]
colors_array = cm.rainbow(np.linspace(0, 1, len(ys)))
rainbow = [colors.rgb2hex(i) for i in colors_array]

# add markers to the map
markers_colors = []
for lats, lons, poi, cluster in zip(newyork_merged['Latitude'], newyork_merged['Longitude'], newyork_merged['Neighborhood'], newyork_merged['Cluster Labels']):
    label = folium.Popup(str(poi) + ' Cluster ' + str(cluster), parse_html=True)
    folium.CircleMarker(
        [lats, lons],
        radius=5,
        popup=label,
        color=rainbow[int(cluster)-1],
        fill=True,
        fill_color=rainbow[int(cluster)-1],
        fill_opacity=0.7).add_to(ny_map_clusters)
       

ny_map_clusters.save('ny_map_cluster.html') #saving the map as image        
ny_map_clusters