Perishleaf

# There are four pages for the list, so we stored the web links for these four pages into `domain`
headers = ({'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36'})
domain = []
domain.append("https://en.wikipedia.org/wiki/Category:Suburbs_of_Sydney")
domain.append("https://en.wikipedia.org/w/index.php?title=Category:Suburbs_of_Sydney&pagefrom=Dharruk%2C+New+South+Wales#mw-pages")
domain.append("https://en.wikipedia.org/w/index.php?title=Category:Suburbs_of_Sydney&pagefrom=Macgraths+Hill%0AMcGraths+Hill%2C+New+South+Wales#mw-pages")
domain.append("https://en.wikipedia.org/w/index.php?title=Category:Suburbs_of_Sydney&pagefrom=Singletons+Mill%2C+New+South+Wales#mw-pages")
# Create a empty list to store content
suburb_list =[]
for i in range(len(domain)):

Perishleaf

# Define a function for compiling info into array
def getDemography(suburb_names, postcode_list, state='NSW'):
    Demography_list=[]
    for suburb, postcode in zip(suburb_names, postcode_list):
        print(suburb)
        suburb = suburb.replace(' ', '-')
        # create the API request URL
        headers = ({'User-Agent':
                    'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36'})
        url = 'https://www.domain.com.au/suburb-profile/{}-nsw-{}'.format(

Perishleaf

# Sydney latitude and longitude values
latitude = -33.892319
longitude = 151.146167
# create a plain Sydney map
population_map = folium.Map(location=[latitude, longitude], zoom_start=11, tiles='cartodbpositron')
# create a list for population scale
bins = list(range(0, 60000, 10000))
# generate choropleth map using the total population of each suburb in Sydney
population_map.choropleth(
    geo_data=NSW_data,

Perishleaf

def getNearbyVenues(names, latitudes, longitudes, radius=500, LIMIT = 100):
    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, 

Perishleaf

# set number of clusters
kclusters = 4
sydney_grouped_clustering = sydney_grouped.drop('Suburb', 1)
# run k-means clustering
kmeans = KMeans(n_clusters=kclusters, random_state=0).fit(sydney_grouped_clustering)
# check cluster labels generated for each row in the dataframe
kmeans.labels_[0:10]
sydney_merged.loc[sydney_merged['Cluster Labels'] == 2, sydney_merged.columns[[0] + list(range(4, sydney_merged.shape[1]))]]

Perishleaf

new_data = []
for x, y, i, k in zip(data_for_pred.House_buy, data_for_pred.House_rent, data_for_pred.Suburb, data_for_pred.Postcode):
    if y != 0:
        x_pred = (y - regr.intercept_[0])/regr.coef_[0][0]
        new_data.append([(i, k, y, x_pred)])
    else:
        y_pred = regr.coef_[0][0]*x + regr.intercept_[0]
        new_data.append([(i, k, y_pred, x)])

Perishleaf

sydney_venues_num = sydney_venues.groupby('Suburb').count()
sydney_venues_num = sydney_venues_num.drop(columns=['Suburb Latitude', 'Suburb Longitude', 'Venue Latitude', 'Venue Longitude', 'Venue Category'])
sydney_venues_num = sydney_venues_num.sort_values(['Venue'], ascending=False).reset_index(drop=False)
sydney_venues_num['Suburb'] = sydney_venues_num['Suburb'].str.title()
print(sydney_venues_num.shape[0])
sydney_venues_num.head(20)

Perishleaf

# Create bar plot for trace2
trace2 = []
for q in Types:
    trace2.append(go.Bar(
        x=median_price_new.sort_values([q], ascending=False).head(10)[q],
        y=median_price_new.sort_values([q], ascending=False).head(10)['Suburb_name_geojson'].str.title().tolist(),
        xaxis='x2',
        yaxis='y2',
        marker=dict(
            color='rgba(91, 207, 135, 0.3)',

Perishleaf

# add a dropdown menu in the layout
layout.update(updatemenus=list([
    dict(x=0,
         y=1,
         xanchor='left',
         yanchor='middle',
         buttons=list([
             dict(
                 args=['visible', [True, False, False, False]],
                 label='Property type: Unit buy/M',

Perishleaf

# Suburbs order should be the same as "id" passed to location
for q in Types:
    trace1.append(go.Choroplethmapbox(
        geojson = Sydney_data,
        locations = median_price_new['id'].tolist(),
        z = median_price_new[q].tolist(), 
        colorscale = pl_deep,
        text = suburbs, 
        colorbar = dict(thickness=20, ticklen=3),
        marker_line_width=0, marker_opacity=0.7,