My Report

Heding of level 2

This is a paragrapf of text

Import the data

We import the players dataset:

import pandas as pd
import seaborn as sns
housing = pd.read_csv('data/melb_data.csv')

Visualisation

Let’s add a picture

Table 1: Market Summary by Region

	For Sale	Median Price	Average Price
Regionname
Southern Metropolitan	4695	$1,250,000	$1,372,963
Eastern Metropolitan	1471	$1,010,000	$1,104,080
South-Eastern Metropolitan	450	$850,000	$922,944
Northern Metropolitan	3890	$806,250	$898,171
Western Metropolitan	2948	$793,000	$866,421
Eastern Victoria	53	$670,000	$699,981
Northern Victoria	41	$540,000	$594,829
Western Victoria	32	$400,000	$397,523

Maps of House Locations

import folium
m = folium.Map(location=(-37.814, 144.96332), tiles="cartodb positron")

# Properties over 3.5M
expensive_properties = housing[housing['Price'] > 3500000]

# Loop through the rows to add markers
for index, row in expensive_properties.iterrows():
    
    lat = row['Lattitude']
    lon = row['Longtitude']
    price = row['Price']
    
    # Marker with a formatted pop-up
    folium.Marker(
        location=[lat, lon],
        popup=f"Price: ${price:,}", 
        tooltip="Click for Price"    # shows text when hovering
    ).add_to(m)
m

Make this Notebook Trusted to load map: File -> Trust Notebook

Locations over 3.5 millions

Suburbs Sales Heatmap

import pandas as pd
import folium
import json

# DATA
suburb_counts = housing['Suburb'].value_counts().reset_index()
suburb_counts.columns = ['Suburb', 'Count']
# Keep this! The map file uses "ABBOTSFORD", so we need to match it.
suburb_counts['Suburb'] = suburb_counts['Suburb'].str.upper() 

# LOCAL MAP FILE
with open('data/suburb-2-vic.geojson.txt', 'r') as f:
    geo_json_data = json.load(f)

# Select the suburbs into the data
my_suburbs = set(suburb_counts['Suburb'])

# Keeping ONLY the map shapes that match with the data (LIST)
filtered_features = []
for feature in geo_json_data['features']:
    # Check if this shape's name is in the list of suburbs
    if feature['properties']['vic_loca_2'] in my_suburbs:
        filtered_features.append(feature)

# Clean map only data sububs
geo_json_data['features'] = filtered_features

# MAP from Folium
m2 = folium.Map(location=[-37.8136, 144.9631], zoom_start=10)

folium.Choropleth(
    geo_data=geo_json_data,
    name='choropleth',
    data=suburb_counts,
    columns=['Suburb', 'Count'],
    
    key_on='feature.properties.vic_loca_2', 
    
    fill_color='Reds', #RdYlGn_r 
    fill_opacity=0.7,
    line_opacity=0.2,
    legend_name='Properties for Sale'
).add_to(m2)

m2

Make this Notebook Trusted to load map: File -> Trust Notebook

Suburb Sales Heatmap

Property by Sellers

import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px

px.scatter(housing, 'Suburb', 'Price')

Scatter Graph