Python for Real Estate

"Maintainable code is more important than clever code." – Guido van Rossum, creator of Python

• Python
• Machine Learning

• A powerful N-dimensional array object.
• Sophisticated (broadcasting) functions.
• Useful linear algebra, Fourier transform, and random number capabilities.

Keras (κέρας) means horn in Greek. It is a reference to a literary image from ancient Greek and Latin literature, first found in the Odyssey, where dream spirits (Oneiroi, singular Oneiros) are divided between those who deceive men with false visions, who arrive to Earth through a gate of ivory, and those who announce a future that will come to pass, who arrive through a gate of horn. It's a play on the words κέρας (horn) / κραίνω (fulfill), and ἐλέφας (ivory) / ἐλεφαίρομαι (deceive).

pip3 install jupyterlab
pip3 install notebook
jupyter notebook

import requests
import json
import numpy as np
import pandas as pd

url = ("https://opendata.vancouver.ca/<endpoint>")
payload = {
  'rows': -1,
  'timezone': 'UTC',
  'pretty': 'true',
  'where': "report_year=2020"
}
response = requests.get(url, params=payload)
records = response.json()

type(records)
list

len(records)
214597

print(json.dumps(records[0], indent=2))

{
  "tax_assessment_year": "2020",
  "street_name": "15TH AVE W",
  "pid": "011-997-851",
  "property_postal_code": "V6K 2Y9",
  "legal_type": "LAND",
  "zone_name": "RS-5",
  "folio": "688078030000",
  "lot": "20",
  "previous_improvement_value": 78800,
  "land_coordinate": "68807803",
  "narrative_legal_line4": null,
  "narrative_legal_line5": null,
  "narrative_legal_line2": "STRICT LOT 526  NEW WESTMINSTER",
  "plan": "VAP3944",
  "narrative_legal_line1": "LOT 20  BLOCK 442  PLAN VAP3944  DI",
  "previous_land_value": 2828000,
  "current_improvement_value": 109000,
  "from_civic_number": null,
  "year_built": "1930",
  "report_year": "2020",
  "neighbourhood_code": "002",
  "zone_category": "One Family Dwelling",
  "big_improvement_year": "1960",
  "tax_levy": null,
  "to_civic_number": "2395",
  "current_land_value": 2494000,
  "district_lot": "526",
  "block": "442",
  "narrative_legal_line3": null
}

dataset = []
for record in records:
      d = dict(record)
      for field in ['year_built']:
          d[field] = int(d[field]) if d[field] else None
      dataset.append(d)

df = pd.DataFrame(dataset)
df = df[~df.isin([0,1])]
df = df.dropna(subset=[
              'tax_assessment_year',
              'current_improvement_value',
              'current_land_value',
              'year_built'])

# First 10 rows
df.head(n=10)

# Columns
df.columns

# Single attribute
df.street_name

# Unlabeled array
df.to_numpy()

# Sort values
df.sort_values(by='current_land_value')

# Create currency converter function
def convert_to_currency(num):
    return '${:,.2f}'.format(num)

# Average land value
convert_to_currency(df.current_land_value.mean())
$1,604,841

# Average improvement value
convert_to_currency(df.current_improvement_value.mean())
$415,351

# Highest land value
convert_to_currency(max(sorted(df.current_land_value)))
$2,759,584,000

# Highest improvement value
convert_to_currency(max(sorted(df.current_improvement_value)))
$693,426,000

import matplotlib.pyplot as plt

zone_counts = df.zone_category.value_counts()
zones = zone_counts.keys().tolist()
zone_list = zone_counts.tolist()

fig = plt.figure(figsize=(20,5))
ax = fig.add_axes([0,0,1,1])
ax.bar(zones, zone_counts)

plt.title("Property Tax Zones", fontsize=20)
plt.xlabel("Zone Category", fontsize=20)
plt.ylabel("Number of Properties", fontsize=20)
plt.xticks(rotation=45, ha='right', fontsize=15)
plt.show()x = df.year_built
y = df.current_land_value + df.current_improvement_value

plt.figure(figsize=(20,5))
plt.title("Assessed Values", fontsize=20)
plt.xlabel("Year", fontsize=20)
plt.ylabel("Price", fontsize=20)
plt.xticks(rotation=45, ha='right', fontsize=15)
plt.scatter(x, y, alpha=0.3, cmap='viridis')