In [1]:

    

from pathlib import Path
import json
from functools import reduce
import math
import datetime as dt
import pytz 
from itertools import product
from collections import OrderedDict
import time
import sys

import requests
import numpy as np
import pandas as pd
import geopandas as gpd
import shapely.ops as so
import plotly as py
import plotly.offline as po
import plotly.graph_objs as go

import helpers as hp

po.init_notebook_mode(connected=True)
%load_ext autoreload
%autoreload 2


    

In [2]:

    

rents = hp.get_data('rents')
print(rents['quarter'].unique())
rents.head()


    

    




['1993-03-01' '1993-06-01' '1993-09-01' '1993-12-01' '1994-03-01'
 '1994-06-01' '1994-09-01' '1994-12-01' '1995-03-01' '1995-06-01'
 '1995-09-01' '1995-12-01' '1996-03-01' '1996-06-01' '1996-09-01'
 '1996-12-01' '1997-03-01' '1997-06-01' '1997-09-01' '1997-12-01'
 '1998-03-01' '1998-06-01' '1998-09-01' '1998-12-01' '1999-03-01'
 '1999-06-01' '1999-09-01' '1999-12-01' '2000-03-01' '2000-06-01'
 '2000-09-01' '2000-12-01' '2001-03-01' '2001-06-01' '2001-09-01'
 '2001-12-01' '2002-03-01' '2002-06-01' '2002-09-01' '2002-12-01'
 '2003-03-01' '2003-06-01' '2003-09-01' '2003-12-01' '2004-03-01'
 '2004-06-01' '2004-09-01' '2004-12-01' '2005-03-01' '2005-06-01'
 '2005-09-01' '2005-12-01' '2006-03-01' '2006-06-01' '2006-09-01'
 '2006-12-01' '2007-03-01' '2007-06-01' '2007-09-01' '2007-12-01'
 '2008-03-01' '2008-06-01' '2008-09-01' '2008-12-01' '2009-03-01'
 '2009-06-01' '2009-09-01' '2009-12-01' '2010-03-01' '2010-06-01'
 '2010-09-01' '2010-12-01' '2011-03-01' '2011-06-01' '2011-09-01'
 '2011-12-01' '2012-03-01' '2012-06-01' '2012-09-01' '2012-12-01'
 '2013-03-01' '2013-06-01' '2013-09-01' '2013-12-01' '2014-03-01'
 '2014-06-01' '2014-09-01' '2014-12-01' '2015-03-01' '2015-06-01'
 '2015-09-01' '2015-12-01' '2016-03-01' '2016-06-01' '2016-09-01'
 '2016-12-01' '2017-03-01' '2017-06-01' '2017-09-01']






    
Out[2]:







  

    

      

      
au2001
      
property_type
      
#bedrooms
      
quarter
      
rent_count
      
rent_mean
      
rent_geo_mean
      
au_name
      
territory
      
region
      
rental_area
    
  
  

    

      
0
      
500100
      
House
      
2
      
1993-03-01
      
NaN
      
NaN
      
NaN
      
Awanui
      
Far North District
      
Northland
      
Rural Far North
    
    

      
1
      
500100
      
House
      
3
      
1993-03-01
      
NaN
      
NaN
      
NaN
      
Awanui
      
Far North District
      
Northland
      
Rural Far North
    
    

      
2
      
500100
      
House
      
2
      
1993-06-01
      
NaN
      
NaN
      
NaN
      
Awanui
      
Far North District
      
Northland
      
Rural Far North
    
    

      
3
      
500100
      
House
      
3
      
1993-06-01
      
NaN
      
NaN
      
NaN
      
Awanui
      
Far North District
      
Northland
      
Rural Far North
    
    

      
4
      
500100
      
House
      
2
      
1993-09-01
      
NaN
      
NaN
      
NaN
      
Awanui
      
Far North District
      
Northland
      
Rural Far North
    
  

In [3]:

    

# What fraction of rental data do we have by #bedrooms?

def hits(group):
    d = {}
    d['hit_frac'] = group['rent_count'].dropna().shape[0]/group['rent_count'].shape[0]
    return pd.Series(d)

f = hp.aggregate_rents(rents, groupby_cols=('au2001', '#bedrooms'))
cond = f['region'] == 'Auckland'
print('census area units')
print(f[cond].copy().groupby('#bedrooms').apply(hits).reset_index())

f = hp.aggregate_rents(rents, groupby_cols=('rental_area', '#bedrooms'))
cond = f['region'] == 'Auckland'
print('rental area units')
print(f[cond].copy().groupby('#bedrooms').apply(hits).reset_index())


    

    




census area units
  #bedrooms  hit_frac
0         1  0.706250
1         2  0.906977
2         3  0.971510
3         4  0.887608
4        5+  0.371795
rental area units
  #bedrooms  hit_frac
0         1  0.919192
1         2  1.000000
2         3  1.000000
3         4  0.979798
4        5+  0.676768

In [4]:

    

# Probe by territory
f = hp.aggregate_rents(rents, groupby_cols=('quarter', 'territory'))
f.head()


    

    
Out[4]:







  

    

      

      
quarter
      
territory
      
region
      
rent_count
      
rent_geo_mean
      
rent_mean
    
  
  

    

      
0
      
1993-03-01
      
Ashburton District
      
Canterbury
      
11.0
      
109.051015
      
110.090909
    
    

      
1
      
1993-03-01
      
Auckland City
      
Auckland
      
2422.0
      
178.693647
      
193.843931
    
    

      
2
      
1993-03-01
      
Buller District
      
West Coast
      
17.0
      
85.020812
      
87.882353
    
    

      
3
      
1993-03-01
      
Carterton District
      
Wellington
      
22.0
      
90.979874
      
97.045455
    
    

      
4
      
1993-03-01
      
Central Hawke'S Bay District
      
Hawke's Bay
      
10.0
      
114.000000
      
115.000000
    
  

In [5]:

    

# Plot
for region, ff in f.groupby('region'):
    data = []
    for territory, g in ff.groupby('territory'):
        trace = go.Scatter(
          x=g['quarter'], 
          y=g['rent_geo_mean'].round(), 
          name=territory,
        )
        data.append(trace)

    layout = go.Layout(
       height=600,
       title='{!s} geometric mean rents'.format(region),
       yaxis=dict(
           ticksuffix=' $',
       )
    )
    fig = go.Figure(data=data, layout=layout)
    po.iplot(fig)


    

In [ ]: