In [ ]:

    

import graphlab


    

In [47]:

    

sales = graphlab.SFrame('home_data.gl/')
sales.save('home_sales.csv', format='csv')


    

In [20]:

    

sales


    

    
Out[20]:





    

        
id
        
date
        
price
        
bedrooms
        
bathrooms
        
sqft_living
        
sqft_lot
        
floors
        
waterfront
    
    

        
7129300520
        
2014-10-13 00:00:00+00:00
        
221900
        
3
        
1
        
1180
        
5650
        
1
        
0
    
    

        
6414100192
        
2014-12-09 00:00:00+00:00
        
538000
        
3
        
2.25
        
2570
        
7242
        
2
        
0
    
    

        
5631500400
        
2015-02-25 00:00:00+00:00
        
180000
        
2
        
1
        
770
        
10000
        
1
        
0
    
    

        
2487200875
        
2014-12-09 00:00:00+00:00
        
604000
        
4
        
3
        
1960
        
5000
        
1
        
0
    
    

        
1954400510
        
2015-02-18 00:00:00+00:00
        
510000
        
3
        
2
        
1680
        
8080
        
1
        
0
    
    

        
7237550310
        
2014-05-12 00:00:00+00:00
        
1225000
        
4
        
4.5
        
5420
        
101930
        
1
        
0
    
    

        
1321400060
        
2014-06-27 00:00:00+00:00
        
257500
        
3
        
2.25
        
1715
        
6819
        
2
        
0
    
    

        
2008000270
        
2015-01-15 00:00:00+00:00
        
291850
        
3
        
1.5
        
1060
        
9711
        
1
        
0
    
    

        
2414600126
        
2015-04-15 00:00:00+00:00
        
229500
        
3
        
1
        
1780
        
7470
        
1
        
0
    
    

        
3793500160
        
2015-03-12 00:00:00+00:00
        
323000
        
3
        
2.5
        
1890
        
6560
        
2
        
0
    


    

        
view
        
condition
        
grade
        
sqft_above
        
sqft_basement
        
yr_built
        
yr_renovated
        
zipcode
        
lat
    
    

        
0
        
3
        
7
        
1180
        
0
        
1955
        
0
        
98178
        
47.51123398
    
    

        
0
        
3
        
7
        
2170
        
400
        
1951
        
1991
        
98125
        
47.72102274
    
    

        
0
        
3
        
6
        
770
        
0
        
1933
        
0
        
98028
        
47.73792661
    
    

        
0
        
5
        
7
        
1050
        
910
        
1965
        
0
        
98136
        
47.52082
    
    

        
0
        
3
        
8
        
1680
        
0
        
1987
        
0
        
98074
        
47.61681228
    
    

        
0
        
3
        
11
        
3890
        
1530
        
2001
        
0
        
98053
        
47.65611835
    
    

        
0
        
3
        
7
        
1715
        
0
        
1995
        
0
        
98003
        
47.30972002
    
    

        
0
        
3
        
7
        
1060
        
0
        
1963
        
0
        
98198
        
47.40949984
    
    

        
0
        
3
        
7
        
1050
        
730
        
1960
        
0
        
98146
        
47.51229381
    
    

        
0
        
3
        
7
        
1890
        
0
        
2003
        
0
        
98038
        
47.36840673
    


    

        
long
        
sqft_living15
        
sqft_lot15
    
    

        
-122.25677536
        
1340.0
        
5650.0
    
    

        
-122.3188624
        
1690.0
        
7639.0
    
    

        
-122.23319601
        
2720.0
        
8062.0
    
    

        
-122.39318505
        
1360.0
        
5000.0
    
    

        
-122.04490059
        
1800.0
        
7503.0
    
    

        
-122.00528655
        
4760.0
        
101930.0
    
    

        
-122.32704857
        
2238.0
        
6819.0
    
    

        
-122.31457273
        
1650.0
        
9711.0
    
    

        
-122.33659507
        
1780.0
        
8113.0
    
    

        
-122.0308176
        
2390.0
        
7570.0
    

[21613 rows x 21 columns]
Note: Only the head of the SFrame is printed.
You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns.

In [22]:

    

#graphlab.canvas.set_target('ipynb')
graphlab.canvas.set_target('browser')
sales.show(view="Scatter Plot", x="sqft_living", y="price")


    

    




Canvas is accessible via web browser at the URL: http://localhost:49199/index.html
Opening Canvas in default web browser.

In [26]:

    

training_data, test_data = sales.random_split(.8, seed=0)


    

In [27]:

    

sqft_model = graphlab.linear_regression.create(training_data, target='price', features=['sqft_living'])


    

    




PROGRESS: Creating a validation set from 5 percent of training data. This may take a while.
          You can set ``validation_set=None`` to disable validation tracking.







    





Linear regression:






    





--------------------------------------------------------






    





Number of examples          : 16512






    





Number of features          : 1






    





Number of unpacked features : 1






    





Number of coefficients    : 2






    





Starting Newton Method






    





--------------------------------------------------------






    





+-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+






    





| Iteration | Passes   | Elapsed Time | Training-max_error | Validation-max_error | Training-rmse | Validation-rmse |






    





+-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+






    





| 1         | 2        | 1.023335     | 4365641.724488     | 4291712.138666       | 260723.730443 | 301989.057716   |






    





+-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+






    





SUCCESS: Optimal solution found.






    

In [28]:

    

print test_data['price'].mean()


    

    




543054.042563

In [30]:

    

print sqft_model.evaluate(test_data)


    

    




{'max_error': 4156269.632260985, 'rmse': 255166.23936085022}

In [34]:

    

import matplotlib.pyplot as plt
%matplotlib inline


    

In [38]:

    

plt.plot(test_data['sqft_living'], test_data['price'], '.', test_data['sqft_living'], sqft_model.predict(test_data), '-')


    

    
Out[38]:





[<matplotlib.lines.Line2D at 0x12b0daf10>,
 <matplotlib.lines.Line2D at 0x12b0dafd0>]






    

In [39]:

    

sqft_model.coefficients


    

    
Out[39]:





    

        
name
        
index
        
value
        
stderr
    
    

        
(intercept)
        
None
        
-44260.376647
        
5012.25604189
    
    

        
sqft_living
        
None
        
280.383290636
        
2.20464242972
    

[2 rows x 4 columns]

In [42]:

    

my_features = ['bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot', 'floors', 'zipcode']


    

In [44]:

    

sales[my_features].show()


    

    




Canvas is updated and available in a tab in the default browser.

In [46]:

    

sales.show(view='BoxWhisker Plog', x='zipcode', y='price')


    

    




Canvas is accessible via web browser at the URL: http://localhost:49199/index.html
Opening Canvas in default web browser.

In [48]:

    

my_features_model = graphlab.linear_regression.create(training_data, target='price', features=my_features)


    

    




PROGRESS: Creating a validation set from 5 percent of training data. This may take a while.
          You can set ``validation_set=None`` to disable validation tracking.







    





Linear regression:






    





--------------------------------------------------------






    





Number of examples          : 16517






    





Number of features          : 6






    





Number of unpacked features : 6






    





Number of coefficients    : 115






    





Starting Newton Method






    





--------------------------------------------------------






    





+-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+






    





| Iteration | Passes   | Elapsed Time | Training-max_error | Validation-max_error | Training-rmse | Validation-rmse |






    





+-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+






    





| 1         | 2        | 0.032225     | 2583192.309717     | 3843891.258173       | 180070.429670 | 223368.514934   |






    





+-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+






    





SUCCESS: Optimal solution found.






    

In [51]:

    

print sqft_model.evaluate(test_data)
print my_features_model.evaluate(test_data)


    

    




{'max_error': 4156269.632260985, 'rmse': 255166.23936085022}
{'max_error': 3533892.07212167, 'rmse': 184441.95401202946}

In [52]:

    

house1 = sales[sales['id']=='5309101200']


    

In [53]:

    

house1


    

    
Out[53]:





    

        
id
        
date
        
price
        
bedrooms
        
bathrooms
        
sqft_living
        
sqft_lot
        
floors
        
waterfront
    
    

        
5309101200
        
2014-06-05 00:00:00+00:00
        
620000
        
4
        
2.25
        
2400
        
5350
        
1.5
        
0
    


    

        
view
        
condition
        
grade
        
sqft_above
        
sqft_basement
        
yr_built
        
yr_renovated
        
zipcode
        
lat
    
    

        
0
        
4
        
7
        
1460
        
940
        
1929
        
0
        
98117
        
47.67632376
    


    

        
long
        
sqft_living15
        
sqft_lot15
    
    

        
-122.37010126
        
1250.0
        
4880.0
    

[? rows x 21 columns]
Note: Only the head of the SFrame is printed. This SFrame is lazily evaluated.
You can use sf.materialize() to force materialization.

In [62]:

    

print house1['price']
print sqft_model.predict(house1)
print my_features_model.predict(house1)


    

    




[620000]
[628659.520878457]
[722175.3027128646]

In [63]:

    

house2 = sales[sales['id']=='1925069082']


    

In [64]:

    

house2


    

    
Out[64]:





    

        
id
        
date
        
price
        
bedrooms
        
bathrooms
        
sqft_living
        
sqft_lot
        
floors
        
waterfront
    
    

        
1925069082
        
2015-05-11 00:00:00+00:00
        
2200000
        
5
        
4.25
        
4640
        
22703
        
2
        
1
    


    

        
view
        
condition
        
grade
        
sqft_above
        
sqft_basement
        
yr_built
        
yr_renovated
        
zipcode
        
lat
    
    

        
4
        
5
        
8
        
2860
        
1780
        
1952
        
0
        
98052
        
47.63925783
    


    

        
long
        
sqft_living15
        
sqft_lot15
    
    

        
-122.09722322
        
3140.0
        
14200.0
    

[? rows x 21 columns]
Note: Only the head of the SFrame is printed. This SFrame is lazily evaluated.
You can use sf.materialize() to force materialization.

In [68]:

    

print house2['price']
print sqft_model.predict(house2)
print my_features_model.predict(house2)


    

    




[2200000]
[1256718.091902175]
[1431549.9450503518]

In [69]:

    

bill_gates = {'bedrooms':[8], 
              'bathrooms':[25], 
              'sqft_living':[50000], 
              'sqft_lot':[225000],
              'floors':[4], 
              'zipcode':['98039'], 
              'condition':[10], 
              'grade':[10],
              'waterfront':[1],
              'view':[4],
              'sqft_above':[37500],
              'sqft_basement':[12500],
              'yr_built':[1994],
              'yr_renovated':[2010],
              'lat':[47.627606],
              'long':[-122.242054],
              'sqft_living15':[5000],
              'sqft_lot15':[40000]}


    

In [72]:

    

print sqft_model.predict(graphlab.SFrame(bill_gates))
print my_features_model.predict(graphlab.SFrame(bill_gates))


    

    




[13974904.155132469]
[13471349.617239237]

In [ ]: