notebook.community

Edit and run

Fire up graphlab create





In [1]:



    


import graphlab
import numpy as np

Load some house sales data





In [2]:



    


sales = graphlab.SFrame('home_data.gl/')



    


















    






[INFO] graphlab.cython.cy_server: GraphLab Create v2.1 started. Logging: C:\Users\Matheus\AppData\Local\Temp\graphlab_server_1506298119.log.0










    






This non-commercial license of GraphLab Create for academic use is assigned to ms.asilvas1@gmail.com and will expire on September 01, 2018.

















In [3]:



    


sales



    


















    
Out[3]:








    

        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.

Exploring the data for housing sales





In [4]:



    


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

Creating a simple regression model of sqft_living to price





In [5]:



    


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

Build the regression model





In [6]:



    


sqft_model = graphlab.linear_regression.create(train_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          : 16502










    







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        | 1.022825     | 4353807.975556     | 2272374.113520       | 261766.829871 | 284095.366091   |










    







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










    







SUCCESS: Optimal solution found.










    
































Evaluate the simple model
















In [7]:



    


print (test_data['price'].mean())



    


















    






543054.042563

























In [ ]:



    


print (sqft_model.evaluate(test_data))



    


















    






{'max_error': 4147104.6089961585, 'rmse': 255198.9260303043}

























Showing predictions
















In [ ]:



    


import matplotlib.pyplot as plt
%matplotlib inline



    



















In [ ]:



    


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



    



















In [ ]:



    


sqft_model.get('coefficients')



    



















Explore other features in the data
















In [ ]:



    


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



    



















In [ ]:



    


sales[myfeatures].show()



    



















In [ ]:



    


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



    



















Build a regression model with more features
















In [ ]:



    


my_features_model = graphlab.linear_regression.create(train_data, target='price', features=myfeatures)



    



















In [ ]:



    


print(myfeatures)



    



















In [ ]:



    


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



    



















Apply learned models to predict prices of 3 houses
















In [ ]:



    


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



    



















In [ ]:



    


house1



    



































In [ ]:



    


print(house1['price'])



    



















In [ ]:



    


print(sqft_model.predict(house1))



    



















In [ ]:



    


print(my_features_model.predict(house1))



    



















Prediction for a second, fancier house
















In [ ]:



    


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



    



















In [ ]:



    


house2



    



































In [ ]:



    


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



    



















Assignment Task
    

  • Select the houses inside the zipcode that cointains the highest average house sale price
    • 

















In [ ]:



    


highest_price=sales[sales['zipcode']=='98039']
highest_price.head()



    



















In [ ]:



    


np.average(highest_price['price'])



    



















In [ ]:



    


sqft_filter = sales[(sales['sqft_living']>2000) & (sales['sqft_living']<4000)]



    



















In [ ]:



    


float(sqft_filter.num_rows()) / float(sales.num_rows())



    



















In [ ]:



    


advanced_features = [
'bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot', 'floors', 'zipcode',
'condition', # condition of house       
'grade', # measure of quality of construction       
'waterfront', # waterfront property       
'view', # type of view        
'sqft_above', # square feet above ground        
'sqft_basement', # square feet in basement        
'yr_built', # the year built        
'yr_renovated', # the year renovated        
'lat', 'long', # the lat-long of the parcel       
'sqft_living15', # average sq.ft. of 15 nearest neighbors         
'sqft_lot15', # average lot size of 15 nearest neighbors 
]



    



















In [ ]:



    


print(sqft_model.evaluate(test_data))



    



















In [ ]:



    


sqft_model=graphlab.linear_regression.create(train_data,target='price',features=myfeatures)
advanced_model=graphlab.linear_regression.create(train_data, target='price', features=advanced_features)



    



















In [ ]:



    


print(sqft_model.evaluate(test_data))
print(advanced_model.evaluate(test_data))



    



















In [ ]:



    


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



    



















In [ ]:



    


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



    



















In [ ]:



    


#Finished Week 2



    
















    


    

        

            

            

                Content source: mattssilva/UW-Machine-Learning-Specialization
            

            
Similar notebooks:

            

            
                notebook.community |
                gallery |
                about