notebook.community

Edit and run 





In [78]:



    


import graphlab



    











In [79]:



    


graphlab.canvas.set_target('ipynb')



    











In [80]:



    


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



    











In [81]:



    


homeData



    


















    
Out[81]:








    

        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.

Question -1

Find the zip code with the highest average house sales price (from the earlier work sheet) and within the houses in that zip code, compute the average price





In [82]:



    


import graphlab.aggregate as agg
homeData.groupby(key_columns='zipcode',operations={'avg_sales_price' : agg.MEAN('price')})



    


















    
Out[82]:








    

        zipcode
        avg_sales_price
    

    

        98033
        803719.532407
    

    

        98032
        251296.24
    

    

        98065
        527961.203226
    

    

        98077
        682774.878788
    

    

        98144
        594547.641399
    

    

        98136
        551688.673004
    

    

        98115
        619900.5506
    

    

        98075
        790576.668524
    

    

        98034
        521652.858716
    

    

        98058
        353608.635165
    



[70 rows x 2 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 [83]:



    


import numpy as np
np.average(homeData.filter_by(['98033'],'zipcode')['price'])



    


















    
Out[83]:








803719.53240740742

















In [84]:



    


def is_valid_home(sqft):
    return (sqft >2000) & (sqft <4000)



    











In [85]:



    


q2homes = homeData[homeData['sqft_living'].apply(lambda x : is_valid_home(x))]



    











In [86]:



    


len(q2homes)



    


















    
Out[86]:








9111

















In [87]:



    


len(homeData)



    


















    
Out[87]:








21613

















In [88]:



    


(len(q2homes)/float(len(homeData)))*100



    


















    
Out[88]:








42.155184379771434

















In [89]:



    


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 
]

Create the test train split





In [90]:



    


train_data, test_data = homeData.random_split(0.7,seed=0)



    











In [91]:



    


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



    











In [92]:



    


my_features_model = graphlab.linear_regression.create(train_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.

PROGRESS: Linear regression:
PROGRESS: --------------------------------------------------------
PROGRESS: Number of examples          : 14542
PROGRESS: Number of features          : 6
PROGRESS: Number of unpacked features : 6
PROGRESS: Number of coefficients    : 115
PROGRESS: Starting Newton Method
PROGRESS: --------------------------------------------------------
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+
PROGRESS: | Iteration | Passes   | Elapsed Time | Training-max_error | Validation-max_error | Training-rmse | Validation-rmse |
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+
PROGRESS: | 1         | 2        | 0.029961     | 3727238.710196     | 1017359.987928       | 180643.719657 | 143067.739283   |
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+

















In [93]:



    


adv_feature_model =  graphlab.linear_regression.create(train_data,target='price',features=advanced_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.

PROGRESS: Linear regression:
PROGRESS: --------------------------------------------------------
PROGRESS: Number of examples          : 14430
PROGRESS: Number of features          : 18
PROGRESS: Number of unpacked features : 18
PROGRESS: Number of coefficients    : 127
PROGRESS: Starting Newton Method
PROGRESS: --------------------------------------------------------
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+
PROGRESS: | Iteration | Passes   | Elapsed Time | Training-max_error | Validation-max_error | Training-rmse | Validation-rmse |
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+
PROGRESS: | 1         | 2        | 0.039397     | 3455720.025271     | 1406097.524156       | 152565.847787 | 137216.740082   |
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+

















In [94]:



    


print my_features_model.evaluate(test_data)



    


















    






{'max_error': 5280200.637821782, 'rmse': 197354.96729077716}

















In [95]:



    


print adv_feature_model.evaluate(test_data)



    


















    






{'max_error': 5097978.206195663, 'rmse': 175532.00695222418}

















In [96]:



    


my_features_model.evaluate(test_data).get('rmse')- adv_feature_model.evaluate(test_data).get('rmse')



    


















    
Out[96]:








21822.960338552977

















In [97]:



    


train_data_1, test_data_1 = homeData.random_split(0.8,seed=0)
my_features_model_1 = graphlab.linear_regression.create(train_data_1,target = 'price',features=my_features)
adv_feature_model_1 =  graphlab.linear_regression.create(train_data_1,target='price',features=advanced_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.

PROGRESS: Linear regression:
PROGRESS: --------------------------------------------------------
PROGRESS: Number of examples          : 16455
PROGRESS: Number of features          : 6
PROGRESS: Number of unpacked features : 6
PROGRESS: Number of coefficients    : 115
PROGRESS: Starting Newton Method
PROGRESS: --------------------------------------------------------
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+
PROGRESS: | Iteration | Passes   | Elapsed Time | Training-max_error | Validation-max_error | Training-rmse | Validation-rmse |
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+
PROGRESS: | 1         | 2        | 0.030532     | 3743119.706075     | 2061742.555508       | 182260.544700 | 176889.975691   |
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+
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.

PROGRESS: Linear regression:
PROGRESS: --------------------------------------------------------
PROGRESS: Number of examples          : 16480
PROGRESS: Number of features          : 18
PROGRESS: Number of unpacked features : 18
PROGRESS: Number of coefficients    : 127
PROGRESS: Starting Newton Method
PROGRESS: --------------------------------------------------------
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+
PROGRESS: | Iteration | Passes   | Elapsed Time | Training-max_error | Validation-max_error | Training-rmse | Validation-rmse |
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+
PROGRESS: | 1         | 2        | 0.037638     | 3474016.382253     | 1394980.351903       | 154597.533311 | 155621.449739   |
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+

















In [98]:



    


print my_features_model_1.evaluate(test_data_1)
print adv_feature_model_1.evaluate(test_data_1)



    


















    






{'max_error': 3464315.0413833335, 'rmse': 179142.60767619964}
{'max_error': 3558676.7762994887, 'rmse': 156717.7897720566}

















In [99]:



    


my_features_model_1.evaluate(test_data_1).get('rmse')- adv_feature_model_1.evaluate(test_data_1).get('rmse')



    


















    
Out[99]:








22424.81790414304

















In [ ]:

Content source: satishkt/ML-Foundations-Coursera

Similar notebooks:

notebook.community | gallery | about