In [2]:

    

import graphlab


    

In [5]:

    

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


    

In [31]:

    

houses_1 = sales[sales['zipcode']=='98039']


    

In [32]:

    

houses_1['price'].mean()


    

    
Out[32]:





2160606.5999999996

In [33]:

    

houses_2 = sales[(sales['sqft_living'] > 2000) & (sales['sqft_living'] < 4000)]


    

In [36]:

    

len(houses_2) / float(len(sales))


    

    
Out[36]:





0.4215518437977143

In [8]:

    

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


    

In [9]:

    

advanced_features = ['bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot', 'floors', 'zipcode', 'condition', 'grade', 'waterfront', 'view', 'sqft_above', 'sqft_basement', 'yr_built', 'yr_renovated', 'lat', 'long', 'sqft_living15', 'sqft_lot15']


    

In [10]:

    

advanced_features_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          : 16510
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        | 1.046632     | 3485902.939104     | 1284169.317824       | 154910.036363 | 149644.352069   |
PROGRESS: +-----------+----------+--------------+--------------------+----------------------+---------------+-----------------+

In [11]:

    

print advanced_features_model.evaluate(test_data)


    

    




{'max_error': 3553409.1030555945, 'rmse': 156714.09846260582}