Predicting house prices:

import graphlab

# Load some house sales data

sales = graphlab.SFrame("home_data.gl")
sales

  id   date  proce  bedrooms bathrooms sqft_living sqft_lot floors
  view conditions

# Exploring the data for housing

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

#Create a simple regression model of sqft_living to price

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

# Build the regression model

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

# Evaluate the simple model

print test_data['price'].mean()

print sqft_model.evaluate(test_data)

# Let's show what our predictions look like

import mathplotlib.pyplot as plt
%matplotlib inline

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

sqft_model.get('coefficients')

# Explore other features in the data

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

sales[myfeatures].show()

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

# Build a regression model with more features

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

print my_features

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

# Apply learned model to predict prices of 2 houses

house1 = sales(sales['id']=='5309101299']


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

# Prediction for a second, fancier house

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

print sqft_model.predict(house2)

print my_features_model.predict(hourse2)

# Explore more those data!!!