In [5]:
import graphlab
In [6]:
sales = graphlab.SFrame('home_data.gl/')
In [7]:
sales
Out[7]:
Una correlacion con el sqft de una casa con su precio
In [8]:
graphlab.canvas.set_target('ipynb')
sales.show(view="Scatter Plot", x="sqft_living", y="price")
Crear nuestro training data y nuestro test data
In [9]:
train_data,test_data = sales.random_split(.8,seed=0)
In [10]:
sqft_model = graphlab.linear_regression.create(train_data, target='price', features=['sqft_living'],validation_set=None)
In [11]:
print sqft_model.evaluate(test_data)
RMSE of about \$255,170!
Importar Matplotlib que es una libreria gráfica.
In [12]:
import matplotlib.pyplot as plt
%matplotlib inline
In [13]:
plt.plot(test_data['sqft_living'],test_data['price'],'.',
test_data['sqft_living'],sqft_model.predict(test_data),'-')
Out[13]:
Los puntos azules son nuestros datos y la linea verde es nuestra regresion lineal que usaremos para predecir los precios de las casas.
Abajo estan los coeficientes de la función.
In [14]:
sqft_model.get('coefficients')
Out[14]:
In [15]:
house1 = sales[sales['id']=='5309101200']
In [16]:
sales
Out[16]:
In [26]:
house3 = sales[sales['id'] == '6414100192']
house3
Out[26]:
In [24]:
print house3['price']
In [25]:
print sqft_model.predict(house3)
In [22]:
house2 = sales[sales['id']=='3793500160']
In [23]:
house2['price']
Out[23]:
In [24]:
house2
Out[24]:
In [28]:
print sqft_model.predict(house2)
In [29]:
house3 = sales[sales['id'] == '1321400060']
In [30]:
print house3['price']
In [31]:
print sqft_model.predict(house3)
In [ ]:
In [ ]:
In [ ]: