Linear Regression - Part 3

In this section, we shall try to apply machine learning to a well known boston dataset.

Real World Examples



In [ ]:

    
from sklearn.datasets import load_boston

data = load_boston()



In [ ]:

    
print(data.DESCR)



In [ ]:

    
data.data[1]



In [ ]:

    
data.target[1]



In [ ]:

    
X = data.data
Y = data.target



In [ ]:

    
from sklearn.dummy import DummyRegressor
dummy_regr = DummyRegressor(strategy="median")
dummy_regr.fit(X, Y)



In [ ]:

    
from sklearn.metrics import mean_squared_error
mean_squared_error(Y, dummy_regr.predict(X))



In [ ]:

    
from sklearn import linear_model
regr = linear_model.LinearRegression()
regr.fit(X, Y)



In [ ]:

    
mean_squared_error(Y, regr.predict(X))



In [1]:

    
from sklearn.svm import LinearSVR
# Step1: create an instance class as `regr`
# Step2: fit the data into class instance



In [ ]:

    
# score
mean_squared_error(Y, regr.predict(X))



In [ ]:

    
from sklearn.ensemble import RandomForestRegressor
# set random_state as zero



In [ ]:

    
# score



In [ ]:



In [ ]: