In this notebook, you will implement ridge regression via gradient descent. You will:
Make sure you have the latest version of GraphLab Create (>= 1.7)
import graphlab as gl
Dataset is from house sales in King County, the region where the city of Seattle, WA is located.
sales = gl.SFrame('data/kc_house_data.gl/')
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-7-efee2ee478f2> in <module>() ----> 1 sales = gl.SFrame('data/kc_house_data.gl/') AttributeError: 'module' object has no attribute 'SFrame'
If we want to do any "feature engineering" like creating new features or adjusting existing ones we should do this directly using the SFrames as seen in the first notebook of Week 2. For this notebook, however, we will work with the existing features.
def calcRSS(model, features, output):
predict = model.predict(features)
error = output - predict
rss = np.sum(np.square(error))
return rss
As in Week 2, we convert the SFrame into a 2D Numpy array. Copy and paste get_numpy_data()
from the second notebook of Week 2.
import numpy as np # note this allows us to refer to numpy as np instead
def get_numpy_data(data_sframe, features, output):
data_sframe['constant'] = 1 # add a constant column to an SFrame
# prepend variable 'constant' to the features list
features = ['constant'] + features
# select the columns of data_SFrame given by the ‘features’ list into the SFrame ‘features_sframe’
features_sframe = data_sframe[features]
# this will convert the features_sframe into a numpy matrix with GraphLab Create >= 1.7!!
features_matrix = features_sframe.to_numpy()
# assign the column of data_sframe associated with the target to the variable ‘output_sarray’
output_sarray['target']=output
# this will convert the SArray into a numpy array:
output_array = output_sarray.to_numpy() # GraphLab Create>= 1.7!!
return(features_matrix, output_array)
Also, copy and paste the predict_output()
function to compute the predictions for an entire matrix of features given the matrix and the weights:
We are now going to move to computing the derivative of the regression cost function. Recall that the cost function is the sum over the data points of the squared difference between an observed output and a predicted output, plus the L2 penalty term.
Cost(w)
= SUM[ (prediction - output)^2 ]
+ l2_penalty*(w[0]^2 + w[1]^2 + ... + w[k]^2).
Since the derivative of a sum is the sum of the derivatives, we can take the derivative of the first part (the RSS) as we did in the notebook for the unregularized case in Week 2 and add the derivative of the regularization part. As we saw, the derivative of the RSS with respect to w[i]
can be written as:
2*SUM[ error*[feature_i] ].
The derivative of the regularization term with respect to w[i]
is:
2*l2_penalty*w[i].
Summing both, we get
2*SUM[ error*[feature_i] ] + 2*l2_penalty*w[i].
That is, the derivative for the weight for feature i is the sum (over data points) of 2 times the product of the error and the feature itself, plus 2*l2_penalty*w[i]
.
We will not regularize the constant. Thus, in the case of the constant, the derivative is just twice the sum of the errors (without the 2*l2_penalty*w[0]
term).
Recall that twice the sum of the product of two vectors is just twice the dot product of the two vectors. Therefore the derivative for the weight for feature_i is just two times the dot product between the values of feature_i and the current errors, plus 2*l2_penalty*w[i]
.
With this in mind complete the following derivative function which computes the derivative of the weight given the value of the feature (over all data points) and the errors (over all data points). To decide when to we are dealing with the constant (so we don't regularize it) we added the extra parameter to the call feature_is_constant
which you should set to True
when computing the derivative of the constant and False
otherwise.
def feature_derivative_ridge(errors, feature, weight, l2_penalty, feature_is_constant):
# If feature_is_constant is True, derivative is twice the dot product of errors and feature
# Otherwise, derivative is twice the dot product plus 2*l2_penalty*weight
return derivative
To test your feature derivartive run the following:
(example_features, example_output) = get_numpy_data(sales, ['sqft_living'], 'price')
my_weights = np.array([1., 10.])
test_predictions = predict_output(example_features, my_weights)
errors = test_predictions - example_output # prediction errors
# next two lines should print the same values
print feature_derivative_ridge(errors, example_features[:,1], my_weights[1], 1, False)
print np.sum(errors*example_features[:,1])*2+20.
print ''
# next two lines should print the same values
print feature_derivative_ridge(errors, example_features[:,0], my_weights[0], 1, True)
print np.sum(errors)*2.
Now we will write a function that performs a gradient descent. The basic premise is simple. Given a starting point we update the current weights by moving in the negative gradient direction. Recall that the gradient is the direction of increase and therefore the negative gradient is the direction of decrease and we're trying to minimize a cost function.
The amount by which we move in the negative gradient direction is called the 'step size'. We stop when we are 'sufficiently close' to the optimum. Unlike in Week 2, this time we will set a maximum number of iterations and take gradient steps until we reach this maximum number. If no maximum number is supplied, the maximum should be set 100 by default. (Use default parameter values in Python.)
With this in mind, complete the following gradient descent function below using your derivative function above. For each step in the gradient descent, we update the weight for each feature before computing our stopping criteria.
def ridge_regression_gradient_descent(feature_matrix, output, initial_weights, step_size, l2_penalty, max_iterations=100):
print 'Starting gradient descent with l2_penalty = ' + str(l2_penalty)
weights = np.array(initial_weights) # make sure it's a numpy array
iteration = 0 # iteration counter
print_frequency = 1 # for adjusting frequency of debugging output
#while not reached maximum number of iterations:
iteration += 1 # increment iteration counter
### === code section for adjusting frequency of debugging output. ===
if iteration == 10:
print_frequency = 10
if iteration == 100:
print_frequency = 100
if iteration%print_frequency==0:
print('Iteration = ' + str(iteration))
### === end code section ===
# compute the predictions based on feature_matrix and weights using your predict_output() function
# compute the errors as predictions - output
# from time to time, print the value of the cost function
if iteration%print_frequency==0:
print 'Cost function = ', str(np.dot(errors,errors) + l2_penalty*(np.dot(weights,weights) - weights[0]**2))
for i in xrange(len(weights)): # loop over each weight
# Recall that feature_matrix[:,i] is the feature column associated with weights[i]
# compute the derivative for weight[i].
#(Remember: when i=0, you are computing the derivative of the constant!)
# subtract the step size times the derivative from the current weight
print 'Done with gradient descent at iteration ', iteration
print 'Learned weights = ', str(weights)
return weights
The L2 penalty gets its name because it causes weights to have small L2 norms than otherwise. Let's see how large weights get penalized. Let us consider a simple model with 1 feature:
simple_features = ['sqft_living']
my_output = 'price'
Let us split the dataset into training set and test set. Make sure to use seed=0
:
train_data,test_data = sales.random_split(.8,seed=0)
In this part, we will only use 'sqft_living'
to predict 'price'
. Use the get_numpy_data
function to get a Numpy versions of your data with only this feature, for both the train_data
and the test_data
.
(simple_feature_matrix, output) = get_numpy_data(train_data, simple_features, my_output)
(simple_test_feature_matrix, test_output) = get_numpy_data(test_data, simple_features, my_output)
Let's set the parameters for our optimization:
initial_weights = np.array([0., 0.])
step_size = 1e-12
max_iterations=1000
First, let's consider no regularization. Set the l2_penalty
to 0.0
and run your ridge regression algorithm to learn the weights of your model. Call your weights:
simple_weights_0_penalty
we'll use them later.
Next, let's consider high regularization. Set the l2_penalty
to 1e11
and run your ridge regression algorithm to learn the weights of your model. Call your weights:
simple_weights_high_penalty
we'll use them later.
This code will plot the two learned models. (The blue line is for the model with no regularization and the red line is for the one with high regularization.)
import matplotlib.pyplot as plt
%matplotlib inline
plt.plot(simple_feature_matrix,output,'k.',
simple_feature_matrix,predict_output(simple_feature_matrix, simple_weights_0_penalty),'b-',
simple_feature_matrix,predict_output(simple_feature_matrix, simple_weights_high_penalty),'r-')
Compute the RSS on the TEST data for the following three sets of weights:
Which weights perform best?
*QUIZ QUESTIONS*
sqft_living
that you learned with no regularization, rounded to 1 decimal place? What about the one with high regularization?Let us now consider a model with 2 features: ['sqft_living', 'sqft_living15']
.
First, create Numpy versions of your training and test data with these two features.
model_features = ['sqft_living', 'sqft_living15'] # sqft_living15 is the average squarefeet for the nearest 15 neighbors.
my_output = 'price'
(feature_matrix, output) = get_numpy_data(train_data, model_features, my_output)
(test_feature_matrix, test_output) = get_numpy_data(test_data, model_features, my_output)
We need to re-inialize the weights, since we have one extra parameter. Let us also set the step size and maximum number of iterations.
initial_weights = np.array([0.0,0.0,0.0])
step_size = 1e-12
max_iterations = 1000
First, let's consider no regularization. Set the l2_penalty
to 0.0
and run your ridge regression algorithm to learn the weights of your model. Call your weights:
multiple_weights_0_penalty
Next, let's consider high regularization. Set the l2_penalty
to 1e11
and run your ridge regression algorithm to learn the weights of your model. Call your weights:
multiple_weights_high_penalty
Compute the RSS on the TEST data for the following three sets of weights:
Which weights perform best?
Predict the house price for the 1st house in the test set using the no regularization and high regularization models. (Remember that python starts indexing from 0.) How far is the prediction from the actual price? Which weights perform best for the 1st house?
*QUIZ QUESTIONS*
sqft_living
that you learned with no regularization, rounded to 1 decimal place? What about the one with high regularization?