def setUp(self):
# Usage:
# Constructor for TestRidgeRegression
# Arguments:
# None
# Create an instance of the Convert Numpy class
self.convert_numpy = ConvertNumpy()
# Create an instance of the Linear Regression class
self.ridge_regression = RidgeRegression()
# Create an instance of the Predict Output Class
self.predict_output = PredictOutput()
# Create an instance of the Residual Sum Squares Class
self.residual_sum_squares = ResidualSumSquares()
# Create an instance of the K Fold Cross Validation Class
self.k_fold_cross_validation = KFoldCrossValidation()
# Create a dictionary type to store relevant data types so that our pandas
# will read the correct information
dtype_dict = {'bathrooms':float, 'waterfront':int, 'sqft_above':int, 'sqft_living15':float,
'grade':int, 'yr_renovated':int, 'price':float, 'bedrooms':float, 'zipcode':str,
'long':float, 'sqft_lot15':float, 'sqft_living':float, 'floors':str, 'condition':int,
'lat':float, 'date':str, 'sqft_basement':int, 'yr_built':int, 'id':str, 'sqft_lot':int,
'view':int}
# Create a kc_house_frame that encompasses all test and train data
self.kc_house_frame = pd.read_csv('./unit_tests/test_data/kc_house/kc_house_data.csv', dtype=dtype_dict)
# Create a kc_house_test_frame that encompasses only train data
self.kc_house_train_frame = pd.read_csv('./unit_tests/test_data/kc_house/kc_house_train_data.csv', dtype=dtype_dict)
# Create a kc_house_frames that encompasses only test data
self.kc_test_frames = pd.read_csv('./unit_tests/test_data/kc_house/kc_house_test_data.csv', dtype=dtype_dict)
# Create a kc_house_train_valid_shuffled that encompasses both train and valid data and shuffled
self.kc_house_train_valid_shuffled = pd.read_csv('./unit_tests/test_data/kc_house_with_validation_k_fold/wk3_kc_house_train_valid_shuffled.csv',
dtype=dtype_dict)
def setUp(self):
# Usage:
# Constructor for TestRidgeRegression
# Arguments:
# None
# Create an instance of the Convert Numpy class
self.convert_numpy = ConvertNumpy()
# Create an instance of the Linear Regression class
self.ridge_regression = RidgeRegression()
# Create an instance of the Predict Output Class
self.predict_output = PredictOutput()
# Create an instance of the Residual Sum Squares Class
self.residual_sum_squares = ResidualSumSquares()
# Create an instance of the K Fold Cross Validation Class
self.k_fold_cross_validation = KFoldCrossValidation()
# Create a dictionary type to store relevant data types so that our pandas
# will read the correct information
dtype_dict = {
'bathrooms': float,
'waterfront': int,
'sqft_above': int,
'sqft_living15': float,
'grade': int,
'yr_renovated': int,
'price': float,
'bedrooms': float,
'zipcode': str,
'long': float,
'sqft_lot15': float,
'sqft_living': float,
'floors': str,
'condition': int,
'lat': float,
'date': str,
'sqft_basement': int,
'yr_built': int,
'id': str,
'sqft_lot': int,
'view': int
}
# Create a kc_house_frame that encompasses all test and train data
self.kc_house_frame = pd.read_csv(
'./unit_tests/test_data/kc_house/kc_house_data.csv',
dtype=dtype_dict)
# Create a kc_house_test_frame that encompasses only train data
self.kc_house_train_frame = pd.read_csv(
'./unit_tests/test_data/kc_house/kc_house_train_data.csv',
dtype=dtype_dict)
# Create a kc_house_frames that encompasses only test data
self.kc_test_frames = pd.read_csv(
'./unit_tests/test_data/kc_house/kc_house_test_data.csv',
dtype=dtype_dict)
# Create a kc_house_train_valid_shuffled that encompasses both train and valid data and shuffled
self.kc_house_train_valid_shuffled = pd.read_csv(
'./unit_tests/test_data/kc_house_with_validation_k_fold/wk3_kc_house_train_valid_shuffled.csv',
dtype=dtype_dict)
class TestRidgeRegression(unittest.TestCase):
# Usage:
# Tests for the Linear Regression Class.
def setUp(self):
# Usage:
# Constructor for TestRidgeRegression
# Arguments:
# None
# Create an instance of the Convert Numpy class
self.convert_numpy = ConvertNumpy()
# Create an instance of the Linear Regression class
self.ridge_regression = RidgeRegression()
# Create an instance of the Predict Output Class
self.predict_output = PredictOutput()
# Create an instance of the Residual Sum Squares Class
self.residual_sum_squares = ResidualSumSquares()
# Create an instance of the K Fold Cross Validation Class
self.k_fold_cross_validation = KFoldCrossValidation()
# Create a dictionary type to store relevant data types so that our pandas
# will read the correct information
dtype_dict = {
'bathrooms': float,
'waterfront': int,
'sqft_above': int,
'sqft_living15': float,
'grade': int,
'yr_renovated': int,
'price': float,
'bedrooms': float,
'zipcode': str,
'long': float,
'sqft_lot15': float,
'sqft_living': float,
'floors': str,
'condition': int,
'lat': float,
'date': str,
'sqft_basement': int,
'yr_built': int,
'id': str,
'sqft_lot': int,
'view': int
}
# Create a kc_house_frame that encompasses all test and train data
self.kc_house_frame = pd.read_csv(
'./unit_tests/test_data/kc_house/kc_house_data.csv',
dtype=dtype_dict)
# Create a kc_house_test_frame that encompasses only train data
self.kc_house_train_frame = pd.read_csv(
'./unit_tests/test_data/kc_house/kc_house_train_data.csv',
dtype=dtype_dict)
# Create a kc_house_frames that encompasses only test data
self.kc_test_frames = pd.read_csv(
'./unit_tests/test_data/kc_house/kc_house_test_data.csv',
dtype=dtype_dict)
# Create a kc_house_train_valid_shuffled that encompasses both train and valid data and shuffled
self.kc_house_train_valid_shuffled = pd.read_csv(
'./unit_tests/test_data/kc_house_with_validation_k_fold/wk3_kc_house_train_valid_shuffled.csv',
dtype=dtype_dict)
def test_01_gradient_descent_no_penalty(self):
# Usage:
# Tests the result on gradient descent with low penalty
# Arguments:
# None
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(
self.kc_house_train_frame, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 0.0
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(
feature_matrix, output, initial_weights, step_size, tolerance,
l2_penalty, max_iterations)
# We will use sqft_iving, and sqft_living15
test_features = ['sqft_living']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(
self.kc_test_frames, test_features, test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.predict_output_linear_regression(
test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_linear_regression(
test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(-0.16311351478746433, 5),
round(final_weights[0], 5))
self.assertEquals(round(263.02436896538489, 3),
round(final_weights[1], 3))
# Assert that rss is correct
self.assertEquals(round(275723632153607.72, -5), round(rss, -5))
def test_02_gradient_descent_high_penalty(self):
# Usage:
# Tests the result on gradient descent with high penalty
# Arguments:
# None
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(
self.kc_house_train_frame, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 1e11
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(
feature_matrix, output, initial_weights, step_size, tolerance,
l2_penalty, max_iterations)
# We will use sqft_iving
test_features = ['sqft_living']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(
self.kc_test_frames, test_features, test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.predict_output_linear_regression(
test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_linear_regression(
test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(0.048718475774044, 5),
round(final_weights[0], 5))
self.assertEquals(round(124.57402057376679, 3),
round(final_weights[1], 3))
# Assert that rss is correct
self.assertEquals(round(694654309578537.25, -5), round(rss, -5))
def test_03_gradient_descent_multiple_high_penalty(self):
# Usage:
# Tests the result on gradient descent with high penalty
# Arguments:
# None
# We will use sqft_iving, and sqft_living15
features = ['sqft_living', 'sqft_living15']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(
self.kc_house_train_frame, features, output, 1)
# Create our initial weights
initial_weights = np.array([0.0, 0.0, 0.0])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 1e11
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(
feature_matrix, output, initial_weights, step_size, tolerance,
l2_penalty, max_iterations)
# We will use sqft_iving, and sqft_living15
test_features = ['sqft_living', 'sqft_living15']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(
self.kc_test_frames, test_features, test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.predict_output_linear_regression(
test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_linear_regression(
test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(0.033601165521060711, 5),
round(final_weights[0], 5))
self.assertEquals(round(91.490167574878328, 3),
round(final_weights[1], 3))
self.assertEquals(round(78.437490333967176, 3),
round(final_weights[2], 3))
# Assert that rss is correct
self.assertEquals(round(500408530236718.31, 0), round(rss, 0))
# Look at the first predicted output
self.assertEquals(round(270449.70602770313, 3),
round(predicted_output[0], 3))
# The first output should be 310000 in the test set
self.assertEquals(310000.0, test_output[0])
def test_04_gradient_descent_k_fold(self):
# Usage:
# Tests best l2_penalty for ridge regression using gradient descent
# Arguments:
# None
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Tolerance
tolerance = None
# Max Iterations to Run
max_iterations = 1000
# Number of Folds
folds = 10
# Store Cross Validation results
cross_validation_results = []
# We want to test l2 penalty values in [10^1, 10^2, 10^3, 10^4, ..., 10^11]
for l2_penalty in np.logspace(1, 11, num=11):
# Create a dictionary of model_parameters
model_parameters = {
'step_size': step_size,
'max_iteration': max_iterations,
'initial_weights': initial_weights,
'tolerance': tolerance,
'l2_penalty': l2_penalty
}
# Compute the cross validation results
cross_validation = self.k_fold_cross_validation.k_fold_cross_validation(
folds, self.kc_house_train_frame,
self.ridge_regression.gradient_descent, model_parameters,
output, features)
# Append it into the results
cross_validation_results.append((l2_penalty, cross_validation))
# Lowest Result
lowest = sorted(cross_validation_results, key=lambda x: x[1])[0]
# Assert True that 10000000 is the l2_penalty that gives the lowest cross validation error
self.assertEquals(10000000.0, lowest[0])
# Assert True that is the lowest l2_penalty
self.assertEquals(round(120916225812152.84, 0), round(lowest[1], 0))
def test_05_hill_climbing(self):
# Usage:
# Tests the result on hill climbing
# Arguments:
# None
# We will use sqft_living for our features
features = ['sqft_living']
# Output will be price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(
self.kc_house_train_frame, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 0.0
# Compute our hill climbing value
final_weights = self.ridge_regression.hill_climbing(
feature_matrix, output, initial_weights, step_size, tolerance,
l2_penalty, max_iterations)
# Assert that the weights is correct
self.assertEquals(round(-7.7535764461428101e+70, -68),
round(final_weights[0], -68))
self.assertEquals(round(-1.9293745396177612e+74, -70),
round(final_weights[1], -70))
class TestRidgeRegression(unittest.TestCase):
"""Test for RidgeRegression.
Uses housing data to test RidgeRegression.
Statics:
_multiprocess_can_split_ (bool): Flag for nose tests to run tests in parallel.
"""
_multiprocess_can_split_ = True
def setUp(self):
"""Constructor for TestRidgeRegression.
Loads housing data, and creates training and testing data.
"""
self.convert_numpy = ConvertNumpy()
self.ridge_regression = RidgeRegression()
self.predict_output = PredictOutput()
self.residual_sum_squares = ResidualSumSquares()
self.k_fold_cross_validation = KFoldCrossValidation()
# Create a dictionary type to store relevant data types so that our pandas
# will read the correct information
dtype_dict = {'bathrooms': float, 'waterfront': int, 'sqft_above': int, 'sqft_living15': float,
'grade': int, 'yr_renovated': int, 'price': float, 'bedrooms': float, 'zipcode': str,
'long': float, 'sqft_lot15': float, 'sqft_living': float, 'floors': str, 'condition': int,
'lat': float, 'date': str, 'sqft_basement': int, 'yr_built': int, 'id': str, 'sqft_lot': int,
'view': int}
# Create a kc_house that encompasses all test and train data
self.kc_house = pd.read_csv('./unit_tests/test_data/regression/kc_house/kc_house_data.csv',
dtype=dtype_dict)
# Create a kc_house_test_frame that encompasses only train data
self.kc_house_train = pd.read_csv('./unit_tests/test_data/regression/kc_house/kc_house_train_data.csv',
dtype=dtype_dict)
# Create a kc_house_frames that encompasses only test data
self.kc_house_test = pd.read_csv('./unit_tests/test_data/regression/kc_house/kc_house_test_data.csv',
dtype=dtype_dict)
# Create a kc_house_train_valid_shuffled that encompasses both train and valid data and shuffled
self.kc_house_train_valid_shuffled = pd.read_csv('./unit_tests/test_data/regression/'
'kc_house_with_validation_k_fold/'
'wk3_kc_house_train_valid_shuffled.csv',
dtype=dtype_dict)
def test_01_gradient_descent_no_penalty(self):
"""Tests gradient descent algorithm.
Tests the result on gradient descent with low penalty.
"""
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 0.0
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(feature_matrix, output,
{"initial_weights": initial_weights,
"step_size": step_size,
"tolerance": tolerance,
"l2_penalty": l2_penalty,
"max_iteration": max_iterations})
# We will use sqft_iving, and sqft_living15
test_features = ['sqft_living']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(self.kc_house_test, test_features,
test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.regression(test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_regression(test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(-0.16311351478746433, 5), round(final_weights[0], 5))
self.assertEquals(round(263.02436896538489, 3), round(final_weights[1], 3))
# Assert that rss is correct
self.assertEquals(round(275723632153607.72, -5), round(rss, -5))
def test_02_gradient_descent_high_penalty(self):
"""Tests gradient descent.
Tests the result on gradient descent with high penalty.
"""
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 1e11
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(feature_matrix, output,
{"initial_weights": initial_weights,
"step_size": step_size,
"tolerance": tolerance,
"l2_penalty": l2_penalty,
"max_iteration": max_iterations})
# We will use sqft_iving
test_features = ['sqft_living']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(self.kc_house_test, test_features,
test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.regression(test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_regression(test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(9.7673000000000005, 5), round(final_weights[0], 5))
self.assertEquals(round(124.572, 3), round(final_weights[1], 3))
# Assert that rss is correct
self.assertEquals(round(694642101500000.0, -5), round(rss, -5))
def test_03_gradient_descent_multiple_high_penalty(self):
"""Tests gradient descent.
Tests gradient descent with multiple features, and high penalty.
"""
# We will use sqft_iving, and sqft_living15
features = ['sqft_living', 'sqft_living15']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train, features, output, 1)
# Create our initial weights
initial_weights = np.array([0.0, 0.0, 0.0])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 1e11
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(feature_matrix, output,
{"initial_weights": initial_weights,
"step_size": step_size,
"tolerance": tolerance,
"l2_penalty": l2_penalty,
"max_iteration": max_iterations})
# We will use sqft_iving, and sqft_living15
test_features = ['sqft_living', 'sqft_living15']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(self.kc_house_test, test_features,
test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.regression(test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_regression(test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(6.7429699999999997, 5), round(final_weights[0], 5))
self.assertEquals(round(91.489000000000004, 3), round(final_weights[1], 3))
self.assertEquals(round(78.437490333967176, 3), round(final_weights[2], 3))
# Assert that rss is correct
self.assertEquals(round(500404800500842.0, -5), round(rss, -5))
# Look at the first predicted output
self.assertEquals(round(270453.53000000003, 3), round(predicted_output[0], 3))
# The first output should be 310000 in the test set
self.assertEquals(310000.0, test_output[0])
def test_04_gradient_descent_k_fold(self):
"""Tests gradient descent with K fold cross validation.
Tests best l2_penalty for ridge regression using gradient descent.
"""
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Tolerance
tolerance = None
# Max Iterations to Run
max_iterations = 1000
# Number of Folds
folds = 10
# Store Cross Validation results
cross_validation_results = []
# We want to test l2 penalty values in [10^1, 10^2, 10^3, 10^4, ..., 10^11]
for l2_penalty in np.logspace(1, 11, num=11):
# Create a dictionary of model_parameters
model_parameters = {'step_size': step_size,
'max_iteration': max_iterations,
'initial_weights': initial_weights,
'tolerance': tolerance,
'l2_penalty': l2_penalty}
# Compute the cross validation results
cv = self.k_fold_cross_validation.k_fold_cross_validation(folds, self.ridge_regression.gradient_descent,
model_parameters, {"data": self.kc_house_train,
"output": output,
"features": features})
# Append it into the results
cross_validation_results.append((l2_penalty, cv))
# Lowest Result
lowest = sorted(cross_validation_results, key=lambda x: x[1])[0]
# Assert True that 10000000 is the l2_penalty that gives the lowest cross validation error
self.assertEquals(10000000.0, lowest[0])
# Assert True that is the lowest l2_penalty
self.assertEquals(round(120916225809145.0, 0), round(lowest[1], 0))
def test_05_gradient_ascent(self):
"""Tests gradient ascent.
Tests gradient ascent and compare it with known values.
"""
# We will use sqft_living for our features
features = ['sqft_living']
# Output will be price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 0.0
# Compute our hill climbing value
final_weights = self.ridge_regression.gradient_ascent(feature_matrix, output,
{"initial_weights": initial_weights,
"step_size": step_size,
"tolerance": tolerance,
"l2_penalty": l2_penalty,
"max_iteration": max_iterations})
# Assert that the weights is correct
self.assertEquals(round(-7.7535764461428101e+70, -68), round(final_weights[0], -68))
self.assertEquals(round(-1.9293745396177612e+74, -70), round(final_weights[1], -70))
def test_07_gradient_ascent_high_tolerance(self):
"""Tests gradient ascent.
Tests gradient ascent and compare it with known values.
"""
# We will use sqft_living for our features
features = ['sqft_living']
# Output will be price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = 1
# L2 Penalty
l2_penalty = 0.0
# Compute our hill climbing value
final_weights = self.ridge_regression.gradient_ascent(feature_matrix, output,
{"initial_weights": initial_weights,
"step_size": step_size,
"tolerance": tolerance,
"l2_penalty": l2_penalty,
"max_iteration": max_iterations})
# Assert that the weights is correct
self.assertEquals(0, round(final_weights[0], -68))
self.assertEquals(0, round(final_weights[1], -70))
def test_08_gradient_descent_no_penalty_high_tolerance(self):
"""Tests gradient descent algorithm.
Tests the result on gradient descent with low penalty.
"""
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 100000
# Tolerance
tolerance = 10000000000
# L2 Penalty
l2_penalty = 0.0
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(feature_matrix, output,
{"initial_weights": initial_weights,
"step_size": step_size,
"tolerance": tolerance,
"l2_penalty": l2_penalty,
"max_iteration": max_iterations})
# We will use sqft_iving, and sqft_living15
test_features = ['sqft_living']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(self.kc_house_test, test_features,
test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.regression(test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_regression(test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(0.093859999999999999, 5), round(final_weights[0], 5))
self.assertEquals(round(262.98200000000003, 3), round(final_weights[1], 3))
# Assert that rss is correct
self.assertEquals(round(275724298300000.0, -5), round(rss, -5))
class TestRidgeRegression(unittest.TestCase):
# Usage:
# Tests for the Linear Regression Class.
def setUp(self):
# Usage:
# Constructor for TestRidgeRegression
# Arguments:
# None
# Create an instance of the Convert Numpy class
self.convert_numpy = ConvertNumpy()
# Create an instance of the Linear Regression class
self.ridge_regression = RidgeRegression()
# Create an instance of the Predict Output Class
self.predict_output = PredictOutput()
# Create an instance of the Residual Sum Squares Class
self.residual_sum_squares = ResidualSumSquares()
# Create an instance of the K Fold Cross Validation Class
self.k_fold_cross_validation = KFoldCrossValidation()
# Create a dictionary type to store relevant data types so that our pandas
# will read the correct information
dtype_dict = {'bathrooms':float, 'waterfront':int, 'sqft_above':int, 'sqft_living15':float,
'grade':int, 'yr_renovated':int, 'price':float, 'bedrooms':float, 'zipcode':str,
'long':float, 'sqft_lot15':float, 'sqft_living':float, 'floors':str, 'condition':int,
'lat':float, 'date':str, 'sqft_basement':int, 'yr_built':int, 'id':str, 'sqft_lot':int,
'view':int}
# Create a kc_house_frame that encompasses all test and train data
self.kc_house_frame = pd.read_csv('./unit_tests/test_data/kc_house/kc_house_data.csv', dtype=dtype_dict)
# Create a kc_house_test_frame that encompasses only train data
self.kc_house_train_frame = pd.read_csv('./unit_tests/test_data/kc_house/kc_house_train_data.csv', dtype=dtype_dict)
# Create a kc_house_frames that encompasses only test data
self.kc_test_frames = pd.read_csv('./unit_tests/test_data/kc_house/kc_house_test_data.csv', dtype=dtype_dict)
# Create a kc_house_train_valid_shuffled that encompasses both train and valid data and shuffled
self.kc_house_train_valid_shuffled = pd.read_csv('./unit_tests/test_data/kc_house_with_validation_k_fold/wk3_kc_house_train_valid_shuffled.csv',
dtype=dtype_dict)
def test_01_gradient_descent_no_penalty(self):
# Usage:
# Tests the result on gradient descent with low penalty
# Arguments:
# None
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train_frame, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 0.0
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(feature_matrix, output,
initial_weights, step_size,
tolerance, l2_penalty, max_iterations)
# We will use sqft_iving, and sqft_living15
test_features = ['sqft_living']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(self.kc_test_frames, test_features, test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.predict_output_linear_regression(test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_linear_regression(test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(-0.16311351478746433, 5), round(final_weights[0], 5))
self.assertEquals(round(263.02436896538489, 3), round(final_weights[1], 3))
# Assert that rss is correct
self.assertEquals(round(275723632153607.72, -5), round(rss, -5))
def test_02_gradient_descent_high_penalty(self):
# Usage:
# Tests the result on gradient descent with high penalty
# Arguments:
# None
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train_frame, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 1e11
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(feature_matrix, output,
initial_weights, step_size,
tolerance, l2_penalty, max_iterations)
# We will use sqft_iving
test_features = ['sqft_living']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(self.kc_test_frames, test_features, test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.predict_output_linear_regression(test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_linear_regression(test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(0.048718475774044, 5), round(final_weights[0], 5))
self.assertEquals(round(124.57402057376679, 3), round(final_weights[1], 3))
# Assert that rss is correct
self.assertEquals(round(694654309578537.25, -5), round(rss, -5))
def test_03_gradient_descent_multiple_high_penalty(self):
# Usage:
# Tests the result on gradient descent with high penalty
# Arguments:
# None
# We will use sqft_iving, and sqft_living15
features = ['sqft_living', 'sqft_living15']
# Output will use price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train_frame, features, output, 1)
# Create our initial weights
initial_weights = np.array([0.0, 0.0, 0.0])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 1e11
# Compute our gradient descent value
final_weights = self.ridge_regression.gradient_descent(feature_matrix, output,
initial_weights, step_size,
tolerance, l2_penalty, max_iterations)
# We will use sqft_iving, and sqft_living15
test_features = ['sqft_living', 'sqft_living15']
# Output will be price
test_output = ['price']
# Convert our test pandas frame to numpy
test_feature_matrix, test_output = self.convert_numpy.convert_to_numpy(self.kc_test_frames, test_features, test_output, 1)
# Predict the output of test features
predicted_output = self.predict_output.predict_output_linear_regression(test_feature_matrix, final_weights)
# Compute RSS
rss = self.residual_sum_squares.residual_sum_squares_linear_regression(test_output, predicted_output)
# Assert that the weights is correct
self.assertEquals(round(0.033601165521060711, 5), round(final_weights[0], 5))
self.assertEquals(round(91.490167574878328, 3), round(final_weights[1], 3))
self.assertEquals(round(78.437490333967176, 3), round(final_weights[2], 3))
# Assert that rss is correct
self.assertEquals(round(500408530236718.31, 0), round(rss, 0))
# Look at the first predicted output
self.assertEquals(round(270449.70602770313, 3), round(predicted_output[0], 3))
# The first output should be 310000 in the test set
self.assertEquals(310000.0, test_output[0])
def test_04_gradient_descent_k_fold(self):
# Usage:
# Tests best l2_penalty for ridge regression using gradient descent
# Arguments:
# None
# We will use sqft_living for our features
features = ['sqft_living']
# Output will use price
output = ['price']
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Tolerance
tolerance = None
# Max Iterations to Run
max_iterations = 1000
# Number of Folds
folds = 10
# Store Cross Validation results
cross_validation_results = []
# We want to test l2 penalty values in [10^1, 10^2, 10^3, 10^4, ..., 10^11]
for l2_penalty in np.logspace(1, 11, num=11):
# Create a dictionary of model_parameters
model_parameters = {'step_size': step_size,
'max_iteration': max_iterations,
'initial_weights': initial_weights,
'tolerance': tolerance,
'l2_penalty': l2_penalty}
# Compute the cross validation results
cross_validation = self.k_fold_cross_validation.k_fold_cross_validation(folds,
self.kc_house_train_frame,
self.ridge_regression.gradient_descent,
model_parameters, output, features)
# Append it into the results
cross_validation_results.append((l2_penalty, cross_validation))
# Lowest Result
lowest = sorted(cross_validation_results, key=lambda x: x[1])[0]
# Assert True that 10000000 is the l2_penalty that gives the lowest cross validation error
self.assertEquals(10000000.0, lowest[0])
# Assert True that is the lowest l2_penalty
self.assertEquals(round(120916225812152.84, 0), round(lowest[1], 0))
def test_05_hill_climbing(self):
# Usage:
# Tests the result on hill climbing
# Arguments:
# None
# We will use sqft_living for our features
features = ['sqft_living']
# Output will be price
output = ['price']
# Convert our pandas frame to numpy
feature_matrix, output = self.convert_numpy.convert_to_numpy(self.kc_house_train_frame, features, output, 1)
# Create our initial weights
initial_weights = np.array([0., 0.])
# Step size
step_size = 1e-12
# Max Iterations to Run
max_iterations = 1000
# Tolerance
tolerance = None
# L2 Penalty
l2_penalty = 0.0
# Compute our hill climbing value
final_weights = self.ridge_regression.hill_climbing(feature_matrix, output,
initial_weights, step_size,
tolerance, l2_penalty, max_iterations)
# Assert that the weights is correct
self.assertEquals(round(-7.7535764461428101e+70, -68), round(final_weights[0], -68))
self.assertEquals(round(-1.9293745396177612e+74, -70), round(final_weights[1], -70))