def main():
# Load the diabetes dataset
diabetes = datasets.load_diabetes()
# Use only one feature
X = np.expand_dims(diabetes.data[:, 2], 1)
# Split the data into training/testing sets
X_train, X_test = np.array(X[:-20]), np.array(X[-20:])
# Split the targets into training/testing sets
y_train, y_test = np.array(diabetes.target[:-20]), np.array(
diabetes.target[-20:])
# Finding regularization constant using cross validation
lowest_error = float("inf")
best_reg_factor = None
print "Finding regularization constant using cross validation:"
k = 10
for regularization_factor in np.arange(0, 0.5, 0.0001):
cross_validation_sets = k_fold_cross_validation_sets(X_train,
y_train,
k=k)
mse = 0
for _X_train, _X_test, _y_train, _y_test in cross_validation_sets:
clf = RidgeRegression(delta=regularization_factor)
clf.fit(_X_train, _y_train)
y_pred = clf.predict(_X_test)
_mse = mean_squared_error(_y_test, y_pred)
mse += _mse
mse /= k
# Print the mean squared error
print "\tMean Squared Error: %s (regularization: %s)" % (
mse, regularization_factor)
# Save reg. constant that gave lowest error
if mse < lowest_error:
best_reg_factor = regularization_factor
lowest_error = mse
# Make final prediction
clf = RidgeRegression(delta=best_reg_factor)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print "Mean squared error: %s (given by reg. factor: %s)" % (
lowest_error, best_reg_factor)
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.plot(X_test[:, 0], y_pred, color='blue', linewidth=3)
plt.show()
def main():
# Load the diabetes dataset
X, y = datasets.make_regression(n_features=1,
n_samples=100,
bias=3,
noise=10)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
# Finding regularization constant using cross validation
lowest_error = float("inf")
best_reg_factor = None
print("Finding regularization constant using cross validation:")
k = 10
for regularization_factor in np.arange(0, 0.3, 0.001):
cross_validation_sets = k_fold_cross_validation_sets(X_train,
y_train,
k=k)
mse = 0
for _X_train, _X_test, _y_train, _y_test in cross_validation_sets:
clf = RidgeRegression(delta=regularization_factor)
clf.fit(_X_train, _y_train)
y_pred = clf.predict(_X_test)
_mse = mean_squared_error(_y_test, y_pred)
mse += _mse
mse /= k
# Print the mean squared error
print("\tMean Squared Error: %s (regularization: %s)" %
(mse, regularization_factor))
# Save reg. constant that gave lowest error
if mse < lowest_error:
best_reg_factor = regularization_factor
lowest_error = mse
# Make final prediction
clf = RidgeRegression(delta=best_reg_factor)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print("Mean squared error: %s (given by reg. factor: %s)" %
(lowest_error, best_reg_factor))
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.plot(X_test[:, 0], y_pred, color='blue', linewidth=3)
plt.title("Ridge Regression (%.2f MSE)" % mse)
plt.show()
def main():
# Load the diabetes dataset
diabetes = datasets.load_diabetes()
# Use only one feature
X = np.expand_dims(diabetes.data[:, 2], 1)
# Split the data into training/testing sets
X_train, X_test = np.array(X[:-20]), np.array(X[-20:])
# Split the targets into training/testing sets
y_train, y_test = np.array(diabetes.target[:-20]), np.array(diabetes.target[-20:])
# Finding regularization constant using cross validation
lowest_error = float("inf")
best_reg_factor = None
print "Finding regularization constant using cross validation:"
k = 10
for regularization_factor in np.arange(0,0.5,0.0001):
cross_validation_sets = k_fold_cross_validation_sets(X_train, y_train, k=k)
mse = 0
for _X_train, _X_test, _y_train, _y_test in cross_validation_sets:
clf = RidgeRegression(delta=regularization_factor)
clf.fit(_X_train, _y_train)
y_pred = clf.predict(_X_test)
_mse = mean_squared_error(_y_test, y_pred)
mse += _mse
mse /= k
# Print the mean squared error
print "\tMean Squared Error: %s (regularization: %s)" % (mse, regularization_factor)
# Save reg. constant that gave lowest error
if mse < lowest_error:
best_reg_factor = regularization_factor
lowest_error = mse
# Make final prediction
clf = RidgeRegression(delta=best_reg_factor)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print "Mean squared error: %s (given by reg. factor: %s)" % (lowest_error, best_reg_factor)
# Plot the results
plt.scatter(X_test[:,0], y_test, color='black')
plt.plot(X_test[:,0], y_pred, color='blue', linewidth=3)
plt.show()
def main():
# Load the diabetes dataset
X, y = datasets.make_regression(n_features=1, n_samples=100, bias=3, noise=10)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
# Finding regularization constant using cross validation
lowest_error = float("inf")
best_reg_factor = None
print ("Finding regularization constant using cross validation:")
k = 10
for regularization_factor in np.arange(0, 0.3, 0.001):
cross_validation_sets = k_fold_cross_validation_sets(
X_train, y_train, k=k)
mse = 0
for _X_train, _X_test, _y_train, _y_test in cross_validation_sets:
clf = RidgeRegression(delta=regularization_factor)
clf.fit(_X_train, _y_train)
y_pred = clf.predict(_X_test)
_mse = mean_squared_error(_y_test, y_pred)
mse += _mse
mse /= k
# Print the mean squared error
print ("\tMean Squared Error: %s (regularization: %s)" % (mse, regularization_factor))
# Save reg. constant that gave lowest error
if mse < lowest_error:
best_reg_factor = regularization_factor
lowest_error = mse
# Make final prediction
clf = RidgeRegression(delta=best_reg_factor)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print ("Mean squared error: %s (given by reg. factor: %s)" % (lowest_error, best_reg_factor))
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.plot(X_test[:, 0], y_pred, color='blue', linewidth=3)
plt.title("Ridge Regression (%.2f MSE)" % mse)
plt.show()