if question == "1":
dataset = load_dataset('nonLinearData.pkl')
X = dataset['X']
y = dataset['y']
Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, random_state=0)
# standard logistic regression
lr = logRegL2(lammy=1)
lr.fit(Xtrain, ytrain)
print("Training error %.3f" % np.mean(lr.predict(Xtrain) != ytrain))
print("Validation error %.3f" % np.mean(lr.predict(Xtest) != ytest))
utils.plotClassifier(lr, Xtrain, ytrain)
utils.savefig("logReg.png")
# kernel logistic regression with a linear kernel
lr_kernel = kernelLogRegL2(kernel_fun=logReg.kernel_linear, lammy=1)
lr_kernel.fit(Xtrain, ytrain)
print("Training error %.3f" %
np.mean(lr_kernel.predict(Xtrain) != ytrain))
print("Validation error %.3f" %
np.mean(lr_kernel.predict(Xtest) != ytest))
utils.plotClassifier(lr_kernel, Xtrain, ytrain)
utils.savefig("logRegLinearKernel.png")
elif question == "1.1":
y_pred = np.zeros(y.size) + utils.mode(y)
error = np.mean(y_pred != y)
print("Mode predictor error: %.3f" % error)
# 3Evaluate decision stump
model = DecisionStumpEquality()
model.fit(X, y)
y_pred = model.predict(X)
error = np.mean(y_pred != y)
print("Decision Stump with inequality rule error: %.3f"
% error)
# Plot result
utils.plotClassifier(model, X, y)
fname = os.path.join("..", "figs", "q6_decisionBoundary.pdf")
plt.xlabel("x-coordinate")
plt.ylabel("y-coordinate")
plt.legend()
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
elif question == "6.2":
# Load citiesSmall dataset
with open(os.path.join('..','data','citiesSmall.pkl'), 'rb') as f:
dataset = pickle.load(f)
X = dataset["X"]
y = dataset["y"]
print("KNN with k={} gets validation error of {}".format(
k_test, y_error))
elif question == '3.3':
with open(os.path.join('..', 'data', 'citiesSmall.pkl'), 'rb') as f:
dataset = pickle.load(f)
X = dataset['X']
y = dataset['y']
Xtest = dataset['Xtest']
ytest = dataset['ytest']
k = 1
model = KNN(k)
model.fit(X, y)
utils.plotClassifier(model, X, y)
fname = os.path.join("..", "figs", "q3_3_knn_training.pdf")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
utils.plotClassifier(model, Xtest, ytest)
fname = os.path.join("..", "figs", "q3_3_knn_test.pdf")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
model = KNeighborsClassifier(n_neighbors=1, p=2)
model.fit(X, y)
utils.plotClassifier(model, X, y)
fname = os.path.join("..", "figs",
"q3_3_sklearn_kneighbors_training.pdf")
plt.savefig(fname)
if question == "1":
dataset = load_dataset('nonLinearData.pkl')
X = dataset['X']
y = dataset['y']
Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, random_state=0)
# standard logistic regression
lr = logRegL2(lammy=1)
lr.fit(Xtrain, ytrain)
print("Training error %.3f" % np.mean(lr.predict(Xtrain) != ytrain))
print("Validation error %.3f" % np.mean(lr.predict(Xtest) != ytest))
utils.plotClassifier(lr, Xtrain, ytrain)
utils.savefig("logReg.png")
# kernel logistic regression with a linear kernel
lr_kernel = kernelLogRegL2(kernel_fun=logReg.kernel_linear, lammy=1)
lr_kernel.fit(Xtrain, ytrain)
print("Training error %.3f" %
np.mean(lr_kernel.predict(Xtrain) != ytrain))
print("Validation error %.3f" %
np.mean(lr_kernel.predict(Xtest) != ytest))
utils.plotClassifier(lr_kernel, Xtrain, ytrain)
utils.savefig("logRegLinearKernel.png")
elif question == "1.1":
if question == "1":
dataset = load_dataset('nonLinearData.pkl')
X = dataset['X']
y = dataset['y']
Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, random_state=0)
# standard logistic regression
lr = logRegL2(lammy=1)
lr.fit(Xtrain, ytrain)
print("Training error %.3f" % np.mean(lr.predict(Xtrain) != ytrain))
print("Validation error %.3f" % np.mean(lr.predict(Xtest) != ytest))
utils.plotClassifier(lr, Xtrain, ytrain)
utils.savefig("logReg.png")
# kernel logistic regression with a linear kernel
lr_kernel = kernelLogRegL2(kernel_fun=logReg.kernel_linear, lammy=1)
lr_kernel.fit(Xtrain, ytrain)
print("Training error %.3f" %
np.mean(lr_kernel.predict(Xtrain) != ytrain))
print("Validation error %.3f" %
np.mean(lr_kernel.predict(Xtest) != ytest))
utils.plotClassifier(lr_kernel, Xtrain, ytrain)
utils.savefig("logRegLinearKernel.png")
elif question == "1.1":
if question == "1":
dataset = load_dataset("nonLinearData.pkl")
X = dataset["X"]
y = dataset["y"]
Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, random_state=0)
# standard logistic regression
lr = logRegL2(lammy=1)
lr.fit(Xtrain, ytrain)
print("Training error %.3f" % np.mean(lr.predict(Xtrain) != ytrain))
print("Validation error %.3f" % np.mean(lr.predict(Xtest) != ytest))
utils.plotClassifier(lr, Xtrain, ytrain)
utils.savefig("logReg.png")
# kernel logistic regression with a linear kernel
lr_kernel = kernelLogRegL2(kernel_fun=logReg.kernel_linear, lammy=1)
lr_kernel.fit(Xtrain, ytrain)
print("Training error %.3f" %
np.mean(lr_kernel.predict(Xtrain) != ytrain))
print("Validation error %.3f" %
np.mean(lr_kernel.predict(Xtest) != ytest))
utils.plotClassifier(lr_kernel, Xtrain, ytrain)
utils.savefig("logRegLinearKernel.png")
elif question == "1.1":
if question == "1":
dataset = load_dataset('nonLinearData.pkl')
X = dataset['X']
y = dataset['y']
Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, random_state=0)
# standard logistic regression
lr = logRegL2(lammy=1)
lr.fit(Xtrain, ytrain)
print("Training error %.3f" % np.mean(lr.predict(Xtrain) != ytrain))
print("Validation error %.3f" % np.mean(lr.predict(Xtest) != ytest))
utils.plotClassifier(lr, Xtrain, ytrain)
utils.savefig("logReg.png")
# kernel logistic regression with a linear kernel
lr_kernel = kernelLogRegL2(kernel_fun=logReg.kernel_linear, lammy=1)
lr_kernel.fit(Xtrain, ytrain)
print("Training error %.3f" %
np.mean(lr_kernel.predict(Xtrain) != ytrain))
print("Validation error %.3f" %
np.mean(lr_kernel.predict(Xtest) != ytest))
utils.plotClassifier(lr_kernel, Xtrain, ytrain)
utils.savefig("logRegLinearKernel.png")
elif question == "1.1":
