def vis_rocs():
data = io.loadmat(
'D:/WashU/2020SPR/CSE517 Machine Learning/data/data_train_default.mat')
X = data['X']
Y = data['Y']
xTr, xTv, yTr, yTv = valsplit(X, Y)
MAXITER = 100
STEPSIZE = 1e-01
# %% Ridge Regression
d, n = xTr.shape
f = lambda w: ridge(w, xTr, yTr, 0.1)
ws = grdescent(f, np.zeros((d, 1)), STEPSIZE, MAXITER)
preds = linearmodel(ws, xTv)
fpr, tpr, sqauc = area_under_roc_curve(yTv, preds)
plt.plot(fpr, tpr, color="blue", linewidth=2.0, label="ridge")
# %% Hinge Loss
d, n = xTr.shape
f = lambda w: hinge(w, xTr, yTr, 0.1)
wh = grdescent(f, np.zeros((d, 1)), STEPSIZE, MAXITER)
preds = linearmodel(wh, xTv)
fpr, tpr, hinauc = area_under_roc_curve(yTv, preds)
plt.plot(fpr, tpr, color="green", linewidth=2.0, label="hinge")
# %% Logistic Regression
d, n = xTr.shape
f = lambda w: logistic(w, xTr, yTr)
wl = grdescent(f, np.zeros((d, 1)), STEPSIZE, MAXITER)
preds = linearmodel(wl, xTv)
fpr, tpr, logauc = area_under_roc_curve(yTv, preds)
plt.plot(fpr, tpr, color="red", linewidth=2.0, label="logistic")
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.legend(loc='upper right')
print("Hinge loss: Area under the curve: %.2f" % hinauc)
print("Logistic loss: Area under the curve: %.2f" % logauc)
print("Squared loss: Area under the curve: %.2f" % sqauc)
plt.show()
return
def trainspamfilter(xTr, yTr):
# INPUT:
# xTr, yTr
#
# OUTPUT: w_trained
#
# Consider optimizing the input parameters for your loss and GD!
f = lambda w: hinge(w, xTr, yTr, 0.001)
# f = lambda w : logistic(w, xTr, yTr, 0.0001)
# f = lambda w : ridge(w, xTr, yTr, 0.09)
w_trained = grdescent(f, np.zeros((xTr.shape[0], 1)), 1e-04, 1000)
io.savemat('w_trained.mat', mdict={'w': w_trained})
return w_trained
def trainspamfilter(xTr, yTr):
#
# INPUT:
# xTr
# yTr
#
# OUTPUT: w_trained
#
# Feel free to change this code any way you want
f = lambda w: hinge(w, xTr, yTr, .1)
w_trained = grdescent(f, np.zeros((xTr.shape[0], 1)), 1e-06, 2000)
io.savemat('w_trained.mat', mdict={'w': w_trained})
return w_trained
def trainspamfilter(xTr, yTr):
#
# INPUT:
# xTr
# yTr
#
# OUTPUT: w_trained
#
# Consider optimizing the input parameters for your loss and GD!
ridge_params = [1e-02, 1000]
f = lambda w: ridge(w, xTr, yTr, .01)
w_trained = grdescent(f, np.zeros((xTr.shape[0], 1)), 0.001, 1000)
io.savemat('w_trained.mat', mdict={'w': w_trained})
return w_trained
def trainspamfilter(xTr, yTr):
#
# INPUT:
# xTr
# yTr
#
# OUTPUT: w_trained
#
# Feel free to change this code any way you want
# f = lambda w : hinge(w,xTr,yTr,.01)
f = lambda w: ridge(w, xTr, yTr, 1)
w_trained = grdescent(f, np.zeros((xTr.shape[0], 1)), 7e-6, 1000)
# w_trained = grdescent(f, np.random.normal(0,1,(xTr.shape[0],1)), 7e-6, 2000)
io.savemat('w_trained.mat', mdict={'w': w_trained})
return w_trained
