err_val = np.zeros((num,num))
err_train = np.zeros((num,num))
# Split training data into subtraining set, validation set
X_tr, y_tr, X_val, y_val = val.split_data(X_train, y_train, frac=frac, seed=seed)
# Filter y values to 0, 1 labels
y_tr_true = mnist_two_filter(y_tr)
y_val_true = mnist_two_filter(y_val)
# Loop over thresholds
for i in range(num):
# Internally loop over lambdas in regularization path
err_val[i,:], err_train[i,:], lams = val.linear_reg_path(X_tr, y_tr_true, X_val,
y_val_true, ri.fit_ridge,
lammax=lammax,
scale=scale,
num=num, error_func=val.loss_01,
thresh=thresh_arr[i], **kwargs)
# Find minimum threshold, lambda from minimum validation error
ind_t,ind_l = np.unravel_index(err_val.argmin(), err_val.shape)
best_lambda = lams[ind_l]
best_thresh = thresh_arr[ind_t]
print("Best lambda:",best_lambda)
print("Best threshold:",best_thresh)
plt.plot(lams,err_val[ind_t,:])
plt.show()
# Fit training set for model parameters using best fit lambda
w0, w = ri.fit_ridge(X_train, y_train_true, lam=best_lambda)
# Set maximum lambda, minimum lambda
lammax = lu.compute_max_lambda(X_train, y_train)
print("Maximum lambda: %.3lf." % lammax)
# Init error arrays
err_val = np.zeros(num)
err_train = np.zeros(num)
# Run a regularization path 1.15
print("Running regularization path for %d lambda bins." % num)
err_val, err_train, lams, nonzeros = val.linear_reg_path(
X_train,
y_train,
X_val,
y_val,
lu.fit_lasso_fast,
lammax=lammax,
scale=2,
num=num,
error_func=val.RMSE,
save_nonzeros=True,
**kwargs)
# Cache results
print("Caching results...")
np.savez(cache,
err_val=err_val,
err_train=err_train,
lams=lams,
nonzeros=nonzeros)
else:
print("Reading from cache...")
frac=frac,
seed=seed)
# Filter y values to 0, 1 labels
y_tr_true = mnist_two_filter(y_tr)
y_val_true = mnist_two_filter(y_val)
# Loop over thresholds
for i in range(num):
# Internally loop over lambdas in regularization path
err_val[i, :], err_train[i, :], lams = val.linear_reg_path(
X_tr,
y_tr_true,
X_val,
y_val_true,
ri.fit_ridge,
lammax=lammax,
scale=scale,
num=num,
error_func=val.loss_01,
thresh=thresh_arr[i],
**kwargs)
# Find minimum threshold, lambda from minimum validation error
ind_t, ind_l = np.unravel_index(err_val.argmin(), err_val.shape)
best_lambda = lams[ind_l]
best_thresh = thresh_arr[ind_t]
print("Best lambda:", best_lambda)
print("Best threshold:", best_thresh)
plt.plot(lams, err_val[ind_t, :])
plt.show()
# Run analysis if answer cache doesn't exist
if not os.path.exists(cache):
print("Cache does not exist, running analysis...")
# Set maximum lambda, minimum lambda
lammax = lu.compute_max_lambda(X_train,y_train)
print("Maximum lambda: %.3lf." % lammax)
# Init error arrays
err_val = np.zeros(num)
err_train = np.zeros(num)
# Run a regularization path 1.15
print("Running regularization path for %d lambda bins." % num)
err_val, err_train, lams, nonzeros = val.linear_reg_path(X_train, y_train, X_val, y_val,
lu.fit_lasso_fast, lammax=lammax, scale=2,
num=num, error_func = val.RMSE,
save_nonzeros=True, **kwargs)
# Cache results
print("Caching results...")
np.savez(cache,err_val=err_val,err_train=err_train,lams=lams,nonzeros=nonzeros)
else:
print("Reading from cache...")
res = np.load(cache)
err_val = res["err_val"]
err_train = res["err_train"]
lams = res["lams"]
nonzeros = res["nonzeros"]
# Find best lambda according to validation error
# and use that to refit training data, test on test data
