YTest = dataset.YTest
XTrainTransf = dataset.XTrainTransf
XTestTransf = dataset.XTestTransf
lambda_opt = {"alpha": 67.1590893061}
#model_list = {ISTA(), FISTA(), Shooting(), ADMM()}
model_list = {modifiedShooting(DistanceCorrelation())}
ext_data = ".npz"
ext_model = ".pkl"
folder = "AlgorithmResults/"
for model in model_list:
lasso = LASSOEstimator(model)
lasso.set_params(**lambda_opt)
lasso.fit(XTrainTransf,YTrain)
y_pred_test = lasso.predict(XTestTransf)
mse_test = mean_squared_error(YTest, y_pred_test)
print ("mse_test "+model.__class__.__name__,mse_test)
y_pred_train = lasso.predict(XTrainTransf)
mse_train = mean_squared_error(YTrain, y_pred_train)
print("mse_train "+model.__class__.__name__,mse_train)
np.savez(folder+model.__class__.__name__+ext_data, XTrain=XTrain, YTrain = YTrain, mse_test=mse_test, XTest=dataset.XTest, YTest = YTest, y_pred_test=y_pred_test,
XTrainTransf=XTrainTransf, XTestTransf=XTestTransf, mse_train = mse_train)
current_informative = np.intersect1d(ordered_indexes, informative_indexes)
current_not_informative = np.array(list(set(ordered_indexes)-set(current_informative)))
if verbose:
print("informative", len(current_informative), "su", len(ordered_indexes))
print("non informative",len(current_not_informative),"su", len(ordered_indexes))
current_train, current_test = get_current_data(XTrain, XTest, ordered_indexes)
indexes_to_extract.append(ordered_indexes)
model_list = {Shooting(weights)}
ext_data = ".npz"
ext_model = ".pkl"
for model in model_list:
lasso = LASSOEstimator(model)
clf = GridSearchCV(lasso, parameters, fit_params = {"verbose" : False}, cv=3, scoring="mean_squared_error")
clf.fit(current_train, YTrain)
lambda_opt = clf.best_params_
if verbose:
print("best lambda", lambda_opt)
lasso.set_params(**lambda_opt)
lasso.fit(current_train,YTrain)
y_pred_train = lasso.predict(current_train)
mse_train = mean_squared_error(YTrain, y_pred_train)
if verbose:
print("mse_train "+model.__class__.__name__,mse_train)
