def prediction(train_features, train_targets, test_features, test_targets):
"""Ridge regression predictions."""
# Test ridge regression predictions.
rr = RidgeRegression(cv='loocv')
reg = rr.find_optimal_regularization(X=train_features, Y=train_targets)
coef = rr.RR(X=train_features, Y=train_targets, omega2=reg)[0]
# Test the model.
sumd = 0.
for tf, tt in zip(test_features, test_targets):
p = (np.dot(coef, tf))
sumd += (p - tt)**2
error = (sumd / len(test_features))**0.5
return error
def test_rr_bootstrap(self):
"""Test ridge regression predictions with bootstrap fitting."""
train_features, train_targets, test_features, test_targets = get_data()
# Test ridge regression predictions.
rr = RidgeRegression(cv='bootstrap')
reg = rr.find_optimal_regularization(X=train_features, Y=train_targets)
coef = rr.RR(X=train_features, Y=train_targets, omega2=reg)[0]
# Test the model.
sumd = 0.
for tf, tt in zip(test_features, test_targets):
p = (np.dot(coef, tf))
sumd += (p - tt)**2
print('Ridge regression prediction:', (sumd / len(test_features))**0.5)
def predict(train_features, train_targets, test_features, test_targets):
"""Function to perform the prediction."""
data = {}
# Set up the ridge regression function.
rr = RidgeRegression(W2=None, Vh=None, cv='loocv')
b = rr.find_optimal_regularization(X=train_features, Y=train_targets)
coef = rr.RR(X=train_features, Y=train_targets, omega2=b)[0]
# Test the model.
sumd = 0.
err = []
for tf, tt in zip(test_features, test_targets):
p = np.dot(coef, tf)
sumd += (p - tt)**2
e = ((p - tt)**2)**0.5
err.append(e)
error = (sumd / len(test_features))**0.5
data['result'] = error
data['size'] = len(train_targets)
return data
# Standardize the training and test data on the same scale.
std = standardize(train_matrix=train, test_matrix=test)
# Standardize the training targets.
train_targets = target_standardize(target)
# Note that predictions will now be made on the standardized scale.
# ## Model example 1 - Ridge regression.
# In[4]:
# Test ridge regression predictions.
rr = RidgeRegression()
reg = rr.find_optimal_regularization(X=std['train'], Y=train_targets['target'])
coef = rr.RR(X=std['train'], Y=train_targets['target'], omega2=reg)[0]
# Test the model.
sumd = 0.
rr_predictions = []
for tf, tt in zip(std['test'], afunc(test)):
p = ((np.dot(coef, tf)) * train_targets['std']) + train_targets['mean']
rr_predictions.append(p)
sumd += (p - tt)**2
# Plotting.
plt3d = plt.figure(0).gca(projection='3d')
# Plot training data.
plt3d.scatter(train[:, 0], train[:, 1], target, color='b')
# Plot exact function.
plt3d.plot_surface(test_x1,
test_x2,
afunc(test).reshape(np.shape(test_x1)),
df_std = (df - df.mean()) / df.std()
df_std.fillna(0.)
parallel_plot(df_std, num=4)
plt.savefig('std.png')
# ## Predictions <a name="predictions"></a>
# [(Back to top)](#head)
#
# We can now try predictions with ridge regression to start. This clearly performs very well with this data. Based on these results, it is unlikely that you would consider moving to more complex models.
# In[13]:
# Set up the ridge regression function.
rr = RidgeRegression(W2=None, Vh=None, cv='loocv')
b = rr.find_optimal_regularization(X=train_features, Y=train_targets)
coef = rr.RR(X=train_features, Y=train_targets, omega2=b)[0]
# Test the model.
sumd = 0.
err = []
pred = []
for tf, tt in zip(test_features, test_targets):
p = np.dot(coef, tf)
pred.append(p)
sumd += (p - tt)**2
e = ((p - tt)**2)**0.5
err.append(e)
error = (sumd / len(test_features))**0.5
print(error)