leg0 = []
leg1 = []
for i, outvec in enumerate(output_VEC):
trainRMSE, testRMSE = A.getTrainTestDependence(outvec)
ax[0].plot(variable,
testRMSE,
linestyle=linestyles[i],
linewidth=3,
marker='.',
markersize=8)
leg0.append(feature_opt_vec[i])
# Coefficients Dependence Multi
featarray, relevant_feats = A.getCoefDependence(outvec,
threshold=0.01,
invert_sign=True)
for j in range(len(relevant_feats)):
ax[1].plot(variable,
featarray[:, j],
linestyle=styles[i][0],
marker=styles[i][1],
linewidth=2.5,
markersize=7)
leg = ax[1].legend(latexify_varcoef(relevant_feats, cdf=False),
bbox_to_anchor=(.98, 1),
fontsize=14)
ax[0].set_xlabel(xlabel, fontsize=14)
ax[0].set_ylabel('RMSE', fontsize=14)
ax[0].legend(leg0)
linestyles = ['solid', 'dashed', 'dashdot', 'dotted']
marker = ['o', 'v', 's',
'*'] #, '^', '>', '<', 'x', 'D', '1', '.', '2', '3', '4']
styles = [[l, m] for l in linestyles for m in marker]
mse = [min(out['alpha_mse_path']) for out in output_vec]
ax[0].plot(variable, testRMSE, '.-', linewidth=3, markersize=8)
# ax[0].plot(variable, mse, '*-', linewidth=3, markersize=8)
ax[0].set_xlabel('$N_{MC}$, Number of Realizations', fontsize=14)
ax[0].set_ylabel('RMSE on $\mathcal D_\t{test}$', fontsize=14)
# ax[0].legend(['Test Error', 'MSE'])
# Coefficients Dependence Multi
featarray, relevant_feats = A.getCoefDependence(output_vec,
threshold=threshold,
invert_sign=invert_sign)
for i in range(len(relevant_feats)):
ax[1].plot(variable,
featarray[:, i],
linestyle=styles[i][0],
marker=styles[i][1],
linewidth=2.5,
markersize=7)
ax[1].set_xlabel('$N_{MC}$, Number of Realizations', fontsize=14)
ax[1].set_ylabel('Coefficients', fontsize=14)
leg = ax[1].legend(latexify_varcoef(relevant_feats, cdf=cdf),
bbox_to_anchor=(1, 1),
fontsize=14)
leg.get_frame().set_linewidth(0.0)