for kk, key in enumerate(test.keys()):
if key in diff_list:
curr_residuals = diff[:, kk]
if key == 'AverageLArQF':
curr_residuals = curr_residuals[
np.abs(curr_residuals) < 1000]
limits = (-1000, 1000)
range = None
else:
curr_residuals = residuals[:, kk]
limits = None
range = (-0.1, 0.1)
rms = utils.nanrms(curr_residuals)
std = stats.tstd(curr_residuals, limits=limits)
std_err = utils.std_error(curr_residuals)
mean = np.mean(curr_residuals)
sem = stats.sem(curr_residuals, nan_policy='omit')
best_to_worst_dict[performance][key]['mean'].append(mean)
best_to_worst_dict[performance][key]['std'].append(std)
best_to_worst_dict[performance][key]['rms'].append(rms)
best_to_worst_dict[performance][key]['std_err'].append(std_err)
best_to_worst_dict[performance][key]['sem'].append(sem)
style_dict = {'best': 'b', 'median': 'g', 'worst': 'r'}
for key in test.keys():
plt.figure()
for performance in performances:
plt.plot(best_to_worst_dict[performance]['latent_space'],
def make_plots(model, train_x, train_y, test_x, test_y, curr_save_folder, model_name):
unit_list = ['[GeV]', '[rad]', '[rad]', '[GeV]']
variable_list = [r'$p_T$', r'$\eta$', r'$\phi$', r'$E$']
line_style = ['--', '-']
colors = ['orange', 'c']
markers = ['*', 's']
model.to('cpu')
# Histograms
idxs = (0, 100000) # Choose events to compare
data = torch.tensor(test_x[idxs[0]:idxs[1]].values, dtype = torch.float)
pred = model(data).detach().numpy()
pred = np.multiply(pred, train_x.std().values)
pred = np.add(pred, train_x.mean().values)
data = np.multiply(data, train_x.std().values)
data = np.add(data, train_x.mean().values)
alph = 0.8
n_bins = 50
for kk in np.arange(4):
plt.figure(kk + 4)
n_hist_data, bin_edges, _ = plt.hist(data[:, kk], color=colors[1], label='Input', alpha=1, bins=n_bins)
n_hist_pred, _, _ = plt.hist(pred[:, kk], color=colors[0], label='Output', alpha=alph, bins=bin_edges)
plt.suptitle(train_x.columns[kk])
plt.xlabel(variable_list[kk] + ' ' + unit_list[kk])
plt.ylabel('Number of events')
ms.sciy()
# plt.yscale('log')
plt.legend()
fig_name = model_name + '_hist_%s' % train_x.columns[kk]
plt.savefig(curr_save_folder + fig_name)
residual_strings = [r'$(p_{T,out} - p_{T,in}) / p_{T,in}$',
r'$(\eta_{out} - \eta_{in}) / \eta_{in}$',
r'$(\phi_{out} - \phi_{in}) / \phi_{in}$',
r'$(E_{out} - E_{in}) / E_{in}$']
residuals = (pred - data.detach().numpy()) / data.detach().numpy()
range = (-.02, .02)
for kk in np.arange(4):
plt.figure()
n_hist_pred, bin_edges, _ = plt.hist(
residuals[:, kk], label='Residuals', linestyle=line_style[0], alpha=alph, bins=100, range=range)
plt.suptitle('Residuals of %s' % train_x.columns[kk])
plt.xlabel(residual_strings[kk]) # (train_x.columns[kk], train_x.columns[kk], train_x.columns[kk]))
plt.ylabel('Number of jets')
ms.sciy()
#plt.yscale('log')
std = np.std(residuals[:, kk])
std_err = utils.std_error(residuals[:, kk])
mean = np.nanmean(residuals[:, kk])
sem = stats.sem(residuals[:, kk], nan_policy='omit')
ax = plt.gca()
plt.text(.75, .8, 'Mean = %f$\pm$%f\n$\sigma$ = %f$\pm$%f' % (mean, sem, std, std_err), bbox={'facecolor': 'white', 'alpha': 0.7, 'pad': 10},
horizontalalignment='center', verticalalignment='center', transform=ax.transAxes, fontsize=18)
fig_name = model_name + '_residual_%s' % train_x.columns[kk]
plt.savefig(curr_save_folder + fig_name)
res_df = pd.DataFrame({'pt': residuals[:, 0], 'eta': residuals[:, 1], 'phi': residuals[:, 2], 'E': residuals[:, 3]})
save = True
# Generate a custom diverging colormap
cmap = sns.diverging_palette(10, 220, as_cmap=True)
#cmap = 'RdBu'
norm = mpl.colors.Normalize(vmin=-1, vmax=1, clip=False)
mappable = mpl.cm.ScalarMappable(norm=norm, cmap=cmap)
group = ['pt', 'eta', 'phi', 'E']
label_kwargs = {'fontsize': 20}
title_kwargs = {"fontsize": 11}
mpl.rcParams['lines.linewidth'] = 1
mpl.rcParams['xtick.labelsize'] = 12
mpl.rcParams['ytick.labelsize'] = 12
group_arr = res_df.values
corr = res_df.corr()
qs = np.quantile(group_arr, q=[.0025, .9975], axis=0)
ndim = qs.shape[1]
ranges = [tuple(qs[:, kk]) for kk in np.arange(ndim)]
figure = corner(group_arr, range=ranges, plot_density=True, plot_contours=True, no_fill_contours=False, #range=[range for i in np.arange(ndim)],
bins=50, labels=group, label_kwargs=label_kwargs, #truths=[0 for kk in np.arange(qs.shape[1])],
show_titles=True, title_kwargs=title_kwargs, quantiles=(0.16, 0.84),
# levels=(1 - np.exp(-0.5), .90), fill_contours=False, title_fmt='.2e')
levels=(1 - np.exp(-0.5), .90), fill_contours=False, title_fmt='.1e')
# # Extract the axes
axes = np.array(figure.axes).reshape((ndim, ndim))
# Loop over the diagonal
linecol = 'r'
linstyl = 'dashed'
# Loop over the histograms
for yi in np.arange(ndim):
for xi in np.arange(yi):
ax = axes[yi, xi]
# Set face color according to correlation
ax.set_facecolor(color=mappable.to_rgba(corr.values[yi, xi]))
cax = figure.add_axes([.87, .4, .04, 0.55])
cbar = plt.colorbar(mappable, cax=cax, format='%.1f', ticks=np.arange(-1., 1.1, 0.2))
cbar.ax.set_ylabel('Correlation', fontsize=20)
if save:
fig_name = 'corner_3d.png'
plt.savefig(curr_save_folder + fig_name)
fig_name = 'hist_%s' % train.columns[kk]
plt.savefig(curr_save_folder + fig_name)
# Residuals
residual_strings = [r'$(p_{T,recon} - p_{T,true}) / p_{T,true}$',
r'$(\eta_{recon} - \eta_{true}) / \eta_{true}$',
r'$(\phi_{recon} - \phi_{true}) / \phi_{true}$',
r'$(E_{recon} - E_{true}) / E_{true}$']
residuals = (pred.detach().numpy() - data.detach().numpy()) / data.detach().numpy()
range = (-.1, .1)
#range=None
for kk in np.arange(len(test.keys())):
plt.figure()
n_hist_pred, bin_edges, _ = plt.hist(
residuals[:, kk], label='Residuals', linestyle=line_style[0], alpha=alph, bins=200, range=range)
plt.suptitle('Residuals of %s' % train.columns[kk])
plt.xlabel(residual_strings[kk]) # (train.columns[kk], train.columns[kk], train.columns[kk]))
plt.ylabel('Number of jets')
ms.sciy()
# plt.yscale('log')
# rms = utils.nanrms(residuals[:, kk])
std = np.std(residuals[:, kk])
std_err = utils.std_error(residuals[:, kk])
mean = np.nanmean(residuals[:, kk])
sem = stats.sem(residuals[:, kk], nan_policy='omit')
ax = plt.gca()
plt.text(.75, .8, 'Mean = %f$\pm$%f\n$\sigma$ = %f$\pm$%f' % (mean, sem, std, std_err), bbox={'facecolor': 'white', 'alpha': 0.7, 'pad': 10},
horizontalalignment='center', verticalalignment='center', transform=ax.transAxes, fontsize=18)
fig_name = 'residual_%s' % train.columns[kk]
plt.savefig(curr_save_folder + fig_name)
mjj_z = np.array(mjj_z_list)
mjj_z = mjj_z[mjj_z > -1e10]
range = (-20, 3000)
n_hist_data, bin_edges, _ = plt.hist(mjj_orig, bins=100, color='c', label='Original', range=range, density=False)
plt.hist(mjj_z, bins=bin_edges, color='orange', alpha=0.8, label='AE output', range=range, density=False)
plt.legend()
plt.xlabel('$m_{jj}$')
plt.ylabel('Number of jets')
plt.suptitle('%dD latent space' % latent_dim)
#plt.yscale('log')
ms.sciy()
std_orig = np.std(mjj_orig)
std_z = np.std(mjj_z)
std_err_orig = utils.std_error(mjj_orig)
std_err_z = utils.std_error(mjj_z)
mean_orig = np.mean(mjj_orig)
mean_z = np.mean(mjj_z)
sem_orig = stats.sem(mjj_orig, nan_policy='omit')
sem_z = stats.sem(mjj_z, nan_policy='omit')
ax = plt.gca()
plt.text(.75, .6, 'Original\nMean=%f$\pm$%f\n$\sigma$=%f$\pm$%f' % (mean_orig, sem_orig, std_orig, std_err_orig), bbox={'facecolor': 'white', 'alpha': 0.7, 'pad': 10},
horizontalalignment='center', verticalalignment='center', transform=ax.transAxes, fontsize=20)
plt.text(.75, .4, 'AE output\nMean=%f$\pm$%f\n$\sigma$=%f$\pm$%f' % (mean_z, sem_z, std_z, std_err_z), bbox={'facecolor': 'white', 'alpha': 0.7, 'pad': 10},
horizontalalignment='center', verticalalignment='center', transform=ax.transAxes, fontsize=20)
if save:
plt.savefig('mjj_%d_z%d_decompressed.png' % (sample, latent_dim))
if not save: