lorenzo.volpi
/
QuaPy
forked from moreo/QuaPy
1
0
Fork 0
Code Pull Requests Activity

updating plots for submission

This commit is contained in:
Alejandro Moreo Fernandez 2021-06-10 09:33:12 +02:00
parent 1aafd10e25
commit 95b21c8bc2
3 changed files with 57 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
TweetSentQuant/gen_plots.py
View File

@ -33,6 +33,12 @@ def plot_error_by_drift(methods, error_name, logscale=False, path=None):
if path is not None:
path = join(path, f'error_by_drift_{error_name}.{plotext}')
method_names, true_prevs, estim_prevs, tr_prevs = gather_results(methods, error_name)
method_order = ['SVM(AE)' if error_name=='ae' else 'SVM(RAE)',
'PCC', 'SVM(KLD)', 'SVM(Q)', 'SVM(NKLD)', 'CC', 'HDy',
'E(PACC)$_\\mathrm{Ptr}$',
'E(PACC)$_\\mathrm{AE}$' if error_name=='ae' else 'E(PACC)$_\\mathrm{RAE}$',
'QuaNet', 'PACC', 'ACC', 'SLD']
qp.plot.error_by_drift(
method_names,
true_prevs,
@ -43,7 +49,8 @@ def plot_error_by_drift(methods, error_name, logscale=False, path=None):
show_std=False,
logscale=logscale,
title=f'Quantification error as a function of distribution shift',
savepath=path
savepath=path,
method_order=method_order
)
@ -52,9 +59,15 @@ def diagonal_plot(methods, error_name, path=None):
if path is not None:
path = join(path, f'diag_{error_name}')
method_names, true_prevs, estim_prevs, tr_prevs = gather_results(methods, error_name)
qp.plot.binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=0, title='Negative', legend=False, show_std=False, savepath=f'{path}_neg.{plotext}')
qp.plot.binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=1, title='Neutral', legend=False, show_std=False, savepath=f'{path}_neu.{plotext}')
qp.plot.binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=2, title='Positive', legend=True, show_std=False, savepath=f'{path}_pos.{plotext}')
method_order = ['SVM(AE)' if error_name == 'ae' else 'SVM(RAE)',
'PCC', 'SVM(KLD)', 'SVM(Q)', 'SVM(NKLD)', 'CC', 'HDy',
'E(PACC)$_\\mathrm{Ptr}$',
'E(PACC)$_\\mathrm{AE}$' if error_name == 'ae' else 'E(PACC)$_\\mathrm{RAE}$',
'QuaNet', 'PACC', 'ACC', 'SLD']
qp.plot.binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=0, title='Negative', legend=False, show_std=False, savepath=f'{path}_neg.{plotext}', method_order=method_order)
qp.plot.binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=1, title='Neutral', legend=False, show_std=False, savepath=f'{path}_neu.{plotext}', method_order=method_order)
qp.plot.binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=2, title='Positive', legend=False, show_std=False, savepath=f'{path}_pos.{plotext}', method_order=method_order)
qp.plot.binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=2, title='Positive', legend=True, show_std=False, savepath=f'{path}_pos.legend.{plotext}', method_order=method_order)
def binary_bias_global(methods, error_name, path=None):
@ -81,15 +94,15 @@ gao_seb_methods = ['cc', 'acc', 'pcc', 'pacc', 'sld', 'svmq', 'svmkld', 'svmnkld
new_methods_ae = ['svmmae' , 'epaccmaeptr', 'epaccmaemae', 'hdy', 'quanet']
new_methods_rae = ['svmmrae' , 'epaccmraeptr', 'epaccmraemrae', 'hdy', 'quanet']
plot_error_by_drift(gao_seb_methods+new_methods_ae, error_name='ae', path=plotdir)
plot_error_by_drift(gao_seb_methods+new_methods_rae, error_name='rae', logscale=True, path=plotdir)
# plot_error_by_drift(gao_seb_methods+new_methods_ae, error_name='ae', path=plotdir)
# plot_error_by_drift(gao_seb_methods+new_methods_rae, error_name='rae', logscale=True, path=plotdir)
diagonal_plot(gao_seb_methods+new_methods_ae, error_name='ae', path=plotdir)
diagonal_plot(gao_seb_methods+new_methods_rae, error_name='rae', path=plotdir)
binary_bias_global(gao_seb_methods+new_methods_ae, error_name='ae', path=plotdir)
binary_bias_global(gao_seb_methods+new_methods_rae, error_name='rae', path=plotdir)
# binary_bias_global(gao_seb_methods+new_methods_ae, error_name='ae', path=plotdir)
# binary_bias_global(gao_seb_methods+new_methods_rae, error_name='rae', path=plotdir)
#
#binary_bias_bins(gao_seb_methods+new_methods_ae, error_name='ae', path=plotdir)
#binary_bias_bins(gao_seb_methods+new_methods_rae, error_name='rae', path=plotdir)

2
TweetSentQuant/gen_tables.py
View File

@ -74,7 +74,7 @@ if __name__ == '__main__':
\\resizebox{\\textwidth}{!}{%
\\begin{tabular}{|c||""" + ('c|' * nold_methods) + '|' + ('c|' * nnew_methods) + """} \hline
& \multicolumn{""" + str(nold_methods) + """}{c||}{Methods tested in~\cite{Gao:2016uq}} &
\multicolumn{""" + str(nnew_methods) + """}{c|}{} \\\\ \hline
\multicolumn{""" + str(nnew_methods) + """}{c|}{Newly added methods} \\\\ \hline
"""
rowreplace={dataset: nicename(dataset) for dataset in datasets}
colreplace={method: nicename(method, eval_name, side=True) for method in methods}

43
quapy/plot.py
View File

@ -13,7 +13,7 @@ plt.rcParams['font.size'] = 16
def binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=1, title=None, show_std=True, legend=True,
train_prev=None, savepath=None):
train_prev=None, savepath=None, method_order=None):
fig, ax = plt.subplots()
ax.set_aspect('equal')
ax.grid()
@ -21,7 +21,15 @@ def binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=1, title=No
method_names, true_prevs, estim_prevs = _merge(method_names, true_prevs, estim_prevs)
for method, true_prev, estim_prev in zip(method_names, true_prevs, estim_prevs):
order = list(zip(method_names, true_prevs, estim_prevs))
if method_order is not None:
table = {method_name:[true_prev, estim_prev] for method_name, true_prev, estim_prev in order}
order = [(method_name, *table[method_name]) for method_name in method_order]
cm = plt.get_cmap('tab20')
NUM_COLORS = len(method_names)
ax.set_prop_cycle(color=[cm(1. * i / NUM_COLORS) for i in range(NUM_COLORS)])
for method, true_prev, estim_prev in order:
true_prev = true_prev[:,pos_class]
estim_prev = estim_prev[:,pos_class]
@ -44,8 +52,12 @@ def binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=1, title=No
if legend:
box = ax.get_position()
ax.set_position([box.x0, box.y0, box.width * 0.8, box.height])
ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))
# ax.set_position([box.x0, box.y0, box.width * 0.8, box.height])
# ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))
# ax.set_position([box.x0, box.y0, box.width * 0.8, box.height])
ax.legend(loc='lower center',
bbox_to_anchor=(1, -0.5),
ncol=(len(method_names)+1)//2)
save_or_show(savepath)
@ -161,7 +173,8 @@ def _merge(method_names, true_prevs, estim_prevs):
def error_by_drift(method_names, true_prevs, estim_prevs, tr_prevs, n_bins=20, error_name='ae', show_std=True,
logscale=False,
title=f'Quantification error as a function of distribution shift',
savepath=None):
savepath=None,
method_order=None):
fig, ax = plt.subplots()
ax.grid()
@ -171,7 +184,8 @@ def error_by_drift(method_names, true_prevs, estim_prevs, tr_prevs, n_bins=20, e
# join all data, and keep the order in which the methods appeared for the first time
data = defaultdict(lambda:{'x':np.empty(shape=(0)), 'y':np.empty(shape=(0))})
method_order = []
if method_order is None:
method_order = []
for method, test_prevs_i, estim_prevs_i, tr_prev_i in zip(method_names, true_prevs, estim_prevs, tr_prevs):
tr_prev_i = np.repeat(tr_prev_i.reshape(1,-1), repeats=test_prevs_i.shape[0], axis=0)
@ -184,10 +198,15 @@ def error_by_drift(method_names, true_prevs, estim_prevs, tr_prevs, n_bins=20, e
if method not in method_order:
method_order.append(method)
print(method_order)
bins = np.linspace(0, 1, n_bins+1)
binwidth = 1 / n_bins
min_x, max_x = None, None
for method in method_order:
min_y, max_y = None, None
cm = plt.get_cmap('tab20')
NUM_COLORS = len(method_order)
ax.set_prop_cycle(color=[cm(1. * i / NUM_COLORS) for i in range(NUM_COLORS)])
for i,method in enumerate(method_order):
tr_test_drifts = data[method]['x']
method_drifts = data[method]['y']
if logscale:
@ -198,7 +217,7 @@ def error_by_drift(method_names, true_prevs, estim_prevs, tr_prevs, n_bins=20, e
for ind in range(len(bins)):
selected = inds==ind
if selected.sum() > 0:
xs.append(ind*binwidth)
xs.append(ind*binwidth-binwidth/2)
ys.append(np.mean(method_drifts[selected]))
ystds.append(np.std(method_drifts[selected]))
@ -207,10 +226,14 @@ def error_by_drift(method_names, true_prevs, estim_prevs, tr_prevs, n_bins=20, e
ystds = np.asarray(ystds)
min_x_method, max_x_method = xs.min(), xs.max()
min_y_method, max_y_method = ys.min(), ys.max()
min_x = min_x_method if min_x is None or min_x_method < min_x else min_x
max_x = max_x_method if max_x is None or max_x_method > max_x else max_x
min_y = min_y_method if min_y is None or min_y_method < min_y else min_y
max_y = max_y_method if max_y is None or max_y_method > max_y else max_y
ax.errorbar(xs, ys, fmt='-', marker='o', label=method, markersize=3, zorder=2)
marker = 'o' #if i < 10 else '^'
ax.errorbar(xs, ys, fmt='-', marker=marker, label=method, markersize=6, zorder=2, linewidth=2.5)
if show_std:
ax.fill_between(xs, ys-ystds, ys+ystds, alpha=0.25)
@ -221,6 +244,8 @@ def error_by_drift(method_names, true_prevs, estim_prevs, tr_prevs, n_bins=20, e
ax.set_position([box.x0, box.y0, box.width * 0.8, box.height])
ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))
ax.set_xlim(min_x, max_x)
ax.fill_between([0.02, 0.1055], min_y, max_y,
facecolor='green', alpha=0.25)
save_or_show(savepath)