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

first push to github

This commit is contained in:
Alejandro Moreo Fernandez 2023-12-17 20:14:38 +01:00
parent 59500a5a42
commit 9bdc7676d6
6 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
distribution_matching/commons.py
View File

@ -10,16 +10,16 @@ from sklearn.linear_model import LogisticRegression
# set to True to get the full list of methods tested in the paper (reported in the appendix)
# set to False to get the reduced list (shown in the body of the paper)
FULL_METHOD_LIST = True
FULL_METHOD_LIST = False
if FULL_METHOD_LIST:
ADJUSTMENT_METHODS = ['ACC', 'PACC']
DISTR_MATCH_METHODS = ['HDy-OvA', 'DM-T', 'DM-HD', 'KDEy-HD', 'DM-CS', 'KDEy-CS']
MAX_LIKE_METHODS = ['DIR', 'EMQ', 'EMQ-BCTS', 'KDEy-ML', 'KDEx-ML']
MAX_LIKE_METHODS = ['DIR', 'EMQ', 'EMQ-BCTS', 'KDEy-ML']
else:
ADJUSTMENT_METHODS = ['PACC']
DISTR_MATCH_METHODS = ['DM-T', 'DM-HD', 'KDEy-HD', 'DM-CS', 'KDEy-CS']
MAX_LIKE_METHODS = ['EMQ', 'KDEy-ML', 'KDEx-ML']
MAX_LIKE_METHODS = ['EMQ', 'KDEy-ML']
# list of methods to consider
METHODS = ADJUSTMENT_METHODS + DISTR_MATCH_METHODS + MAX_LIKE_METHODS

16
distribution_matching/tables/gen_tables_compact.py
View File

@ -67,11 +67,11 @@ def make_table(tabs, eval, benchmark_groups, benchmark_names, compact=False):
for i, (tab, group, name) in enumerate(zip(tabs, benchmark_groups, benchmark_names)):
tablines = tab.latexTabular(benchmark_replace=nice_bench, endl='\\\\'+ cline, aslines=True)
tablines[0] = tablines[0].replace('\multicolumn{1}{c|}{}', '\\textbf{'+name+'}')
if not compact:
tabular += '\n'.join(tablines)
else:
if compact or len(tab.benchmarks)==1:
# if compact, keep the method names and the average; discard the rest
tabular += tablines[0] + '\n' + tablines[-1] + '\n'
tabular += tablines[0] + '\n' + tablines[1 if len(tab.benchmarks)==1 else -1] + '\n'
else:
tabular += '\n'.join(tablines)
tabular += "\n" + "\\textit{Rank} & " + tab.getRankTable(prec_mean=0 if name.startswith('LeQua') else 1).latexAverage()
if i < (len(tabs) - 1):
@ -158,7 +158,7 @@ def gen_tables_tweet(eval):
def gen_tables_lequa(Methods, task, eval):
# generating table for LeQua-T1A or Lequa-T1B; only one table with two rows, one for MAE, another for MRAE
tab = new_table([f'Average'], Methods)
tab = new_table([task], Methods)
print('Generating table for T1A@Lequa', eval, end='')
dir_results = f'../results/lequa/{task}/{eval}'
@ -168,7 +168,7 @@ def gen_tables_lequa(Methods, task, eval):
if os.path.exists(result_path):
df = pd.read_csv(result_path)
print(f'{method}', end=' ')
tab.add('Average', method, df[eval].values)
tab.add(task, method, df[eval].values)
else:
print(f'MISSING-{method}', end=' ')
print()
@ -186,7 +186,7 @@ if __name__ == '__main__':
tabs.append(gen_tables_uci_multiclass(eval))
tabs.append(gen_tables_lequa(METHODS, 'T1B', eval))
names = ['Tweets', 'UCI-multi', 'LeQua-T1B']
names = ['Tweets', 'UCI-multi', 'LeQua']
table = make_table(tabs, eval, benchmark_groups=tabs, benchmark_names=names)
save_table(f'./latex/multiclass_{eval}.tex', table)
@ -200,7 +200,7 @@ if __name__ == '__main__':
# print uci-bin compacted plus lequa-T1A for the main body
tabs.append(gen_tables_lequa(BIN_METHODS, 'T1A', eval))
table = make_table(tabs, eval, benchmark_groups=tabs, benchmark_names=['UCI-binary', 'LeQua-T1A'], compact=True)
table = make_table(tabs, eval, benchmark_groups=tabs, benchmark_names=['UCI-binary', 'LeQua'], compact=True)
save_table(f'./latex/binary_{eval}.tex', table)
print("[Tables Done] runing latex")

2
examples/uci_experiments.py
View File

@ -116,7 +116,7 @@ def run(experiment):
model,
protocol=APP(test, n_prevalences=21, repeats=100)
)
test_true_prevalence = data.test.prevalence()
test_true_prevalence = data.mixture.prevalence()
evaluate_experiment(true_prevalences, estim_prevalences)
save_results(dataset_name, model_name, run, optim_loss,

2
laboratory/main_tweets_auto.py
View File

@ -48,7 +48,7 @@ if __name__ == '__main__':
csv.write(f'Method\tDataset\tMAE\tMRAE\n')
for data, quantifier, quant_name in gen_methods():
quantifier.fit(data.training)
protocol = UPP(data.test, repeats=100)
protocol = UPP(data.mixture, repeats=100)
report = qp.evaluation.evaluation_report(quantifier, protocol, error_metrics=['mae', 'mrae'], verbose=True)
means = report.mean()
csv.write(f'{quant_name}\t{data.name}\t{means["mae"]:.5f}\t{means["mrae"]:.5f}\n')

2
laboratory/method_dxs.py
View File

@ -133,7 +133,7 @@ if __name__ == '__main__':
csv.write(f'Method\tDataset\tMAE\tMRAE\n')
for data, quantifier, quant_name in gen_methods():
quantifier.fit(data.training)
report = qp.evaluation.evaluation_report(quantifier, APP(data.test, repeats=repeats), error_metrics=['mae','mrae'], verbose=True)
report = qp.evaluation.evaluation_report(quantifier, APP(data.mixture, repeats=repeats), error_metrics=['mae', 'mrae'], verbose=True)
means = report.mean()
csv.write(f'{quant_name}\t{data.name}\t{means["mae"]:.5f}\t{means["mrae"]:.5f}\n')

2
quapy/method/neural.py
View File

@ -38,7 +38,7 @@ class QuaNetTrainer(BaseQuantifier):
>>> # train QuaNet (QuaNet is an alias to QuaNetTrainer)
>>> model = QuaNet(classifier, qp.environ['SAMPLE_SIZE'], device='cuda')
>>> model.fit(dataset.training)
>>> estim_prevalence = model.quantify(dataset.test.instances)
>>> estim_prevalence = model.quantify(dataset.mixture.instances)
:param classifier: an object implementing `fit` (i.e., that can be trained on labelled data),
`predict_proba` (i.e., that can generate posterior probabilities of unlabelled examples) and