def display_results(self):
# Extract scores for plotting
self.cv_mean_scores = [
round(result[1], self.SCORE_DECIMAL_PLACES)
for result in self.results
]
self.test_scores = [
round(result[2], self.SCORE_DECIMAL_PLACES)
for result in self.results
]
self.elapsed_times = [
round(result[3], self.TIME_DECIMAL_PLACES)
for result in self.results
]
create_2_bar_plot(self.classifier_name_shortcut_list,
'Classifier scores',
'Accuracy',
self.cv_mean_scores,
self.test_scores,
'cv means',
'test set',
y_range_tuple=(0, 1),
should_autolabel=True)
create_bar_plot(self.classifier_name_shortcut_list,
'Elapsed training times',
'Time in seconds',
self.elapsed_times,
color='red')
self.print_results_table()
def plot_comparison():
p1 = ['BBC News Summary', 'ArXiv Dataset']
p2 = ''
p3 = 'Celność testowa'
p4 = [0.9809, 0.8542]
p5 = [0.9182, 0.619]
p6 = 'uczenie nadzorowane'
p7 = 'uczenie nienadzorowane'
create_2_bar_plot(p1, p2, p3, p4, p5, p6, p7)
# # Load from disk
# classifier_list = util.load_classifier_list(classifier_name_list,
# CLASSIFIERS_AND_RESULTS_DIR_PATH)
# results = util.load_object(RESULTS_PATH)
# create_cv_test_time_plots(results, classifier_name_shortcut_list)
cv_mean_scores = [round(result[1], SCORE_DECIMAL_PLACES) for result in results]
test_scores = [round(result[2], SCORE_DECIMAL_PLACES) for result in results]
elapsed_times = [round(result[3], TIME_DECIMAL_PLACES) for result in results]
# create_bar_plot(classifier_name_shortcut_list, 'Classifier scores', 'Accuracy',
# cv_mean_scores, y_range_tuple=(0, 1))
create_2_bar_plot(classifier_name_shortcut_list,
'Classifier scores',
'Accuracy',
cv_mean_scores,
test_scores,
'cv means',
'test set',
y_range_tuple=(0, 1),
should_autolabel=False)
create_bar_plot(classifier_name_shortcut_list,
'Elapsed training times',
'Time in seconds',
elapsed_times,
color='red')
# results_df = pd.DataFrame(
# [[classifier_name_shortcut_list[i], results[i][1], results[i][2]] for i in
# range(0, len(results))]).T
results_df = pd.DataFrame([[
# util.save_object(results, RESULTS_PATH)
# util.save_classifier_list(classifier_list, classifier_name_list,
# CLASSIFIERS_AND_RESULTS_DIR_PATH)
return results
results = train_and_save(classifier_list, classifier_name_list, training_data)
mean_scores = [round(result[1], SCORE_DECIMAL_PLACES) for result in results]
test_scores = [round(result[2], SCORE_DECIMAL_PLACES) for result in results]
elapsed_times = [round(result[3], TIME_DECIMAL_PLACES) for result in results]
create_2_bar_plot(classifier_name_shortcut_list,
'Classifier scores',
'Accuracy',
mean_scores,
test_scores,
'cv means',
'test set',
y_range_tuple=(0, 1))
create_bar_plot(classifier_name_shortcut_list,
'Elapsed training times',
'Time in seconds',
elapsed_times,
color='red')
# LR
# CV Accuracy (5-fold): [0.53598633 0.53020957 0.53526308 0.53578329 0.53255054]
# Mean CV Accuracy: 0.5339585613382408 Test Accuracy: 0.5334731505650527
# Time elapsed: 1860.7 seconds