def different_plots(x_values, y_values, baseline, legend):
"""Tests potentially problematic plot setups."""
plot_multiple_runs(x_values, y_values, labels=legend)
plot_multiple_runs(x_values,
y_values,
labels=legend,
smoothing_window_size=3)
plot_multiple_runs_with_baselines(x_values,
y_values,
baseline,
labels=legend)
plot_multiple_runs_with_baselines(x_values,
y_values,
baseline,
labels=legend,
smoothing_window_size=3)
def plot_save(self,
title,
series,
series_baselines,
ylabel,
labels,
date,
docs_folder,
doc,
smoothing_size: int = None):
"""Baselines are in dotted grey, the model outputs are colored."""
f = plot_multiple_runs_with_baselines(
self._steps[0],
series,
series_baselines,
title=title,
xlabel='Simulation step',
ylim=[0, 1.1],
ylabel=ylabel,
smoothing_window_size=smoothing_size,
labels=labels)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
def publish_results_for_layer(document: Document, docs_folder: str,
measurement_manager: MeasurementManager,
topology_parameters: List[str],
layer_id: int, num_layers: int,
show_conv_agreements: bool,
is_train_test_classifier_computed: bool):
"""Publish results for each layer separately
This uses the data measured and computed for each run by the Task0TaAnalysisLayerComponent and aggregated
and stored in the measurement_manager.
"""
logger.info(f'publishing results for layer {layer_id}...')
num_boosted_clusters = measurement_manager.get_values_from_all_runs(
f'num_boosted_getter_{layer_id}')
average_boosting_dur = measurement_manager.get_values_from_all_runs(
f'average_boosting_dur_{layer_id}')
average_deltas = measurement_manager.get_values_from_all_runs(
f'average_delta_{layer_id}')
base_weak_class_accuracy = measurement_manager.get_custom_data_from_all_runs(
f'base_weak_class_accuracy_{layer_id}')
clustering_agreements = measurement_manager.get_custom_data_from_all_runs(
f'clustering_agreements_{layer_id}')
average_steps_deltas = measurement_manager.get_items_from_all_runs(
f'average_delta_{layer_id}')
sp_evaluation_steps = [key for key, value in average_steps_deltas[0]]
labels = topology_parameters
document.add(f"<br><br><br><b>Results for layer {layer_id}</b><br>")
prefix = 'L' + str(layer_id) + '--'
testing_phase_ids = list(range(0, len(
clustering_agreements[0][0]))) # x-axis values
if is_train_test_classifier_computed:
weak_class_accuracy_train = measurement_manager.get_custom_data_from_all_runs(
f'weak_class_accuracy_train_{layer_id}')
weak_class_accuracy_test = measurement_manager.get_custom_data_from_all_runs(
f'weak_class_accuracy_test_{layer_id}')
title = prefix + ' Weak classifier accuracy (trained on train, tested on train data)'
plot_multiple_runs_with_baselines(testing_phase_ids,
weak_class_accuracy_train,
base_weak_class_accuracy,
title=title,
ylabel='Accuracy (1 ~ 100%)',
xlabel='steps',
labels=labels,
ylim=[-0.1, 1.1],
hide_legend=True,
path=path.join(
docs_folder, title),
doc=document)
title = prefix + ' Weak classifier accuracy (trained on train, tested on test data)'
plot_multiple_runs_with_baselines(testing_phase_ids,
weak_class_accuracy_test,
base_weak_class_accuracy,
title=title,
ylabel='Accuracy (1 ~ 100%)',
xlabel='steps',
labels=labels,
ylim=[-0.1, 1.1],
hide_legend=True,
path=path.join(
docs_folder, title),
doc=document)
weak_class_accuracy = measurement_manager.get_custom_data_from_all_runs(
f'weak_class_accuracy_{layer_id}')
title = prefix + ' Weak classifier accuracy (trained on test, tested on test)'
plot_multiple_runs_with_baselines(testing_phase_ids,
weak_class_accuracy,
base_weak_class_accuracy,
title=title,
ylabel='Accuracy (1 ~ 100%)',
xlabel='steps',
labels=labels,
ylim=[-0.1, 1.1],
hide_legend=True,
path=path.join(docs_folder, title),
doc=document)
title = prefix + '- Average boosting duration'
plot_multiple_runs(sp_evaluation_steps,
average_boosting_dur,
title=title,
ylabel='duration',
xlabel='steps',
labels=labels,
hide_legend=True,
path=path.join(docs_folder, title),
doc=document)
title = prefix + '- Num boosted clusters'
plot_multiple_runs(sp_evaluation_steps,
num_boosted_clusters,
title=title,
ylabel='Num boosted clusters / total clusters',
xlabel='steps',
labels=labels,
ylim=[-0.1, 1.1],
hide_legend=True,
path=path.join(docs_folder, title),
doc=document)
title = prefix + '- Average_deltas'
plot_multiple_runs(
sp_evaluation_steps,
average_deltas,
title=title,
ylabel='average_deltas',
xlabel='steps',
labels=labels,
disable_ascii_labels=True,
hide_legend=True,
# use_scatter=True,
path=path.join(docs_folder, title),
doc=document)
# if this is not the top layer, show conv agreements only if required
if show_conv_agreements or layer_id == (num_layers - 1):
agreements = clustering_agreements
for run_id, run_agreements in enumerate(agreements):
for expert_id, expert_agreements in enumerate(run_agreements):
Task0TaAnalysisTemplate._plot_agreement(
prefix, expert_id, run_id, testing_phase_ids,
expert_agreements, document, docs_folder)
logger.info('done')
def publish_results(self, document: Document, docs_folder: str,
measurement_manager: MeasurementManager,
topology_parameters: List[str]):
"""An alternative to the _publish_results method, this is called from _publish_results now
Draw and add your plots to the document here.
"""
steps = measurement_manager.get_values_from_all_runs('current_step')
plotted_training_phase_id = measurement_manager.get_values_from_all_runs(
'training_phase_id')
plotted_testing_phase_id = measurement_manager.get_values_from_all_runs(
'testing_phase_id')
plotted_is_learning = measurement_manager.get_values_from_all_runs(
'is_learning')
labels = topology_parameters
document.add(
f"<br><br><br><b>Common results from the TopExpert</b><br>")
title = 'training_phase_id'
plot_multiple_runs(steps,
plotted_training_phase_id,
title=title,
ylabel='training_phase_id',
xlabel='steps',
labels=labels,
path=path.join(docs_folder, title),
doc=document)
title = 'testing_phase_id'
plot_multiple_runs(steps,
plotted_testing_phase_id,
title=title,
ylabel='testing_phase_id',
xlabel='steps',
labels=labels,
path=path.join(docs_folder, title),
doc=document)
title = 'is_learning'
plot_multiple_runs(steps,
plotted_is_learning,
title=title,
ylabel='is_learning',
xlabel='steps',
labels=labels,
path=path.join(docs_folder, title),
doc=document)
predicted_labels_mse = measurement_manager.get_custom_data_from_all_runs(
'predicted_labels_mse')
testing_phases_x = list(range(0, len(predicted_labels_mse[0])))
model_accuracy = measurement_manager.get_custom_data_from_all_runs(
'model_accuracy')
baseline_accuracy = measurement_manager.get_custom_data_from_all_runs(
'baseline_accuracy')
# plot the classification accuracy
title = 'Label reconstruction accuracy (step-wise)'
plot_multiple_runs_with_baselines(testing_phases_x,
model_accuracy,
baseline_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing phase ID',
ylim=[-0.1, 1.1],
labels=labels,
hide_legend=True,
path=path.join(docs_folder, title),
doc=document)
model_se_accuracy = measurement_manager.get_custom_data_from_all_runs(
'model_se_accuracy')
baseline_se_accuracy = measurement_manager.get_custom_data_from_all_runs(
'baseline_se_accuracy')
# plot the classification accuracy
title = 'Label reconstruction SE accuracy (object-wise)'
plot_multiple_runs_with_baselines(testing_phases_x,
model_se_accuracy,
baseline_se_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing_phase ID',
ylim=[-0.1, 1.1],
labels=labels,
hide_legend=True,
path=path.join(docs_folder, title),
doc=document)
baseline_labels_mse = measurement_manager.get_custom_data_from_all_runs(
'baseline_labels_mse')
# plot the MSE
title = 'Mean Square Error of label reconstruction'
plot_multiple_runs_with_baselines(
testing_phases_x,
predicted_labels_mse,
baseline_labels_mse,
title=title,
ylabel='MSE',
xlabel='testing phase ID',
labels=labels,
hide_legend=True,
ylim=[-0.1, 0.2], # just for better resolution
path=path.join(docs_folder, title),
doc=document)
for layer_id in reversed(range(self._experiment_params.num_layers)):
self.publish_results_for_layer(
document, docs_folder, measurement_manager,
topology_parameters, layer_id,
self._experiment_params.num_layers,
self._experiment_params.show_conv_agreements,
self._experiment_params.is_train_test_classifier_computed)
def _publish_results(self):
"""Plot and save the results."""
doc = Document()
date = get_stamp()
labels = ExperimentTemplateBase.parameters_to_string(
self._topology_parameters_list)
for manager in self._layer_measurement_managers:
manager.publish_results(labels=labels,
date=date,
docs_folder=self._docs_folder,
doc=doc)
# plot the running MSE
title = 'Mean Square Error of TA classification'
f = plot_multiple_runs_with_baselines(self._steps,
self._predicted_labels_mse,
self._baseline_labels_mse,
title=title,
ylabel='mse',
xlabel='steps',
labels=labels)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
title = 'TA classification accuracy'
f = plot_multiple_runs_with_baselines(
self._steps,
self._classification_accuracy,
self._random_classification_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='steps',
labels=labels)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
title = 'TA classification accuracy - (SE-metric)'
f = plot_multiple_runs_with_baselines(
self._steps,
self._se_classification_accuracy,
self._se_random_classification_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='steps',
labels=labels)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
title = 'is_learning'
f = plot_multiple_runs(
self._steps,
self._is_learning_info,
title=title,
ylabel='is learning',
xlabel='steps',
)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
doc.write_file(
path.join(self._docs_folder,
to_safe_name(self._complete_name() + date + ".html")))
print('done')
def _publish_results(self):
doc = Document()
doc.add(self._get_heading('_not set'))
params_str = pprint.pformat(
Task0TrainTestTemplateRelearning.pprint_parameters_to_string(self._topology_parameters_list), 1, 160
)
doc.add(f"<p><b>Parameters:</b><br /><pre>learning rate: {self._learning_rate},\n" + params_str + "</pre></p>")
labels = ExperimentTemplateBase.parameters_to_string(self._topology_parameters_list)
testing_phases = list(range(0, len(self._clustering_agreement_list[0][0])))
for i, run_label in enumerate(self._run_labels):
title = 'Clustering agreement ' + run_label
f = plot_multiple_runs(
testing_phases,
self._clustering_agreement_list[i],
title=title,
ylabel='agreement',
xlabel='testing training_phases',
disable_ascii_labels=True,
hide_legend=True,
ylim=[ClusterAgreementMeasurement.NO_VALUE - 0.1, 1.1]
)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
title = 'Model classification accuracy (step-wise)'
f = plot_multiple_runs_with_baselines(
testing_phases,
self._model_accuracy,
self._baseline_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing phase',
ylim=[-0.1, 1.1],
labels=self._run_labels
)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
title = 'Model SE classification accuracy (step-wise)'
f = plot_multiple_runs_with_baselines(
testing_phases,
self._model_se_accuracy,
self._baseline_se_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing_phase',
ylim=[-0.1, 1.1],
labels=self._run_labels
)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
title = 'Weak classifier accuracy trained on SP outputs to labels'
f = plot_multiple_runs_with_baselines(
testing_phases,
self._weak_class_accuracy,
self._base_weak_class_accuracy,
title=title,
ylabel='Accuracy (1 ~ 100%)',
xlabel='steps',
labels=labels,
ylim=[-0.1, 1.1],
hide_legend=True
)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
title = 'Average Deltas Train'
f = plot_multiple_runs(
[self._sp_evaluation_period * i for i in range(0, len(self._average_delta_train[0]))],
self._average_delta_train,
title=title,
ylabel='average_deltas',
xlabel='steps',
labels=self._run_labels,
disable_ascii_labels=True,
use_scatter=False
)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
title = 'Average Deltas Test'
f = plot_multiple_runs(
[self._sp_evaluation_period * i for i in range(0, len(self._average_delta_test[0]))],
self._average_delta_test,
title=title,
ylabel='average_deltas',
xlabel='steps',
labels=self._run_labels,
disable_ascii_labels=True,
use_scatter=False
)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
title = 'Average boosting duration'
f = plot_multiple_runs(
[self._sp_evaluation_period * i for i in range(0, len(self._average_boosting_dur[0]))],
self._average_boosting_dur,
title=title,
ylabel='duration',
xlabel='steps',
labels=labels,
hide_legend=True
)
add_fig_to_doc(f, path.join(self._docs_folder, title), doc)
doc.write_file(path.join(self._docs_folder, "main.html"))
print('done')
def publish_results(self, labels, date, docs_folder, doc):
doc.add(f"<br><br><br><b>Results for layer {self._layer_id}</b><br>")
prefix = 'L' + str(self._layer_id) + '--'
testing_phase_ids = list(range(0, len(self._clustering_agreements[0][0]))) # x-axis values
title = prefix + ' Weak classifier accuracy trained on SP outputs to labels'
f = plot_multiple_runs_with_baselines(
testing_phase_ids,
self._weak_class_accuracy,
self._base_weak_class_accuracy,
title=title,
ylabel='Accuracy (1 ~ 100%)',
xlabel='steps',
labels=labels,
ylim=[-0.1, 1.1],
hide_legend=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
title = prefix + '- Average boosting duration'
f = plot_multiple_runs(
self._sp_evaluation_steps[0],
self._average_boosting_dur,
title=title,
ylabel='duration',
xlabel='steps',
labels=labels,
hide_legend=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
title = prefix + '- Num boosted clusters'
f = plot_multiple_runs(
self._sp_evaluation_steps[0],
self._num_boosted_clusters,
title=title,
ylabel='Num boosted clusters / total clusters',
xlabel='steps',
labels=labels,
ylim=[-0.1, 1.1],
hide_legend=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
title = prefix + '- Average_deltas'
f = plot_multiple_runs(
self._sp_evaluation_steps[0],
self._average_deltas,
title=title,
ylabel='average_deltas',
xlabel='steps',
labels=labels,
disable_ascii_labels=True,
hide_legend=True
# use_scatter=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
# if this is not the top layer, show conv agreements only if required
if self._show_conv_agreements or self._layer_id == (self._num_layers - 1):
agreements = self._clustering_agreements
for run_id, run_agreements in enumerate(agreements):
for expert_id, expert_agreements in enumerate(run_agreements):
self._plot_agreement(
prefix,
expert_id,
run_id,
testing_phase_ids,
expert_agreements,
docs_folder,
doc
)
def _publish_results_to_doc(self, doc: Document, date: str, docs_folder: path):
"""Adds my results to the results produced by the base class"""
super()._publish_results_to_doc(doc, date, docs_folder)
doc.add(f"<br><br><br><b>Common results</b><br>")
labels = ExperimentTemplateBase.extract_params_for_legend(self._topology_parameters_list)
title = 'training_phase_id'
f = plot_multiple_runs(
self._steps,
self._plotted_training_phase_id,
title=title,
ylabel='training_phase_id',
xlabel='steps',
labels=labels
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
title = 'testing_phase_id'
f = plot_multiple_runs(
self._steps,
self._plotted_testing_phase_id,
title=title,
ylabel='testing_phase_id',
xlabel='steps',
labels=labels
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
if self._plot_is_learning:
# plot the classification accuracy
title = 'Is Learning'
f = plot_multiple_runs(
self._steps,
self._is_learning_info,
title=title,
ylabel='learning=True?',
xlabel='steps',
ylim=[-0.1, 1.1],
labels=labels
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
testing_phase_ids = list(range(0, len(self._mutual_info[0]))) # x-axis values
title = 'Top-layer L' + str(self._top_layer_id()) + ' Mutual information of SP output with labels'
f = plot_multiple_runs_with_baselines(
testing_phase_ids,
self._mutual_info,
self._base_mutual_info,
title=title,
ylabel='Normalized mutual information',
xlabel='steps',
labels=labels,
ylim=[-0.1, 1.1],
hide_legend=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
# plot the classification accuracy
title = 'Label reconstruction accuracy (step-wise)'
f = plot_multiple_runs_with_baselines(
testing_phase_ids,
self._model_accuracy,
self._baseline_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing phase ID',
ylim=[-0.1, 1.1],
labels=labels,
hide_legend=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
# plot the classification accuracy
title = 'Label reconstruction SE accuracy'
f = plot_multiple_runs_with_baselines(
testing_phase_ids,
self._model_se_accuracy,
self._baseline_se_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing_phase ID',
ylim=[-0.1, 1.1],
labels=labels,
hide_legend=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
# plot the MSE
title = 'Mean Square Error of label reconstruction'
f = plot_multiple_runs_with_baselines(
testing_phase_ids,
self._predicted_labels_mse,
self._baseline_labels_mse,
title=title,
ylabel='MSE',
xlabel='testing phase ID',
labels=labels,
hide_legend=True,
ylim=[-0.1, 0.2] # just for better resolution
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
for manager in reversed(self._layer_measurement_managers):
manager.publish_results(labels=title, date=date, docs_folder=docs_folder, doc=doc)
def publish_results(self, document: Document, docs_folder: str,
measurement_manager: MeasurementManager,
topology_parameters: List[str]):
"""An alternative to the _publish_results method, this is called from _publish_results now
Draw and add your plots to the document here.
"""
steps = measurement_manager.get_values_from_all_runs('current_step')
plotted_training_phase_id = measurement_manager.get_values_from_all_runs(
'training_phase_id')
plotted_testing_phase_id = measurement_manager.get_values_from_all_runs(
'testing_phase_id')
labels = topology_parameters
title = 'training_phase_id'
f = plot_multiple_runs(steps,
plotted_training_phase_id,
title=title,
ylabel='training_phase_id',
xlabel='steps',
labels=labels)
add_fig_to_doc(f, path.join(docs_folder, title), document)
title = 'testing_phase_id'
f = plot_multiple_runs(steps,
plotted_testing_phase_id,
title=title,
ylabel='testing_phase_id',
xlabel='steps',
labels=labels)
add_fig_to_doc(f, path.join(docs_folder, title), document)
max_x = max(steps[0])
average_delta_train_0 = measurement_manager.get_items_from_all_runs(
'average_delta0_train')
test_sp_steps = [key for key, value in average_delta_train_0[0]]
title = 'average_delta_train_layer0'
f = plot_multiple_runs(test_sp_steps,
[[value for key, value in sequence]
for sequence in average_delta_train_0],
title=title,
ylabel='average_deltas',
xlabel='steps',
labels=labels,
xlim=[0, max_x],
disable_ascii_labels=True,
hide_legend=True
# use_scatter=True
)
add_fig_to_doc(f, path.join(docs_folder, title), document)
average_delta_train_1 = measurement_manager.get_items_from_all_runs(
'average_delta1_train')
title = 'average_delta_train_layer1'
f = plot_multiple_runs(test_sp_steps,
[[value for key, value in sequence]
for sequence in average_delta_train_1],
title=title,
ylabel='average_deltas',
xlabel='steps',
labels=labels,
xlim=[0, max_x],
disable_ascii_labels=True,
hide_legend=True
# use_scatter=True
)
add_fig_to_doc(f, path.join(docs_folder, title), document)
predicted_labels_mse = measurement_manager.get_custom_data_from_all_runs(
'predicted_labels_mse')
testing_phases_x = list(range(0, len(predicted_labels_mse[0])))
model_accuracy = measurement_manager.get_custom_data_from_all_runs(
'model_accuracy')
baseline_accuracy = measurement_manager.get_custom_data_from_all_runs(
'baseline_accuracy')
# plot the classification accuracy
title = 'Label reconstruction accuracy (step-wise)'
f = plot_multiple_runs_with_baselines(testing_phases_x,
model_accuracy,
baseline_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing phase ID',
ylim=[-0.1, 1.1],
labels=labels,
hide_legend=True)
add_fig_to_doc(f, path.join(docs_folder, title), document)
model_se_accuracy = measurement_manager.get_custom_data_from_all_runs(
'model_se_accuracy')
baseline_se_accuracy = measurement_manager.get_custom_data_from_all_runs(
'baseline_se_accuracy')
# plot the classification accuracy
title = 'Label reconstruction SE accuracy (step-wise)'
f = plot_multiple_runs_with_baselines(testing_phases_x,
model_se_accuracy,
baseline_se_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing_phase ID',
ylim=[-0.1, 1.1],
labels=labels,
hide_legend=True)
add_fig_to_doc(f, path.join(docs_folder, title), document)
baseline_labels_mse = measurement_manager.get_custom_data_from_all_runs(
'baseline_labels_mse')
# plot the MSE
title = 'Mean Square Error of label reconstruction'
f = plot_multiple_runs_with_baselines(
testing_phases_x,
predicted_labels_mse,
baseline_labels_mse,
title=title,
ylabel='MSE',
xlabel='testing phase ID',
labels=labels,
hide_legend=True,
ylim=[-0.1, 0.2] # just for better resolution
)
add_fig_to_doc(f, path.join(docs_folder, title), document)
def _publish_results_to_doc(self, doc: Document, date: str, docs_folder: os.path):
"""An alternative to the _publish_results method, this is called from _publish_results now
Draw and add your topologies to the document here.
"""
labels = ExperimentTemplateBase.extract_params_for_legend(self._topology_parameters_list)
title = 'training_phase_id'
f = plot_multiple_runs(
self._steps,
self._plotted_training_phase_id,
title=title,
ylabel='training_phase_id',
xlabel='steps',
labels=labels
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
title = 'testing_phase_id'
f = plot_multiple_runs(
self._steps,
self._plotted_testing_phase_id,
title=title,
ylabel='testing_phase_id',
xlabel='steps',
labels=labels
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
# plot the classification accuracy
title = 'Is Learning'
f = plot_multiple_runs(
self._steps,
self._is_learning_info,
title=title,
ylabel='learning=True?',
xlabel='steps',
ylim=[-0.1, 1.1],
labels=labels
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
max_x = max(self._steps[0])
title = 'average_delta_train_layer0'
f = plot_multiple_runs(
self._test_sp_steps[0],
self._average_delta_train_0,
title=title,
ylabel='average_deltas',
xlabel='steps',
labels=labels,
xlim=[0, max_x],
disable_ascii_labels=True,
hide_legend=True
# use_scatter=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
title = 'average_delta_train_layer1'
f = plot_multiple_runs(
self._test_sp_steps[0],
self._average_delta_train_1,
title=title,
ylabel='average_deltas',
xlabel='steps',
labels=labels,
xlim=[0, max_x],
disable_ascii_labels=True,
hide_legend=True
# use_scatter=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
testing_phases_x = list(range(0, len(self._predicted_labels_mse[0])))
# plot the classification accuracy
title = 'Label reconstruction accuracy (step-wise)'
f = plot_multiple_runs_with_baselines(
testing_phases_x,
self._model_accuracy,
self._baseline_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing phase ID',
ylim=[-0.1, 1.1],
labels=labels,
hide_legend=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
# plot the classification accuracy
title = 'Label reconstruction SE accuracy (step-wise)'
f = plot_multiple_runs_with_baselines(
testing_phases_x,
self._model_se_accuracy,
self._baseline_se_accuracy,
title=title,
ylabel='accuracy (1 ~ 100%)',
xlabel='testing_phase ID',
ylim=[-0.1, 1.1],
labels=labels,
hide_legend=True
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
# plot the MSE
title = 'Mean Square Error of label reconstruction'
f = plot_multiple_runs_with_baselines(
testing_phases_x,
self._predicted_labels_mse,
self._baseline_labels_mse,
title=title,
ylabel='MSE',
xlabel='testing phase ID',
labels=labels,
hide_legend=True,
ylim=[-0.1, 0.2] # just for better resolution
)
add_fig_to_doc(f, path.join(docs_folder, title), doc)
