def test_confusion_matrix_vis_api(csv_filename):
"""Ensure pdf and png figures can be saved via visualisation API call.
:param csv_filename: csv fixture from tests.fixtures.filenames.csv_filename
:return: None
"""
experiment = Experiment(csv_filename)
test_stats = experiment.test_stats_full[1]
viz_outputs = ('pdf', 'png')
for viz_output in viz_outputs:
vis_output_pattern_pdf = experiment.model.exp_dir_name + '/*.{}'.format(
viz_output
)
visualize.confusion_matrix(
[test_stats, test_stats],
experiment.ground_truth_metadata,
experiment.output_feature_name,
top_n_classes=[0],
normalize=False,
model_names=['Model1', 'Model2'],
output_directory=experiment.model.exp_dir_name,
file_format=viz_output
)
figure_cnt = glob.glob(vis_output_pattern_pdf)
assert 4 == len(figure_cnt)
shutil.rmtree(experiment.model.exp_dir_name, ignore_errors=True)
def test_confusion_matrix_vis_api(experiment_to_use):
"""Ensure pdf and png figures can be saved via visualization API call.
:param experiment_to_use: Object containing trained model and results to
test visualization
:return: None
"""
experiment = experiment_to_use
# extract test stats only
test_stats = experiment.test_stats_full
viz_outputs = ('pdf', 'png')
with TemporaryDirectory() as tmpvizdir:
for viz_output in viz_outputs:
vis_output_pattern_pdf = tmpvizdir + '/*.{}'.format(
viz_output
)
visualize.confusion_matrix(
[test_stats, test_stats],
experiment.ground_truth_metadata,
experiment.output_feature_name,
top_n_classes=[0],
normalize=False,
model_names=['Model1', 'Model2'],
output_directory=tmpvizdir,
file_format=viz_output
)
figure_cnt = glob.glob(vis_output_pattern_pdf)
assert 4 == len(figure_cnt)
"./profile_images")
with open("./config.yaml") as f:
config = yaml.safe_load(f.read())
model = LudwigModel(config, logging_level=logging.INFO)
train_stats, preprocessed_data, output_directory = model.train(
dataset=training_set)
# Generates predictions and performance statistics for the test set.
test_stats, predictions, output_directory = model.evaluate(
test_set, collect_predictions=True, collect_overall_stats=True)
confusion_matrix(
[test_stats],
model.training_set_metadata,
"account_type",
top_n_classes=[2],
model_names=[""],
normalize=True,
output_directory="./visualizations",
file_format="png",
)
# Visualizes learning curves, which show how performance metrics changed over time during training.
learning_curves(train_stats,
output_feature_name="account_type",
output_directory="./visualizations",
file_format="png")
