def test_read_supported_file(self):
from hypernets.tabular.datasets.dsutils import basedir
csv_file = f'{basedir}/heart-disease-uci.csv'
df_csv = ExperimentJobCreator._read_file(csv_file)
assert df_csv.shape[0] > 1
file_path = common_util.get_temp_file_path(prefix="heart-disease-uci",
suffix=".parquet")
df_csv.to_parquet(file_path)
df_parquet = pd.read_parquet(file_path)
assert df_parquet.shape == df_csv.shape
def test_make_tempfile():
temp_file_path: str = common_util.get_temp_file_path(prefix='prefix', suffix='.txt')
assert not os.path.exists(temp_file_path)
assert os.path.basename(temp_file_path).startswith('prefix')
assert os.path.basename(temp_file_path).endswith('.txt')
temp_file_dir_created = common_util.get_temp_dir_path(prefix='prefix', suffix='prefix', create=True)
assert os.path.exists(temp_file_dir_created)
temp_file_dir_not_created = common_util.get_temp_dir_path(prefix='prefix', suffix='prefix', create=False)
assert not os.path.exists(temp_file_dir_not_created)
def test_regression_task_report():
df = dsutils.load_boston()
df['Constant'] = [0 for i in range(df.shape[0])]
df['Id'] = [i for i in range(df.shape[0])]
target = 'target'
df_train, df_eval = train_test_split(df, test_size=0.2)
df_train['Drifted'] = np.random.random(df_train.shape[0])
df_eval['Drifted'] = np.random.random(df_eval.shape[0]) * 100
file_path = common_util.get_temp_file_path(prefix="report_excel_",
suffix=".xlsx")
print(file_path)
experiment = make_experiment(
PlainModel,
df_train,
target=target,
eval_data=df_eval.copy(),
test_data=df_eval.copy(),
drift_detection_threshold=0.4,
drift_detection_min_features=3,
drift_detection_remove_size=0.5,
search_space=PlainSearchSpace(enable_lr=False,
enable_nn=False,
enable_dt=False,
enable_dtr=True),
report_render='excel',
report_render_options={'file_path': file_path})
estimator = experiment.run(max_trials=3)
assert estimator is not None
mlr_callback = None
mle_callback = None
for callback in experiment.callbacks:
if isinstance(callback, MLReportCallback):
mlr_callback = callback
if isinstance(callback, MLEvaluateCallback):
mle_callback = callback
assert mlr_callback is not None
_experiment_meta: ExperimentMeta = mlr_callback.experiment_meta_
assert len(_experiment_meta.resource_usage) > 0
assert len(_experiment_meta.steps) == 5
assert os.path.exists(file_path)
assert mle_callback is not None
assert _experiment_meta.evaluation_metric is not None
assert len(_experiment_meta.prediction_stats) == 1
assert len(_experiment_meta.datasets) == 3
def run_export_excel_report(maker, has_eval_data=True, str_label=True):
df = dsutils.load_blood()
df['Constant'] = [0 for i in range(df.shape[0])]
df['Id'] = [i for i in range(df.shape[0])]
target = 'Class'
labels = ["no", "yes"]
if str_label:
df[target] = df[target].map(lambda v: labels[v])
df_train, df_eval = train_test_split(df, test_size=0.2)
df_train['Drifted'] = np.random.random(df_train.shape[0])
df_eval['Drifted'] = np.random.random(df_eval.shape[0]) * 100
file_path = common_util.get_temp_file_path(prefix="report_excel_",
suffix=".xlsx")
print(file_path)
experiment = maker(df_train, target, df_eval, file_path)
estimator = experiment.run(max_trials=3)
assert estimator is not None
mlr_callback = None
mle_callback = None
for callback in experiment.callbacks:
if isinstance(callback, MLReportCallback):
mlr_callback = callback
if isinstance(callback, MLEvaluateCallback):
mle_callback = callback
assert mlr_callback is not None
_experiment_meta: ExperimentMeta = mlr_callback.experiment_meta_
assert len(_experiment_meta.resource_usage) > 0
assert os.path.exists(file_path)
if has_eval_data:
assert mle_callback is not None
assert _experiment_meta.confusion_matrix is not None
assert _experiment_meta.classification_report is not None
assert len(_experiment_meta.prediction_elapsed) == 2
assert _experiment_meta.confusion_matrix.data.shape == (
2, 2) # binary classification
assert len(_experiment_meta.datasets) == 3
else:
assert len(_experiment_meta.datasets) == 2
return _experiment_meta
def test_render(self):
steps_meta = [
self.create_data_clean_step_meta(),
self.create_ensemble_step_meta()
]
experiment_meta = ExperimentMeta(
task=const.TASK_BINARY,
datasets=self.create_dataset_meta(),
steps=steps_meta,
evaluation_metric=self.create_binary_metric_data(),
confusion_matrix=self.create_confusion_matrix_data(),
resource_usage=self.create_resource_monitor_df(),
prediction_stats=self.create_prediction_stats_df())
p = common_util.get_temp_file_path(prefix="report_excel_",
suffix=".xlsx")
print(p)
ExcelReportRender(file_path=p).render(experiment_meta)
assert os.path.exists(p)