def update_and_test(training_df: DataFrame, test_df: DataFrame, job: Job):
train_data = _drop_columns(training_df)
test_data = _drop_columns(test_df)
job.encoding = job.incremental_train.encoding
job.encoding.save()
job.save()
if list(train_data.columns.values
) != job.incremental_train.encoding.features:
# TODO: how do I align the two feature vectors?
train_data, _ = train_data.align(
pd.DataFrame(columns=job.incremental_train.encoding.features),
axis=1,
join='right')
train_data = train_data.fillna(0)
test_data, _ = test_data.align(
pd.DataFrame(columns=job.incremental_train.encoding.features),
axis=1,
join='right')
test_data = test_data.fillna(0)
# TODO: UPDATE if incremental, otherwise just test
model_split = _update(job, train_data)
results_df, auc = _test(model_split,
test_data,
evaluation=True,
is_binary_classifier=_check_is_binary_classifier(
job.labelling.type))
results = _prepare_results(results_df, auc)
return results, model_split
def regression(training_df: DataFrame, test_df: DataFrame,
clusterer: Clustering, job: Job) -> (dict, dict):
"""main regression entry point
train and tests the regressor using the provided data
:param clusterer:
:param training_df: training DataFrame
:param test_df: testing DataFrame
:param job: job configuration
:return: predictive_model scores and split
"""
train_data, test_data = _prep_data(training_df, test_df)
job.encoding = duplicate_orm_row(
Encoding.objects.filter(pk=job.encoding.pk)[0]
) # TODO: maybe here would be better an intelligent get_or_create...
job.encoding.features = list(train_data.columns.values)
job.encoding.save()
job.save()
model_split = _train(train_data, _choose_regressor(job), clusterer)
results_df = _test(model_split, test_data)
results = calculate_results_regression(results_df, job.labelling)
return results, model_split
def classification(training_df: DataFrame, test_df: DataFrame,
clusterer: Clustering, job: Job) -> (dict, dict):
"""main classification entry point
train and tests the classifier using the provided data
:param clusterer:
:param training_df: training DataFrame
:param test_df: testing DataFrame
:param job: job configuration
:return: predictive_model scores and split
"""
train_data = _drop_columns(training_df)
test_data = _drop_columns(test_df)
job.encoding = duplicate_orm_row(
job.encoding
) #TODO: maybe here would be better an intelligent get_or_create...
job.encoding.features = list(train_data.columns.values)
job.encoding.save()
job.save()
model_split = _train(train_data, _choose_classifier(job), clusterer)
results_df, auc = _test(model_split,
test_data,
evaluation=True,
is_binary_classifier=_check_is_binary_classifier(
job.labelling.type))
results = _prepare_results(results_df, auc)
return results, model_split
def cross_validated_regression(training_df: DataFrame,
test_df: DataFrame,
clusterer: Clustering,
job: Job,
cv=2) -> (dict, dict):
"""main regression entry point
train and tests the regressor using the provided data
:param clusterer:
:param training_df: training DataFrame
:param test_df: testing DataFrame
:param job: job configuration
:param cv: cross validation amount
:return: predictive_model scores and split
"""
train_data, test_data = _prep_data(training_df, test_df)
# job.encoding = duplicate_orm_row(Encoding.objects.filter(pk=job.encoding.pk)[0]) # TODO: maybe here would be better an intelligent get_or_create...
job.encoding = Encoding.objects.create(
data_encoding=job.encoding.data_encoding,
value_encoding=job.encoding.value_encoding,
add_elapsed_time=job.encoding.add_elapsed_time,
add_remaining_time=job.encoding.add_remaining_time,
add_executed_events=job.encoding.add_executed_events,
add_resources_used=job.encoding.add_resources_used,
add_new_traces=job.encoding.add_new_traces,
features=job.encoding.features,
prefix_length=job.encoding.prefix_length,
padding=job.encoding.padding,
task_generation_type=job.encoding.task_generation_type)
job.encoding.features = list(train_data.columns.values)
job.encoding.save()
job.save()
model_split = _train(train_data,
_choose_regressor(job),
clusterer,
do_cv=True)
results_df = _test(model_split, test_data)
results = calculate_results_regression(results_df, job.labelling)
return results, model_split
def classification(training_df: DataFrame, test_df: DataFrame,
clusterer: Clustering, job: Job) -> (dict, dict):
"""main classification entry point
train and tests the classifier using the provided data
:param clusterer:
:param training_df: training DataFrame
:param test_df: testing DataFrame
:param job: job configuration
:return: predictive_model scores and split
"""
train_data = _drop_columns(training_df)
test_data = _drop_columns(test_df)
# job.encoding = duplicate_orm_row(Encoding.objects.filter(pk=job.encoding.pk)[0]) # TODO: maybe here would be better an intelligent get_or_create...
job.encoding = Encoding.objects.create(
data_encoding=job.encoding.data_encoding,
value_encoding=job.encoding.value_encoding,
add_elapsed_time=job.encoding.add_elapsed_time,
add_remaining_time=job.encoding.add_remaining_time,
add_executed_events=job.encoding.add_executed_events,
add_resources_used=job.encoding.add_resources_used,
add_new_traces=job.encoding.add_new_traces,
features=job.encoding.features,
prefix_length=job.encoding.prefix_length,
padding=job.encoding.padding,
task_generation_type=job.encoding.task_generation_type)
job.encoding.features = list(train_data.columns.values)
job.encoding.save()
job.save()
model_split = _train(train_data, _choose_classifier(job), clusterer)
results_df, auc = _test(model_split,
test_data,
evaluation=True,
is_binary_classifier=_check_is_binary_classifier(
job.labelling.type))
results = _prepare_results(results_df, auc)
return results, model_split