def experiment_with_boston(self,
init_kwargs,
run_kwargs,
row_count=3000,
with_dask=False):
if with_dask:
X = self.boston
y = X.pop('target')
else:
X = dsutils.load_boston()
if row_count is not None:
X = X.head(row_count)
X['target'] = LabelEncoder().fit_transform(X['target'])
y = X.pop('target')
y = y.astype('float64')
hyper_model = create_plain_model(with_encoder=True)
tb = get_tool_box(X, y)
X_train, X_test, y_train, y_test = \
tb.train_test_split(X, y, test_size=0.3, random_state=9527)
X_train, X_eval, y_train, y_eval = \
tb.train_test_split(X_train, y_train, test_size=0.3, random_state=9527)
init_kwargs = {
'X_eval': X_eval,
'y_eval': y_eval,
'X_test': X_test,
**init_kwargs
}
compete_experiment = CompeteExperiment(hyper_model, X_train, y_train,
**init_kwargs)
base_experiment = Experiment(hyper_model, X_train, y_train,
**init_kwargs)
mydict_compete = compete_experiment.get_data_character()
mydict_base = base_experiment.get_data_character()
assert mydict_base
assert mydict_compete
assert mydict_base['experimentType'] == 'base'
assert mydict_compete['experimentType'] == 'compete'
assert mydict_base['target']['taskType'] == 'regression'
assert mydict_base['target']['freq'] is None
assert mydict_base['target']['unique']
assert mydict_base['target']['mean'] is not None
assert mydict_base['target']['max'] is not None
assert mydict_base['target']['min'] is not None
assert mydict_base['target']['stdev'] is not None
assert mydict_base['target']['dataType'] is 'float'
assert len(mydict_base['targetDistribution']) <= 10
assert mydict_base['datasetShape']['X_train']
assert mydict_base['datasetShape']['y_train']
assert mydict_base['datasetShape']['X_eval']
assert mydict_base['datasetShape']['y_eval']
assert mydict_base['datasetShape']['X_test']
assert mydict_compete['featureDistribution']
def experiment_with_movie_lens(init_kwargs,
run_kwargs,
row_count=None,
with_dask=False):
hyper_model = create_plain_model(reward_metric='f1',
with_encoder=True,
with_dask=with_dask)
X = dsutils.load_movielens()
# X['genres'] = X['genres'].apply(lambda s: s.replace('|', ' '))
X['timestamp'] = X['timestamp'].apply(datetime.fromtimestamp)
if row_count is not None:
X = X.head(row_count)
if with_dask:
setup_dask(None)
X = dd.from_pandas(X, npartitions=1)
y = X.pop('rating')
tb = get_tool_box(X, y)
X_train, X_test, y_train, y_test = \
tb.train_test_split(X, y, test_size=0.3, random_state=9527)
X_train, X_eval, y_train, y_eval = \
tb.train_test_split(X_train, y_train, test_size=0.3, random_state=9527)
init_kwargs = {
'X_eval': X_eval,
'y_eval': y_eval,
'X_test': X_test,
'ensemble_size': 0,
'drift_detection': False,
**init_kwargs
}
run_kwargs = {'max_trials': 3, **run_kwargs}
experiment = CompeteExperiment(hyper_model, X_train, y_train,
**init_kwargs)
estimator = experiment.run(**run_kwargs)
assert estimator
preds = estimator.predict(X_test)
proba = estimator.predict_proba(X_test)
if with_dask:
preds, proba = tb.to_local(preds, proba)
score = tb.metrics.calc_score(
y_test,
preds,
proba,
metrics=['auc', 'accuracy', 'f1', 'recall', 'precision'],
task=experiment.task)
print('evaluate score:', score)
assert score
def experiment_with_bank_data(init_kwargs,
run_kwargs,
row_count=3000,
with_dask=False):
hyper_model = create_plain_model(with_encoder=True, with_dask=with_dask)
X = dsutils.load_bank()
if row_count is not None:
X = X.head(row_count)
X['y'] = LabelEncoder().fit_transform(X['y'])
if with_dask:
setup_dask(None)
X = dd.from_pandas(X, npartitions=1)
y = X.pop('y')
tb = get_tool_box(X, y)
scorer = tb.metrics.metric_to_scoring(hyper_model.reward_metric)
X_train, X_test, y_train, y_test = \
tb.train_test_split(X, y, test_size=0.3, random_state=9527)
X_train, X_eval, y_train, y_eval = \
tb.train_test_split(X_train, y_train, test_size=0.3, random_state=9527)
init_kwargs = {
'X_eval': X_eval,
'y_eval': y_eval,
'X_test': X_test,
'scorer': scorer,
'ensemble_size': 0,
'drift_detection': False,
**init_kwargs
}
run_kwargs = {'max_trials': 3, **run_kwargs}
experiment = CompeteExperiment(hyper_model, X_train, y_train,
**init_kwargs)
estimator = experiment.run(**run_kwargs)
assert estimator
preds = estimator.predict(X_test)
proba = estimator.predict_proba(X_test)
if with_dask:
preds, proba = tb.to_local(preds, proba)
score = tb.metrics.calc_score(
y_test,
preds,
proba,
metrics=['auc', 'accuracy', 'f1', 'recall', 'precision'])
print('evaluate score:', score)
assert score