def setup_class(cls):
from sklearn.preprocessing import LabelEncoder
df = dsutils.load_bank()
df['y'] = LabelEncoder().fit_transform(df['y'])
cls.bank_data = df
cls.movie_lens = dsutils.load_movielens()
os.makedirs(cls.work_dir)
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 test_category_datetime_text(self):
df = dsutils.load_movielens()
df['genres'] = df['genres'].apply(lambda s: s.replace('|', ' '))
df['timestamp'] = df['timestamp'].apply(datetime.fromtimestamp)
ftt = FeatureGenerationTransformer(
task='binary',
text_cols=['title'],
categories_cols=['gender', 'genres'])
x_t = ftt.fit_transform(df)
xt_columns = x_t.columns.to_list()
assert 'CROSS_CATEGORICAL_gender__genres' in xt_columns
assert 'TFIDF__title____0__' in xt_columns
assert 'DAY__timestamp__' in xt_columns
def setup_class(cls):
from sklearn.preprocessing import LabelEncoder
df = dsutils.load_bank()
df['y'] = LabelEncoder().fit_transform(df['y']) # binary task target
df['education'] = LabelEncoder().fit_transform(
df['education']) # multiclass task target
cls.bank_data = df
cls.bank_data_cudf = cudf.from_pandas(df)
cls.boston_data = dsutils.load_blood()
cls.boston_data_cudf = cudf.from_pandas(cls.boston_data)
cls.movie_lens = dsutils.load_movielens()
os.makedirs(cls.work_dir)
def setup_class(cls):
cls.bank_data = dsutils.load_bank()
cls.movie_lens = dsutils.load_movielens()
def setup_class(cls):
setup_dask(cls)
cls.bank_data = dd.from_pandas(dsutils.load_bank(), npartitions=2)
cls.movie_lens = dd.from_pandas(dsutils.load_movielens(),
npartitions=2)