def test_run_multiclass(self):
data = dsutils.load_glass_uci()
conf = deeptable.ModelConfig(
# dnn_units=((256, 0, False), (128, 0, False)),
# dnn_activation='relu',
fixed_embedding_dim=False,
embeddings_output_dim=0,
apply_gbm_features=False,
auto_discrete=False,
)
bt = batch_trainer.BatchTrainer(
data,
'x_10',
eval_size=0.2,
validation_size=0.2,
eval_metrics=['AUC', 'accuracy', 'recall', 'precision', 'f1'],
# AUC/recall/precision/f1/mse/mae/msle/rmse/r2
dt_config=conf,
verbose=0,
dt_epochs=1,
# seed=9527,
cross_validation=True,
stratified=False,
num_folds=5,
)
ms = bt.start()
assert ms.leaderboard().shape[1], 7
def test_load_data(self):
df_adult = dsutils.load_adult()
df_glass = dsutils.load_glass_uci()
df_hd = dsutils.load_heart_disease_uci()
df_bank = dsutils.load_bank()
df_boston = dsutils.load_boston()
assert df_adult.shape, (32561, 15)
assert df_glass.shape, (214, 11)
assert df_hd.shape, (303, 14)
assert df_bank.shape, (108504, 18)
assert df_boston.shape, (506, 14)
def setup_class(self):
setup_dask(self)
print("Loading datasets...")
data = dd.from_pandas(dsutils.load_glass_uci(), npartitions=2)
self.y = data.pop(10).values
self.X = data
conf = deeptable.ModelConfig(metrics=['AUC'], apply_gbm_features=False, )
self.dt = deeptable.DeepTable(config=conf)
self.X_train, self.X_test, self.y_train, self.y_test = \
[t.persist() for t in get_tool_box(data).train_test_split(self.X, self.y, test_size=0.2, random_state=42)]
self.model, self.history = self.dt.fit(self.X_train, self.y_train, batch_size=32, epochs=3)
def setup_class(self):
print("Loading datasets...")
data = dsutils.load_glass_uci()
self.y = data.pop(10).values
self.X = data
conf = deeptable.ModelConfig(
metrics=['AUC'],
apply_gbm_features=False,
)
self.dt = deeptable.DeepTable(config=conf)
self.X_train, \
self.X_test, \
self.y_train, \
self.y_test = train_test_split(self.X, self.y, test_size=0.2, random_state=42)
self.model, self.history = self.dt.fit(self.X_train,
self.y_train,
epochs=1)
def run_glass_uci():
df = dsutils.load_glass_uci()
df.columns = [f'col_{c}' if c != 10 else 'y' for c in df.columns.to_list()]
# train(df, 'y', 'Recall')
train(df, 'y', 'AUC')