def run(distribute_strategy=None, batch_size=32, epochs=5):
# loading data
df = dsutils.load_bank()
df_train, df_test = train_test_split(df, test_size=0.2, random_state=42)
y = df_train.pop('y')
y_test = df_test.pop('y')
# training
config = deeptable.ModelConfig(
nets=deepnets.DeepFM,
earlystopping_patience=999,
apply_class_weight=True,
distribute_strategy=distribute_strategy,
)
dt = deeptable.DeepTable(config=config)
model, history = dt.fit(df_train, y, batch_size=batch_size, epochs=epochs)
# evaluation
result = dt.evaluate(df_test, y_test, verbose=0)
print('score:', result)
# scoring
preds = dt.predict(df_test)
uniques = np.unique(preds, return_counts=True)
print({k: v for k, v in zip(*uniques)})
def test_bankdata(self):
rs = RandomSearcher(mini_dt_space, optimize_direction=OptimizeDirection.Maximize, )
hdt = HyperDT(rs,
callbacks=[SummaryCallback(), FileLoggingCallback(rs, output_dir=f'hotexamples_com/hyn_logs')],
# reward_metric='accuracy',
reward_metric='AUC',
dnn_params={
'hidden_units': ((256, 0, False), (256, 0, False)),
'dnn_activation': 'relu',
},
)
df = dsutils.load_bank().sample(frac=0.1, random_state=9527)
df.drop(['id'], axis=1, inplace=True)
df_train, df_test = train_test_split(df, test_size=0.2, random_state=42)
y = df_train.pop('y')
y_test = df_test.pop('y')
hdt.search(df_train, y, df_test, y_test, max_trials=3, )
best_trial = hdt.get_best_trial()
assert best_trial
estimator = hdt.final_train(best_trial.space_sample, df_train, y)
score = estimator.predict(df_test)
result = estimator.evaluate(df_test, y_test)
assert len(score) == len(y_test)
assert result
assert isinstance(estimator.model, DeepTable)
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 test_importances(self):
if have_eli5:
df = dsutils.load_bank().head(100)
df.drop(['id'], axis=1, inplace=True)
X, X_test = train_test_split(df, test_size=0.2, random_state=42)
y = X.pop('y')
y_test = X_test.pop('y')
config = deeptable.ModelConfig(nets=['dnn_nets'], auto_discrete=True, metrics=['AUC'])
dt = deeptable.DeepTable(config=config)
dt.fit(X, y, epochs=1)
fi = get_score_importances(dt, X_test, y_test, 'AUC', 1, mode='max')
assert fi.shape == (16, 2)
fi2 = get_score_importances(dt, X_test, y_test, 'log_loss', 1, mode='min')
assert fi2.shape == (16, 2)
def test_shap(self):
if have_shap:
df = dsutils.load_bank().head(100)
df.drop(['id'], axis=1, inplace=True)
X, X_test = train_test_split(df, test_size=0.2, random_state=42)
y = X.pop('y')
y_test = X_test.pop('y')
config = deeptable.ModelConfig(nets=['dnn_nets'],
auto_discrete=True,
metrics=['AUC'])
dt = deeptable.DeepTable(config=config)
dt.fit(X, y, epochs=1)
dt_explainer = DeepTablesExplainer(dt, X, num_samples=10)
shap_values = dt_explainer.get_shap_values(X[:1], nsamples='auto')
assert shap_values[0].shape == (1, 16)
rs = MCTSSearcher(my_space, max_node_space=5)
hdt = HyperDT(rs,
callbacks=[SummaryCallback(),
FileLoggingCallback(rs)],
reward_metric='AUC',
dnn_params={
'dnn_units': ((256, 0, False), (256, 0, False)),
'dnn_activation': 'relu',
})
from deeptables.datasets import dsutils
df = dsutils.load_bank()[:1000]
print("data shape: ")
print(df.shape)
df.drop(['id'], axis=1, inplace=True)
y = df.pop("y")
X = df
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=12)
t1 = time.time()
hdt.search(X_train, y_train, X_test, y_test, max_trails=1)
def setup_class(cls):
cls.df_bank = dsutils.load_bank().sample(frac=0.01)
cls.df_movielens = dsutils.load_movielens()