def test_fit_objectives_tab_transformer(
X_wide,
X_tab,
target,
objective,
X_wide_test,
X_tab_test,
X_test,
pred_dim,
probs_dim,
):
wide = Wide(np.unique(X_wide).shape[0], pred_dim)
tab_transformer = TabTransformer(
column_idx={k: v
for v, k in enumerate(colnames)},
embed_input=embed_input_tt,
continuous_cols=colnames[5:],
)
model = WideDeep(wide=wide, deeptabular=tab_transformer, pred_dim=pred_dim)
trainer = Trainer(model, objective=objective, verbose=0)
trainer.fit(X_wide=X_wide, X_tab=X_tab, target=target, batch_size=16)
preds = trainer.predict(X_wide=X_wide, X_tab=X_tab, X_test=X_test)
if objective == "binary":
pass
else:
probs = trainer.predict_proba(X_wide=X_wide,
X_tab=X_tab,
X_test=X_test)
assert preds.shape[0] == 32, probs.shape[1] == probs_dim
def test_fit_objectives(
X_wide,
X_tab,
target,
objective,
X_wide_test,
X_tab_test,
X_test,
pred_dim,
probs_dim,
):
wide = Wide(np.unique(X_wide).shape[0], pred_dim)
deeptabular = TabMlp(
mlp_hidden_dims=[32, 16],
mlp_dropout=[0.5, 0.5],
column_idx=column_idx,
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
model = WideDeep(wide=wide, deeptabular=deeptabular, pred_dim=pred_dim)
trainer = Trainer(model, objective=objective, verbose=0)
trainer.fit(X_wide=X_wide, X_tab=X_tab, target=target, batch_size=16)
preds = trainer.predict(X_wide=X_wide, X_tab=X_tab, X_test=X_test)
if objective == "binary":
pass
else:
probs = trainer.predict_proba(X_wide=X_wide,
X_tab=X_tab,
X_test=X_test)
assert preds.shape[0] == 32, probs.shape[1] == probs_dim
def test_fit_with_deephead():
wide = Wide(np.unique(X_wide).shape[0], 1)
deeptabular = TabMlp(
mlp_hidden_dims=[32, 16],
column_idx=column_idx,
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
deephead = nn.Sequential(nn.Linear(16, 8), nn.Linear(8, 4))
model = WideDeep(wide=wide,
deeptabular=deeptabular,
pred_dim=1,
deephead=deephead)
trainer = Trainer(model, objective="binary", verbose=0)
trainer.fit(X_wide=X_wide,
X_tab=X_tab,
target=target_binary,
batch_size=16)
preds = trainer.predict(X_wide=X_wide, X_tab=X_tab, X_test=X_test)
probs = trainer.predict_proba(X_wide=X_wide, X_tab=X_tab, X_test=X_test)
assert preds.shape[0] == 32, probs.shape[1] == 2
def test_predict_with_individual_component(wide, deeptabular, deeptext,
deepimage, X_wide, X_tab, X_text,
X_img, target):
model = WideDeep(wide=wide,
deeptabular=deeptabular,
deeptext=deeptext,
deepimage=deepimage)
trainer = Trainer(model, objective="binary", verbose=0)
trainer.fit(
X_wide=X_wide,
X_tab=X_tab,
X_text=X_text,
X_img=X_img,
target=target,
batch_size=16,
)
# simply checking that runs and produces outputs
preds = trainer.predict(X_wide=X_wide,
X_tab=X_tab,
X_text=X_text,
X_img=X_img)
assert preds.shape[0] == 32 and "train_loss" in trainer.history