def test_early_stop():
wide = Wide(100, 1)
deepdense = DeepDense(
hidden_layers=[32, 16],
dropout=[0.5, 0.5],
deep_column_idx=deep_column_idx,
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
model = WideDeep(wide=wide, deepdense=deepdense)
model.compile(
method="binary",
callbacks=[
EarlyStopping(min_delta=0.1,
patience=3,
restore_best_weights=True,
verbose=1)
],
verbose=1,
)
model.fit(X_wide=X_wide,
X_deep=X_deep,
target=target,
val_split=0.2,
n_epochs=5)
# length of history = patience+1
assert len(model.history._history["train_loss"]) == 3 + 1
def test_fit_methods(
X_wide,
X_deep,
target,
method,
X_wide_test,
X_deep_test,
X_test,
pred_dim,
probs_dim,
):
wide = Wide(np.unique(X_wide).shape[0], pred_dim)
deepdense = DeepDense(
hidden_layers=[32, 16],
dropout=[0.5, 0.5],
deep_column_idx=deep_column_idx,
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
model = WideDeep(wide=wide, deepdense=deepdense, pred_dim=pred_dim)
model.compile(method=method, verbose=0)
model.fit(X_wide=X_wide, X_deep=X_deep, target=target)
preds = model.predict(X_wide=X_wide, X_deep=X_deep, X_test=X_test)
if method == "binary":
pass
else:
probs = model.predict_proba(X_wide=X_wide,
X_deep=X_deep,
X_test=X_test)
assert preds.shape[0] == 100, probs.shape[1] == probs_dim
def test_model_checkpoint(save_best_only, max_save, n_files):
wide = Wide(100, 1)
deepdense = DeepDense(
hidden_layers=[32, 16],
dropout=[0.5, 0.5],
deep_column_idx=deep_column_idx,
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
model = WideDeep(wide=wide, deepdense=deepdense)
model.compile(
method="binary",
callbacks=[
ModelCheckpoint("weights/test_weights",
save_best_only=save_best_only,
max_save=max_save)
],
verbose=0,
)
model.fit(X_wide=X_wide,
X_deep=X_deep,
target=target,
n_epochs=5,
val_split=0.2)
n_saved = len(os.listdir("weights/"))
for f in os.listdir("weights/"):
os.remove("weights/" + f)
assert n_saved <= n_files
def test_initializers_with_pattern():
wide = Wide(100, 1)
deepdense = DeepDense(
hidden_layers=[32, 16],
dropout=[0.5, 0.5],
deep_column_idx=deep_column_idx,
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
deeptext = DeepText(vocab_size=vocab_size, embed_dim=32, padding_idx=0)
model = WideDeep(wide=wide,
deepdense=deepdense,
deeptext=deeptext,
pred_dim=1)
cmodel = c(model)
org_word_embed = []
for n, p in cmodel.named_parameters():
if "word_embed" in n:
org_word_embed.append(p)
model.compile(method="binary", verbose=0, initializers=initializers_2)
init_word_embed = []
for n, p in model.named_parameters():
if "word_embed" in n:
init_word_embed.append(p)
assert torch.all(org_word_embed[0] == init_word_embed[0].cpu())
def test_focal_loss(X_wide, X_deep, target, method, output_dim, probs_dim):
wide = Wide(100, output_dim)
deepdense = model3 = DeepDense(hidden_layers=[32, 16],
dropout=[0.5, 0.5],
deep_column_idx=deep_column_idx,
embed_input=embed_input,
continuous_cols=colnames[-5:])
model = WideDeep(wide=wide, deepdense=deepdense, output_dim=output_dim)
model.compile(method=method, verbose=0, with_focal_loss=True)
model.fit(X_wide=X_wide, X_deep=X_deep, target=target)
probs = model.predict_proba(X_wide=X_wide, X_deep=X_deep)
assert probs.shape[1] == probs_dim
def test_filepath_error():
wide = Wide(np.unique(X_wide).shape[0], 1)
deepdense = DeepDense(
hidden_layers=[16, 4],
deep_column_idx=deep_column_idx,
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
model = WideDeep(wide=wide, deepdense=deepdense)
with pytest.raises(ValueError):
model.compile(
method="binary",
callbacks=[ModelCheckpoint(filepath="wrong_file_path")],
verbose=0,
)
def test_fit_with_deephead():
wide = Wide(np.unique(X_wide).shape[0], 1)
deepdense = DeepDense(
hidden_layers=[32, 16],
deep_column_idx=deep_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,
deepdense=deepdense,
pred_dim=1,
deephead=deephead)
model.compile(method="binary", verbose=0)
model.fit(X_wide=X_wide,
X_deep=X_deep,
target=target_binary,
batch_size=16)
preds = model.predict(X_wide=X_wide, X_deep=X_deep, X_test=X_test)
probs = model.predict_proba(X_wide=X_wide, X_deep=X_deep, X_test=X_test)
assert preds.shape[0] == 32, probs.shape[1] == 2
def test_initializers_1(): wide = Wide(100, 1) deepdense = DeepDense(hidden_layers=[32,16], dropout=[0.5, 0.5], deep_column_idx=deep_column_idx, embed_input=embed_input, continuous_cols=colnames[-5:]) deeptext = DeepText( vocab_size=vocab_size, embed_dim=32, padding_idx=0) deepimage=DeepImage(pretrained=True) model = WideDeep(wide=wide, deepdense=deepdense, deeptext=deeptext, deepimage=deepimage, output_dim=1) cmodel = c(model) org_weights = [] for n,p in cmodel.named_parameters(): if n in test_layers_1: org_weights.append(p) model.compile(method='binary', verbose=0, initializers=initializers_1) init_weights = [] for n,p in model.named_parameters(): if n in test_layers_1: init_weights.append(p) res = all([torch.all((1-(a==b).int()).bool()) for a,b in zip(org_weights, init_weights)]) assert res
def test_basic_run_with_metrics_multiclass():
wide = Wide(np.unique(X_wide).shape[0], 3)
deepdense = DeepDense(
hidden_layers=[32, 16],
dropout=[0.5, 0.5],
deep_column_idx={k: v
for v, k in enumerate(colnames)},
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
model = WideDeep(wide=wide, deepdense=deepdense, pred_dim=3)
model.compile(method="multiclass", metrics=[Accuracy], verbose=False)
model.fit(
X_wide=X_wide,
X_deep=X_deep,
target=target_multi,
n_epochs=1,
batch_size=16,
val_split=0.2,
)
assert ("train_loss" in model.history._history.keys()
and "train_acc" in model.history._history.keys())
deep_column_idx={k:v for v,k in enumerate(colnames)}
X_deep = np.vstack(embed_cols+cont_cols).transpose()
# Text Array
padded_sequences = np.random.choice(np.arange(1,100), (100, 48))
vocab_size = 1000
X_text = np.hstack((np.repeat(np.array([[0,0]]), 100, axis=0), padded_sequences))
# target
target = np.random.choice(2, 100)
###############################################################################
# Test that history saves the information adequately
###############################################################################
wide = Wide(100, 1)
deepdense = DeepDense(hidden_layers=[32,16], dropout=[0.5, 0.5], deep_column_idx=deep_column_idx,
embed_input=embed_input, continuous_cols=colnames[-5:])
model = WideDeep(wide=wide, deepdense=deepdense)
wide_opt_1 = torch.optim.Adam(model.wide.parameters())
deep_opt_1 = torch.optim.Adam(model.deepdense.parameters())
wide_sch_1 = StepLR(wide_opt_1, step_size=4)
deep_sch_1 = CyclicLR(deep_opt_1, base_lr=0.001, max_lr=0.01, step_size_up=10, cycle_momentum=False)
optimizers_1 = {'wide': wide_opt_1, 'deepdense': deep_opt_1}
lr_schedulers_1 = {'wide': wide_sch_1, 'deepdense': deep_sch_1}
wide_opt_2 = torch.optim.Adam(model.wide.parameters())
deep_opt_2 = RAdam(model.deepdense.parameters())
wide_sch_2 = StepLR(wide_opt_2, step_size=4)
deep_sch_2 = StepLR(deep_opt_2, step_size=4)
optimizers_2 = { 'wide': wide_opt_2, 'deepdense':deep_opt_2}
lr_schedulers_2 = {'wide': wide_sch_2,'deepdense': deep_sch_2}
df.drop("yield", axis=1, inplace=True)
target = "yield_cat"
target = np.array(df[target].values)
prepare_wide = WidePreprocessor(wide_cols=wide_cols,
crossed_cols=crossed_cols)
X_wide = prepare_wide.fit_transform(df)
prepare_deep = DensePreprocessor(embed_cols=cat_embed_cols,
continuous_cols=continuous_cols)
X_deep = prepare_deep.fit_transform(df)
wide = Wide(wide_dim=X_wide.shape[1], pred_dim=3)
deepdense = DeepDense(
hidden_layers=[64, 32],
dropout=[0.2, 0.2],
deep_column_idx=prepare_deep.deep_column_idx,
embed_input=prepare_deep.embeddings_input,
continuous_cols=continuous_cols,
)
model = WideDeep(wide=wide, deepdense=deepdense, pred_dim=3)
model.compile(method="multiclass", metrics=[Accuracy, F1Score])
model.fit(
X_wide=X_wide,
X_deep=X_deep,
target=target,
n_epochs=1,
batch_size=32,
val_split=0.2,
)
# image
X_image = torch.rand(100, 3, 28, 28)
# Define the model components
# wide
wide = Wide(10, 1)
if use_cuda:
wide.cuda()
# deep
deepdense = DeepDense(
hidden_layers=[16, 8],
dropout=[0.5, 0.2],
deep_column_idx=deep_column_idx,
embed_input=embed_input,
continuous_cols=continuous_cols,
)
deepdense = nn.Sequential(deepdense, nn.Linear(8, 1))
if use_cuda:
deepdense.cuda()
# text
deeptext = TestDeepText()
if use_cuda:
deeptext.cuda()
# image
deepimage = TestDeepImage()
if use_cuda:
X_deep_tr,
X_deep_val,
X_text_tr,
X_text_val,
X_img_tr,
X_img_val,
y_train,
y_val,
) = train_test_split(X_wide, X_deep, X_text, X_img, target)
# build model components
wide = Wide(np.unique(X_wide).shape[0], 1)
deepdense = DeepDense(
hidden_layers=[32, 16],
dropout=[0.5, 0.5],
deep_column_idx={k: v
for v, k in enumerate(colnames)},
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
deeptext = DeepText(vocab_size=vocab_size, embed_dim=32, padding_idx=0)
deepimage = DeepImage(pretrained=True)
# transforms
mean = [0.406, 0.456, 0.485] # BGR
std = [0.225, 0.224, 0.229] # BGR
transforms1 = [ToTensor, Normalize(mean=mean, std=std)]
transforms2 = [Normalize(mean=mean, std=std)]
##############################################################################
# Test many possible scenarios of data inputs I can think off. Surely users
from torch import nn
from pytorch_widedeep.models import (
Wide,
DeepText,
WideDeep,
DeepDense,
DeepImage,
)
embed_input = [(u, i, j)
for u, i, j in zip(["a", "b", "c"][:4], [4] * 3, [8] * 3)]
deep_column_idx = {k: v for v, k in enumerate(["a", "b", "c"])}
wide = Wide(10, 1)
deepdense = DeepDense(hidden_layers=[16, 8],
deep_column_idx=deep_column_idx,
embed_input=embed_input)
deeptext = DeepText(vocab_size=100, embed_dim=8)
deepimage = DeepImage(pretrained=False)
###############################################################################
# test raising 'output dim errors'
###############################################################################
@pytest.mark.parametrize(
"deepcomponent, component_name",
[
(None, "dense"),
(deeptext, "text"),
(deepimage, "image"),
colnames = list(string.ascii_lowercase)[:10]
embed_cols = [np.random.choice(np.arange(5), 10) for _ in range(5)]
cont_cols = [np.random.rand(10) for _ in range(5)]
X_deep = torch.from_numpy(np.vstack(embed_cols + cont_cols).transpose())
X_deep_emb = X_deep[:, :5]
X_deep_cont = X_deep[:, 5:]
###############################################################################
# Embeddings and NO continuous_cols
###############################################################################
embed_input = [(u, i, j) for u, i, j in zip(colnames[:5], [5] * 5, [16] * 5)]
model1 = DeepDense(hidden_layers=[32, 16],
dropout=[0.5, 0.2],
deep_column_idx={k: v
for v, k in enumerate(colnames[:5])},
embed_input=embed_input)
def test_deep_dense_embed():
out = model1(X_deep_emb)
assert out.size(0) == 10 and out.size(1) == 16
###############################################################################
# Continous cols but NO embeddings
###############################################################################
continuous_cols = colnames[-5:]
model2 = DeepDense(hidden_layers=[32, 16],
dropout=[0.5, 0.2],