def prepare_data(results_dir):
train, test = load_dataset()
cat_embed_cols = []
for col in train.columns:
if train[col].dtype == "O" or train[col].nunique(
) < 200 and col != "target":
cat_embed_cols.append(col)
num_cols = [
c for c in train.columns if c not in cat_embed_cols + ["target"]
]
args = read_best_model_args(results_dir)
prepare_tab = TabPreprocessor(
embed_cols=cat_embed_cols,
continuous_cols=num_cols,
scale=True,
for_tabtransformer=True,
)
X_train = prepare_tab.fit_transform(train)
y_train = train.target.values
X_test = prepare_tab.transform(test)
y_test = test.target.values
mlp_hidden_dims_same = len(cat_embed_cols)
return mlp_hidden_dims_same, args, prepare_tab, X_train, X_test, y_train, y_test
embed_dropout=args.embed_dropout,
)
model = WideDeep(deeptabular=deeptabular)
return model
if __name__ == "__main__":
model_name = "tabresnet"
results_dir, models_dir = set_dirs(model_name)
prepare_tab, X_train, X_test, y_train, y_test = prepare_data(results_dir)
args = read_best_model_args(results_dir)
model = set_model(args, prepare_tab)
run_experiment_and_save(
model,
model_name,
results_dir,
models_dir,
args,
X_train,
X_test,
y_train,
y_test,
)
# 200 is rather arbitraty but one has to make a decision as to how to decide
# if something will be represented as embeddings or continuous in a "kind-of"
# automated way
cat_embed_cols = []
for col in train.columns:
if train[col].dtype == "O" or train[col].nunique() < 200 and col != "target":
cat_embed_cols.append(col)
# all columns will be represented by embeddings
prepare_tab = TabPreprocessor(embed_cols=cat_embed_cols, for_tabtransformer=True)
X_train = prepare_tab.fit_transform(train)
y_train = train.target.values
X_test = prepare_tab.transform(test)
y_test = test.target.values
args = read_best_model_args(RESULTS_DIR)
if args.mlp_hidden_dims == "same":
mlp_hidden_dims = [
len(cat_embed_cols) * args.input_dim,
len(cat_embed_cols) * args.input_dim,
(len(cat_embed_cols) * args.input_dim) // 2,
]
elif args.mlp_hidden_dims == "None":
mlp_hidden_dims = None
else:
mlp_hidden_dims = eval(args.mlp_hidden_dims)
deeptabular = TabTransformer(
column_idx=prepare_tab.column_idx,
embed_input=prepare_tab.embeddings_input,
results_d["trainer_history"] = trainer.history
results_d["trainer_lr_history"] = trainer.lr_history
results_d["runtime"] = runtime
with open(results_dir / filename, "wb") as f:
pickle.dump(results_d, f)
if __name__ == "__main__":
model_name = "tabmlp"
results_dir, models_dir = set_dirs(model_name)
prepare_tab, X_train, X_test, y_train, y_test = prepare_data(results_dir)
args = read_best_model_args(results_dir, exp_idx=0)
model = set_model(args, prepare_tab)
run_experiment_and_save(
model,
model_name,
results_dir,
models_dir,
args,
X_train,
X_test,
y_train,
y_test,
fl_exp_indx=0,
)