import sys import pytest @pytest.mark.skipif(sys.platform == "darwin", reason="do not run on mac os") def test_cv(): from flaml import AutoML import pandas as pd import requests train_data = { "sentence1": [ 'Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .', "Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion .", "They had published an advertisement on the Internet on June 10 , offering the cargo for sale , he added .", "Around 0335 GMT , Tab shares were up 19 cents , or 4.4 % , at A $ 4.56 , having earlier set a record high of A $ 4.57 .", ], "sentence2": [ 'Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .', "Yucaipa bought Dominick 's in 1995 for $ 693 million and sold it to Safeway for $ 1.8 billion in 1998 .", "On June 10 , the ship 's owners had published an advertisement on the Internet , offering the explosives for sale .", "Tab shares jumped 20 cents , or 4.6 % , to set a record closing high at A $ 4.57 .", ], "label": [1, 0, 1, 0], "idx": [0, 1, 2, 3], } train_dataset = pd.DataFrame(train_data) custom_sent_keys = ["sentence1", "sentence2"] label_key = "label" X_train = train_dataset[custom_sent_keys] y_train = train_dataset[label_key] automl = AutoML() automl_settings = { "gpu_per_trial": 0, "max_iter": 3, "time_budget": 5, "task": "seq-classification", "metric": "accuracy", "n_splits": 3, } automl_settings["custom_hpo_args"] = { "model_path": "google/electra-small-discriminator", "output_dir": "test/data/output/", "ckpt_per_epoch": 1, "fp16": False, } try: automl.fit(X_train=X_train, y_train=y_train, **automl_settings) except requests.exceptions.HTTPError: return if __name__ == "__main__": test_cv()