def test_memory_usage_dataframe(): np.random.seed(0) df = DataFrame() nelem = 1000 df["keys"] = hkeys = np.arange(nelem, dtype=np.float64) df["vals"] = hvals = np.random.random(nelem) nbytes = hkeys.nbytes + hvals.nbytes sizeof = df.memory_usage().sum() assert sizeof >= nbytes serialized_nbytes = len(pickle.dumps(df, protocol=pickle.HIGHEST_PROTOCOL)) # assert at least sizeof bytes were serialized assert serialized_nbytes >= sizeof