def test_load_glass_ternary_landolt(self):
df = load_glass_ternary_landolt()
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df), 6118)
df = load_glass_ternary_landolt(unique_composition=False)
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df), 7191)
df = load_glass_ternary_landolt(processing="meltspin")
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df), 5736)
df = load_glass_ternary_landolt(processing="sputtering")
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df), 403)
with self.assertRaises(ValueError):
df = load_glass_ternary_landolt(processing="spittering")
def test_load_glass_ternary_landolt(self):
df = load_glass_ternary_landolt()
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df), 6118)
df = load_glass_ternary_landolt(unique_composition=False)
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df), 7191)
df = load_glass_ternary_landolt(processing="meltspin")
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df), 5736)
df = load_glass_ternary_landolt(processing="sputtering")
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df), 403)
with self.assertRaises(ValueError):
df = load_glass_ternary_landolt(processing="spittering")
target = "gfa"
timelimit_secs = 7200
rs = 29
feature_output_path = "example_data/matbench_data/featurized_data/"
model_tmp_path = r'example_data/matbench_data/autosklearn_output/tmp/'
model_output_path = r'example_data/matbench_data/autosklearn_output/output/'
feature_output_file = \
os.path.join(feature_output_path,
"{}_all_featurized_data.csv".format(data_name))
if os.path.exists(feature_output_file):
df = pd.read_csv(feature_output_file, index_col=0)
else:
df_init = load_glass_ternary_landolt()
prof = Profile()
prof.enable()
featzer = Featurize()
df_feats = featzer.featurize_formula(df_init, featurizers="all")
prep = PreProcess(max_colnull=0.1)
df = prep.preprocess(df_feats)
prof.create_stats()
print("featurize time:\n")
pstats.Stats(prof).strip_dirs().sort_stats("time").print_stats(5)
if os.path.exists(feature_output_path):
print("output path: {} exists!".format(feature_output_path))