def setUp(self):
df = load_dataset("elastic_tensor_2015").rename(
columns={"formula": "composition"})
self.df = df[["composition", "K_VRH"]]
self.df_struc = df[["composition", "structure", "K_VRH"]]
self.extra_features = df["G_VRH"]
self.target = "K_VRH"
self.config = get_preset_config("debug_single")
self.config_cached = get_preset_config("debug_single",
cache_src=CACHE_SRC)
self.pipe = MatPipe(**self.config)
self.pipe_cached = MatPipe(**self.config_cached)
def __init__(self,
autofeaturizer=None,
cleaner=None,
reducer=None,
learner=None):
transformers = [autofeaturizer, cleaner, reducer, learner]
if not all(transformers):
if any(transformers):
raise AutomatminerError(
"Please specify all dataframe"
"transformers (autofeaturizer, learner,"
"reducer, and cleaner), or none (to use"
"default).")
else:
config = get_preset_config("express")
autofeaturizer = config["autofeaturizer"]
cleaner = config["cleaner"]
reducer = config["reducer"]
learner = config["learner"]
self.autofeaturizer = autofeaturizer
self.cleaner = cleaner
self.reducer = reducer
self.learner = learner
self.pre_fit_df = None
self.post_fit_df = None
self.ml_type = None
self.target = None
self.version = get_version()
super(MatPipe, self).__init__()
def from_preset(preset: str = "express", **powerups):
"""
Get a preset MatPipe from a string using
automatminer.presets.get_preset_config
See get_preeset_config for more inspect.
Args:
preset (str): The preset configuration to use.
Current presets are:
- production
- express (recommended for most problems)
- express_single (no AutoML, XGBoost only)
- heavy
- debug
- debug_single (no AutoML, XGBoost only)
powerups (kwargs): General upgrades/changes to apply.
Current powerups are:
- cache_src (str): The cache source if you want to save
features.
- n_jobs (int): The number of parallel process to use when
running.
"""
config = get_preset_config(preset, **powerups)
return MatPipe(**config)
def __init__(self, autofeaturizer=None, cleaner=None, reducer=None,
learner=None, logger=True, log_level=None):
transformers = [autofeaturizer, cleaner, reducer, learner]
if not all(transformers):
if any(transformers):
raise AutomatminerError("Please specify all dataframe"
"transformers (autofeaturizer, learner,"
"reducer, and cleaner), or none (to use"
"default).")
else:
config = get_preset_config("production")
autofeaturizer = config["autofeaturizer"]
cleaner = config["cleaner"]
reducer = config["reducer"]
learner = config["learner"]
self._logger = self.get_logger(logger, level=log_level)
self.autofeaturizer = autofeaturizer
self.cleaner = cleaner
self.reducer = reducer
self.learner = learner
self.autofeaturizer._logger = self.get_logger(logger)
self.cleaner._logger = self.get_logger(logger)
self.reducer._logger = self.get_logger(logger)
self.learner._logger = self.get_logger(logger)
self.pre_fit_df = None
self.post_fit_df = None
self.is_fit = False
self.ml_type = None
def test_missing(self):
with self.assertRaises(ValueError):
_ = get_preset_config("QWERTYUIOP1234567890")
def test_caching_powerup(self):
cache_src = "./somefile.json"
prod = get_preset_config("production", cache_src=cache_src)
self.assertEqual(prod[AF_KEY].cache_src, cache_src)
MatPipe(**prod)
def test_heavy(self):
heavy = get_preset_config("heavy")
for k in KEYSET:
self.assertTrue(k in heavy.keys())
MatPipe(**heavy)
def test_express_single(self):
express_single = get_preset_config("express_single")
for k in KEYSET:
self.assertTrue(k in express_single.keys())
MatPipe(**express_single)
def test_express(self):
express = get_preset_config("express")
for k in KEYSET:
self.assertTrue(k in express.keys())
MatPipe(**express)
def test_debug_single(self):
debug_single = get_preset_config("debug_single")
for k in KEYSET:
self.assertTrue(k in debug_single.keys())
MatPipe(**debug_single)
def test_debug(self):
debug = get_preset_config("debug")
for k in KEYSET:
self.assertTrue(k in debug.keys())
MatPipe(**debug)
def test_production(self):
prod = get_preset_config("production")
for k in KEYSET:
self.assertTrue(k in prod.keys())
MatPipe(**prod)
def setUp(self):
basedir = os.path.dirname(os.path.realpath(__file__))
df = pd.read_csv(basedir + "/mini_automl_df.csv", index_col=0)
self.train_df = df.copy(deep=True).iloc[:450]
self.test_df = df.copy(deep=True).iloc[451:]
self.tpot = get_preset_config("debug")["learner"]
def test_n_jobs_powerup(self):
n_jobs = 1
prod = get_preset_config("production", n_jobs=n_jobs)
self.assertEqual(prod[AF_KEY].n_jobs, n_jobs)
self.assertEqual(prod[ML_KEY].tpot_kwargs["n_jobs"], n_jobs)
MatPipe(**prod)
def setUp(self):
self.config = get_preset_config("debug")
def setUp(self):
self.config = get_preset_config('debug')
