def test_persistence_and_digest(self):
pipe = MatPipe(**debug_config)
with self.assertRaises(NotFittedError):
pipe.save()
df = self.df[-200:]
pipe.fit(df, self.target)
filename = os.path.join(test_dir, "test_pipe.p")
pipe.save(filename=filename)
pipe = MatPipe.load(filename, logger=False)
df_test = pipe.predict(self.df[-220:-201], self.target)
self.assertTrue(self.target in df_test.columns)
self.assertTrue(self.target + " predicted" in df_test.columns)
digest_file = os.path.join(test_dir, "matdigest.txt")
digest = pipe.digest(filename=digest_file)
self.assertTrue(os.path.isfile(digest_file))
self.assertTrue(isinstance(digest, str))
def run_task(self, fw_spec):
# Read data from fw_spec
pipe_config_dict = fw_spec["pipe_config"]
fold = fw_spec["fold"]
kfold_config = fw_spec["kfold_config"]
target = fw_spec["target"]
data_pickle = fw_spec["data_pickle"]
clf_pos_label = fw_spec["clf_pos_label"]
problem_type = fw_spec["problem_type"]
learner_name = pipe_config_dict["learner_name"]
cache = fw_spec["cache"]
learner_kwargs = pipe_config_dict["learner_kwargs"]
reducer_kwargs = pipe_config_dict["reducer_kwargs"]
cleaner_kwargs = pipe_config_dict["cleaner_kwargs"]
autofeaturizer_kwargs = pipe_config_dict["autofeaturizer_kwargs"]
# Modify data_pickle based on computing resource
data_dir = os.environ['AMM_DATASET_DIR']
data_file = os.path.join(data_dir, data_pickle)
# Modify save_dir based on computing resource
bench_dir = os.environ['AMM_BENCH_DIR']
base_save_dir = fw_spec["base_save_dir"]
base_save_dir = os.path.join(bench_dir, base_save_dir)
save_dir = fw_spec.pop("save_dir")
save_dir = os.path.join(base_save_dir, save_dir)
if not os.path.exists(save_dir):
os.makedirs(save_dir)
from multiprocessing import cpu_count
ont = os.environ.get("OMP_NUM_THREADS", None)
print("Number of omp threads: {}".format(ont))
print("Number of cpus: {}".format(cpu_count()))
# n_jobs = int(cpu_count()/2)
# print("Setting number of featurization jobs to: {}".format(n_jobs))
# autofeaturizer_kwargs["n_jobs"] = n_jobs
# learner_kwargs["verbosity"] = 3
# Set up pipeline config
if learner_name == "TPOTAdaptor":
learner = TPOTAdaptor(**learner_kwargs)
elif learner_name == "rf":
warnings.warn(
"Learner kwargs passed into RF regressor/classifiers bc. rf being used."
)
learner = SinglePipelineAdaptor(
regressor=RandomForestRegressor(**learner_kwargs),
classifier=RandomForestClassifier(**learner_kwargs))
else:
raise ValueError("{} not supported by RunPipe yet!"
"".format(learner_name))
if cache:
autofeaturizer_kwargs["cache_src"] = os.path.join(
base_save_dir, "features.json")
pipe_config = {
"learner": learner,
"reducer": FeatureReducer(**reducer_kwargs),
"cleaner": DataCleaner(**cleaner_kwargs),
"autofeaturizer": AutoFeaturizer(**autofeaturizer_kwargs)
}
logger = initialize_logger(AMM_LOGGER_BASENAME, filepath=save_dir)
pipe = MatPipe(**pipe_config, logger=logger)
# Set up dataset
# Dataset should already be set up correctly as pickle beforehand.
# this includes targets being converted to classification, removing
# extra columns, having the names of featurization cols set to the
# same as the matpipe config, etc.
df = pd.read_pickle(data_file)
# Check other parameters that would otherwise not be checked until after
# benchmarking, hopefully saves some errors at the end during scoring.
if problem_type not in [AMM_CLF_NAME, AMM_REG_NAME]:
raise ValueError("Problem must be either classification or "
"regression.")
elif problem_type == AMM_CLF_NAME:
if not isinstance(clf_pos_label, (str, bool)):
raise TypeError(
"The classification positive label should be a "
"string, or bool not {}."
"".format(type(clf_pos_label)))
elif clf_pos_label not in df[target]:
raise ValueError("The classification positive label should be"
"present in the target column.")
elif len(df[target].unique()) > 2:
raise ValueError("Only binary classification scoring available"
"at this time.")
# Set up testing scheme
if problem_type == AMM_REG_NAME:
kfold = KFold(**kfold_config)
else:
kfold = StratifiedKFold(**kfold_config)
if fold >= kfold.n_splits:
raise ValueError("{} is out of range for KFold with n_splits="
"{}".format(fold, kfold))
# Run the benchmark
t1 = time.time()
results = pipe.benchmark(df,
target,
kfold,
fold_subset=[fold],
cache=True)
result_df = results[0]
elapsed_time = time.time() - t1
# Save everything
pipe.save(os.path.join(save_dir, "pipe.p"))
pipe.digest(os.path.join(save_dir, "digest.txt"))
result_df.to_csv(os.path.join(save_dir, "test_df.csv"))
pipe.post_fit_df.to_csv(os.path.join(save_dir, "fitted_df.csv"))
# Evaluate model
true = result_df[target]
test = result_df[target + " predicted"]
pass_to_storage = {}
if problem_type == AMM_REG_NAME:
pass_to_storage["r2"] = r2_score(true, test)
pass_to_storage["mae"] = mean_absolute_error(true, test)
pass_to_storage['rmse'] = sqrt(mean_squared_error(true, test))
elif problem_type == AMM_CLF_NAME:
pass_to_storage["f1"] = f1_score(true,
test,
pos_label=clf_pos_label)
pass_to_storage["roc_auc"] = roc_auc_score(true, test)
pass_to_storage["accuracy"] = accuracy_score(true, test)
else:
raise ValueError("Scoring method for problem type {} not supported"
"".format(problem_type))
# Extract important details for storage
try:
# TPOT Adaptor
best_pipeline = [
str(step) for step in pipe.learner.best_pipeline.steps
]
except AttributeError:
best_pipeline = str(pipe.learner.best_pipeline)
features = pipe.learner.features
n_features = len(features)
fold_orig = list(kfold.split(df, y=df[target]))[fold]
n_samples_train_original = len(fold_orig[0])
n_samples_test_original = len(fold_orig[1])
pass_to_storage.update({
"target": target,
"best_pipeline": best_pipeline,
"elapsed_time": elapsed_time,
"features": features,
"n_features": n_features,
"n_test_samples_original": n_samples_test_original,
"n_train_samples_original": n_samples_train_original,
"n_train_samples": len(pipe.post_fit_df),
"n_test_samples": len(test),
"test_sample_frac_retained": len(test) / n_samples_test_original,
"completion_time": datetime.datetime.now(),
"base_save_dir": base_save_dir,
"save_dir": save_dir
})
fw_spec.update(pass_to_storage)
class TestMatPipe(unittest.TestCase):
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 test_transferability(self):
df_train = self.df.iloc[:200]
df_test = self.df.iloc[201:250]
self.pipe.fit(df_train, self.target)
df_test = self.pipe.predict(df_test, self.target)
true = df_test[self.target]
test = df_test[self.target + " predicted"]
self.assertTrue("composition" not in df_test.columns)
self.assertTrue(r2_score(true, test) > 0.5)
# Use the same pipe object by refitting and reusing
df_train2 = self.df.iloc[250:450]
df_test2 = self.df.iloc[451:500]
self.pipe.fit(df_train2, self.target)
df_test2 = self.pipe.predict(df_test2, self.target)
true2 = df_test2[self.target]
test2 = df_test2[self.target + " predicted"]
self.assertTrue("composition" not in df_test2.columns)
self.assertTrue(r2_score(true2, test2) > 0.5)
def test_user_features(self):
df = self.df
df["G_VRH"] = self.extra_features
self.assertTrue("G_VRH" in df.columns)
self.assertTrue("K_VRH" in df.columns)
df_train = df.iloc[:200]
df_test = df.iloc[201:250]
self.pipe.fit(df_train, self.target)
# If shear modulus is included as a feature it should probably show up
# in the final pipeline
self.assertTrue("G_VRH" in self.pipe.learner.features)
df_test = self.pipe.predict(df_test, self.target)
true = df_test[self.target]
test = df_test[self.target + " predicted"]
self.assertTrue(r2_score(true, test) > 0.75)
@unittest.skipIf(int(os.environ.get("SKIP_INTENSIVE", 0)),
"Test too intensive for CircleCI commit builds.")
def test_benchmarking_no_cache(self):
pipe = self.pipe
# Make sure we can't run a cached run with no cache AF and cache pipe
with self.assertRaises(AutomatminerError):
self._run_benchmark(cache=True, pipe=pipe)
self._run_benchmark(cache=False, pipe=pipe)
@unittest.skipIf(int(os.environ.get("SKIP_INTENSIVE", 0)),
"Test too intensive for CircleCI commit builds.")
def test_benchmarking_cache(self):
pipe = self.pipe_cached
# Make sure we can't run a cached run with no cache AF and cache pipe
with self.assertRaises(AutomatminerError):
self._run_benchmark(cache=False, pipe=pipe)
self._run_benchmark(cache=True, pipe=pipe)
def test_persistence_and_digest(self):
with self.assertRaises(NotFittedError):
self.pipe.save()
df = self.df[-200:]
self.pipe.fit(df, self.target)
filename = os.path.join(test_dir, PIPE_PATH)
self.pipe.save(filename=filename)
self.pipe = MatPipe.load(filename, logger=False)
df_test = self.pipe.predict(self.df[-220:-201], self.target)
self.assertTrue(self.target in df_test.columns)
self.assertTrue(self.target + " predicted" in df_test.columns)
digest_file = os.path.join(test_dir, DIGEST_PATH)
digest = self.pipe.digest(filename=digest_file)
self.assertTrue(os.path.isfile(digest_file))
self.assertTrue(isinstance(digest, str))
def _run_benchmark(self, cache, pipe):
# Test static, regular benchmark (no fittable featurizers)
df = self.df.iloc[500:600]
kfold = KFold(n_splits=5)
df_tests = pipe.benchmark(df, self.target, kfold, cache=cache)
self.assertEqual(len(df_tests), kfold.n_splits)
# Make sure we retain a good amount of test samples...
df_tests_all = pd.concat(df_tests)
self.assertGreaterEqual(len(df_tests_all), 0.95 * len(df))
# Test static subset of kfold
df2 = self.df.iloc[500:550]
df_tests2 = pipe.benchmark(df2,
self.target,
kfold,
fold_subset=[0, 3],
cache=cache)
self.assertEqual(len(df_tests2), 2)
def tearDown(self):
for remnant in [CACHE_SRC, PIPE_PATH, DIGEST_PATH]:
if os.path.exists(remnant):
os.remove(remnant)