def test_benchmarking(self):
pipe = MatPipe(**debug_config)
df = self.df.iloc[500:700]
df_test = pipe.benchmark(df, self.target, test_spec=0.25)
self.assertEqual(df_test.shape[0], 50)
true = df_test[self.target]
test = df_test[self.target + " predicted"]
self.assertTrue(r2_score(true, test) > 0.5)
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)
else:
removed_feat = idx
if removed_feat not in rm_feats:
rm_feats.append(removed_feat)
self.logger.debug('"{}" correlates strongly with '
'"{}"'.format(feature, idx))
self.logger.debug(
'removing "{}"...'.format(removed_feat))
if removed_feat == feature:
break
if len(rm_feats) > 0:
df = df.drop(rm_feats, axis=1)
self.logger.info('These {} features were removed due to cross '
'correlation with the current features more than '
'{}:\n{}'.format(len(rm_feats), R_max, rm_feats))
return df
if __name__ == "__main__":
from matminer.datasets.dataset_retrieval import load_dataset
from automatminer.pipeline import MatPipe, debug_config
target = "eij_max"
df = load_dataset("piezoelectric_tensor").rename(
columns={"formula": "composition"})[[
target, "composition", "structure"
]]
mp = MatPipe(**debug_config)
df2 = mp.benchmark(df, target, test_spec=0.2)
print(df2)