from tqdm import tqdm
verbose = False
# # Script Inputs
target_cols = ["g_o", "g_oh", ]
# # Read Data
# +
df_eff_ox = get_df_eff_ox()
df_ads = get_df_ads()
df_ads = df_ads.set_index(["compenv", "slab_id", "active_site", ], drop=False)
df_features = get_df_features()
df_features.index = df_features.index.droplevel(level=5)
df_jobs = get_df_jobs()
df_slab = get_df_slab()
df_jobs_data = get_df_jobs_data()
df_jobs_data["rerun_from_oh"] = df_jobs_data["rerun_from_oh"].fillna(value=False)
df_dft = get_df_dft()
df_job_ids = get_df_job_ids()
df_job_ids = df_job_ids.set_index("job_id")
df_job_ids = df_job_ids[~df_job_ids.index.duplicated(keep='first')]
# -
directory = os.path.join(root_path_i, "out_data")
if not os.path.exists(directory): os.makedirs(directory)
path_i = os.path.join(root_path_i, "out_data/df_features.pickle")
with open(path_i, "wb") as fle:
pickle.dump(df_features, fle)
# #########################################################
# #########################################################
import pickle
import os
with open(path_i, "rb") as fle:
df_features = pickle.load(fle)
# #########################################################
# -
from methods import get_df_features
get_df_features().head()
# #########################################################
print(20 * "# # ")
print("All done!")
print("Run time:", np.round((time.time() - ti) / 60, 3), "min")
print("collect_feature_data.ipynb")
print(20 * "# # ")
# #########################################################
# + active=""
#
#
#