def test_rdkit_log(capfd):
"""Test multiple rdkit log scenarios."""
check_logs_are_shown(capfd)
with dm.without_rdkit_log():
check_logs_are_not_shown(capfd)
check_logs_are_shown(capfd)
dm.disable_rdkit_log()
check_logs_are_not_shown(capfd)
dm.enable_rdkit_log()
check_logs_are_shown(capfd)
dm.disable_rdkit_log()
with dm.without_rdkit_log():
check_logs_are_not_shown(capfd)
check_logs_are_not_shown(capfd)
import pyarrow.dataset as ds
from pyarrow import Table
from pyarrow import csv
import pyarrow as pa
from pyarrow.parquet import ParquetWriter
import pathlib
import pandas as pd
import pyarrow.feather as fe
import datamol as dm
import operator
dm.disable_rdkit_log()
dataset = [
'/data/dockop_glide_d3/second50k_glide_molchunkout/second50k_glide_out.molchunk',
'/data/dockop_glide_d3/first50k_glide_molchunkout',
'/data/dockop_glide_d3/thirdd50k_glide_molchunkout/third50k_glide_out.molchunk',
'/data/dockop_glide_d3/fourth50k_glide_molchunkout/fourth50k_glide_out.molchunk',
'/data/dockop_glide_d3/fithround_glide_molchunkout/fifth50k_glide_out.molchunk'
]
dflist = []
for data in dataset:
dataset = ds.dataset(data, format="feather")
df = dataset.to_table().to_pandas()
dflist.append(df)
def combine_unique_molchunks_with_identical_columns(molchunk_1, molchunk_2):
outer_merged = pd.merge(molchunk_1, molchunk_2, how='outer')
return outer_merged