Merge pull request #2525 from Suzukazole/flake8fix

Featurizers, transformers, and splitters for MolNet.

"""

import os

import importlib

import inspect

import logging

import json

from typing import Dict, List, Any

from typing import Dict, Any

import deepchem as dc

from deepchem.feat.base_classes import Featurizer

from deepchem.trans.transformers import Transformer

from deepchem.splits.splitters import Splitter

from collections import OrderedDict

import numpy as np

from deepchem.molnet.load_function.molnet_loader import TransformerGenerator, _MolnetLoader

from deepchem.data import Dataset

from typing import List, Optional, Tuple, Union

from deepchem.molnet.load_function.bace_features import bace_user_specified_features

BACE_URL = "https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/bace.csv"

BACE_REGRESSION_TASKS = ["pIC50"]

  time2 = time.time()

  ########## TIMING ################

  # TIMING

  logger.info("TIMING: FACTORS fitting took %0.3f s" % (time2 - time1))

  return train_dataset, valid_dataset, test_dataset

  else:

    logger.info("Featurizing datasets")

    train_dataset, valid_dataset, test_dataset = \

    gen_factors(FACTORS_tasks=FACTORS_tasks, data_dir=data_dir, train_dir=train_dir,

                valid_dir=valid_dir, test_dir=test_dir, shard_size=shard_size)

    train_dataset, valid_dataset, test_dataset = gen_factors(

        FACTORS_tasks=FACTORS_tasks,

        data_dir=data_dir,

        train_dir=train_dir,

        valid_dir=valid_dir,

        test_dir=test_dir,

        shard_size=shard_size)

  transformers = get_transformers(train_dataset)

               data_dir,

               shard_size=2000):

  """Load KAGGLE datasets. Does not do train/test split"""

  ############################################################## TIMING

  # TIMING

  time1 = time.time()

  ############################################################## TIMING

  # TIMING

  # Set some global variables up top

  train_files = os.path.join(data_dir,

                             "KAGGLE_training_disguised_combined_full.csv.gz")

  valid_dataset.move(valid_dir)

  test_dataset.move(test_dir)

  ############################################################## TIMING

  # TIMING

  time2 = time.time()

  logger.info("TIMING: KAGGLE fitting took %0.3f s" % (time2 - time1))

  ############################################################## TIMING

  # TIMING

  return train_dataset, valid_dataset, test_dataset