Added first version of model command. Need to wire in connections to make it run.

from deep_chem.utils.save import load_model

from deep_chem.utils.evaluate import compute_model_performance

def parse_args(input_args=None):

  """Parse command-line arguments."""

  parser = argparse.ArgumentParser()

  subparsers = parser.add_subparsers(title='Modes')

  # FEATURIZE FLAGS

def add_featurization_command(subparsers):

  featurize_cmd = subparsers.add_parser("featurize",

      help="Featurize raw input data.")

  featurize_cmd.add_argument("--input-file", required=1,

      help="Folder to generate processed dataset in.")

  featurize_cmd.set_defaults(func=featurize_input)

  # Train/Test Splits flag 

def add_train_test_command(subparsers):

  train_test_cmd = subparsers.add_parser("train-test-split",

      help="Apply standard data transforms to raw features generated by featurize,\n"

           "then split data into train/test and store data as (X,y) matrices.")

      choices=["log", "normalize"],

      help="Transforms to apply to output data.")

  train_test_cmd.add_argument("--feature-types", nargs="+", required=1,

                      help="Types of featurizations to use.\n"

                           "Each featurization must correspond to subdirectory in\n"

                           "generated data directory.")

      help="Types of featurizations to use. Each featurization must correspond\n"

           "to subdirectory in generated data directory.")

  train_test_cmd.add_argument("--paths", nargs="+", required=1,

      help="Paths to input datasets.")

  train_test_cmd.add_argument("--splittype", type=str, default="scaffold",

      choices=["scaffold", "random", "specified"],

                       help="Type of train/test data-splitting.\n"

                            "scaffold uses Bemis-Murcko scaffolds.\n"

      help="Type of train/test data-splitting. 'scaffold' uses Bemis-Murcko scaffolds.\n"

           "specified requires that split be in original data.")

  train_test_cmd.add_argument("--weight-positives", type=bool, default=False,

      help="Weight positive examples to have same total weight as negatives.")

      help="Location to save test set.")

  train_test_cmd.set_defaults(func=train_test_input)

  # TRAIN FLAGS

  train_cmd = subparsers.add_parser("fit",

                  help="Fit a model to training data.")

  group = train_cmd.add_argument_group("load-and-transform")

  group.add_argument("--task-type", default="classification",

                      choices=["classification", "regression"],

                      help="Type of learning task.")

  group.add_argument("--saved-data", required=1,

                     help="Location of saved transformed data.")

  # TODO(rbharath): CODE SMELL. This shouldn't be shuttled around

  group.add_argument("--paths", nargs="+", required=1,

                      help="Paths to input datasets.")

  group = train_cmd.add_argument_group("model")

def add_model_arguments(fit_cmd):

  group = fit_cmd.add_argument_group("model")

  group.add_argument("--model", required=1,

      choices=["logistic", "rf_classifier", "rf_regressor",

      "linear", "ridge", "lasso", "lasso_lars", "elastic_net",

      help="Type of model to build. Some models may allow for\n"

           "further specification of hyperparameters. See flags below.")

  group = train_cmd.add_argument_group("Neural Net Parameters")

  group = fit_cmd.add_argument_group("Neural Net Parameters")

  group.add_argument("--n-hidden", type=int, default=500,

      help="Number of hidden neurons for NN models.")

  group.add_argument("--learning-rate", type=float, default=0.01,

  group.add_argument("--validation-split", type=float, default=0.0,

      help="Percent of training data to use for validation.")

  group = train_cmd.add_argument_group("save")

def add_fit_command(subparsers):

  # TRAIN FLAGS

  fit_cmd = subparsers.add_parser("fit",

      help="Fit a model to training data.")

  group = fit_cmd.add_argument_group("load-and-transform")

  group.add_argument("--task-type", default="classification",

      choices=["classification", "regression"],

      help="Type of learning task.")

  group.add_argument("--saved-data", required=1,

      help="Location of saved transformed data.")

  # TODO(rbharath): CODE SMELL. This shouldn't be shuttled around

  group.add_argument("--paths", nargs="+", required=1,

                      help="Paths to input datasets.")

  add_model_arguments(fit_cmd)

  group = fit_cmd.add_argument_group("save")

  group.add_argument("--saved-out", type=str, required=1,

      help="Location to save trained model.")

  train_cmd.set_defaults(func=fit_model)

  fit_cmd.set_defaults(func=fit_model)

def add_eval_command(subparsers):

  eval_cmd = subparsers.add_parser("eval",

      help="Evaluate trained model on test data processed by transform.")

  group = eval_cmd.add_argument_group("load model/data")

      help="Outputted predictions on the test set.")

  eval_cmd.set_defaults(func=eval_trained_model)

# TODO(rbharath): There are a lot of duplicate commands introduced here. Is

# there a nice way to factor them?

def add_model_command(subparsers):

  model_cmd = subparsers.add_parser("model",

      help="Combines featurize, train-test-split, fit, eval into one command\n"

           "for user convenience.")

  featurize_group = model_cmd.add_argument_group("featurize")

  featurize_group.add_argument("--input-file", required=1,

      help="Input file with data.")

  featurize_group.add_argument("--fields", required=1, nargs="+",

      help = "Names of fields. Fields correspond to columns in csv files,\n"

             "and to molecular property names for SDF files.")

  featurize_group.add_argument("--field-types", required=1, nargs="+",

      choices=["string", "float", "list-string", "list-float", "ndarray"],

      help="Type of data in fields.")

  featurize_group.add_argument("--feature-fields", type=str, nargs="+",

      help="Optional endpoint that holds pre-computed feature vector")

  featurize_group.add_argument("--prediction-field", type=str, required=1,

      help="Name of measured endpoint to predict.")

  featurize_group.add_argument("--split-field", type=str, default=None,

      help="Name of endpoint specifying train/test split.")

  featurize_group.add_argument("--smiles-field", type=str, default="smiles",

      help="Name of endpoint specifying SMILES for molecule.")

  featurize_group.add_argument("--id-field", type=str, default=None,

      help="Name of endpoint specifying unique identifier for molecule.\n"

           "If none is specified, then smiles-endpoint is used as identifier.")

  featurize_group.add_argument("--feature-types", nargs="+", required=1,

      help="Types of featurizations to use. Each featurization must correspond\n"

           "to subdirectory in generated data directory.")

  featurize_group.add_argument("--out", required=1,

      help="Folder to generate processed dataset in.")

  train_test_group = model_cmd.add_argument_group("train_test_group")

  train_test_group.add_argument("--input-transforms", nargs="+", default=[],

      choices=["normalize-and-truncate"],

      help="Transforms to apply to input data.")

  train_test_group.add_argument("--output-transforms", nargs="+", default=[],

      choices=["log", "normalize"],

      help="Transforms to apply to output data.")

  train_test_group.add_argument("--mode", default="singletask",

      choices=["singletask", "multitask"],

      help="Type of model being built.")

  train_test_group.add_argument("--splittype", type=str, default="scaffold",

      choices=["scaffold", "random", "specified"],

      help="Type of train/test data-splitting. 'scaffold' uses Bemis-Murcko scaffolds.\n"

           "specified requires that split be in original data.")

  add_model_arguments(model_cmd)

  model_cmd.add_argument("--task-type", default="classification",

      choices=["classification", "regression"],

      help="Type of learning task.")

  model_cmd.add_argument("--csv-out", type=str, default=None,

      help="Outputted predictions on the test set.")

def parse_args(input_args=None):

  """Parse command-line arguments."""

  parser = argparse.ArgumentParser()

  subparsers = parser.add_subparsers(title='Modes')

  add_featurization_command(subparsers)

  add_train_test_command(subparsers)

  add_fit_command(subparsers)

  add_eval_command(subparsers)

  add_model_command(subparsers)

  return parser.parse_args(input_args)

def featurize_input(args):