Merge pull request #1424 from VIGS25/enhance-disk-dataset

import shutil

import json

from multiprocessing.dummy import Pool

import warnings

__author__ = "Bharath Ramsundar"

__copyright__ = "Copyright 2016, Stanford University"

  @staticmethod

  def from_numpy(X,

                 y,

                 y=None,

                 w=None,

                 ids=None,

                 tasks=None,

    n_samples = len(X)

    if ids is None:

      ids = np.arange(n_samples)

    if y is not None:

      if w is None:

        w = np.ones_like(y)

      if tasks is None:

        if len(y.shape) > 1:

          n_tasks = y.shape[1]

        else:

          n_tasks = 1

        tasks = np.arange(n_tasks)

    else:

      if w is not None:

        warnings.warn('y is None but w is not None. Setting w to None',

                      UserWarning)

        w = None

      if tasks is not None:

        warnings.warn('y is None but tasks is not None. Setting tasks to None',

                      UserWarning)

        tasks = None

    # raw_data = (X, y, w, ids)

    return DiskDataset.create_dataset(

        [(X, y, w, ids)], data_dir=data_dir, tasks=tasks, verbose=verbose)