Committing first draft of solubility ipynb.

- nosetests -v deepchem

after_success:

- source devtools/travis-ci/after_sucess.sh

# AWS access_key and secret key secured through travis secure var api.

env:

  global:

  - secure: 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

          visible_inds.append(ind)

      yield df.loc[visible_inds]

  def train_valid_test_split(self, splittype, train_dir, test_dir,

                             valid_dir=None, frac_train=.8, frac_valid=.1,

                             frac_test=.1, seed=None):

  def train_valid_test_split(self, splittype, train_dir=None,

                             valid_dir=None, test_dir=None, frac_train=.8,

                             frac_valid=.1, frac_test=.1, seed=None):

    """

    Splits self into train/validation/test sets.

      train_inds, valid_inds, test_inds = self._specified_split()

    else:

      raise ValueError("improper splittype.")

    train_samples, valid_samples, test_samples = None, None, None

    if train_dir is not None:

      train_samples = FeaturizedSamples(samples_dir=train_dir, 

                                        dataset_files=self.dataset_files,

                                        featurizers=self.featurizers)

      train_samples._set_compound_df(self.compounds_df.iloc[train_inds])

    if test_dir is not None:

      test_samples = FeaturizedSamples(samples_dir=test_dir, 

                                       dataset_files=self.dataset_files,

                                       featurizers=self.featurizers)

      test_samples._set_compound_df(self.compounds_df.iloc[test_inds])

    if valid_dir is None:

      valid_samples = None

    else:

    if valid_dir is not None:

      valid_samples = FeaturizedSamples(samples_dir=valid_dir, 

                                       dataset_files=self.dataset_files,

                                       featurizers=self.featurizers)

    Returns FeaturizedDataset objects.

    """

    train_samples, _, test_samples = self.train_valid_test_split(

        splittype, train_dir, test_dir, valid_dir=None,

        splittype, train_dir, valid_dir=None, test_dir=test_dir,

        frac_train=frac_train, frac_test=1-frac_train, frac_valid=0.)

    return train_samples, test_samples

import numpy as np

import warnings

from deepchem.utils.save import log

from sklearn.metrics import mean_squared_error

from sklearn.metrics import roc_auc_score

from sklearn.metrics import r2_score

    Computes statistics of model on test data and saves results to csv.

    """

    pred_y_df = self.model.predict(self.dataset)

    if self.verbose:

      print("Saving predictions to %s" % csv_out)

    log("Saving predictions to %s" % csv_out, self.verbose)

    pred_y_df.to_csv(csv_out)

    if self.task_type == "classification":

          rms = np.nan

        performance_df.loc[i] = [task_name, r2s, rms]

    if self.verbose:

      print("Saving model performance scores to %s" % stats_file)

    log("Saving model performance scores to %s" % stats_file, self.verbose)

    performance_df.to_csv(stats_file)

    return pred_y_df, performance_df