Merge branch 'master' of https://github.com/deepchem/deepchem into deprem

- pip install coveralls

- python setup.py install

script:

- nosetests --with-flaky -a '!slow' --with-timer --with-coverage --cover-package=deepchem -v deepchem --nologcapture

- nosetests --with-flaky -a '!slow' --with-timer --with-coverage --cover-package=deepchem

  -v deepchem --nologcapture

- find ./deepchem | grep .py$ |xargs python -m doctest -v

- bash devtools/travis-ci/test_format_code.sh

after_success:

- echo $TRAVIS_SECURE_ENV_VARS

- coveralls

deploy:

  provider: pypi

  user: "lilleswing"

  password:

    secure: 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

prune datasets

prune examples

# DeepChem

[![Build Status](https://travis-ci.org/deepchem/deepchem.svg?branch=master)](https://travis-ci.org/deepchem/deepchem)

[![Coverage Status](https://coveralls.io/repos/github/deepchem/deepchem/badge.svg?branch=master)](https://coveralls.io/github/deepchem/deepchem?branch=master)

[![Anaconda-Server Badge](https://anaconda.org/deepchem/deepchem/badges/version.svg)](https://anaconda.org/deepchem/deepchem)

[![PyPI version](https://badge.fury.io/py/deepchem.svg)](https://badge.fury.io/py/deepchem)

DeepChem aims to provide a high quality open-source toolchain that

democratizes the use of deep-learning in drug discovery, materials science, quantum chemistry, and biology.

1. Question: I'm seeing some failures in my test suite having to do with MKL

   ```Intel MKL FATAL ERROR: Cannot load libmkl_avx.so or libmkl_def.so.```

   Answer: This is a general issue with the newest version of `scikit-learn` enabling MKL by default. This doesn't play well with many linux systems. See BVLC/caffe#3884 for discussions. The following seems to fix the issue

   Answer: This is a general issue with the newest version of `scikit-learn` enabling MKL by default. This doesn't play well with many linux systems. See [BVLC/caffe#3884](https://github.com/BVLC/caffe/issues/3884) for discussions. The following seems to fix the issue

   ```bash

   conda install nomkl numpy scipy scikit-learn numexpr

   conda remove mkl mkl-service

from deepchem.data.data_loader import CSVLoader

from deepchem.data.data_loader import UserCSVLoader

from deepchem.data.data_loader import SDFLoader

from deepchem.data.data_loader import FASTALoader

import deepchem.data.tests

from deepchem.utils.save import log

from deepchem.utils.save import load_csv_files

from deepchem.utils.save import load_sdf_files

from deepchem.utils.save import encode_fasta_sequence

from deepchem.feat import UserDefinedFeaturizer

from deepchem.data import DiskDataset

    self.log_every_n = log_every_n

  def featurize(self, input_files, data_dir=None, shard_size=8192):

    """Featurize provided files and write to specified location."""

    """Featurize provided files and write to specified location.

    For large datasets, automatically shards into smaller chunks

    for convenience.

    Parameters

    ----------

    input_files: list

      List of input filenames.

    data_dir: str

      (Optional) Directory to store featurized dataset.

    shard_size: int

      (Optional) Number of examples stored in each shard.

    """

    log("Loading raw samples now.", self.verbose)

    log("shard_size: %d" % shard_size, self.verbose)

    log("Currently featurizing feature_type: %s" %

        self.featurizer.__class__.__name__, self.verbose)

    return featurize_mol_df(shard, self.featurizer, field=self.mol_field)

class FASTALoader(DataLoader):

  """

  Handles loading of FASTA files.

  """

  def __init__(self, verbose=True):

    """Initialize loader."""

    self.verbose = verbose

  def featurize(self, input_files, data_dir=None):

    """Featurizes fasta files.

    Parameters

    ----------

    input_files: list

      List of fasta files.

    data_dir: str

      (Optional) Name of directory where featurized data is stored.

    """

    if not isinstance(input_files, list):

      input_files = [input_files]

    def shard_generator():

      for input_file in input_files:

        X = encode_fasta_sequence(input_file)

        ids = np.ones(len(X))

        # (X, y, w, ids)

        yield X, None, None, ids

    return DiskDataset.create_dataset(shard_generator(), data_dir)