Fixed issues with classification data sets

[dickeygh]

Features.py:

1. Added the section at lines 54-68. This section searches the data (contains featurizations) list and deletes the Nonetype elements of the list. The section also deletes the correlating target row from the df dataframe. This change allows for the clintox and BBBP data sets to run properly. #60

Main.py:

1. Adjusted slightly for classification workflow; no major changes.

[pep8speaks]

Hello @dickeygh! Thanks for updating this PR. We checked the lines you've touched for PEP 8 issues, and found:

• In the file core/features.py:

Line 55:5: E303 too many blank lines (2) Line 55:80: E501 line too long (113 > 79 characters) Line 58:80: E501 line too long (104 > 79 characters) Line 63:20: E711 comparison to None should be 'if cond is None:' Line 68:5: E303 too many blank lines (2) Line 68:80: E501 line too long (105 > 79 characters) Line 111:80: E501 line too long (82 > 79 characters) Line 116:69: E251 unexpected spaces around keyword / parameter equals

• In the file core/models.py:

Line 89:80: E501 line too long (91 > 79 characters) Line 103:80: E501 line too long (91 > 79 characters)

• In the file core/train.py:

Line 105:59: E261 at least two spaces before inline comment Line 105:80: E501 line too long (186 > 79 characters) Line 117:80: E501 line too long (105 > 79 characters)

Comment last updated at 2020-07-09 19:39:00 UTC