diff options
| author | adamhrv <adam@ahprojects.com> | 2019-03-19 12:20:38 +0100 |
|---|---|---|
| committer | adamhrv <adam@ahprojects.com> | 2019-03-19 12:20:38 +0100 |
| commit | 53f6e26015e65b8696ed1a6e5c74bdfef14b3ac2 (patch) | |
| tree | 8bf8b0019ff604b2165bc66e3b5deaba355b46af /megapixels/commands/datasets/pull_spreadsheet.py | |
| parent | 389f1f162720b577fcc652c95620eadd5e77ec43 (diff) | |
add cmds
Diffstat (limited to 'megapixels/commands/datasets/pull_spreadsheet.py')
| -rw-r--r-- | megapixels/commands/datasets/pull_spreadsheet.py | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/megapixels/commands/datasets/pull_spreadsheet.py b/megapixels/commands/datasets/pull_spreadsheet.py index 0094ea59..b8b68094 100644 --- a/megapixels/commands/datasets/pull_spreadsheet.py +++ b/megapixels/commands/datasets/pull_spreadsheet.py @@ -20,7 +20,7 @@ from app.utils.logger_utils import Logger log = Logger.getLogger() -opt_sheets = ['datasets', 'relationships', 'funding', 'references', 'sources', 'tags', 'citations', 'legal', ] +opt_sheets = ['datasets', 'relationships', 'funding', 'references', 'sources', 'tags', 'citations', 'legal'] @click.command() @click.option('-n', '--name', 'opt_spreadsheets', multiple=True, @@ -65,14 +65,14 @@ def clean_datasets_sheet_ft(df): # clean data for FT df = df[df['ft_share'] == 'Y'] keys = ['key', 'name_short', 'name_full', 'url', 'downloaded', 'purpose', 'wild'] - keys += ['campus', 'year_start', 'year_end', 'year_published', 'images', 'videos', 'identities', 'faces', 'youtube', 'flickr', 'google', 'bing', 'comment'] + keys += ['campus', 'year_start', 'year_end', 'year_published', 'images', 'videos', 'identities', 'faces_or_persons', 'youtube', 'flickr', 'google', 'bing', 'comment'] return df[keys] def clean_datasets_sheet_nyt(df): # clean data for FT df = df[df['ft_share'] == 'Y'] keys = ['key', 'name_short', 'name_full', 'url', 'downloaded', 'purpose', 'wild'] - keys += ['campus', 'year_start', 'year_end', 'year_published', 'images', 'videos', 'identities', 'faces', 'youtube', 'flickr', 'google', 'bing', 'comment'] + keys += ['campus', 'year_start', 'year_end', 'year_published', 'images', 'videos', 'identities', 'faces_or_persons', 'youtube', 'flickr', 'google', 'bing', 'comment'] return df[keys] def fetch_spreadsheet(): |