| from collections import defaultdict | |
| def node(): | |
| return defaultdict(node) | |
| def word_exists(word, node): | |
| if not word: | |
| return None in node | |
| return word_exists(word[1:], node[word[0]]) |
| # Lint JSON with python (the exit 255 stops xargs after the first failed command) | |
| find . -name "*.json" -print | xargs -Ixx bash -c "echo JSON linting xx 1>&2; cat xx | python -mjson.tool > /dev/null || exit 255" |
If a project has to have multiple git repos (e.g. Bitbucket and Github) then it's better that they remain in sync.
Usually this would involve pushing each branch to each repo in turn, but actually Git allows pushing to multiple repos in one go.
If in doubt about what git is doing when you run these commands, just
| def dataframe_difference(df1, df2, which=None): | |
| """Find rows which are different.""" | |
| comparison_df = df1.merge(df2, | |
| indicator=True, | |
| how='outer') | |
| if which is None: | |
| diff_df = comparison_df[comparison_df['_merge'] != 'both'] | |
| else: | |
| diff_df = comparison_df[comparison_df['_merge'] == which] | |
| diff_df.to_csv('data/diff.csv') |
