better handling of svyglm objects and factor predictors

[tzoltak]

Please ensure the following before submitting a PR:

• [v] if suggesting code changes or improvements, open an issue first

• [v] for all but trivial changes (e.g., typo fixes), add your name to DESCRIPTION

• [v] for all but trivial changes (e.g., typo fixes), documentation your change in NEWS.md with a parenthetical reference to the issue number being addressed

• [v] if changing documentation, edit files in /R not /man and run devtools::document() to update documentation

• [v] add code or new test files to /tests for any new functionality or bug fix

• [v] make sure R CMD check runs without error before submitting the PR

• More Straightforward handling of "svyglm" objects from package survey (remove the design argument from margins.svyglm()). design in margins.svyglm #124

• Better handling of factor predictors. at and factors #116, margins(at = ) fails when only one factor level is specified #121, Problem with factors that have unused levels #125

• Added coef() method for "margins" class. Feature request: coef method for margins objects #131

[tzoltak]

And #132 is also solved.