Add documentation for methods #17
Conversation
lokeshh
changed the title
| # | ||
| # @param [Symbol] as_a Specifies the form of output | ||
| # | ||
| # @return [Array, Hash] coefficients of the model |
There was a problem hiding this comment.
In this and some other methods it looks like, if as_a=:array is specified, then a Daru::Vector is returned, rather than an Array... Is that an issue? (If it is, I think that it can be a separate pull request though)
There was a problem hiding this comment.
You're right it will need to be fixed.
|
I read that Likelihood is a tool for summarizing the data’s evidence about unknown parameters. But here it doesn't take any input and returns a single value, so it's surprising me and I am not sure what its meant for. |
|
@lokeshh The log-likelihood is a function of the unknown parameters (such as the regression coefficients). The MLE (maximum likelihood estimation) algorithm aims to find values for the unknown parameters, at which the log-likelihood is maximized. I think here, It is useful, for example, if you fit two different models to the same data, and want to compare them. Then |
| @@ -74,6 +105,24 @@ def fitted_mean_values | |||
| @regression.fitted_mean_values | |||
| end | |||
|
|
|||
| # Returns for every data point obtained using the model | |||
There was a problem hiding this comment.
I think here is a typo. Do you mean "Returns the residual for (...)"?
lokeshh
changed the title
|
I think it can be merged now. I haven't changed the method names in this PR because it was for documentation purpose. For that I have this PR which also refactor some code #28 |
Addresses #4