yardstick
yardstick copied to clipboard
tidymodels
Tidy methods for measuring model performance
It would be awesome to add weighted normalized gini to the set of available metrics for regression. This is useful in insurance when we want to evaluate to performance of...
## Nash-Sutcliffe efficiency (NSE) Please consider adding the Nash and Sutcliffe Efficiency ([NSE](https://en.wikipedia.org/wiki/Nash%E2%80%93Sutcliffe_model_efficiency_coefficient)) metric. It is highly used in hydrological studies, as it indicates how different the modeled-observed relationship is...
High frequency areas of the `conf_mat()` can be hard to read because of the contrast. something should be done. It is hard because sometime the text isn't super needed (at...
Here's what I want to do specifically. For example, let's say I have monthly trading data for all tickers in the stock market. I want to be able to sort...
## Feature Right now, passing anything that's truthy to `na_rm` will remove NA values, while values that can't be casted to logical crash in an `if` statement: ``` r yardstick::rmse_vec(c(1,...
The documentation for classification_cost mentions both "cost" and "costs" as the correct column name for classification costs in the costs data frame.
I've working on a tabular dataset where multiple rows are linked forming an "session". Within the session, one of the rows are our target action, and the goal for the...
In order to deal with business-like objectives in demand forecasting, it is good practice to use asymmetric metrics. For example, a retailer loses more money, if he underestimates the demand...
## Feature In situations when users want a quick overview of both in-class and model-wide precision, recall, F1 and support, `sklearn.metrics.classification_report` [seems like a very useful function](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html). As far as...
Hello, I'm not sure the implementation of Mean Percentage Error is correct there: https://github.com/tidymodels/yardstick/blob/8d41dc5c8b8eab1324704af2beb205e2610ad2cc/R/num-mpe.R#L113 In my opinion it should be calculated by doing `estimate - truth` instead of `truth -...
