patsy
patsy copied to clipboard
Describing statistical models in Python using symbolic formulas
Is it currently possible to build a sparse design matrix from a formula? This is desirable for formulas with lot of categorical variables and their interactions, which are naturally represented...
Use cases: - It should be possible to pickle a `DesignMatrixBuilder` (and/or `DesignInfo`, same issue) - Checking if two designs are the same: this comes up for rERPy -- it's...
See my stackoverflow question here https://stackoverflow.com/questions/71550468/does-python-have-an-analogue-to-rs-splinesns I am thinking that there is not current way to make this happen in patsy. I am requesting a feature for a `ns` function...
R lets you regress a target against all the variables in the dataframe by simply typing "target ~ ." This is particularly useful when we have lots of columns and...
This one's a minor fix imposing approximate comparison in floats.
Hello, I've added the function `poly` which attempts to reproduce R's `poly` function. See here: https://stat.ethz.ch/R-manual/R-devel/library/stats/html/poly.html Thanks.
As per patsy's [documentation](https://patsy.readthedocs.io/en/latest/formulas.html#intercept-handling), the following results in a design matrix with no intercept: ```python >>> patsy.dmatrix('a + b - 1', pandas.DataFrame({'a':[1,2], 'b':[3,4]})) ``` ``` DesignMatrix with shape (2, 2)...
Hello, This is a continuation effort of #86 and #67. My apologies if this is viewed as stepping on someone else's toes... but this is an interesting--and useful topic--for me....
For some use cases, it would be nice to have patsy code a design matrix as if it were going to include an intercept (so e.g. it would exclude some...
Hello, I have a proposal that really came about because of the way I've been interacting with patsy. My datasets are kind of long and kind of wide. I have...