mutliple regression using rpy

[libiger]

Hi,

I am trying to perform multiple regression in python using rpy.
I can get it to work for two arrays, however when I try to regress a matrix and an array (as in the following code) I get an error message (below.)
Can someone please help?

Thanks,
Ondrej

from rpy import *

phenotypes = array([4,5,4,3])
X = array([1,2,3,4],[3,2,4,5],[6,5,4,3])
d = r.data_frame(x=X, y=phenotypes)
model = r("y~x")
set_default_mode(NO_CONVERSION)
linear_model = r.lm(model, data = d)
set_default_mode(BASIC_CONVERSION)
print r.summary(linear_model)


Traceback (most recent call last):
  File "genback.py", line 242, in ?
    linear_model = r.lm(model, data = d)
rpy.RException: Error in eval(expr, envir, enclos) : object "x" not found

[bartonc]

Hi,

I am trying to perform multiple regression in python using rpy.
I can get it to work for two arrays, however when I try to regress a matrix and an array (as in the following code) I get an error message (below.)
Can someone please help?

Thanks,
Ondrej

from rpy import *

phenotypes = array([4,5,4,3])
X = array([1,2,3,4],[3,2,4,5],[6,5,4,3])
d = r.data_frame(x=X, y=phenotypes)
model = r("y~x")
set_default_mode(NO_CONVERSION)
linear_model = r.lm(model, data = d)
set_default_mode(BASIC_CONVERSION)
print r.summary(linear_model)


Traceback (most recent call last):
  File "genback.py", line 242, in ?
    linear_model = r.lm(model, data = d)
rpy.RException: Error in eval(expr, envir, enclos) : object "x" not found

I don't use that package, but one thing stands out:

d = r.data_frame(x=X, y=phenotypes)

Ok; get d from the object r's data_frame() method.

model = r("y~x")

? What does r do when called instead of using an access method?

linear_model = r.lm(model, data = d)

Ok; get linear_model from the object r's lm() method.