I am using rpy2 to do some non-linear regression in r from python.
import rpy2.robjects as robjects
from rpy2.robjects import DataFrame, Formula
from rpy2.robjects import r
import rpy2.robjects.numpy2ri as npr
import numpy as np
from rpy2.robjects.packages import importr
r.nls(rates * 1-(1/(10^(a * count ^ (b-1)))), weights=count, start=list(a=a, b=b))
I have the following errors:
LookupError: 'nls' not found
AttributeError: 'R' object has no attribute 'nls'
It is also calling '~' as invalid syntax (I change it to * to get past it, but I do need it to be '~')
Any ideas on what is going wrong?
The code works fine in R.
This is the full code that works fine in R:
#This recipe assumes that the data is in a csv file called 'ratedata.csv' and that the values are in columns titled:
#Entity, Trials and Successes
#Data must be sorted in order of number of applications (i.e. the 'Trials' column) highest to lowest.
data <- read.csv("ratedata.csv") #get the data
count <- data$Trials #define count as the number of trials
rates <- data$Successes / data$Trials #define rate as the success rate for each entity
a <- .05 #set initial values for a and b to generate predicted rates
b <- 1.1 #these values need to be reasonably sensible otherwise the later estimate will not converge sensibly
fit <- nls(rates ~ 1-(1/(10^(a * count ^ (b-1)))), weights=count, start=list(a=a, b=b)) #non-linear least squares fit of data, weighted by count (weighting is optional but helps if it won't converge sensibly)
summary(fit) #to show estimates of a and b
coef <- as.vector(coef(fit)) #extract the coefficients into a vector for re-use
a <- coef[[1]] # extract the calculated coefficient for a
b <- coef[[2]] # extract the calculated coefficient for b
confidence <- confint(fit)
intervals <- as.vector(confidence[c(2,4)])
predopt <- 1-(1/(10^(a * count ^ (b-1)))) #predict rate by count with optimised coefficients
se <- sqrt(( predopt* (1-predopt))/count) #calculate standard error for predicted rate
upper95 <- predopt + 2*se #upper 95% limit - roughly speaking. Wald interval is appropriate in this case.
lower95 <- predopt - 2*se #lower 95% limit
upper99 <- predopt + 3*se #upper 99% limit
lower99 <- predopt - 3*se #lower 99% limit
xlim <- range(count + 10) #setup plot
ylim <- range(c(upper99, 0)) #lower limit truncated at zero
main <- plot(count, rates, pch = 21, col = "navajowhite4", bg = "mistyrose4") #plot rates by organisation
lines(count, predopt, type="l", xlim=xlim, ylim=ylim, xlab="Trials", ylab="Predicted rate", col = "red") #plot predicted rate
lines (count, upper95, lty="dashed") #plot upper limit
lines (count, lower95, lty="dashed") #plot lower limit
lines (count, upper99, lty="dotted") #plot upper limit
lines (count, lower99, lty="dotted") #plot lower limit
cat("The least-squares values of a and b are", coef[[1]], "and", coef[[2]], "respectively", "\n")
print(confint(fit))
if (intervals[[1]] < 1 & intervals [[2]] > 1)
{
message ("There is probably no relationship between success rate and number of trials")
} else
{
message ("There is probably a relationship between success rate and number of trials")
}
The columns Trials and Successes are just two columns of 48 integers (they can be anything. Trials ranges from 129 to 2359 and Successes range from 8 to 365
Updated problem 19.40pm 25th Jan 2018
Current code is:
import rpy2.robjects as ro
from rpy2.robjects.packages import importr
count = ro.IntVector([1,2,3,4,5])
rates = ro.IntVector([1,2,3,4,5])
a = ro.FloatVector([0.5])
b = ro.FloatVector([1.1])
base = importr('base', robject_translations={'with': '_with'})
stats = importr('stats', robject_translations={'format_perc': '_format_perc'})
my_formula = stats.as_formula('rates ~ 1-(1/(10^(a * count ^ (b-1))))')
d = ro.ListVector({'a': a, 'b': b})
fit = stats.nls(my_formula, weights=count, start=d)
I am getting the error:
---------------------------------------------------------------------------
RRuntimeError Traceback (most recent call last)
<ipython-input-2-3f7fcd7d7851> in <module>()
6 d = ro.ListVector({'a': a, 'b': b})
7
----> 8 fit = stats.nls(my_formula, weights=count, start=d)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\rpy2\robjects\functions.py in __call__(self, *args, **kwargs)
176 v = kwargs.pop(k)
177 kwargs[r_k] = v
--> 178 return super(SignatureTranslatedFunction, self).__call__(*args, **kwargs)
179
180 pattern_link = re.compile(r'\\link\{(.+?)\}')
~\AppData\Local\Continuum\anaconda3\lib\site-packages\rpy2\robjects\functions.py in __call__(self, *args, **kwargs)
104 for k, v in kwargs.items():
105 new_kwargs[k] = conversion.py2ri(v)
--> 106 res = super(Function, self).__call__(*new_args, **new_kwargs)
107 res = conversion.ri2ro(res)
108 return res
RRuntimeError: Error in (function (formula, data = parent.frame(), start, control = nls.control(), :
parameters without starting value in 'data': rates, count
I am guessing my count and rates variables are not lists? or something else? I have tried messing around and converting them but to no avail. Any help much appreciated!
This is the code I made for the dataframe:
dataf = ro.DataFrame({})
d = {'count': ro.IntVector((1,2,3,4,5)),'rates': ro.IntVector((1,2,3,4,5))}
dataf = ro.DataFrame(d)
count = dataf.rx(True, 'count')
rates = dataf.rx(True, 'rates')
