Last active
August 29, 2015 14:04
-
-
Save sjewo/92c01155967b980803bb to your computer and use it in GitHub Desktop.
Read Stata 13 files into R with rPython and pandas
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# install.packages("rPython") | |
# requires pandas | |
stata13 <- function(dat, | |
convert.factors = TRUE){ | |
require("rPython") | |
# make dat known to python | |
python.assign('dat',dat) | |
python.exec('import pandas as pd') | |
# convert.factors | |
if (convert.factors %in% c(TRUE, NA)) { | |
python.exec('stata = pd.read_stata(dat)') | |
} else{ | |
python.exec('stata = pd.read_stata(dat, convert_categoricals=False, convert_dates=True)') | |
} | |
# panda export as json | |
python.exec('jso = stata.to_json()') | |
# # return a OrderedDict or loads will return an unordererd data.frame | |
python.exec('from collections import OrderedDict') | |
python.exec('statal = json.loads(jso, object_pairs_hook=OrderedDict)') | |
stata_l <- (function (var.name) { | |
python.command <- paste("_r_return = json.dumps( [", var.name, | |
"] )", sep = "") | |
python.exec(python.command, get.exception = FALSE) | |
ret <- .C("py_get_var", "_r_return", not.found.var = integer(1), | |
resultado = character(1), PACKAGE = "rPython") | |
if (ret$not.found.var) | |
stop("Variable not found") | |
#message(ret$resultado) | |
ret <- fromJSON(ret$resultado, nullValue=NA) | |
if (length(ret) == 1) | |
ret <- ret[[1]] | |
ret | |
})('statal') | |
stataDD <- data.frame(stata_l) | |
return(stataDD) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment