Last active
August 29, 2015 14:28
-
-
Save KristofferC/207dcc6f4f22eed73562 to your computer and use it in GitHub Desktop.
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
using DataFrames | |
using DataFramesMeta | |
using GLM | |
using Base.Collections | |
function f(ds) | |
DPY = 252 ## days per year | |
NWINDOW = 126 ## can be smaller or larger than 252 | |
FMCOL = 1 | |
DAYCOL = 2 | |
# create two empty arrays to store b_ols and sd_ols value | |
b_ols = DataArray(Float64, size(ds)[1]) | |
sd_ols = DataArray(Float64, size(ds)[1]) | |
for i = 1:size(ds)[1] | |
thisDay = ds[i, :day] ## Julia DataFrame way of accessing data, in R: ds$day[i] | |
if mod(thisDay, DPY) != 0 | |
continue | |
end | |
if thisDay < DPY | |
continue | |
end | |
thisFm = ds[i, :fm] | |
# Find the rows that fits with given Fm | |
cands_fm = searchsorted(ds[FMCOL].data, thisFm) | |
# Find the last index where the day is >= thisDay - 1 | |
start_days = searchsortedfirst(ds[DAYCOL].data, thisDay - NWINDOW, | |
cands_fm[1], cands_fm[end], Forward) | |
# Find the first index where day is < thisDay - 1 | |
end_days = searchsortedlast(ds[DAYCOL].data, thisDay - 1, | |
cands_fm[1], cands_fm[end], Forward) | |
# Extract subset from data | |
dataSubset = ds[start_days:end_days, :] | |
olsReg = fit(LinearModel, xr ~ xm, dataSubset) ## OLS from package GLM | |
b_ols[i] = coef(olsReg)[2] ## returns the OLS coefficients | |
sd_ols[i] = stderr(olsReg)[2] ## returns the OLS coefficients' standard error | |
print(i, " ") | |
end | |
ds[:b_ols] = b_ols | |
ds[:sd_ols] = sd_ols | |
print("\nOLS Beta Regressions are Done\n") | |
return ds | |
end | |
ds = readtable("xri.csv") ## a sample data set | |
@time f(ds); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment