personal mini cheat sheet: R time series - xts from csv file, and more xts basics that I tend to forget

csv2xts--and-more.R

# see also:
# https://s3.amazonaws.com/assets.datacamp.com/blog_assets/xts_Cheat_Sheet_R.pdf


# Open csv file using read.zoo
my_tsdata <- read.zoo("my_tsdata.csv", sep = ",", FUN = as.Date, header = TRUE, index.column = 1)
my_tsdata <- as.xts(my_tsdata)


 
# merge by row : Use rbind - no sorting is done by the xts module
temps_xts <- rbind(temps_1_xts, temps_2_xts)
# merge by column - two xts objects by column - index correctly
flights_temps <- merge(flights_xts, temps_monthly)


# convert periods. 
# note param for no Open-High-Low-Close in the input data.
# use first in subperiod 
temps_monthly <- to.period(temps_xts, period = "months", OHLC = FALSE, indexAt = "firstof")


## Split-apply-combine with index column magically preserved
# Split _One column_  into separate lists per month
monthly_split <- split(my_xts$mean , f = "months")
mean_of_means <- lapply(monthly_split, FUN = mean) # list-of one-column lists
my_monthly <- as.xts(as.numeric(mean_of_means), order.by = index)
#alternative
my_monthly <- do.call(rbind, mean_of_means) # list of many-column lists

# Fill NAs :
#  last observation carried forward
my_locf <- na.locf(my_xts)

#  next observation carried backward 
my_nocb <- na.locf(my_xts, fromLast=TRUE)

#  linear approximation
my_approx <- na.approx(my_xts)

## create lags, merge by column
# Create a one month lag 
monthlag <- lag(my_xts$dat, k = 1)

# Create a one year lag of US unemployment
yearlag <- lag(my_xts$dat, k = 12)

# Merge your original data with your new lags 
my_lags <- merge(my_xts, monthlag, yearlag)

# lag+merge in one go: diff
my_xts$monthlydiff <- diff(my_xts$dat, lag = 1, differences = 1)

# smoothen, or interpolate smaller differences 
my_xts$year_avg <- rollapply(my_xts$dat, width = 12, FUN = mean)


# endpoints and period.apply go together.
# Identify a column of dates 
close <- endpoints(my_xts, on = "years")

# Calculate closing average at end each period, (_not_ throughout)
period.apply(my_xts[, "some_column"], close, mean)

# using the index column
weekday <- .indexwday(myxts)