...@@ -372,23 +372,23 @@ show.data.dir.contents() ...@@ -372,23 +372,23 @@ show.data.dir.contents()
### information) ### information)
# To load raw r-data, only for BEL and 2009 # To load raw r-data, only for BEL and 2009
my.data = load.fadn.raw.rds( my.raw.data.BEL = load.fadn.raw.rds(
countries = "BEL", countries = "BEL",
years = 2009 years = 2009
) )
# my.data is a single large data.table, with the original csv columns and rows # my.data is a single large data.table, with the original csv columns and rows
nrow(my.data) #Number of rows nrow(my.raw.data.BEL) #Number of rows
names(my.data) #Column names names(my.raw.data.BEL) #Column names
length(names(my.data)) #Number of columns length(names(my.raw.data.BEL)) #Number of columns
str(my.data) #Overall structure str(my.raw.data.BEL) #Overall structure
################################################################## ##################################################################
## LOAD STRUCTURED R-DATA ## ## LOAD STRUCTURED R-DATA ##
################################################################## ##################################################################
#To load structured data, for BEL and 2009 #To load structured data, for BEL and 2009
my.data.2009 = load.fadn.str.rds( my.str.data.2009.BEL = load.fadn.str.rds(
countries = "BEL", countries = "BEL",
years = 2009, years = 2009,
extraction_dir = new.str.name # Location of the str r-data extraction_dir = new.str.name # Location of the str r-data
...@@ -396,19 +396,19 @@ my.data.2009 = load.fadn.str.rds( ...@@ -396,19 +396,19 @@ my.data.2009 = load.fadn.str.rds(
# You can see that my.data is a list, with three elements: info, costs, crops # You can see that my.data is a list, with three elements: info, costs, crops
str(my.data.2009) str(my.str.data.2009.BEL)
# You can access each individual element like this # You can access each individual element like this
str(my.data.2009$info) str(my.str.data.2009.BEL$info)
str(my.data.2009$costs) str(my.str.data.2009.BEL$costs) # NULL
str(my.data.2009$crops) str(my.str.data.2009.BEL$crops)
# The first columns of each of the above elements (info, costs, crops) # The first columns of each of the above elements (info, costs, crops)
# are created according to the ID section of the raw_str_map # are created according to the ID section of the raw_str_map
names(my.data.2009$info) names(my.str.data.2009.BEL$info)
names(my.data.2009$costs) names(my.str.data.2009.BEL$costs) # NULL
names(my.data.2009$crops) names(my.str.data.2009.BEL$crops)
# info and costs data.tables are in wide-format (each observation in a single row, # info and costs data.tables are in wide-format (each observation in a single row,
...@@ -418,29 +418,29 @@ names(my.data.2009$crops) ...@@ -418,29 +418,29 @@ names(my.data.2009$crops)
# #
# See https://seananderson.ca/2013/10/19/reshape/ for # See https://seananderson.ca/2013/10/19/reshape/ for
# discussion of the two types of data formats # discussion of the two types of data formats
head(my.data.2009$info) head(my.str.data.2009.BEL$info)
head(my.data.2009$costs) head(my.str.data.2009.BEL$costs) # NULL
head(my.data.2009$crops) head(my.str.data.2009.BEL$crops)
# Also on the attributes section of each of the above elements, we can access # Also on the attributes section of each of the above elements, we can access
# the column formulas and descriptions, as defined in the raw_str_map file. # the column formulas and descriptions, as defined in the raw_str_map file.
View( View(
attr(my.data.2009$info,"column.descriptions") attr(my.str.data.2009.BEL$info,"column.descriptions")
) )
# View(
# attr(my.str.data.2009.BEL$costs,"column.descriptions")
# ) # NULL
View( View(
attr(my.data.2009$costs,"column.descriptions") attr(my.str.data.2009.BEL$crops,"column.descriptions")
)
View(
attr(my.data.2009$crops,"column.descriptions")
) )
# Especially for the crops element, we can also see the description # Especially for the crops element, we can also see the description
# CROP column # CROP column
View( View(
attr(my.data.2009$crops,"crops.descriptions") attr(my.str.data.2009.BEL$crops,"crops.descriptions")
) )
################################################################# #################################################################
...@@ -487,7 +487,7 @@ my.data = load.fadn.str.rds(extraction_dir = new.str.name) ...@@ -487,7 +487,7 @@ my.data = load.fadn.str.rds(extraction_dir = new.str.name)
############################################################################ ############################################################################
#We load structured data for all available countries and years #We load structured data for all available countries and years
my.str.data = load.fadn.str.rds(extraction_dir = new.str.name) my.str.data = load.fadn.str.rds(extraction_dir = "a")
##---------------------------------------------------------------- ##----------------------------------------------------------------
## HOW MANY FARMS FOR EACH COUNTY AND EACH YEAR -- ## HOW MANY FARMS FOR EACH COUNTY AND EACH YEAR --
...@@ -609,7 +609,7 @@ my.str.data$info[,list(Nobs_sample=.N,Nobs_represented=sum(WEIGHT)), ...@@ -609,7 +609,7 @@ my.str.data$info[,list(Nobs_sample=.N,Nobs_represented=sum(WEIGHT)),
by=.(COUNTRY,YEAR)] by=.(COUNTRY,YEAR)]
# only for full sample (common id over years in selected data) # only for full sample (common id over years in selected data)
my.str.data$info[id %in% collected.common.id_str[[1]], my.str.data$info[ID %in% collected.common.id_str[[1]],
list(Nobs_sample=.N, list(Nobs_sample=.N,
Nobs_represented=sum(WEIGHT)), Nobs_represented=sum(WEIGHT)),
by=.(COUNTRY,YEAR)] by=.(COUNTRY,YEAR)]
......
This diff is collapsed.
File added