stat243-ps1.txt

stat243-ps1.txt

# download the data
wget -O apricots.zip "http://data.un.org/Handlers/DownloadHandler.ashx?DataFilter=itemCode:526&DataMartId=FAO&Format=csv&c=2,3,4,5,6,7&s=countryName:asc,elementCode:asc,year:desc"

unzip -p apricots.zip > apricots.csv

# split into region and country
grep -v "+" apricots.csv > countries.csv
grep "+" apricots.csv > regions.csv

# put all the 2005 data to a new countries05.csv file
awk -F "\"*,\"*" '$4 == 2005 ' countries.csv > countries05.csv

# find out the which countries harvested the most 
grep -i 'Area Harvested' countries05.csv | sort -t',' -n -k6 -r | head -5

# automate it
for var in $(seq 1965 10 2005)
do
  echo $var
  grep -i -e ${var} countries.csv | grep -i 'Area Harvested' | sort -t',' -n -k6 -r | head -5 > top${var}.txt
done