USA UCD/MCD Deaths 2017-2022

data_usa_ucd_mcd_deaths_2017-2022.sh

#!/bin/sh

BASE_URL="https://ftp.cdc.gov/pub/Health_Statistics/NCHS/Datasets/DVS/mortality"
OUTPUT_DIR="mortality_data"
YEARS="2017 2018 2019 2020 2021 2022"
OUTPUT_CSV="mcd.csv"
mkdir -p "$OUTPUT_DIR"
echo "id,year,month,age,ucd,mcd" > "$OUTPUT_CSV"
for YEAR in $YEARS; do
    YY="${YEAR: -2}"  # Extract last two digits of the year
    ZIP_FILE="mort${YEAR}us.zip"
    wget -q --show-progress -O "$OUTPUT_DIR/$ZIP_FILE" "$BASE_URL/$ZIP_FILE"
    unzip -o "$OUTPUT_DIR/$ZIP_FILE" -d "$OUTPUT_DIR"
    DATA_FILE=$(find "$OUTPUT_DIR" -type f -iname "Mort20${YY}US.PubUse.txt" \
      -or -iname "VS${YY}*MORT.DUSMCPUB*")
    awk -v year="$YEAR" 'BEGIN{OFS=","}
        NR > 1 { 
            if(substr($0, 20, 1) == 4) next;
            year = substr($0, 102, 4);
            id = sprintf("%d%07d", year, FNR);
            month = substr($0, 65, 2);
            age = (substr($0, 70, 1) == 1 ? substr($0, 71, 3) : 0);
            ucd = substr($0, 146, 4);
            mcds = int(substr($0, 163, 2));
            for (i = 0; i < mcds; i++) {
                print id, year, month, age, ucd, substr($0, 165 + i * 7 + 2, 4);
            }
        }' "$DATA_FILE" >> "$OUTPUT_CSV"
done
rm -f "$OUTPUT_DIR"