dataforcanada/d4c-datapkg-statistical
1
0
Fork 0
mirror of https://github.com/dataforcanada/d4c-datapkg-statistical.git synced 2026-06-13 14:10:55 +02:00
Code Issues Packages Projects Releases Wiki Activity

Process 2024-06 national address register

Browse Source
This commit is contained in:
Diego Ripley
2025-06-07 15:39:28 +00:00
parent b3c5f8767f
commit 4d16ef8232
3 changed files with 559 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
national_address_register/process.sh
+7 -8
View File
@@ -5,7 +5,6 @@ EXTRACTED_FOLDER="${DATA_FOLDER}/national_address_register/extracted"
process_202412() {
# Process 2024-12 vintage
# Extract files
echo "Extracting ${INPUT_FOLDER}/2024-12/202412.zip to ${EXTRACTED_FOLDER}/2024-12"
unzip -q -n ${INPUT_FOLDER}/2024-12/202412.zip -d ${EXTRACTED_FOLDER}/2024-12
jupyter execute process_2024_12.ipynb
@@ -13,26 +12,26 @@ process_202412() {
process_202406() {
# Process 2024-06 vintage
echo "Extracting ${INPUT_FOLDER}/2024.zip"
unzip -q -n ${INPUT_FOLDER}/2024.zip -d ${EXTRACTED_FOLDER}/2024-06
# Encoding is utf-8
echo "Extracting ${INPUT_FOLDER}/2024-06/2024.zip"
unzip -q -n ${INPUT_FOLDER}/2024-06/2024.zip -d ${EXTRACTED_FOLDER}/2024-06
jupyter execute process_2024_12.ipynb
}
process_2023() {
# Process 2023
echo "Extracting ${INPUT_FOLDER}/2023.zip"
unzip -q -n ${INPUT_FOLDER}/2023.zip -d ${EXTRACTED_FOLDER}/2023
echo "Extracting ${INPUT_FOLDER}/2023/2023.zip"
unzip -q -n ${INPUT_FOLDER}/2023/2023.zip -d ${EXTRACTED_FOLDER}/2023
# Encoding is latin-1
}
process_2022() {
# Process 2022
echo "Extracting ${INPUT_FOLDER}/2022.zip"
echo "Extracting ${INPUT_FOLDER}/2022/2022.zip"
unzip -q -n ${INPUT_FOLDER}/2022.zip -d ${EXTRACTED_FOLDER}/2022
# Encoding is latin-1
}
process_202412
#process_202406
process_202406
#process_2023
#process_2022