Rerun data pipelines
This commit is contained in:
parent
4c95815dc8
commit
fc10381692
27 changed files with 2143 additions and 215 deletions
|
|
@ -32,7 +32,7 @@ public class Parquet {
|
|||
static Postcodes loadEnglandPostcodes(String parquetPath, Path refOut) throws Exception {
|
||||
try (DuckDBConnection conn = connect(); Statement stmt = conn.createStatement()) {
|
||||
stmt.execute("CREATE TABLE postcodes AS SELECT pcds, lat, \"long\" FROM read_parquet('"
|
||||
+ escapePath(parquetPath) + "') WHERE ctry = 'E92000001' AND doterm IS NULL");
|
||||
+ escapePath(parquetPath) + "') WHERE ctry25cd = 'E92000001' AND doterm IS NULL");
|
||||
copyToParquet(stmt, "SELECT * FROM postcodes", refOut);
|
||||
|
||||
try (ResultSet rs = stmt.executeQuery("SELECT COUNT(*) FROM postcodes")) {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue