data cleanup

uchicago-dsi · Mar 29, 2024 · 67cb682 · 67cb682
1 parent 187809e
commit 67cb682
Show file tree

Hide file tree

Showing 5 changed files with 1 addition and 0 deletions.
diff --git a/public/data/_concentration_metrics_wide_ds.parquet b/public/data/_concentration_metrics_wide_ds.parquet
diff --git a/public/data/concentration_metrics_wide_ds.parquet b/public/data/concentration_metrics_wide_ds.parquet
diff --git a/public/data/gravity_dollar_pivoted.parquet b/public/data/gravity_dollar_pivoted.parquet
diff --git a/public/data/gravity_no_dollar_pivoted.parquet b/public/data/gravity_no_dollar_pivoted.parquet
diff --git a/scripts/csv_to_parquet.py b/scripts/csv_to_parquet.py
@@ -10,6 +10,7 @@
 compression = "gzip"
 for csv in csvs:
     df = pd.read_csv(csv)
+    df['GEOID'] = df['GEOID'].astype(str).str.zfill(11)
     parquet = path.splitext(csv)[0] + ".parquet"
     df.to_parquet(parquet, compression=compression)
 # %%