fix(main.py): drop columns with all NaN values to improve data qualit…

…y and reduce file size

feat(main.py): add leading zeros to the prefecture number in the output file name for better sorting and readability

main.py

@@ -23,5 +23,6 @@ def delete_headers(df, line_number):
     dfs = [delete_headers(x, 2) for x in dfs[1:]]
     dfs.insert(0, first_df)
     merged_df = pd.concat(dfs).replace('\n', '', regex=True).replace('\r', '', regex=True).replace('\r\n', '', regex=True).replace('\n\r', '', regex=True)
-    result_df = merged_df.dropna(subset=[0])
-    result_df.to_csv(f"./output_files/{i}_{PREFECTURES[i-1]}.csv", header=False, index=False)
+    result_df = merged_df.dropna(subset=[0]).dropna(axis=1)
+    prefecture_number = str(i).zfill(2)
+    result_df.to_csv(f"./output_files/{prefecture_number}_{PREFECTURES[i-1]}.csv", header=False, index=False)