From e3129e785e3695fe3af196a68bd809eeda9b6b6b Mon Sep 17 00:00:00 2001
From: Struan Donald <struan@exo.org.uk>
Date: Thu, 28 Nov 2024 17:04:07 +0000
Subject: [PATCH] utility command to pivot a CSV

helpful for turning CSVs with multuple rows per constituency into ones
with multuple columns per constituency
---
 hub/management/commands/pivot_csv.py | 48 ++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 hub/management/commands/pivot_csv.py

diff --git a/hub/management/commands/pivot_csv.py b/hub/management/commands/pivot_csv.py
new file mode 100644
index 000000000..0d4895ce7
--- /dev/null
+++ b/hub/management/commands/pivot_csv.py
@@ -0,0 +1,48 @@
+import json
+
+from django.conf import settings
+from django.core.management.base import BaseCommand
+
+import pandas as pd
+
+
+class Command(BaseCommand):
+    def add_arguments(self, parser):
+        parser.add_argument(
+            "--infile",
+            action="store",
+            help="File to process",
+        )
+
+        parser.add_argument(
+            "--outfile",
+            action="store",
+            help="File to output to",
+        )
+
+        parser.add_argument(
+            "--column",
+            action="store",
+            help="Column to pivot on",
+        )
+
+        parser.add_argument(
+            "--value_column",
+            action="store",
+            help="Column with values",
+        )
+
+        parser.add_argument(
+            "--index",
+            action="store",
+            help="Column with index",
+        )
+
+    def handle(self, *args, **kwargs):
+        df = pd.read_csv(settings.BASE_DIR / "data" / kwargs["infile"])
+        df = df.pivot(
+            columns=kwargs["column"],
+            values=kwargs["value_column"],
+            index=kwargs["index"],
+        )
+        df.to_csv(settings.BASE_DIR / "data" / kwargs["outfile"])