diff --git a/code/01_baseline/04_preprocess_english_house_price.ipynb b/code/01_baseline/04_preprocess_english_house_price.ipynb
new file mode 100644
index 0000000..4b15333
--- /dev/null
+++ b/code/01_baseline/04_preprocess_english_house_price.ipynb
@@ -0,0 +1,131 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f4eff720-400d-4388-9bb9-689c514fa853",
+   "metadata": {},
+   "source": [
+    "# Preprocess house price\n",
+    "\n",
+    "Get house price per OA across England as a Parquet file\n",
+    "\n",
+    "## A new attribute-linked residential property price dataset for England and Wales 2011-2019\n",
+    "\n",
+    "We can use https://reshare.ukdataservice.ac.uk/854942/ that derived a price per sqm from link between sales data and EPC."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7afeffbf-f1ed-43da-bc1b-61a457429095",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "aa061ba2-0eaf-4737-beac-bc4f54c2de90",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It is 6.3GB...\n",
+    "linked_epc_path = \"https://reshare.ukdataservice.ac.uk/854942/1/tranall2011_19.csv\""
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "99c06f6a-18b4-444d-a21e-bb7bd414ec14",
+   "metadata": {},
+   "source": [
+    "Filter only Tyne and Wear for the last two years (2018-19)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4517557e-be6f-46fe-9bcc-1675e6098343",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "epc = pd.read_csv(linked_epc_path)\n",
+    "epc[\"dateoftransfer\"] = pd.to_datetime(epc.dateoftransfer)\n",
+    "last2years = epc[epc.dateoftransfer > datetime.datetime(2018, 1, 1)]"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "283843a2-78ac-4549-9905-76d4f7f3f0fa",
+   "metadata": {},
+   "source": [
+    "Link to geometry"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bc1e3a99-a0b5-4f34-bca1-d63da9dbec1f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "oa = gpd.read_file(   \"https://borders.ukdataservice.ac.uk/ukborders/easy_download/prebuilt/shape/infuse_oa_lyr_2011_clipped.zip\", engine=\"pyogrio\"\n",
+    ")\n",
+    "agg = (\n",
+    "    last2years[[\"oa11\", \"priceper\", \"numberrooms\", \"price\", \"tfarea\"]]\n",
+    "    .groupby(\"oa11\")\n",
+    "    .mean()\n",
+    "    .reset_index()\n",
+    ")\n",
+    "agg_oa = oa.merge(agg, left_on=\"geo_code\", right_on=\"oa11\", how=\"inner\")\n",
+    "agg_oa"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0897d793-c5a6-49ca-a321-be31dd595bb8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agg_oa.to_file(\n",
+    "    f\"{data_folder}/processed/house_prices/price_per_sqm.gpkg\", engine=\"pyogrio\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "582514fb-515d-49e1-b554-d6fa00687338",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}