Feature/odbiz scripts

.gitignore

@@ -0,0 +1,2 @@
+# Ignore the following directories
+.ipynb_checkpoints*

scripts/Businesses/1-PreProcessing/BackupRawFiles.ipynb

@@ -0,0 +1,69 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# BackupRawFiles.ipynb\n",
+    "This notebook compresses all non-archived files under `1-PreProcessing/raw` into the `odbiz_raw_backup.zip` file.\n",
+    "\n",
+    "This provides a convenient way for us to backup our raw datasets. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'/home/jovyan/ODBiz/1-PreProcessing/odbiz_raw_backup.zip'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import shutil\n",
+    "\n",
+    "dir_to_compress = '/home/jovyan/ODBiz/1-PreProcessing/raw'\n",
+    "output_filename = '/home/jovyan/ODBiz/1-PreProcessing/odbiz_raw_backup'\n",
+    "\n",
+    "shutil.make_archive(output_filename, 'zip', dir_to_compress)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:root] *",
+   "language": "python",
+   "name": "conda-root-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

scripts/Businesses/1-PreProcessing/README_preprocessing.md

@@ -0,0 +1,20 @@
+# 1-PreProcessing
+The purpose of this step is to do some basic data cleaning, especially if certain datasets are especially troublesome for the rest of our pipeline to deal with.
+
+## `preprocessing_main.ipynb`
+Hitting "Run all" on this Jupyter notebook will run all the necessary scripts in the correct order. A lot of the documentation was already written in the file `preprocessing_main.ipynb`, so it will not be repeated here.
+
+## `ODBizSources.csv`
+The file `ODBizSources.csv` stores metadata about our source files, including links to the original sources. Our source files are stored in `/home/jovyan/ODBiz/1-PreProcessing/raw`.
+
+---
+
+## Dropped rows
+The scripts below will drop entries if they meet certain conditions that we deem as being irrelevant given the scope of this project
+
+### `process_vancouver.py`
+The Vancouver dataset duplicates every approved business year after year. As a result, about 80% of it's entries are duplicates. So, this script detects all duplicate sets based on the following columns: `['BusinessName', 'Province', 'BusinessType', 'Unit', 'House', 'Street', 'City', 'Province', 'PostalCode', 'Country']`
+
+The script keeps the most recent entry and removes all the other duplicates.
+
+In addition, this script removes entries that do not have a valid Canadian province code (i.e., they reside in states/provinces outside of Canada)

scripts/Businesses/PreProcessing/burn_test.ipynb → scripts/Businesses/1-PreProcessing/burn_test.ipynb

@@ -2,14 +2,14 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 1,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2022-03-09T16:13:37.195853Z",
-     "iopub.status.busy": "2022-03-09T16:13:37.195419Z",
-     "iopub.status.idle": "2022-03-09T16:13:37.200410Z",
-     "shell.execute_reply": "2022-03-09T16:13:37.199323Z",
-     "shell.execute_reply.started": "2022-03-09T16:13:37.195810Z"
+     "iopub.execute_input": "2022-08-05T19:38:43.114168Z",
+     "iopub.status.busy": "2022-08-05T19:38:43.113840Z",
+     "iopub.status.idle": "2022-08-05T19:38:43.121707Z",
+     "shell.execute_reply": "2022-08-05T19:38:43.120987Z",
+     "shell.execute_reply.started": "2022-08-05T19:38:43.114075Z"
     },
     "tags": []
    },
@@ -21,18 +21,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2022-03-10T20:36:04.766397Z",
-     "iopub.status.busy": "2022-03-10T20:36:04.765776Z",
-     "iopub.status.idle": "2022-03-10T20:36:05.801784Z",
-     "shell.execute_reply": "2022-03-10T20:36:05.800840Z",
-     "shell.execute_reply.started": "2022-03-10T20:36:04.766275Z"
+     "iopub.execute_input": "2022-08-05T19:38:45.841340Z",
+     "iopub.status.busy": "2022-08-05T19:38:45.840958Z",
+     "iopub.status.idle": "2022-08-05T19:38:46.985150Z",
+     "shell.execute_reply": "2022-08-05T19:38:46.983742Z",
+     "shell.execute_reply.started": "2022-08-05T19:38:45.841289Z"
     },
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'geopandas'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "Input \u001b[0;32mIn [2]\u001b[0m, in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mpandas\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mpd\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mgeopandas\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mgpd\u001b[39;00m\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mfolium\u001b[39;00m\n",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'geopandas'"
+     ]
+    }
+   ],
    "source": [
     "import pandas as pd\n",
     "import geopandas as gpd\n",
@@ -191,7 +203,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },

scripts/Businesses/1-PreProcessing/burnaby_york.ipynb

@@ -0,0 +1,132 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-08-09T19:33:50.959950Z",
+     "iopub.status.busy": "2022-08-09T19:33:50.959370Z",
+     "iopub.status.idle": "2022-08-09T19:33:52.917541Z",
+     "shell.execute_reply": "2022-08-09T19:33:52.916006Z",
+     "shell.execute_reply.started": "2022-08-09T19:33:50.959879Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "ERROR 1: PROJ: proj_create_from_database: Open of /opt/conda/envs/odbiz/share/proj failed\n"
+     ]
+    },
+    {
+     "ename": "DriverError",
+     "evalue": "/home/jovyan/ODBiz/1-PreProcessing/raw/shapefiles/Business_Licences.geojson: No such file or directory",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mCPLE_OpenFailedError\u001b[0m                      Traceback (most recent call last)",
+      "File \u001b[0;32mfiona/_shim.pyx:83\u001b[0m, in \u001b[0;36mfiona._shim.gdal_open_vector\u001b[0;34m()\u001b[0m\n",
+      "File \u001b[0;32mfiona/_err.pyx:291\u001b[0m, in \u001b[0;36mfiona._err.exc_wrap_pointer\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;31mCPLE_OpenFailedError\u001b[0m: /home/jovyan/ODBiz/1-PreProcessing/raw/shapefiles/Business_Licences.geojson: No such file or directory",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001b[0;31mDriverError\u001b[0m                               Traceback (most recent call last)",
+      "Input \u001b[0;32mIn [1]\u001b[0m, in \u001b[0;36m<cell line: 12>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      9\u001b[0m name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mBC_Burnaby_shapefile\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     10\u001b[0m fp \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mraw_shp_dir\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/Business_Licences.geojson\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m---> 12\u001b[0m city \u001b[38;5;241m=\u001b[39m \u001b[43mgpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_file\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfp\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     14\u001b[0m \u001b[38;5;66;03m#city = city.set_crs(, allow_override=True)\u001b[39;00m\n\u001b[1;32m     15\u001b[0m \u001b[38;5;66;03m#city = city.to_crs()\u001b[39;00m\n\u001b[1;32m     17\u001b[0m city\u001b[38;5;241m.\u001b[39mexplore()\n",
+      "File \u001b[0;32m/opt/conda/envs/odbiz/lib/python3.10/site-packages/geopandas/io/file.py:253\u001b[0m, in \u001b[0;36m_read_file\u001b[0;34m(filename, bbox, mask, rows, engine, **kwargs)\u001b[0m\n\u001b[1;32m    250\u001b[0m     path_or_bytes \u001b[38;5;241m=\u001b[39m filename\n\u001b[1;32m    252\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m engine \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfiona\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m--> 253\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read_file_fiona\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    254\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpath_or_bytes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrom_bytes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbbox\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbbox\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmask\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrows\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrows\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m    255\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    256\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m engine \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyogrio\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m    257\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m _read_file_pyogrio(\n\u001b[1;32m    258\u001b[0m         path_or_bytes, bbox\u001b[38;5;241m=\u001b[39mbbox, mask\u001b[38;5;241m=\u001b[39mmask, rows\u001b[38;5;241m=\u001b[39mrows, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs\n\u001b[1;32m    259\u001b[0m     )\n",
+      "File \u001b[0;32m/opt/conda/envs/odbiz/lib/python3.10/site-packages/geopandas/io/file.py:294\u001b[0m, in \u001b[0;36m_read_file_fiona\u001b[0;34m(path_or_bytes, from_bytes, bbox, mask, rows, **kwargs)\u001b[0m\n\u001b[1;32m    291\u001b[0m     reader \u001b[38;5;241m=\u001b[39m fiona\u001b[38;5;241m.\u001b[39mopen\n\u001b[1;32m    293\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m fiona_env():\n\u001b[0;32m--> 294\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m \u001b[43mreader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath_or_bytes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m features:\n\u001b[1;32m    295\u001b[0m \n\u001b[1;32m    296\u001b[0m         \u001b[38;5;66;03m# In a future Fiona release the crs attribute of features will\u001b[39;00m\n\u001b[1;32m    297\u001b[0m         \u001b[38;5;66;03m# no longer be a dict, but will behave like a dict. So this should\u001b[39;00m\n\u001b[1;32m    298\u001b[0m         \u001b[38;5;66;03m# be forwards compatible\u001b[39;00m\n\u001b[1;32m    299\u001b[0m         crs \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    300\u001b[0m             features\u001b[38;5;241m.\u001b[39mcrs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124minit\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m    301\u001b[0m             \u001b[38;5;28;01mif\u001b[39;00m features\u001b[38;5;241m.\u001b[39mcrs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124minit\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m features\u001b[38;5;241m.\u001b[39mcrs\n\u001b[1;32m    302\u001b[0m             \u001b[38;5;28;01melse\u001b[39;00m features\u001b[38;5;241m.\u001b[39mcrs_wkt\n\u001b[1;32m    303\u001b[0m         )\n\u001b[1;32m    305\u001b[0m         \u001b[38;5;66;03m# handle loading the bounding box\u001b[39;00m\n",
+      "File \u001b[0;32m/opt/conda/envs/odbiz/lib/python3.10/site-packages/fiona/env.py:408\u001b[0m, in \u001b[0;36mensure_env_with_credentials.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    405\u001b[0m \u001b[38;5;129m@wraps\u001b[39m(f)\n\u001b[1;32m    406\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mwrapper\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m    407\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m local\u001b[38;5;241m.\u001b[39m_env:\n\u001b[0;32m--> 408\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    409\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    410\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(args[\u001b[38;5;241m0\u001b[39m], \u001b[38;5;28mstr\u001b[39m):\n",
+      "File \u001b[0;32m/opt/conda/envs/odbiz/lib/python3.10/site-packages/fiona/__init__.py:264\u001b[0m, in \u001b[0;36mopen\u001b[0;34m(fp, mode, driver, schema, crs, encoding, layer, vfs, enabled_drivers, crs_wkt, **kwargs)\u001b[0m\n\u001b[1;32m    261\u001b[0m     path \u001b[38;5;241m=\u001b[39m parse_path(fp)\n\u001b[1;32m    263\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m mode \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ma\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m):\n\u001b[0;32m--> 264\u001b[0m     c \u001b[38;5;241m=\u001b[39m \u001b[43mCollection\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdriver\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdriver\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    265\u001b[0m \u001b[43m                   \u001b[49m\u001b[43mlayer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlayer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43menabled_drivers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43menabled_drivers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    266\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m mode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mw\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[1;32m    267\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m schema:\n\u001b[1;32m    268\u001b[0m         \u001b[38;5;66;03m# Make an ordered dict of schema properties.\u001b[39;00m\n",
+      "File \u001b[0;32m/opt/conda/envs/odbiz/lib/python3.10/site-packages/fiona/collection.py:162\u001b[0m, in \u001b[0;36mCollection.__init__\u001b[0;34m(self, path, mode, driver, schema, crs, encoding, layer, vsi, archive, enabled_drivers, crs_wkt, ignore_fields, ignore_geometry, **kwargs)\u001b[0m\n\u001b[1;32m    160\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[1;32m    161\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msession \u001b[38;5;241m=\u001b[39m Session()\n\u001b[0;32m--> 162\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msession\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstart\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    163\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmode \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ma\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mw\u001b[39m\u001b[38;5;124m'\u001b[39m):\n\u001b[1;32m    164\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msession \u001b[38;5;241m=\u001b[39m WritingSession()\n",
+      "File \u001b[0;32mfiona/ogrext.pyx:540\u001b[0m, in \u001b[0;36mfiona.ogrext.Session.start\u001b[0;34m()\u001b[0m\n",
+      "File \u001b[0;32mfiona/_shim.pyx:90\u001b[0m, in \u001b[0;36mfiona._shim.gdal_open_vector\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;31mDriverError\u001b[0m: /home/jovyan/ODBiz/1-PreProcessing/raw/shapefiles/Business_Licences.geojson: No such file or directory"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import geopandas as gpd\n",
+    "import pandas as pd\n",
+    "\n",
+    "raw_shp_dir = '/home/jovyan/ODBiz/1-PreProcessing/raw/shapefiles'\n",
+    "out_dir = '/home/jovyan/ODBiz/1-PreProcessing' # Default\n",
+    "\n",
+    "\n",
+    "name = \"BC_Burnaby_shapefile\"\n",
+    "fp = f\"{raw_shp_dir}/Business_Licences.geojson\"\n",
+    "\n",
+    "city = gpd.read_file(fp)\n",
+    "\n",
+    "#city = city.set_crs(, allow_override=True)\n",
+    "#city = city.to_crs()\n",
+    "\n",
+    "city.explore()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-06-27T14:45:18.340157Z",
+     "iopub.status.busy": "2022-06-27T14:45:18.339952Z",
+     "iopub.status.idle": "2022-06-27T14:45:18.365361Z",
+     "shell.execute_reply": "2022-06-27T14:45:18.343352Z",
+     "shell.execute_reply.started": "2022-06-27T14:45:18.340131Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BC_Burnaby_shapefile\n",
+      "epsg:4326\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(name)\n",
+    "print(city.crs)\n",
+    "#city = city.to_crs(epsg=4326)\n",
+    "#print(city.crs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    " # sub_city = city.head(500)\n",
+    "\n",
+    "city['lon'] = city.centroid.x\n",
+    "city['lat'] = city.centroid.y"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:root] *",
+   "language": "python",
+   "name": "conda-root-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}