feat: add osm data

2025-09-21 16:23:44 +02:00
parent 63e23d6600
commit c1b502c878
39 changed files with 955 additions and 338 deletions
@@ -0,0 +1,107 @@
+{
+ "cells": [
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "# Qualitative Analysis",
+   "id": "d20715dd63f57364"
+  },
+  {
+   "cell_type": "code",
+   "id": "c93a55c8",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-09-21T13:34:50.973298Z",
+     "start_time": "2025-09-21T13:34:50.969142Z"
+    }
+   },
+   "source": [
+    "import pandas as pd\n",
+    "import geopandas as gpd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "import sys\n",
+    "import os\n",
+    "\n",
+    "sys.path.append(os.path.abspath(\"..\"))\n",
+    "from core.utils.data_loader import DataLoader\n",
+    "from core.config.pipeline_config import PipelineConfig"
+   ],
+   "outputs": [],
+   "execution_count": 3
+  },
+  {
+   "cell_type": "code",
+   "id": "c0b00261",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-09-21T13:34:51.002610Z",
+     "start_time": "2025-09-21T13:34:50.998586Z"
+    }
+   },
+   "source": [
+    "config = PipelineConfig(\n",
+    "    paths={\n",
+    "        \"root_dir\": \"../data\",\n",
+    "        \"data_dir\": \"../data/dataset\",\n",
+    "        \"models_dir\": \"../models\",\n",
+    "        \"outputs_dir\": \"../data/processed\",\n",
+    "        \"logs_dir\": \"../logs\",\n",
+    "        \"configs_dir\": \"../configs\",\n",
+    "        \"checkpoints_dir\": \"../checkpoints\"\n",
+    "    }\n",
+    ")\n",
+    "\n",
+    "loader = DataLoader(config)"
+   ],
+   "outputs": [],
+   "execution_count": 4
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-09-21T13:35:27.430639Z",
+     "start_time": "2025-09-21T13:34:51.013412Z"
+    }
+   },
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": 5,
+   "source": [
+    "gdf = gpd.read_file(\"../osm/provinces.shp\")\n",
+    "gdf_proj = gdf.to_crs(epsg=32732)\n",
+    "gdf['centroid'] = gdf_proj.geometry.centroid.to_crs(gdf.crs)\n",
+    "\n",
+    "df = loader.load_csv_complete(config.paths.data_dir / \"names_featured.csv\")"
+   ],
+   "id": "b38394ce38864379"
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "## Exploration",
+   "id": "a1af5626d2a948d6"
+  }
+ ],
+ "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": "3.11.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}