Merge pull request #29 from zazuko/geocoding-limits

geocoding limits

Author: ludovicm67

notebooks/zefix/zefix.ipynb

@@ -85,14 +85,15 @@
     "import folium\n",
     "import mapclassify\n",
     "import matplotlib as mpl\n",
-    "import matplotlib.pyplot as plt\n",
     "import pandas as pd\n",
     "import geopandas as gpd\n",
     "import plotly.express as px\n",
     "import plotly.graph_objects as go\n",
-    "from plotly.subplots import make_subplots\n",
     "\n",
     "from graphly.api_client import SparqlClient\n",
+    "from geopy.extra.rate_limiter import RateLimiter\n",
+    "from geopy.geocoders import Nominatim\n",
+    "from shapely.geometry import Point\n",
     "\n",
     "%matplotlib inline"
    ]
@@ -501,6 +502,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "geolocator = Nominatim(user_agent=\"zefix\")\n",
+    "find_location = RateLimiter(geolocator.geocode, min_delay_seconds=1)\n",
+    "\n",
     "def geocode(df: pd.DataFrame, cache_file: str=\"addresses.json\"):\n",
     "\n",
     "    if os.path.isfile(cache_file): \n",
@@ -513,8 +517,16 @@
     "    is_new_address = ~df.address.isin(cached_addresses)\n",
     "\n",
     "    if any(is_new_address):\n",
-    "        new_locations = gpd.tools.geocode(df.address[is_new_address], user_agent=\"zazuko\", provider=\"nominatim\")\n",
-    "        new_locations[\"address\"] = df.address[is_new_address]\n",
+    "        \n",
+    "        coordinates = []\n",
+    "        addresses = []\n",
+    "        for address in df.address[is_new_address]:\n",
+    "            location = find_location(address)\n",
+    "            if coordinates:\n",
+    "                coordinates.append(Point(location))\n",
+    "                addresses.append(address)\n",
+    "\n",
+    "        new_locations = gpd.GeoDataFrame.from_dict({\"address\": addresses, \"geometry\": coordinates})\n",
     "        new_locations = new_locations.set_crs(epsg=4326)\n",
     "        new_locations = new_locations[~new_locations.geometry.is_empty]\n",
     "        all_locations = gpd.GeoDataFrame(pd.concat([new_locations, cached_locations], ignore_index=True), crs=new_locations.crs)\n",
@@ -609,7 +621,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.0"
+   "version": "3.9.12"
   },
   "title": "Central Business Name Index - Zefix"
  },