{ "cells": [ { "cell_type": "markdown", "id": "0622863c-96b6-46ee-90e8-63795b6657d3", "metadata": {}, "source": [ "# Employment by sector and departement" ] }, { "cell_type": "code", "execution_count": 1, "id": "c9720bdf-e8aa-429e-a584-c13545b65d11", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/usr/local/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", " from .autonotebook import tqdm as notebook_tqdm\n" ] } ], "source": [ "from pynsee.localdata import get_local_metadata, get_nivgeo_list, get_local_data\n", "from pynsee.geodata import get_geodata, GeoFrDataFrame\n", "from pynsee.metadata import get_activity_list\n", "from shapely import wkt\n", "\n", "import pandas as pd\n", "from pandas.api.types import CategoricalDtype\n", "import seaborn as sns\n", "import math\n", "\n", "from matplotlib.pyplot import pie\n", "import matplotlib.pyplot as plt\n", "from mpl_toolkits.axes_grid1.inset_locator import inset_axes\n", "\n", "# get a list all data available : datasets and variables\n", "metadata = get_local_metadata()\n", "\n", "# geographic metadata\n", "nivgeo = get_nivgeo_list()" ] }, { "cell_type": "code", "execution_count": 2, "id": "baf5c64a-ecd1-44dc-8d03-80956987f5ec", "metadata": {}, "outputs": [], "source": [ "# get departement map\n", "dep = get_geodata('ADMINEXPRESS-COG-CARTO.LATEST:departement')\n", "\n", "dep = dep.transform_overseas(departement=['971', '972', '974', '973', '976'],\n", " factor=[1.5, 1.5, 1.5, 0.3, 1.5])\n", "\n", "dep = dep.zoom(factor = 3.5 , startAngle = math.pi * (1 - 3 * 1/9))\n", "\n", "dep = dep[[\"code_insee\", \"geometry\"]]\n", "dep = dep.rename(columns={'code_insee': 'CODEGEO'})" ] }, { "cell_type": "code", "execution_count": 3, "id": "bb2dd5fc-66db-4082-b369-5116e9c87da9", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "INSEE API credentials have not been found: please try to reuse pynsee.init_conn to save them locally.\n", "Otherwise, you can still use environment variables as follow:\n", "\n", "import os\n", "os.environ['sirene_key'] = 'my_sirene_key'\n", "Getting data: 100%|██████████| 101/101 [03:01<00:00, 1.80s/it] \n" ] } ], "source": [ "# get local data from INSEE API\n", "data = get_local_data(\n", " dataset_version='GEO2020FLORES2017', variables='NA17', nivgeo='DEP')\n", "\n", "data = data.rename(columns={'NA17': 'A17'})" ] }, { "cell_type": "code", "execution_count": 4, "id": "77d3461b-d370-43e6-bd8b-c25745e956a3", "metadata": {}, "outputs": [], "source": [ "# keep only headcounts and remove the total from the data\n", "df = data[data[\"UNIT\"] == \"NBSALET\"].reset_index(drop=True)\n", "df = df[~df[\"A17\"].isin([\"ENS\"])].reset_index(drop=True)" ] }, { "cell_type": "code", "execution_count": 5, "id": "b3907494-29f8-4834-a6e8-4b8bd717eaf8", "metadata": {}, "outputs": [], "source": [ "# compute share of activity in total employment by department\n", "df['employment_share'] = 100 * df[\"OBS_VALUE\"] / df['OBS_VALUE'].groupby(df['CODEGEO']).transform('sum')" ] }, { "cell_type": "code", "execution_count": 6, "id": "18328ca2-247d-48ab-b456-3510349e3dd7", "metadata": {}, "outputs": [], "source": [ "# merge values and geographic limits\n", "datamap = GeoFrDataFrame(df.merge(dep, how = 'left', on = 'CODEGEO'))" ] }, { "cell_type": "code", "execution_count": 7, "id": "af629b33-3b0d-4a82-9986-b14ce6fbde21", "metadata": {}, "outputs": [], "source": [ "# add english activity labels at A17 level\n", "activity = get_activity_list(\"A17\")\n", "activity[\"TITLE_A17_EN\"] = activity[\"A17\"] + \" - \" + activity[\"TITLE_A17_EN\"]\n", "datamap = datamap.merge(activity, how='left', on='A17')" ] }, { "cell_type": "code", "execution_count": 8, "id": "aa3580b9-b3ab-404f-820e-8a75a42f8798", "metadata": {}, "outputs": [], "source": [ "# compute center location for each departement\n", "datamap[\"center\"] = datamap.geometry.centroid\n", "\n", "# list of departements\n", "list_dep = datamap[\"CODEGEO\"].unique()" ] }, { "cell_type": "code", "execution_count": 9, "id": "f252d2e4-b50e-4f85-bd68-1d6f2d7f85ca", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
| \n", " | CODEGEO | \n", "NIVGEO | \n", "UNIT_label_fr | \n", "UNIT | \n", "A17 | \n", "OBS_VALUE | \n", "NA17_label | \n", "DATASET_VERSION | \n", "DATASET_NAME | \n", "DATA_DATE | \n", "employment_share | \n", "geometry | \n", "A5 | \n", "A10 | \n", "TITLE_A17_EN | \n", "TITLE_A17_FR | \n", "center | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", "24 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "OQ | \n", "47091.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "39.785237 | \n", "MULTIPOLYGON (((27120.328 5599468.283, 27106.6... | \n", "OQ | \n", "OQ | \n", "OQ - Public administration and defence, educat... | \n", "Administration publique, enseignement, santé h... | \n", "POINT (82503.91 5638329.284) | \n", "
| 1 | \n", "33 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "OQ | \n", "199158.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "32.943017 | \n", "MULTIPOLYGON (((-139393.72 5554680.837, -13928... | \n", "OQ | \n", "OQ | \n", "OQ - Public administration and defence, educat... | \n", "Administration publique, enseignement, santé h... | \n", "POINT (-64234.389 5594353.684) | \n", "
| 2 | \n", "71 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "OQ | \n", "61315.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "34.317841 | \n", "MULTIPOLYGON (((548723.5 5861512.99, 548643.52... | \n", "OQ | \n", "OQ | \n", "OQ - Public administration and defence, educat... | \n", "Administration publique, enseignement, santé h... | \n", "POINT (505726.208 5884496.126) | \n", "
| 3 | \n", "01 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "OQ | \n", "54202.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "29.047782 | \n", "MULTIPOLYGON (((533898.382 5802670.867, 534054... | \n", "OQ | \n", "OQ | \n", "OQ - Public administration and defence, educat... | \n", "Administration publique, enseignement, santé h... | \n", "POINT (595403.95 5796511.951) | \n", "
| 4 | \n", "22 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "OQ | \n", "66843.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "36.247933 | \n", "MULTIPOLYGON (((-400990.704 6236235.694, -4009... | \n", "OQ | \n", "OQ | \n", "OQ - Public administration and defence, educat... | \n", "Administration publique, enseignement, santé h... | \n", "POINT (-318975.243 6180666.226) | \n", "
| ... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
| 1763 | \n", "13 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "C2 | \n", "1446.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "0.182878 | \n", "MULTIPOLYGON (((582085.39 5342294.655, 582092.... | \n", "BE | \n", "BE | \n", "C2 - Manufacture of coke and refined petroleum... | \n", "Cokéfaction et raffinage | \n", "POINT (566101.71 5395492.184) | \n", "
| 1764 | \n", "26 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "C2 | \n", "0.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "0.000000 | \n", "MULTIPOLYGON (((559856.744 5511665.293, 559637... | \n", "BE | \n", "BE | \n", "C2 - Manufacture of coke and refined petroleum... | \n", "Cokéfaction et raffinage | \n", "POINT (575197.887 5572442.063) | \n", "
| 1765 | \n", "59 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "C2 | \n", "269.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "0.027313 | \n", "MULTIPOLYGON (((336295.261 6472777.256, 336428... | \n", "BE | \n", "BE | \n", "C2 - Manufacture of coke and refined petroleum... | \n", "Cokéfaction et raffinage | \n", "POINT (357475.652 6524772.888) | \n", "
| 1766 | \n", "27 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "C2 | \n", "0.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "0.000000 | \n", "MULTIPOLYGON (((74664.181 6343633.985, 75574.8... | \n", "BE | \n", "BE | \n", "C2 - Manufacture of coke and refined petroleum... | \n", "Cokéfaction et raffinage | \n", "POINT (110910.519 6294369.44) | \n", "
| 1767 | \n", "33 | \n", "DEP | \n", "Postes salariés dans les établissements | \n", "NBSALET | \n", "C2 | \n", "0.0 | \n", "Activité économique en 17 postes (NA - A17) | \n", "GEO2020FLORES2017 | \n", "Fichier localisé des rémunérations et de l'emp... | \n", "2017.0 | \n", "0.000000 | \n", "MULTIPOLYGON (((-139393.72 5554680.837, -13928... | \n", "BE | \n", "BE | \n", "C2 - Manufacture of coke and refined petroleum... | \n", "Cokéfaction et raffinage | \n", "POINT (-64234.389 5594353.684) | \n", "
1768 rows × 17 columns
\n", "| \n", " | employment_share | \n", "
|---|---|
| TITLE_A17_EN | \n", "\n", " |
| OQ - Public administration and defence, education, human health and social work activities | \n", "36.017645 | \n", "
| GZ - Wholesale and retail trade; repair of motor vehicles and motorcycles | \n", "13.797260 | \n", "
| MN - Professional, scientific, technical, administrative and support service activities | \n", "9.349464 | \n", "
| C5 - Other manufacturing | \n", "6.822302 | \n", "
| FZ - Construction | \n", "6.040776 | \n", "
| HZ - Transportation and storage | \n", "5.366087 | \n", "
| IZ - Accommodation and food service activities | \n", "4.072490 | \n", "
| RU - Other services activities | \n", "3.733203 | \n", "
| C1 - Manufacture of food products, beverages and tobacco products | \n", "3.016751 | \n", "
| KZ - Financial and insurance activities | \n", "2.961577 | \n", "
| JZ - Information and communication | \n", "1.843239 | \n", "
| C3 - Manufacture of electrical, computer and electronic equipment; Manufacture of machinery | \n", "1.714648 | \n", "
| DE - Mining and quarrying; energy, water supply, sewerage, waste management and remediation activities | \n", "1.606920 | \n", "
| AZ - Agriculture, forestry and fishing | \n", "1.422385 | \n", "
| C4 - Manufacture of transport equipment | \n", "1.343475 | \n", "
| LZ - Real estate activities | \n", "0.872148 | \n", "
| C2 - Manufacture of coke and refined petroleum products | \n", "0.019630 | \n", "