diff --git a/docs/examples/example_automotive_industry_sirene.ipynb b/docs/examples/example_automotive_industry_sirene.ipynb index bdcd16db..b5b60ab2 100644 --- a/docs/examples/example_automotive_industry_sirene.ipynb +++ b/docs/examples/example_automotive_industry_sirene.ipynb @@ -13,7 +13,16 @@ "execution_count": 1, "id": "c34a1e8c-c386-41c4-b5bd-16d8d3085c02", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/opt/conda/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": [ "import pandas as pd\n", "import numpy as np\n", @@ -27,281 +36,39 @@ "from pynsee import *" ] }, - { - "cell_type": "code", - "execution_count": 2, - "id": "afd9bb1b-b5e9-4eb1-8da6-f0dfa716c35b", - "metadata": {}, - "outputs": [], - "source": [ - "# get activity list\n", - "naf5 = get_activity_list('NAF5')\n", - "\n", - "# search data in SIRENE database\n", - "data = search_sirene(variable=\"activitePrincipaleEtablissement\",\n", - " pattern='29.10Z', kind='siret', number=2000)" - ] - }, { "cell_type": "code", "execution_count": 3, - "id": "4b5071e6-9d3f-4f80-b2b5-bd775d8cac5b", + "id": "114dc865-8239-4f23-b202-900aef8c8dcb", "metadata": {}, "outputs": [], "source": [ - "data.to_csv('sirene.csv')" + "init_conn(sirene_key='f7345356-8301-4567-b453-568301456723')" ] }, { "cell_type": "code", "execution_count": 4, - "id": "fdcb6abc-cead-4fd2-b5ad-662a9f5f33cf", + "id": "afd9bb1b-b5e9-4eb1-8da6-f0dfa716c35b", "metadata": {}, "outputs": [ { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
sirennicsiretdateDebutdateCreationEtablissementdateCreationUniteLegaledateFindenominationUniteLegalenomUniteLegaleprenomUsuelUniteLegale...libelleVoie2EtablissementcodePostal2EtablissementlibelleCommune2EtablissementlibelleCommuneEtranger2EtablissementdistributionSpeciale2EtablissementcodeCommune2EtablissementcodeCedex2EtablissementlibelleCedex2EtablissementcodePaysEtranger2EtablissementlibellePaysEtranger2Etablissement
000658019500011006580195000112008-01-011965-01-011965-01-01NoneSOCIETE INDUSTRIELLE POUR LE DEVELOPPEMENT DE ...NoneNone...NoneNoneNoneNoneNoneNoneNoneNoneNoneNone
108552019500109085520195001092022-09-012022-06-301955-01-01NoneSAFRANoneNone...NoneNoneNoneNoneNoneNoneNoneNoneNoneNone
230169230700020301692307000202020-12-312014-08-151965-01-01NoneGARAGE BEYRISNoneNone...NoneNoneNoneNoneNoneNoneNoneNoneNoneNone
330227922900025302279229000252014-07-251900-01-011975-01-01NoneRAPIDONoneNone...NoneNoneNoneNoneNoneNoneNoneNoneNoneNone
430227922900033302279229000332008-01-011996-01-011975-01-01NoneRAPIDONoneNone...NoneNoneNoneNoneNoneNoneNoneNoneNoneNone
\n", - "

5 rows × 96 columns

\n", - "
" - ], - "text/plain": [ - " siren nic siret dateDebut dateCreationEtablissement \\\n", - "0 006580195 00011 00658019500011 2008-01-01 1965-01-01 \n", - "1 085520195 00109 08552019500109 2022-09-01 2022-06-30 \n", - "2 301692307 00020 30169230700020 2020-12-31 2014-08-15 \n", - "3 302279229 00025 30227922900025 2014-07-25 1900-01-01 \n", - "4 302279229 00033 30227922900033 2008-01-01 1996-01-01 \n", - "\n", - " dateCreationUniteLegale dateFin \\\n", - "0 1965-01-01 None \n", - "1 1955-01-01 None \n", - "2 1965-01-01 None \n", - "3 1975-01-01 None \n", - "4 1975-01-01 None \n", - "\n", - " denominationUniteLegale nomUniteLegale \\\n", - "0 SOCIETE INDUSTRIELLE POUR LE DEVELOPPEMENT DE ... None \n", - "1 SAFRA None \n", - "2 GARAGE BEYRIS None \n", - "3 RAPIDO None \n", - "4 RAPIDO None \n", - "\n", - " prenomUsuelUniteLegale ... libelleVoie2Etablissement \\\n", - "0 None ... None \n", - "1 None ... None \n", - "2 None ... None \n", - "3 None ... None \n", - "4 None ... None \n", - "\n", - " codePostal2Etablissement libelleCommune2Etablissement \\\n", - "0 None None \n", - "1 None None \n", - "2 None None \n", - "3 None None \n", - "4 None None \n", - "\n", - " libelleCommuneEtranger2Etablissement distributionSpeciale2Etablissement \\\n", - "0 None None \n", - "1 None None \n", - "2 None None \n", - "3 None None \n", - "4 None None \n", - "\n", - " codeCommune2Etablissement codeCedex2Etablissement \\\n", - "0 None None \n", - "1 None None \n", - "2 None None \n", - "3 None None \n", - "4 None None \n", - "\n", - " libelleCedex2Etablissement codePaysEtranger2Etablissement \\\n", - "0 None None \n", - "1 None None \n", - "2 None None \n", - "3 None None \n", - "4 None None \n", - "\n", - " libellePaysEtranger2Etablissement \n", - "0 None \n", - "1 None \n", - "2 None \n", - "3 None \n", - "4 None \n", - "\n", - "[5 rows x 96 columns]" - ] - }, - "execution_count": 4, - "metadata": {}, - "output_type": "execute_result" + "name": "stderr", + "output_type": "stream", + "text": [ + "1 - Getting data: 100%|██████████| 1000/1000 [00:03<00:00, 307.70it/s]\n", + "2/2 - Getting data: 100%|██████████| 342/342 [00:00<00:00, 342.96it/s]\n", + "This function may return personal data, please check and comply with the legal framework relating to personal data protection !\n" + ] } ], "source": [ - "data.head()" + "# get activity list\n", + "naf5 = get_activity_list('NAF5')\n", + "\n", + "# search data in SIRENE database\n", + "data = search_sirene(variable=\"activitePrincipaleEtablissement\",\n", + " pattern='29.10Z', kind='siret', number=2000)" ] }, { @@ -314,8 +81,8 @@ "name": "stderr", "output_type": "stream", "text": [ - "For at least one point, exact location has not been found, city location has been given instead | 0/49 [00:00" ] @@ -504,6 +282,22 @@ "ax.set_axis_off()\n", "plt.show()" ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c02616a8-fc67-47b0-b5b7-a8d657a70ecf", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b388d8f7-8888-4f96-87b0-712320a902c6", + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -522,7 +316,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.12.3" + "version": "3.12.7" } }, "nbformat": 4, diff --git a/pynsee/sirene/_request_sirene.py b/pynsee/sirene/_request_sirene.py index d9fe7ea6..85f45f9c 100644 --- a/pynsee/sirene/_request_sirene.py +++ b/pynsee/sirene/_request_sirene.py @@ -23,6 +23,7 @@ def _request_sirene(query, kind, number=1001): raise ValueError("!!! kind should be among : siren siret !!!") INSEE_api_sirene_siren = "https://api.insee.fr/api-sirene/3.11" + number_query_limit = 1000 number_query = min(number_query_limit, number)