Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: add NAF code sections #15

Merged
merged 2 commits into from
May 31, 2022
Merged

feat: add NAF code sections #15

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
232e553
feat: add NAF code sections
May 25, 2022
7920b55
fix: add code NAF section dict directly to notebook
May 26, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions labels/sections_codes_naf.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"01":"A","02":"A","03":"A","05":"B","06":"B","07":"B","08":"B","09":"B","10":"C","11":"C","12":"C","13":"C","14":"C","15":"C","16":"C","17":"C","18":"C","19":"C","20":"C","21":"C","22":"C","23":"C","24":"C","25":"C","26":"C","27":"C","28":"C","29":"C","30":"C","31":"C","32":"C","33":"C","35":"D","36":"E","37":"E","38":"E","39":"E","41":"F","42":"F","43":"F","45":"G","46":"G","47":"G","49":"H","50":"H","51":"H","52":"H","53":"H","55":"I","56":"I","58":"J","59":"J","60":"J","61":"J","62":"J","63":"J","64":"K","65":"K","66":"K","68":"L","69":"M","70":"M","71":"M","72":"M","73":"M","74":"M","75":"M","77":"N","78":"N","79":"N","80":"N","81":"N","82":"N","84":"O","85":"P","86":"Q","87":"Q","88":"Q","90":"R","91":"R","92":"R","93":"R","94":"S","95":"S","96":"S","97":"T","98":"T","99":"U"}
65 changes: 64 additions & 1 deletion process-data-before-indexation.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,8 @@
"import os, shutil\n",
"import numpy as np\n",
"import swifter\n",
"import math"
"import math\n",
"import json"
]
},
{
Expand Down Expand Up @@ -61,6 +62,18 @@
"os.makedirs(os.path.dirname(OUTPUT_DATA_FOLDER), exist_ok=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if \"LABELS_FOLDER\" not in locals():\n",
" LABELS_FOLDER = \"./labels/\"\n",
"else:\n",
" print(LABELS_FOLDER)"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down Expand Up @@ -512,6 +525,47 @@
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Sections Codes NAF"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def load_file(file_name: str):\n",
" with open(file_name) as json_file:\n",
" file_decoded = json.load(json_file)\n",
" return file_decoded\n",
"# sections_NAF = load_file(f\"{LABELS_FOLDER}sections_codes_naf.json\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"sections_NAF = {\n",
"\"01\":\"A\",\"02\":\"A\",\"03\":\"A\",\"05\":\"B\",\"06\":\"B\",\"07\":\"B\",\"08\":\"B\",\"09\":\"B\",\"10\":\"C\",\"11\":\"C\",\"12\":\"C\",\"13\":\"C\",\"14\":\"C\",\n",
" \"15\":\"C\",\"16\":\"C\",\"17\":\"C\",\"18\":\"C\",\"19\":\"C\",\"20\":\"C\",\"21\":\"C\",\"22\":\"C\",\"23\":\"C\",\"24\":\"C\",\"25\":\"C\",\"26\":\"C\",\"27\":\"C\",\n",
" \"28\":\"C\",\"29\":\"C\",\"30\":\"C\",\"31\":\"C\",\"32\":\"C\",\"33\":\"C\",\"35\":\"D\",\"36\":\"E\",\"37\":\"E\",\"38\":\"E\",\"39\":\"E\",\"41\":\"F\",\"42\":\"F\",\n",
" \"43\":\"F\",\"45\":\"G\",\"46\":\"G\",\"47\":\"G\",\"49\":\"H\",\"50\":\"H\",\"51\":\"H\",\"52\":\"H\",\"53\":\"H\",\"55\":\"I\",\"56\":\"I\",\"58\":\"J\",\"59\":\"J\",\n",
" \"60\":\"J\",\"61\":\"J\",\"62\":\"J\",\"63\":\"J\",\"64\":\"K\",\"65\":\"K\",\"66\":\"K\",\"68\":\"L\",\"69\":\"M\",\"70\":\"M\",\"71\":\"M\",\"72\":\"M\",\"73\":\"M\",\n",
" \"74\":\"M\",\"75\":\"M\",\"77\":\"N\",\"78\":\"N\",\"79\":\"N\",\"80\":\"N\",\"81\":\"N\",\"82\":\"N\",\"84\":\"O\",\"85\":\"P\",\"86\":\"Q\",\"87\":\"Q\",\"88\":\"Q\",\n",
" \"90\":\"R\",\"91\":\"R\",\"92\":\"R\",\"93\":\"R\",\"94\":\"S\",\"95\":\"S\",\"96\":\"S\",\"97\":\"T\",\"98\":\"T\",\"99\":\"U\"\n",
"}"
]
},
{
"cell_type": "markdown",
"metadata": {
"tags": []
},
"source": [
"# Nombre établissements"
]
Expand Down Expand Up @@ -543,6 +597,15 @@
"df_unite_legale = pd.merge(df_unite_legale, df_out2, on=\"siren\", how=\"left\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df_unite_legale[\"section_activite_principale\"] = df_unite_legale['activite_principale_unite_legale'].str[:2].map(sections_NAF)"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down
1 change: 1 addition & 0 deletions utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,7 @@ def format_sirene_notebook(**kwargs):
"msgs": "Ran from Airflow " + ENV + " !",
"DATA_DIR": TMP_FOLDER + DAG_FOLDER + DAG_NAME + "/data/",
"OUTPUT_DATA_FOLDER": TMP_FOLDER + DAG_FOLDER + DAG_NAME + "/output/",
"LABELS_FOLDER": TMP_FOLDER + DAG_FOLDER + DAG_NAME + "/labels/",
"ELASTIC_INDEX": elastic_index,
},
)
Expand Down