Feat: première version en notebook
This commit is contained in:
commit
7aca068a8d
|
@ -0,0 +1,10 @@
|
|||
clean_raw:
|
||||
rm -rf ./PLESNA Compta SYSTEM/raw/**/*.csv
|
||||
|
||||
clean_built:
|
||||
rm -rf ./PLESNA Compta SYSTEM/staging/**/*.csv
|
||||
rm -rf ./PLESNA Compta SYSTEM/gold/**/*.csv
|
||||
rm -rf ./PLESNA Compta SYSTEM/datamart/**/*.csv
|
||||
|
||||
clean_all: clean_built clean_raw
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
# E(T)LT pour Plesna
|
||||
|
||||
## Stages
|
||||
|
||||
- Raw: fichiers les plus brutes possibles
|
||||
|
||||
- historique (fichiers avant création datawharehouse)
|
||||
- pdf (depuis les agences)
|
||||
- banque (extract depuis le web)
|
||||
- patrimoine
|
||||
|
||||
- Staging: importation des données brutes triées par années
|
||||
|
||||
- locataire (fait)
|
||||
- charge (fait)
|
||||
- banque (fait)
|
||||
- patrimoine (dimension): description des lots
|
||||
|
||||
- Gold: données enrichies (catégorie, lots...) et testée
|
||||
|
||||
- locataire
|
||||
- charge
|
||||
- banque
|
||||
- patrimoine
|
||||
|
||||
- DataMart: données organisées pour analyse
|
||||
|
||||
- lot\_<lot_id>\_loyer: historique de tous les loyers du lot
|
||||
- lot\_<lot_id>\_travaux: historique de tous les travaux du lot
|
||||
- lot\_<lot_id>\_description: historique des identifications du lot
|
||||
|
||||
- pnl\_<annee>: agrégation des loyers, charges et banques par mois et immeuble
|
File diff suppressed because one or more lines are too long
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,206 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bc224455-95ed-4e33-864d-442396301cd4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Staging vers Gold"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "d5dff9f3-ec7d-4fc7-8471-5ed1fbf6cf06",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from pathlib import Path\n",
|
||||
"import pandas as pd"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "4e5779f6-e0ad-46f8-b684-49af4205f084",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"staging_path = Path(\"../PLESNA Compta SYSTEM/staging\")\n",
|
||||
"assert staging_path.exists()\n",
|
||||
"gold_path = Path(\"../PLESNA Compta SYSTEM/gold\")\n",
|
||||
"assert gold_path.exists()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "2074af18-4f81-49cb-9d9c-f50e7408e7fc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def to_csv(df, dest):\n",
|
||||
" if dest.exists():\n",
|
||||
" df.to_csv(dest, mode=\"a\", header=False, index=False)\n",
|
||||
" else:\n",
|
||||
" df.to_csv(dest, index=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "cc74ba91-855a-41e7-8709-122425f98fb6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### clean gold"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "82de8bc5-8d1e-47fb-af28-076ed90835a9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for f in gold_path.glob(\"**/*.csv\"):\n",
|
||||
" f.unlink()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "539446e1-835e-4d79-a8d8-ddd5823f30f9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## CRG"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "a6423b7d-657f-4897-8dd3-fbca68318367",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[PosixPath('../PLESNA Compta SYSTEM/staging/CRG/2020.csv'), PosixPath('../PLESNA Compta SYSTEM/staging/CRG/2018.csv'), PosixPath('../PLESNA Compta SYSTEM/staging/CRG/2022.csv'), PosixPath('../PLESNA Compta SYSTEM/staging/CRG/2021.csv'), PosixPath('../PLESNA Compta SYSTEM/staging/CRG/2023.csv'), PosixPath('../PLESNA Compta SYSTEM/staging/CRG/2019.csv'), PosixPath('../PLESNA Compta SYSTEM/staging/CRG/2017.csv')]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"crg_path = staging_path / \"CRG\"\n",
|
||||
"assert crg_path.exists()\n",
|
||||
"crg_files = list(crg_path.glob(\"*.csv\"))\n",
|
||||
"print(crg_files)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "edcf15c4-aa3c-40c7-805d-ae8933decf8c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"../PLESNA Compta SYSTEM/gold/CRG/2020.csv\n",
|
||||
"../PLESNA Compta SYSTEM/gold/CRG/2018.csv\n",
|
||||
"../PLESNA Compta SYSTEM/gold/CRG/2022.csv\n",
|
||||
"../PLESNA Compta SYSTEM/gold/CRG/2021.csv\n",
|
||||
"../PLESNA Compta SYSTEM/gold/CRG/2023.csv\n",
|
||||
"../PLESNA Compta SYSTEM/gold/CRG/2019.csv\n",
|
||||
"../PLESNA Compta SYSTEM/gold/CRG/2017.csv\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"for f in crg_files:\n",
|
||||
" df = pd.read_csv(f)\n",
|
||||
" df = df.assign(\n",
|
||||
" Impact = df[\"Crédit\"] - df[\"Débit\"],\n",
|
||||
" )\n",
|
||||
" dest = gold_path / f\"CRG/{f.name}\"\n",
|
||||
" print(dest)\n",
|
||||
" to_csv(df, dest)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "811f6b89-be5a-4290-b3d5-466ec42eb3ae",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Banque"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "c017b0a4-8c41-482e-85b1-4a10be84270b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[PosixPath('../PLESNA Compta SYSTEM/staging/Banque/2020.csv'), PosixPath('../PLESNA Compta SYSTEM/staging/Banque/2022.csv'), PosixPath('../PLESNA Compta SYSTEM/staging/Banque/2021.csv')]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"banque_path = staging_path / \"Banque\"\n",
|
||||
"assert banque_path.exists()\n",
|
||||
"banque_files = list(banque_path.glob(\"*.csv\"))\n",
|
||||
"print(banque_files)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "b04b0d11-dd74-4463-bd6f-c59528cc080e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"../PLESNA Compta SYSTEM/gold/Banque/2020.csv\n",
|
||||
"../PLESNA Compta SYSTEM/gold/Banque/2022.csv\n",
|
||||
"../PLESNA Compta SYSTEM/gold/Banque/2021.csv\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"for f in banque_files:\n",
|
||||
" df = pd.read_csv(f)\n",
|
||||
" df = df.assign(\n",
|
||||
" Impact = df[\"Crédit\"] - df[\"Débit\"],\n",
|
||||
" )\n",
|
||||
" dest = gold_path / f\"Banque/{f.name}\"\n",
|
||||
" print(dest)\n",
|
||||
" to_csv(df, dest)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.11.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
Loading…
Reference in New Issue