--- title: Essais et développement de la méthode de calage sur marges keywords: fastai sidebar: home_sidebar nb_path: "notebooks/calmar/calage_sur_marges.ipynb" ---
from leximpact_socio_fisca_simu_etat.config import Configuration
config = Configuration(project_folder="leximpact-prepare-data")
import unittest
tc = unittest.TestCase()
import numpy as np
import pandas as pd
import seaborn as sns
import leximpact_prepare_data.calmar
calmar.linear(10)
# sample=erfs, X=RFR, d=wprm nos poids de sondage et Y notre variable d'intéret
sample = pd.DataFrame(
[
[1, 1, 0, 12], # Bucket 0
[2, 1, 0, 32],
[3, 1, 0, 5],
[4, 1, 46, 0], # Bucket 0-100
[5, 1, 99, 4323],
[6, 1, 90, 104],
[7, 1, 250, 102], # Bucket 250-1000
[8, 1, 300, 1253],
[9, 1, 1000, 92],
[10, 1, 21_000, 9217], # Bucket 1000-25000
[11, 1, 12_000, 91],
[12, 1, 1000, 0],
[13, 1, 8000, 0],
[14, 1, 1830, 9812],
[15, 1, 1185, 100281],
[16, 1, 1981, 9822],
[17, 1, 18417, 91],
[18, 1, 26_000, 2301], # Bucket 25000-50000
[19, 1, 49_000, 87203],
],
columns=["idfoy", "d", "X", "Y"],
)
sample.head()
estimateur_y = (sample["d"] * sample["Y"]).sum()
print(estimateur_y)