Tweak everything for 2023

This commit is contained in:
Aarni Koskela
2023-09-04 15:40:25 +03:00
parent 5d40fcbae9
commit e730ee89fe
19 changed files with 1453 additions and 143 deletions

View File

@@ -1,11 +1,15 @@
import pandas as pd
from pulkka.column_maps import KKPALKKA_COL, VUOSITULOT_COL
from pulkka.config import OUT_DIR
from pulkka.data_ingest import read_data, force_tulot_numeric, force_age_numeric
from pulkka.data_ingest import read_data, force_age_numeric
from ydata_profiling import ProfileReport
def main():
df = read_data()
df = force_tulot_numeric(df)
df[KKPALKKA_COL] = pd.to_numeric(df[KKPALKKA_COL], errors="coerce")
df[VUOSITULOT_COL] = pd.to_numeric(df[VUOSITULOT_COL], errors="coerce")
df = force_age_numeric(df)
profile = ProfileReport(df)
profile.config.vars.cat.n_obs = 20