koodiklinikka/palkkakysely
1
0
Fork 0
mirror of https://github.com/koodiklinikka/palkkakysely.git synced 2026-03-05 15:00:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adjust obvious data errors in TYOAIKA (h/t tvainika)

Browse Source
This commit is contained in:
Aarni Koskela
2023-09-25 14:16:59 +03:00
parent 6bb7038cc7
commit 2049638e13
3 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
data/2023/results-en.xlsx
View File

Binary file not shown.

BIN
data/2023/results-fi.xlsx
View File

Binary file not shown.

5
pulkka/data_ingest.py
View File

@@ -147,6 +147,11 @@ def read_data() -> pd.DataFrame:
df[SUKUPUOLI_COL] = df[SUKUPUOLI_COL].apply(map_sukupuoli).astype("category") df[SUKUPUOLI_COL] = df[SUKUPUOLI_COL].apply(map_sukupuoli).astype("category")
df[IKA_COL] = df[IKA_COL].astype("category") df[IKA_COL] = df[IKA_COL].astype("category")
# Assume that people entering 37.5 (hours) as their työaika means 100%
df.loc[df[TYOAIKA_COL] == 37.5, TYOAIKA_COL] = 100
# Assume there is no actual 10x koodari among us
df.loc[df[TYOAIKA_COL] == 1000, TYOAIKA_COL] = 100
df[TYOAIKA_COL] = to_percentage(df[TYOAIKA_COL], 100) df[TYOAIKA_COL] = to_percentage(df[TYOAIKA_COL], 100)
df[LAHITYO_COL] = to_percentage(df[LAHITYO_COL], 100) df[LAHITYO_COL] = to_percentage(df[LAHITYO_COL], 100)