From 2049638e13ea75df9cf29ad059ca0a662f92b1dd Mon Sep 17 00:00:00 2001
From: Aarni Koskela <akx@iki.fi>
Date: Mon, 25 Sep 2023 14:16:59 +0300
Subject: [PATCH] Adjust obvious data errors in TYOAIKA (h/t tvainika)

---
 data/2023/results-en.xlsx | Bin 12931 -> 12931 bytes
 data/2023/results-fi.xlsx | Bin 95096 -> 95096 bytes
 pulkka/data_ingest.py     |   5 +++++
 3 files changed, 5 insertions(+)

diff --git a/data/2023/results-en.xlsx b/data/2023/results-en.xlsx
index ee5037d5e52e6f1490473e6a2ff9817289dc3b1b..8a1f39f8ded1bd08066ef2de5526de8875eb2278 100644
GIT binary patch
delta 181
zcmZopZBFG4@MdNaVc_84V7RSlxslg{kr_yDj$n)s12Z;@t3yQYN~AG^McibhdBBVm
zjc6t?<B(PdM2)YGKA17NUiSr9CQGjrBJfDx86+@S!vI3(8Tf(u`wi?s^dv)jFxSb@
Y0!-H$T7l_ZhOS_m$;b>$TN`-*0K=6zn*aa+

delta 181
zcmZopZBFG4@MdNaVc_84U|7A|Vk55yBQucR9KjeN24-v)SBHq)l}KX-i@3>1^MDyC
z8qrK(#v!c^h#FrVeK2Ekz3vOJOqO0LMBtIWGe}^vh5>}mGw=iR_Z!%O=t+k5V6Ky)
Y1(>civ;xz+3|+xAlaU#iwl?wr0BsCG&j0`b

diff --git a/data/2023/results-fi.xlsx b/data/2023/results-fi.xlsx
index e84fba0b321beba6d10c939d286ff965835851e8..06c7c4a955754c82db05bce21fd652cbf59a76c3 100644
GIT binary patch
delta 206
zcmezIjP=JeR^9+_W)=|!4h{~6TZ)z&c|91Jfpl{O<Ms$f#y3JB&USYZMoX~p_GVGW
zG-j~a8wtj&05B^ulQEhJ%-WvK*a1=Jl*_0OW=${2V|)RYjL&B*g$P|QU~~ovO_wc%
yGLj1!{lFqy3K{LdjIV`^_F#s25u*i|QB=fe1!k--Vsr&Fz85i?ff)wHj2-}FkV5PL

delta 206
zcmezIjP=JeR^9+_W)=|!4h{~6Rl6-V@_H~b1L@`n#_bV|jBkWMobB!+jFw>G?aiW$
zY0O};Hxi6l0bo{SCSx=cn6*8du>+#cDVI?n%$i=3$M^y)8K2Ks3K6<qz~~GTnl4)i
yWh56e`hi8Z6f)X@8D9$-?ZFK5B1Q`^qo|0{3d~qv#OMlUd@o`&12YVY89e}OT}vPU

diff --git a/pulkka/data_ingest.py b/pulkka/data_ingest.py
index d9647c9..0743458 100644
--- a/pulkka/data_ingest.py
+++ b/pulkka/data_ingest.py
@@ -147,6 +147,11 @@ def read_data() -> pd.DataFrame:
     df[SUKUPUOLI_COL] = df[SUKUPUOLI_COL].apply(map_sukupuoli).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[LAHITYO_COL] = to_percentage(df[LAHITYO_COL], 100)