mirror of
https://github.com/koodiklinikka/palkkakysely.git
synced 2026-03-13 01:03:30 +00:00
Add 2025 survey data support
The 2025 survey uses a single English-only xlsx (instead of separate fi/en files) with a restructured schema: compensation is split into base salary, commission, lomaraha, bonus, and equity components; working time is h/week instead of percentage; and competitive salary is categorical instead of boolean. Vuositulot is now synthesized from the component fields. Drop COLUMN_MAP_2024, COLUMN_MAP_2024_EN_TO_FI, VALUE_MAP_2024_EN_TO_FI, read_initial_dfs_2024, read_data_2024, map_sukupuoli, map_vuositulot, split_boolean_column_to_other, apply_fixups, and the associated gender value lists and boolean text maps. All of this exists in version history. - KKPALKKA now includes base salary + commission (median 5500 → 5800) - Apply map_numberlike to tuntilaskutus and vuosilaskutus columns to handle string values like "60 000" and "100 000" - Filter out zeros when computing tunnusluvut on the index page so stats reflect actual reported values Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -3,9 +3,6 @@ from __future__ import annotations
|
||||
IKA_COL = "Ikä"
|
||||
KAUPUNKI_COL = "Kaupunki"
|
||||
KIKY_COL = "Onko palkkasi nykyroolissasi mielestäsi kilpailukykyinen?"
|
||||
KIKY_OTHER_COL = (
|
||||
"Onko palkkasi nykyroolissasi mielestäsi kilpailukykyinen? (muut vastaukset)"
|
||||
)
|
||||
KKPALKKA_COL = "Kuukausipalkka"
|
||||
KK_TULOT_COL = "Kk-tulot (laskennallinen)"
|
||||
KK_TULOT_NORM_COL = "Kk-tulot (laskennallinen, normalisoitu)"
|
||||
@@ -18,9 +15,7 @@ PALKANSAAJA_VAI_LASKUTTAJA_COL = "Palkansaaja vai laskuttaja"
|
||||
PALVELUT_COL = "Palvelut"
|
||||
ROOLI_COL = "Rooli"
|
||||
ROOLI_NORM_COL = "Rooli (normalisoitu)"
|
||||
SIIRTYNYT_COL = (
|
||||
"Oletko siirtynyt palkansaajasta laskuttajaksi tai päinvastoin 1.10.2023 jälkeen?"
|
||||
)
|
||||
SIIRTYNYT_COL = "Siirtynyt palkansaaja/laskuttaja"
|
||||
SUKUPUOLI_COL = "Sukupuoli"
|
||||
TUNTILASKUTUS_ALV0_COL = "Tuntilaskutus (ALV 0%, euroina)"
|
||||
TYOAIKA_COL = "Työaika"
|
||||
@@ -30,68 +25,67 @@ VUOSILASKUTUS_ALV0_COL = "Vuosilaskutus (ALV 0%, euroina)"
|
||||
VUOSITULOT_COL = "Vuositulot"
|
||||
ID_COL = "Vastaustunniste"
|
||||
|
||||
COLUMN_MAP_2024 = {
|
||||
"Timestamp": "Timestamp",
|
||||
"Oletko palkansaaja vai laskuttaja?": PALKANSAAJA_VAI_LASKUTTAJA_COL,
|
||||
"Oletko siirtynyt palkansaajasta laskuttajaksi tai päinvastoin 1.10.2023 jälkeen?": SIIRTYNYT_COL,
|
||||
"Ikä": "Ikä",
|
||||
"Sukupuoli": "Sukupuoli",
|
||||
"Työkokemus alalta (vuosina)": TYOKOKEMUS_COL,
|
||||
"Koulutustaustasi": "Koulutustaustasi",
|
||||
"Tulojen muutos viime vuodesta (%)": "Tulojen muutos viime vuodesta (%)",
|
||||
"Montako vuotta olet tehnyt laskuttavaa työtä alalla?": "Montako vuotta olet tehnyt laskuttavaa työtä alalla?",
|
||||
"Mitä palveluja tarjoat?": PALVELUT_COL,
|
||||
"Tuntilaskutus (ALV 0%, euroina)": TUNTILASKUTUS_ALV0_COL,
|
||||
"Vuosilaskutus (ALV 0%, euroina)": VUOSILASKUTUS_ALV0_COL,
|
||||
"Hankitko asiakkaasi itse suoraan vai käytätkö välitysfirmojen palveluita?": "Hankitko asiakkaasi itse suoraan vai käytätkö välitysfirmojen palveluita?",
|
||||
"Mistä asiakkaat ovat?": MISTA_ASIAKKAAT_COL,
|
||||
"Työpaikka": "Työpaikka",
|
||||
"Missä kaupungissa työpaikkasi pääasiallinen toimisto sijaitsee?": KAUPUNKI_COL,
|
||||
"Millaisessa yrityksessä työskentelet?": MILLAISESSA_COL,
|
||||
"Työaika": TYOAIKA_COL,
|
||||
"Kuinka suuren osan ajasta teet lähityönä toimistolla?": LAHITYO_COL,
|
||||
"Rooli / titteli": ROOLI_COL,
|
||||
"Kuukausipalkka (brutto, euroina)": KKPALKKA_COL,
|
||||
"Vuositulot (sis. bonukset, osingot yms, euroina)": VUOSITULOT_COL,
|
||||
"Vapaa kuvaus kokonaiskompensaatiomallista": "Vapaa kuvaus kokonaiskompensaatiomallista",
|
||||
"Onko palkkasi nykyroolissasi mielestäsi kilpailukykyinen?": KIKY_COL,
|
||||
"Vapaa sana": "Vapaa sana",
|
||||
"Palautetta kyselystä ja ideoita ensi vuoden kyselyyn": PALAUTE_COL,
|
||||
}
|
||||
COMMISSION_COL = "Provisio (kk, brutto)"
|
||||
LOMARAHA_COL = "Lomaraha (EUR)"
|
||||
BONUS_COL = "Bonus (EUR)"
|
||||
EQUITY_COL = "Osakkeet/optiot (EUR)"
|
||||
SENIORITY_COL = "Seniority"
|
||||
|
||||
COLUMN_MAP_2024_EN_TO_FI = {
|
||||
COLUMN_MAP_2025 = {
|
||||
"Timestamp": "Timestamp",
|
||||
"Employee or entrepreneur": "Oletko palkansaaja vai laskuttaja?",
|
||||
"Have you switched from employment to entrepreneurship or vice versa after 1.10.2023?": "Oletko siirtynyt palkansaajasta laskuttajaksi tai päinvastoin 1.10.2023 jälkeen?",
|
||||
"Age": "Ikä",
|
||||
"Gender": "Sukupuoli",
|
||||
"Relevant work experience from the industry (in years)": "Työkokemus alalta (vuosina)",
|
||||
"Employee or entrepreneur": PALKANSAAJA_VAI_LASKUTTAJA_COL,
|
||||
"Switched from employment to entrepreneurship, or vice versa, in 2025?": SIIRTYNYT_COL,
|
||||
"Age": IKA_COL,
|
||||
"Gender": SUKUPUOLI_COL,
|
||||
"Finnish fluency": "Suomen kielen taito",
|
||||
"Work language": "Työkieli",
|
||||
"Relevant work experience from the industry (in years)": TYOKOKEMUS_COL,
|
||||
"Years at current employer": "Vuosia nykyisellä työnantajalla",
|
||||
"Companies worked for": "Työpaikkojen lukumäärä",
|
||||
"Company size": "Yrityksen koko",
|
||||
"Education": "Koulutustaustasi",
|
||||
"Change in income from last year (in %)": "Tulojen muutos viime vuodesta (%)",
|
||||
"How many years have you worked as an entrepreneur in this industry?": "Montako vuotta olet tehnyt laskuttavaa työtä alalla?",
|
||||
"What services do you offer?": "Mitä palveluja tarjoat?",
|
||||
"Hourly rate (VAT 0%, in euros)": "Tuntilaskutus (ALV 0%, euroina)",
|
||||
"Yearly billing (VAT 0%, in euros)": "Vuosilaskutus (ALV 0%, euroina)",
|
||||
"Field of Study": "Opintoala",
|
||||
"Change in pay rate from last year (%)": "Tulojen muutos viime vuodesta (%)",
|
||||
"Years as entrepreneur": "Montako vuotta olet tehnyt laskuttavaa työtä alalla?",
|
||||
"What services do you offer?": PALVELUT_COL,
|
||||
"Hourly rate (VAT 0%, in euros)": TUNTILASKUTUS_ALV0_COL,
|
||||
"Yearly billing (VAT 0%, in euros)": VUOSILASKUTUS_ALV0_COL,
|
||||
"Billable hours per week": "Laskutettavat tunnit viikossa",
|
||||
"Weeks not billing": "Viikot ilman laskutusta",
|
||||
"Billing methods": "Laskutustavat",
|
||||
"Contract length": "Sopimuksen pituus",
|
||||
"Do you use agencies or find your clients yourself?": "Hankitko asiakkaasi itse suoraan vai käytätkö välitysfirmojen palveluita?",
|
||||
"Where are your clients from?": "Mistä asiakkaat ovat?",
|
||||
"Company": "Työpaikka",
|
||||
"In which city is your office?": "Missä kaupungissa työpaikkasi pääasiallinen toimisto sijaitsee?",
|
||||
"What kind of a company you work in?": "Millaisessa yrityksessä työskentelet?",
|
||||
"Full time / part time": "Työaika",
|
||||
"How much of your work time you spend in company office? (in %)": "Kuinka suuren osan ajasta teet lähityönä toimistolla?",
|
||||
"Role / title": "Rooli / titteli",
|
||||
"Monthly salary (gross, in EUR)": "Kuukausipalkka (brutto, euroina)",
|
||||
"Yearly income (incl. bonuses, etc; in EUR)": "Vuositulot (sis. bonukset, osingot yms, euroina)",
|
||||
"Where are your clients from?": MISTA_ASIAKKAAT_COL,
|
||||
"Company": TYOPAIKKA_COL,
|
||||
"City": KAUPUNKI_COL,
|
||||
"What kind of a company you work in?": MILLAISESSA_COL,
|
||||
"Working time (h/week)": TYOAIKA_COL,
|
||||
"Time in office (%)": LAHITYO_COL,
|
||||
"Role / title": ROOLI_COL,
|
||||
"Seniority level": SENIORITY_COL,
|
||||
"Formal Seniority": "Virallinen senioriteetti",
|
||||
"Base salary (gross, monthly EUR)": KKPALKKA_COL,
|
||||
"Commission (gross, monthly EUR)": COMMISSION_COL,
|
||||
"Lomaraha (Holiday bonus, in EUR)": LOMARAHA_COL,
|
||||
"Bonus (EUR)": BONUS_COL,
|
||||
"Equity (EUR)": EQUITY_COL,
|
||||
"Free description of your compensation model": "Vapaa kuvaus kokonaiskompensaatiomallista",
|
||||
"Is your salary competitive?": "Onko palkkasi nykyroolissasi mielestäsi kilpailukykyinen?",
|
||||
"Competitive salary": KIKY_COL,
|
||||
"Bonus": "Bonukset (kuvaus)",
|
||||
"Non-fringe benefits": "Edut (ei luontoisedut)",
|
||||
"Yearly Tax-Free Benefits (EUR)": "Vuosittaiset verovapaat edut (EUR)",
|
||||
"Fringe benefits (luontoisedut)": "Luontoisedut",
|
||||
"Operating system": "Käyttöjärjestelmä",
|
||||
"Language": "Ohjelmointikieli",
|
||||
"Web Frameworks": "Web-kehykset",
|
||||
"Data Engineering & Machine Learning": "Data & ML",
|
||||
"DevOps & Cloud Platforms": "DevOps & pilvi",
|
||||
"Databases": "Tietokannat",
|
||||
"What was left unasked that you want to answer to?": "Vapaa sana",
|
||||
"Feedback of the survey": "Palautetta kyselystä ja ideoita ensi vuoden kyselyyn",
|
||||
"Feedback of the survey": PALAUTE_COL,
|
||||
}
|
||||
|
||||
# ensure all columns have translations
|
||||
assert set(COLUMN_MAP_2024.keys()) == set(COLUMN_MAP_2024_EN_TO_FI.values())
|
||||
|
||||
VALUE_MAP_2024_EN_TO_FI = {
|
||||
VALUE_MAP_2025 = {
|
||||
PALKANSAAJA_VAI_LASKUTTAJA_COL: {
|
||||
"Employee": "Palkansaaja",
|
||||
"Entrepreneur": "Laskuttaja",
|
||||
@@ -122,9 +116,36 @@ VALUE_MAP_2024_EN_TO_FI = {
|
||||
"Tampere (etänä Berliiniin)": "Tampere",
|
||||
"Turku/remote (HQ Austin, TX)": "Turku",
|
||||
"Ulkomailla": "Ulkomaat",
|
||||
"Remote": "Etätyö",
|
||||
"remote": "Etätyö",
|
||||
"Fully remote": "Etätyö",
|
||||
"Fully remote work": "Etätyö",
|
||||
"100% remote, no main office": "Etätyö",
|
||||
"Completely distributed and remote": "Etätyö",
|
||||
"Remote without HQ": "Etätyö",
|
||||
"Remote (US)": "Ulkomaat",
|
||||
"Outside Finland": "Ulkomaat",
|
||||
"Abroad": "Ulkomaat",
|
||||
"No centrla office, multiple locations with employees": "Etätyö",
|
||||
},
|
||||
MILLAISESSA_COL: {
|
||||
"Product company with softaware as their core business": "Tuotetalossa, jonka core-bisnes on softa",
|
||||
"Product company with software as their core business": "Tuotetalossa, jonka core-bisnes on softa",
|
||||
"A company where software is a support role (for example banks or healthcare)": "Yritys, jossa softa tukirooli",
|
||||
"Consulting": "Konsultointi",
|
||||
"Public or third sector": "Julkinen/kolmas sektori",
|
||||
},
|
||||
SUKUPUOLI_COL: {
|
||||
"Male": "mies",
|
||||
"Female": "nainen",
|
||||
"Non-binary": "muu",
|
||||
"Prefer not to say": None,
|
||||
},
|
||||
KIKY_COL: {
|
||||
"Above market": "Yli markkinatason",
|
||||
"Average market": "Markkinataso",
|
||||
"Below market": "Alle markkinatason",
|
||||
"Not sure": "En osaa sanoa",
|
||||
},
|
||||
}
|
||||
|
||||
@@ -211,9 +232,7 @@ MALE_GENDER_VALUES = (
|
||||
"äiä",
|
||||
)
|
||||
|
||||
IDS_TO_DROP = {
|
||||
"0bf579f8b0a771b9", # 2 euron palkka, rooli "2"
|
||||
"9a3b73d810f6e983", # apache hyökkäyshelikopteri
|
||||
IDS_TO_DROP_2025 = {
|
||||
"18121abbdb13303c", # duplicate of d5ac88f64a922e6c (submitted 3 min later)
|
||||
}
|
||||
FI_EXPECTED_ROW_COUNT = 682
|
||||
EN_EXPECTED_ROW_COUNT = 51
|
||||
EXPECTED_ROW_COUNT_2025 = 683
|
||||
|
||||
@@ -5,27 +5,25 @@ import re
|
||||
import warnings
|
||||
|
||||
import numpy as np
|
||||
import pandas
|
||||
import pandas as pd
|
||||
|
||||
from pulkka.column_maps import (
|
||||
BOOLEAN_TEXT_TO_BOOLEAN_MAP,
|
||||
COLUMN_MAP_2024,
|
||||
COLUMN_MAP_2024_EN_TO_FI,
|
||||
BONUS_COL,
|
||||
COLUMN_MAP_2025,
|
||||
COMMISSION_COL,
|
||||
COMPANY_MAP,
|
||||
EN_EXPECTED_ROW_COUNT,
|
||||
EQUITY_COL,
|
||||
EXPECTED_ROW_COUNT_2025,
|
||||
FEMALE_GENDER_VALUES,
|
||||
FI_EXPECTED_ROW_COUNT,
|
||||
ID_COL,
|
||||
IDS_TO_DROP,
|
||||
IDS_TO_DROP_2025,
|
||||
IKA_COL,
|
||||
KIKY_COL,
|
||||
KIKY_OTHER_COL,
|
||||
KK_TULOT_COL,
|
||||
KK_TULOT_NORM_COL,
|
||||
KKPALKKA_COL,
|
||||
LAHITYO_COL,
|
||||
LANG_COL,
|
||||
LOMARAHA_COL,
|
||||
MALE_GENDER_VALUES,
|
||||
NO_GENDER_VALUES,
|
||||
OTHER_GENDER_VALUES,
|
||||
@@ -34,16 +32,18 @@ from pulkka.column_maps import (
|
||||
ROOLI_COL,
|
||||
ROOLI_NORM_COL,
|
||||
SUKUPUOLI_COL,
|
||||
TUNTILASKUTUS_ALV0_COL,
|
||||
TYOAIKA_COL,
|
||||
TYOKOKEMUS_COL,
|
||||
TYOPAIKKA_COL,
|
||||
VALUE_MAP_2024_EN_TO_FI,
|
||||
VALUE_MAP_2025,
|
||||
VUOSILASKUTUS_ALV0_COL,
|
||||
VUOSITULOT_COL,
|
||||
)
|
||||
from pulkka.config import DATA_DIR, YEAR
|
||||
|
||||
|
||||
def map_sukupuoli(r: pd.Series) -> str | None:
|
||||
def map_sukupuoli(r: pd.Series) -> str | None: # Unused in 2025
|
||||
value = r[SUKUPUOLI_COL]
|
||||
if not isinstance(value, str):
|
||||
return value
|
||||
@@ -84,44 +84,29 @@ def map_numberlike(d):
|
||||
return d
|
||||
|
||||
|
||||
def ucfirst(val):
|
||||
def ucfirst(val) -> str:
|
||||
if isinstance(val, str):
|
||||
return val[0].upper() + val[1:]
|
||||
return val
|
||||
|
||||
|
||||
def hash_row(r: pd.Series) -> str:
|
||||
source_data = f"{r[LANG_COL]}.{int(r.Timestamp.timestamp() * 1000)}"
|
||||
source_data = (
|
||||
f"en.{int(r.Timestamp.timestamp() * 1000)}" # NB (2025): hard-codes `en`!
|
||||
)
|
||||
return hashlib.sha256(source_data.encode()).hexdigest()[:16]
|
||||
|
||||
|
||||
def read_initial_dfs() -> pd.DataFrame:
|
||||
df_fi: pd.DataFrame = pd.read_excel(
|
||||
DATA_DIR / "results-fi.xlsx",
|
||||
skiprows=[1], # Google Sheets exports one empty row
|
||||
)
|
||||
df_fi[LANG_COL] = "fi"
|
||||
df: pd.DataFrame = pd.read_excel(DATA_DIR / "data.xlsx")
|
||||
df.columns = df.columns.str.strip()
|
||||
|
||||
if len(df_fi) < FI_EXPECTED_ROW_COUNT:
|
||||
if len(df) < EXPECTED_ROW_COUNT_2025:
|
||||
raise ValueError(
|
||||
f"Expected at least {FI_EXPECTED_ROW_COUNT} rows in the Finnish data, got {len(df_fi)}",
|
||||
f"Expected at least {EXPECTED_ROW_COUNT_2025} rows, got {len(df)}",
|
||||
)
|
||||
|
||||
df_en: pd.DataFrame = pd.read_excel(
|
||||
DATA_DIR / "results-en.xlsx",
|
||||
skiprows=[1], # Google Sheets exports one empty row
|
||||
)
|
||||
df_en[LANG_COL] = "en"
|
||||
|
||||
if len(df_fi) < EN_EXPECTED_ROW_COUNT:
|
||||
raise ValueError(
|
||||
f"Expected at least {EN_EXPECTED_ROW_COUNT} rows in the English data, got {len(df_en)}",
|
||||
)
|
||||
|
||||
df_en = df_en.rename(columns=COLUMN_MAP_2024_EN_TO_FI)
|
||||
df = pd.concat([df_fi, df_en], ignore_index=True)
|
||||
df = df[df["Timestamp"].notna()] # Remove rows with no timestamp
|
||||
df[LANG_COL] = df[LANG_COL].astype("category")
|
||||
# Give each row a unique hash ID
|
||||
df[ID_COL] = df.apply(hash_row, axis=1)
|
||||
# Ensure truncated sha is unique
|
||||
@@ -146,38 +131,75 @@ def map_case_insensitive(series: pd.Series, mapping: dict[str, str]) -> pd.Serie
|
||||
|
||||
|
||||
def read_data() -> pd.DataFrame:
|
||||
if YEAR != "2024":
|
||||
if YEAR != "2025":
|
||||
raise ValueError(
|
||||
"This code only works for 2024. "
|
||||
"This code only works for 2025. "
|
||||
"Please use an older revision for older data.",
|
||||
)
|
||||
df = read_initial_dfs()
|
||||
|
||||
df = df.rename(columns=COLUMN_MAP_2024)
|
||||
df = df.rename(columns=COLUMN_MAP_2025)
|
||||
|
||||
for col, val_map in VALUE_MAP_2024_EN_TO_FI.items():
|
||||
for col, val_map in VALUE_MAP_2025.items():
|
||||
df[col] = df[col].map(val_map).fillna(df[col]).astype("category")
|
||||
|
||||
# Drop known bogus data
|
||||
df = df.drop(df[df[ID_COL].isin(IDS_TO_DROP)].index)
|
||||
df = df.drop(df[df[ID_COL].isin(IDS_TO_DROP_2025)].index)
|
||||
|
||||
df[SUKUPUOLI_COL] = df.apply(map_sukupuoli, axis=1).astype("category")
|
||||
# Drop duplicate submissions: rows identical on all columns except
|
||||
# Timestamp and ID (keep the earliest submission)
|
||||
content_cols = [c for c in df.columns if c not in ("Timestamp", ID_COL)]
|
||||
before = len(df)
|
||||
df = df.sort_values("Timestamp").drop_duplicates(subset=content_cols, keep="first")
|
||||
n_dupes = before - len(df)
|
||||
if n_dupes:
|
||||
warnings.warn(f"Dropped {n_dupes} duplicate submission(s)")
|
||||
|
||||
# Gender is already mapped via VALUE_MAP_2025
|
||||
df[SUKUPUOLI_COL] = df[SUKUPUOLI_COL].astype("category")
|
||||
df[IKA_COL] = df[IKA_COL].astype("category")
|
||||
df[KIKY_COL] = df[KIKY_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)
|
||||
# Working time is in h/week — normalize to fraction of 37.5h
|
||||
df[TYOAIKA_COL] = to_percentage(df[TYOAIKA_COL], 37.5)
|
||||
# Time in office is already a percentage
|
||||
df[LAHITYO_COL] = to_percentage(df[LAHITYO_COL], 100)
|
||||
|
||||
# Split out non-boolean answers from KIKY_COL to KIKY_OTHER_COL
|
||||
df = split_boolean_column_to_other(df, KIKY_COL, KIKY_OTHER_COL)
|
||||
|
||||
# Try to clean up numbers with spaces, etc. to real numbers
|
||||
df[KKPALKKA_COL] = df[KKPALKKA_COL].apply(map_numberlike)
|
||||
df[VUOSITULOT_COL] = df[VUOSITULOT_COL].apply(map_numberlike)
|
||||
df[TUNTILASKUTUS_ALV0_COL] = pd.to_numeric(
|
||||
df[TUNTILASKUTUS_ALV0_COL].apply(map_numberlike),
|
||||
errors="coerce",
|
||||
)
|
||||
df[VUOSILASKUTUS_ALV0_COL] = pd.to_numeric(
|
||||
df[VUOSILASKUTUS_ALV0_COL].apply(map_numberlike),
|
||||
errors="coerce",
|
||||
)
|
||||
|
||||
# Synthesize Vuositulot from components:
|
||||
# (base_salary + commission) * 12 + lomaraha + bonus + equity
|
||||
for comp_col in [COMMISSION_COL, LOMARAHA_COL, BONUS_COL, EQUITY_COL]:
|
||||
df[comp_col] = pd.to_numeric(
|
||||
df[comp_col].apply(map_numberlike),
|
||||
errors="coerce",
|
||||
).fillna(0)
|
||||
|
||||
# Fold commission into monthly salary so KKPALKKA = base + commission
|
||||
df[KKPALKKA_COL] = (
|
||||
pd.to_numeric(df[KKPALKKA_COL], errors="coerce").fillna(0) + df[COMMISSION_COL]
|
||||
)
|
||||
|
||||
base_yearly = df[KKPALKKA_COL] * 12
|
||||
lomaraha = df.get(LOMARAHA_COL, 0)
|
||||
bonus = df.get(BONUS_COL, 0)
|
||||
equity = df.get(EQUITY_COL, 0)
|
||||
|
||||
df[VUOSITULOT_COL] = base_yearly + lomaraha + bonus + equity
|
||||
# If base salary is missing/zero, vuositulot should be NaN
|
||||
df.loc[
|
||||
pd.to_numeric(df[KKPALKKA_COL], errors="coerce").fillna(0) == 0,
|
||||
VUOSITULOT_COL,
|
||||
] = np.nan
|
||||
|
||||
# Fix up Työpaikka
|
||||
df[TYOPAIKKA_COL] = df[TYOPAIKKA_COL].replace("-", np.nan)
|
||||
@@ -214,7 +236,7 @@ def read_data() -> pd.DataFrame:
|
||||
return df
|
||||
|
||||
|
||||
def to_percentage(ser: pandas.Series, norm_max: float) -> pandas.Series:
|
||||
def to_percentage(ser: pd.Series, norm_max: float) -> pd.Series:
|
||||
"""
|
||||
Convert a series of numbers to a percentage
|
||||
"""
|
||||
@@ -227,54 +249,16 @@ def to_percentage(ser: pandas.Series, norm_max: float) -> pandas.Series:
|
||||
return ser.clip(lower=0)
|
||||
|
||||
|
||||
def split_boolean_column_to_other(df, col, other_col):
|
||||
df[col] = df[col].replace(BOOLEAN_TEXT_TO_BOOLEAN_MAP)
|
||||
df[other_col] = df[col].apply(
|
||||
lambda r: r if (r and not isinstance(r, bool)) else None,
|
||||
)
|
||||
df[col] = (
|
||||
df[col]
|
||||
.apply(
|
||||
lambda value: (
|
||||
["Ei", "Kyllä"][value]
|
||||
if isinstance(value, bool)
|
||||
else (np.nan if not value else "Muu")
|
||||
),
|
||||
)
|
||||
.astype("category")
|
||||
)
|
||||
# reorder columns so that other_col is right after col
|
||||
cols = list(df.columns)
|
||||
cols.remove(other_col)
|
||||
cols.insert(cols.index(col) + 1, other_col)
|
||||
df = df[cols]
|
||||
return df
|
||||
|
||||
|
||||
def force_age_numeric(df):
|
||||
def force_age_numeric(df: pd.DataFrame) -> pd.DataFrame:
|
||||
age_map = {}
|
||||
for cat in df[IKA_COL].cat.categories:
|
||||
m = re.match(r"^(\d+)-(\d+) v", cat)
|
||||
m = re.match(r"^(\d+)-(\d+)( v)?", cat)
|
||||
if m:
|
||||
age_map[cat] = int(round(float(m.group(1)) + float(m.group(2))) / 2)
|
||||
df[IKA_COL] = df[IKA_COL].apply(lambda r: age_map.get(r, r))
|
||||
return df
|
||||
|
||||
|
||||
def main():
|
||||
pd.set_option("display.max_column", None)
|
||||
pd.set_option("display.max_rows", None)
|
||||
pd.set_option("display.max_seq_items", None)
|
||||
pd.set_option("display.max_colwidth", 500)
|
||||
pd.set_option("expand_frame_repr", True)
|
||||
df = read_data()
|
||||
print(df.head())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
|
||||
def apply_fixups(df: pd.DataFrame, fixups: list[tuple[dict, dict]]) -> pd.DataFrame:
|
||||
for match_cond, replace_cond in fixups:
|
||||
match_keys, match_values = zip(*match_cond.items())
|
||||
@@ -286,3 +270,17 @@ def apply_fixups(df: pd.DataFrame, fixups: list[tuple[dict, dict]]) -> pd.DataFr
|
||||
replace_keys, replace_values = zip(*replace_cond.items())
|
||||
df.loc[ix, list(replace_keys)] = replace_values
|
||||
return df
|
||||
|
||||
|
||||
def main() -> None:
|
||||
pd.set_option("display.max_column", None)
|
||||
pd.set_option("display.max_rows", None)
|
||||
pd.set_option("display.max_seq_items", None)
|
||||
pd.set_option("display.max_colwidth", 500)
|
||||
pd.set_option("expand_frame_repr", True)
|
||||
df = read_data()
|
||||
print(df.head())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
@@ -43,3 +43,28 @@ def rename_na(df: pd.DataFrame, col: str, na_name: str) -> None:
|
||||
df[col] = df[col].astype("string")
|
||||
df.loc[df[col].isna(), col] = na_name
|
||||
df[col] = df[col].astype("category")
|
||||
|
||||
|
||||
def explode_multiselect(
|
||||
series: pd.Series,
|
||||
*,
|
||||
sep: str = ", ",
|
||||
top_n: int | None = None,
|
||||
) -> pd.Series:
|
||||
"""
|
||||
Explode a comma-separated multiselect column into value counts.
|
||||
|
||||
Returns a Series of counts indexed by individual values,
|
||||
sorted descending. Optionally limited to top_n entries.
|
||||
"""
|
||||
counts = (
|
||||
series.dropna()
|
||||
.str.split(sep)
|
||||
.explode()
|
||||
.str.strip()
|
||||
.loc[lambda s: s != ""]
|
||||
.value_counts()
|
||||
)
|
||||
if top_n is not None:
|
||||
counts = counts.head(top_n)
|
||||
return counts
|
||||
|
||||
@@ -1,8 +1,11 @@
|
||||
{% extends "_base.html" %}
|
||||
{% macro eur_span(number) -%}
|
||||
<span title="{{ number }}" class="eur" data-number="{{ number }}">{{ number }} €</span>
|
||||
{%- endmacro %}
|
||||
{% macro tunnusluvut_points(df, col_name, title) %}
|
||||
{% with num_kk = df[pd.to_numeric(df[col_name], errors='coerce').notnull()][col_name] %}
|
||||
<li title="n = {{ num_kk.count() }}">{{ title }}, keskiarvo = {{ num_kk.mean()|round(0) }} €</li>
|
||||
<li title="n = {{ num_kk.count() }}">{{ title }}, mediaani = {{ num_kk.median()|round(0) }} €</li>
|
||||
{% with num_kk = df[col_name][pd.to_numeric(df[col_name], errors='coerce') > 0].dropna() %}
|
||||
<li title="n = {{ num_kk.count() }}">{{ title }}, keskiarvo = {{ eur_span(num_kk.mean()|round(0)) }}</li>
|
||||
<li title="n = {{ num_kk.count() }}">{{ title }}, mediaani = {{ eur_span(num_kk.median()|round(0)) }}</li>
|
||||
{% endwith %}
|
||||
{% endmacro %}
|
||||
{% block body %}
|
||||
@@ -74,6 +77,15 @@
|
||||
International</a> (CC BY 4.0).<br>
|
||||
Mankelointityökalujen lisenssi on <a href="https://opensource.org/licenses/MIT">MIT</a>.
|
||||
</p>
|
||||
<script>
|
||||
for (const eur of document.querySelectorAll(".eur")) {
|
||||
// Try to parse data-number, format as browser-native currency
|
||||
const number = parseFloat(eur.dataset.number);
|
||||
if (!isNaN(number)) {
|
||||
eur.textContent = number.toLocaleString("fi-FI", {style: "currency", currency: "EUR"});
|
||||
}
|
||||
}
|
||||
</script>
|
||||
{% endblock %}
|
||||
{% block footer %}
|
||||
<footer>
|
||||
|
||||
Reference in New Issue
Block a user