mirror of
https://github.com/koodiklinikka/palkkakysely.git
synced 2026-03-13 14:03:44 +00:00
663cd3d349
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>
71 lines
1.6 KiB
Python
71 lines
1.6 KiB
Python
from typing import Optional
|
|
|
|
import pandas as pd
|
|
|
|
|
|
def q25(x):
|
|
return x.quantile(0.25)
|
|
|
|
|
|
def q50(x):
|
|
return x.quantile(0.5)
|
|
|
|
|
|
def q75(x):
|
|
return x.quantile(0.75)
|
|
|
|
|
|
def q90(x):
|
|
return x.quantile(0.9)
|
|
|
|
|
|
def get_categorical_stats(
|
|
df: pd.DataFrame,
|
|
category_col: str,
|
|
value_col: str,
|
|
*,
|
|
na_as_category: Optional[str] = None,
|
|
) -> pd.DataFrame:
|
|
# Drop records where value is not numeric before grouping...
|
|
df = df.copy()
|
|
df[value_col] = pd.to_numeric(df[value_col], errors="coerce")
|
|
df = df[df[value_col].notna() & df[value_col] > 0]
|
|
if na_as_category:
|
|
rename_na(df, category_col, na_as_category)
|
|
# ... then carry on.
|
|
group = df[[category_col, value_col]].groupby(category_col, observed=False)
|
|
return group[value_col].agg(
|
|
["mean", "min", "max", "median", "count", q25, q50, q75, q90],
|
|
)
|
|
|
|
|
|
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
|