koodiklinikka/palkkakysely
1
0
Fork 0
mirror of https://github.com/koodiklinikka/palkkakysely.git synced 2026-02-13 11:52:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

Show quantiles

Browse Source
This commit is contained in:
Aarni Koskela
2021-02-19 16:46:17 +02:00
parent 496541e477
commit 382898d150
2 changed files with 50 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
data_utils.py
View File

@@ -3,6 +3,22 @@ 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,
@@ -20,4 +36,6 @@ def get_categorical_stats(
df[category_col] = df[category_col].astype("category")
# ... then carry on.
group = df[[category_col, value_col]].groupby(category_col)
return group[value_col].agg(["mean", "min", "max", "median", "count"])
return group[value_col].agg(
["mean", "min", "max", "median", "count", q25, q50, q75, q90]
)