koodiklinikka/palkkakysely
1
0
Fork 0
mirror of https://github.com/koodiklinikka/palkkakysely.git synced 2026-02-22 21:55:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow remapping nans to a category

Browse Source
This commit is contained in:
Aarni Koskela
2021-02-19 15:38:45 +02:00
parent 483d193d4d
commit 8ffa8badf4
2 changed files with 16 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
chart_utils.py
View File

@@ -16,8 +16,10 @@ def set_yaxis_cash(plot):
plot.yaxis[0].formatter = bm.NumeralTickFormatter(format="€0") plot.yaxis[0].formatter = bm.NumeralTickFormatter(format="€0")
def get_categorical_stats_plot(df, *, category): def get_categorical_stats_plot(df, *, category, na_as_category=None):
df = get_categorical_stats(df, category, "Vuositulot") df = get_categorical_stats(
df, category, "Vuositulot", na_as_category=na_as_category
)
df.reset_index(inplace=True) df.reset_index(inplace=True)
df[category] = df[category].astype("category") df[category] = df[category].astype("category")
plot = bp.figure( plot = bp.figure(

14
data_utils.py
View File

@@ -1,13 +1,23 @@
from typing import Optional
import pandas as pd import pandas as pd
def get_categorical_stats( def get_categorical_stats(
df: pd.DataFrame, category_col: str, value_col: str df: pd.DataFrame,
category_col: str,
value_col: str,
*,
na_as_category: Optional[str] = None,
) -> pd.DataFrame: ) -> pd.DataFrame:
# Drop records where value is not numeric before grouping... # Drop records where value is not numeric before grouping...
df = df.copy() df = df.copy()
df[value_col] = pd.to_numeric(df[value_col], errors="coerce") df[value_col] = pd.to_numeric(df[value_col], errors="coerce")
df = df[df[value_col].notna() & df[value_col] > 0] df = df[df[value_col].notna() & df[value_col] > 0]
if na_as_category:
df[category_col] = df[category_col].astype("string")
df.loc[df[category_col].isna(), category_col] = na_as_category
df[category_col] = df[category_col].astype("category")
# ... then carry on. # ... then carry on.
group = df[[category_col, value_col]].groupby(category_col) group = df[[category_col, value_col]].groupby(category_col)
return group[value_col].agg(["mean", "min", "max", "median"]) return group[value_col].agg(["mean", "min", "max", "median", "count"])