統計学の勉強ノート

1 散布図

# import altair with an abbreviated alias
import altair as alt

# load a sample dataset as a pandas DataFrame
from vega_datasets import data
cars = data.cars()
cars

                          Name  Miles_per_Gallon  ...       Year  Origin
0    chevrolet chevelle malibu              18.0  ... 1970-01-01     USA
1            buick skylark 320              15.0  ... 1970-01-01     USA
2           plymouth satellite              18.0  ... 1970-01-01     USA
3                amc rebel sst              16.0  ... 1970-01-01     USA
4                  ford torino              17.0  ... 1970-01-01     USA
..                         ...               ...  ...        ...     ...
401            ford mustang gl              27.0  ... 1982-01-01     USA
402                  vw pickup              44.0  ... 1982-01-01  Europe
403              dodge rampage              32.0  ... 1982-01-01     USA
404                ford ranger              28.0  ... 1982-01-01     USA
405                 chevy s-10              31.0  ... 1982-01-01     USA

[406 rows x 9 columns]

# make the chart
alt.Chart(cars).mark_point().encode(
    x='Horsepower',
    y='Miles_per_Gallon',
    color='Origin',
).interactive()

# make the chart
alt.Chart(cars).mark_point().encode(
    x='Horsepower',
    y='Miles_per_Gallon',
    color='Origin',
)

2 ヒストグラム

2.1 Movies

import altair as alt
from vega_datasets import data

source = data.movies.url
source

'https://cdn.jsdelivr.net/npm/vega-datasets@v1.29.0/data/movies.json'

alt.Chart(source).mark_bar().encode(
    alt.X("IMDB_Rating:Q", bin=True),
    y='count()',
)

2.2 Penguins-Adelie

library(tidyverse)
library(palmerpenguins)
df<-penguins |> drop_na()
write.csv(df,"penguins.csv",row.names = FALSE,na="")

import polars as pl
import math
penguins=pl.read_csv("penguins.csv")
penguins

shape: (333, 8)

species	island	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g	sex	year
str	str	f64	f64	i64	i64	str	i64
"Adelie"	"Torgersen"	39.1	18.7	181	3750	"male"	2007
"Adelie"	"Torgersen"	39.5	17.4	186	3800	"female"	2007
"Adelie"	"Torgersen"	40.3	18.0	195	3250	"female"	2007
"Adelie"	"Torgersen"	36.7	19.3	193	3450	"female"	2007
"Adelie"	"Torgersen"	39.3	20.6	190	3650	"male"	2007
…	…	…	…	…	…	…	…
"Chinstrap"	"Dream"	55.8	19.8	207	4000	"male"	2009
"Chinstrap"	"Dream"	43.5	18.1	202	3400	"female"	2009
"Chinstrap"	"Dream"	49.6	18.2	193	3775	"male"	2009
"Chinstrap"	"Dream"	50.8	19.0	210	4100	"male"	2009
"Chinstrap"	"Dream"	50.2	18.7	198	3775	"female"	2009

penguins_adelie=penguins.filter(pl.col("species")=="Adelie")
penguins_adelie

shape: (146, 8)

species	island	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g	sex	year
str	str	f64	f64	i64	i64	str	i64
"Adelie"	"Torgersen"	39.1	18.7	181	3750	"male"	2007
"Adelie"	"Torgersen"	39.5	17.4	186	3800	"female"	2007
"Adelie"	"Torgersen"	40.3	18.0	195	3250	"female"	2007
"Adelie"	"Torgersen"	36.7	19.3	193	3450	"female"	2007
"Adelie"	"Torgersen"	39.3	20.6	190	3650	"male"	2007
…	…	…	…	…	…	…	…
"Adelie"	"Dream"	36.6	18.4	184	3475	"female"	2009
"Adelie"	"Dream"	36.0	17.8	195	3450	"female"	2009
"Adelie"	"Dream"	37.8	18.1	193	3750	"male"	2009
"Adelie"	"Dream"	36.0	17.1	187	3700	"female"	2009
"Adelie"	"Dream"	41.5	18.5	201	4000	"male"	2009

g_width=100
g_height=g_width*2/(1+math.sqrt(5))
chart=alt.Chart(penguins_adelie).mark_bar().encode(
    alt.X("bill_length_mm", bin=True),
    y='count()',
).properties(
    width=g_width,
    height=g_height)
chart

chart.save('penguins_adelie.png', ppi=200)

保存したファイルを表示

2.3 Penguins-Facet by species

penguins=penguins.with_columns(pl.lit(48).alias("a"))
chart1=alt.Chart(penguins).mark_bar().encode(
    alt.X("bill_length_mm").bin(),
    y="count()",
    row="species"
).properties(
    width=g_width*1.5,
    height=g_height*1.5)
chart1

chart1.save('penguins_facet.png', ppi=200)

保存したファイルを表示

chart1=alt.Chart().mark_bar().encode(
    alt.X("bill_length_mm").bin(),
    y="count()",
).properties(
    width=g_width*1.5,
    height=g_height*1.5)
chart2=alt.Chart().mark_rule().encode(
  x="a"
)
chart=(chart1+chart2).facet(row="species",data=penguins)
chart

chart.save('penguins_facet_vline.png', ppi=200)

保存したファイルを表示

3 参考文献

4 Python version

import platform
"Python version "+platform.python_version()

'Python version 3.12.3'