Xuliqin The homework5

import pandas as pd
url ='https://raw.githubusercontent.com/tidyverse/datascience-box/refs/heads/main/course-materials/lab-instructions/lab-02/data/plastic-waste.csv'
df = pd.read_csv(url)
df

	code	entity	continent	year	gdp_per_cap	plastic_waste_per_cap	mismanaged_plastic_waste_per_cap	mismanaged_plastic_waste	coastal_pop	total_pop
0	AFG	Afghanistan	Asia	2010	1614.255001	NaN	NaN	NaN	NaN	31411743.0
1	ALB	Albania	Europe	2010	9927.181841	0.069	0.032	29705.0	2530533.0	3204284.0
2	DZA	Algeria	Africa	2010	12870.602699	0.144	0.086	520555.0	16556580.0	35468208.0
3	ASM	American Samoa	Oceania	2010	NaN	NaN	NaN	NaN	NaN	68420.0
4	AND	Andorra	Europe	2010	NaN	NaN	NaN	NaN	NaN	84864.0
...	...	...	...	...	...	...	...	...	...	...
235	VNM	Vietnam	Asia	2010	4408.168612	0.103	0.090	1833819.0	55858245.0	87848445.0
236	ESH	Western Sahara	Africa	2010	NaN	NaN	NaN	NaN	NaN	530500.0
237	YEM	Yemen	Asia	2010	4478.743599	0.103	0.077	169181.0	6048920.0	NaN
238	ZMB	Zambia	Africa	2010	3279.277161	NaN	NaN	NaN	NaN	13088570.0
239	ZWE	Zimbabwe	Africa	2010	1474.877128	NaN	NaN	NaN	NaN	12571454.0

240 rows × 10 columns

import pandas as pd
from lets_plot import *

LetsPlot.setup_html()

(
  ggplot(df, aes("continent", "plastic_waste_per_cap")) +
  geom_histogram()
)

(
  ggplot(df, aes("continent", "plastic_waste_per_cap"))
  + geom_boxplot()
)

import seaborn as sns
import matplotlib.pyplot as plt

# 利用violinplot函数绘制小提琴图
sns.violinplot(x=df["continent"], y=df["plastic_waste_per_cap"])

plt.show()

(
    ggplot(df, aes("plastic_waste_per_cap", "mismanaged_plastic_waste_per_cap")) +
  geom_point()
)

(
    ggplot(
        df,
        aes(
            "plastic_waste_per_cap",
            "mismanaged_plastic_waste_per_cap",
            colour="continent",
        ),
    )
    + geom_point()
)

(
    ggplot(df, aes(x="total_pop", y="plastic_waste_per_cap", colour="continent"))
    + geom_point()
    + xlim(0, 150000000)
    + ylim(0, 0.8)
)

(
    ggplot(df, aes(x="coastal_pop", y="plastic_waste_per_cap", colour="continent"))
    + geom_point()
    + xlim(0, 50000000)
    + ylim(0, 0.8)
)