교과서 Chapter 8

read_csv

import pandas as pd
import matplotlib.pyplot as plt    
import seaborn as sns    
mpg=pd.read_csv('data/mpg.csv')
mpg.head()

	manufacturer	model	displ	year	cyl	trans	drv	cty	hwy	fl	category
0	audi	a4	1.8	1999	4	auto(l5)	f	18	29	p	compact
1	audi	a4	1.8	1999	4	manual(m5)	f	21	29	p	compact
2	audi	a4	2.0	2008	4	manual(m6)	f	20	31	p	compact
3	audi	a4	2.0	2008	4	auto(av)	f	21	30	p	compact
4	audi	a4	2.8	1999	6	auto(l5)	f	16	26	p	compact

scatterplot

• seaborn 을 사용한 산점도

sns.scatterplot(data=mpg,x="displ",y="hwy",hue="drv").set(xlim=[3,6], ylim=[10,30])
#plt.figure(figsize=(8,7))
plt.show()

• plotly 를 사용한 산점도

import plotly.express as px
px.scatter(data_frame=mpg, x='cty',y='hwy',color='drv')

barplot

df_mpg=mpg.groupby("drv", as_index=False).agg(mean_hwy=('hwy','mean'))
sns.barplot(data=df_mpg, x="drv",y="mean_hwy",hue="drv")

groupby & barplot

df_mpg= df_mpg.sort_values("mean_hwy",ascending=False)
#208page
df_mpg=mpg.groupby("drv",as_index=False) \
          .agg(n=("drv","count"))    
sns.barplot(df_mpg,x="drv",y='n',hue="drv")

countplot

sns.countplot(mpg,x='drv',order=['4','f','r'])