Visualising Multivariate data using seaborn

In [1]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from mpl_toolkits.basemap import Basemap
%matplotlib inline
import warnings
warnings.filterwarnings('ignore')

In [2]:

cars = pd.read_csv("http://web.pdx.edu/~gerbing/data/cars.csv")

In [3]:

cars.columns = ["model","mpg","cyl","engine","hp","weight","accelerate","year","origin"]

In [4]:

cars.head()

Out[4]:

	model	mpg	cyl	engine	hp	weight	accelerate	year	origin
0	amc ambassador dpl	15.0	8	390.0	190	3850	8.5	70	American
1	amc gremlin	21.0	6	199.0	90	2648	15.0	70	American
2	amc hornet	18.0	6	199.0	97	2774	15.5	70	American
3	amc rebel sst	16.0	8	304.0	150	3433	12.0	70	American
4	buick estate wagon (sw)	14.0	8	455.0	225	3086	10.0	70	American

Joint plot¶

It is used to visualise bivariate distribution

In [5]:

sns.jointplot(x='hp', y='mpg', data=cars, size = 8)

Out[5]:

<seaborn.axisgrid.JointGrid at 0x11a8bdb70>

'kind' parameter in joint plot¶

scatter, reg, resid, kde, hex

In [6]:

sns.jointplot(x='hp', y='mpg', data=cars, kind='hex')

Out[6]:

<seaborn.axisgrid.JointGrid at 0x11d62d390>

In [7]:

sns.jointplot(x='hp', y='mpg', data=cars, kind='reg')

Out[7]:

<seaborn.axisgrid.JointGrid at 0x11d62dcc0>

pairplot( )¶

In [8]:

sns.pairplot(cars)

Out[8]:

<seaborn.axisgrid.PairGrid at 0x11dbe4828>

In [9]:

sns.pairplot(cars, hue='origin', kind='reg')

Out[9]:

<seaborn.axisgrid.PairGrid at 0x120531128>