Python : Seaborn Visualization

import pandas as pd 
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

# 데이터셋 
iris = sns.load_dataset('iris')
titanic = sns.load_dataset('titanic')
tips = sns.load_dataset('tips')
flights = sns.load_dataset('flights')

x = iris.petal_length.values

sns.rugplot(x)

<matplotlib.axes._subplots.AxesSubplot at 0x1a175ec950>

sns.kdeplot(x)

<matplotlib.axes._subplots.AxesSubplot at 0x1a18ce6890>

sns.distplot(x, rug=True, kde=True, bins=50)

<matplotlib.axes._subplots.AxesSubplot at 0x1a18d9d1d0>

plt.hist(x, bins=50)

(array([ 2.,  2.,  7., 13., 13., 11.,  0.,  2.,  0.,  0.,  0.,  0.,  0.,
         0.,  0.,  0.,  1.,  0.,  0.,  2.,  0.,  2.,  2.,  1.,  3.,  5.,
         3.,  6.,  4.,  8.,  3.,  5.,  4.,  9.,  8.,  2.,  2.,  2.,  9.,
         3.,  3.,  2.,  2.,  3.,  1.,  1.,  0.,  1.,  2.,  1.]),
 array([1.   , 1.118, 1.236, 1.354, 1.472, 1.59 , 1.708, 1.826, 1.944,
        2.062, 2.18 , 2.298, 2.416, 2.534, 2.652, 2.77 , 2.888, 3.006,
        3.124, 3.242, 3.36 , 3.478, 3.596, 3.714, 3.832, 3.95 , 4.068,
        4.186, 4.304, 4.422, 4.54 , 4.658, 4.776, 4.894, 5.012, 5.13 ,
        5.248, 5.366, 5.484, 5.602, 5.72 , 5.838, 5.956, 6.074, 6.192,
        6.31 , 6.428, 6.546, 6.664, 6.782, 6.9  ]),
 <a list of 50 Patch objects>)

titanic

	survived	pclass	sex	age	sibsp	parch	fare	embarked	class	who	adult_male	deck	embark_town	alive	alone
0	0	3	male	22.0	1	0	7.2500	S	Third	man	True	NaN	Southampton	no	False
1	1	1	female	38.0	1	0	71.2833	C	First	woman	False	C	Cherbourg	yes	False
2	1	3	female	26.0	0	0	7.9250	S	Third	woman	False	NaN	Southampton	yes	True
3	1	1	female	35.0	1	0	53.1000	S	First	woman	False	C	Southampton	yes	False
4	0	3	male	35.0	0	0	8.0500	S	Third	man	True	NaN	Southampton	no	True
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
886	0	2	male	27.0	0	0	13.0000	S	Second	man	True	NaN	Southampton	no	True
887	1	1	female	19.0	0	0	30.0000	S	First	woman	False	B	Southampton	yes	True
888	0	3	female	NaN	1	2	23.4500	S	Third	woman	False	NaN	Southampton	no	False
889	1	1	male	26.0	0	0	30.0000	C	First	man	True	C	Cherbourg	yes	True
890	0	3	male	32.0	0	0	7.7500	Q	Third	man	True	NaN	Queenstown	no	True

891 rows × 15 columns

# Count Plot 
sns.countplot(x='class', data=titanic)

<matplotlib.axes._subplots.AxesSubplot at 0x1a22bd7810>

tips

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4
...	...	...	...	...	...	...	...
239	29.03	5.92	Male	No	Sat	Dinner	3
240	27.18	2.00	Female	Yes	Sat	Dinner	2
241	22.67	2.00	Male	Yes	Sat	Dinner	2
242	17.82	1.75	Male	No	Sat	Dinner	2
243	18.78	3.00	Female	No	Thur	Dinner	2

244 rows × 7 columns

sns.countplot(x='day', data=tips)

<matplotlib.axes._subplots.AxesSubplot at 0x1a22cae310>

sns.jointplot(x='sepal_length', y='sepal_width', data=iris, kind='kde')

<seaborn.axisgrid.JointGrid at 0x1a2309c450>

sns.pairplot(iris)

<seaborn.axisgrid.PairGrid at 0x1a23373590>

sns.pairplot(iris, hue='species')

<seaborn.axisgrid.PairGrid at 0x1a23cd8590>

iris.head(10)

	sepal_length	sepal_width	petal_length	petal_width	species
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
4	5.0	3.6	1.4	0.2	setosa
5	5.4	3.9	1.7	0.4	setosa
6	4.6	3.4	1.4	0.3	setosa
7	5.0	3.4	1.5	0.2	setosa
8	4.4	2.9	1.4	0.2	setosa
9	4.9	3.1	1.5	0.1	setosa

# 2차원 카테고리

titanic_size = titanic.pivot_table(index='class', columns='sex', aggfunc='size')
titanic_size

sex	female	male
class
First	94	122
Second	76	108
Third	144	347

sns.heatmap(titanic_size, cmap='summer', annot=True, fmt='d')

<matplotlib.axes._subplots.AxesSubplot at 0x1a245e0250>

sns.barplot(y='day', x='total_bill', data=tips, hue='sex')

<matplotlib.axes._subplots.AxesSubplot at 0x1a25408550>

sns.boxplot(x='day', y='total_bill', data=tips, hue='sex')

<matplotlib.axes._subplots.AxesSubplot at 0x1a2562b910>