seaborn可视化

# 查看当前挂载的数据集目录 !ls /home/kesci/input/ 

# 查看个人持久化工作区文件 !ls /home/kesci/work/ 

# 查看当前kernerl下的package !pip list --format=columns 

# 显示cell运行时长 %load_ext klab-autotime 

import matplotlib.pyplot as plt %matplotlib inline import seaborn as sns sns.set() import numpy as np import pandas as pd 

data=np.random.multivariate_normal([0,0],[[5,2],[2,2]],size=2000)  data=pd.DataFrame(data,columns=['x','y']) 

data.head() 

Out[9]:

	x	y
0	0.571117	-0.158731
1	2.522765	2.033863
2	-3.413121	-0.566827
3	-1.788482	-0.308131
4	3.565947	2.668333

for col in 'xy':#频次直方图     plt.hist(data[col],normed=True,alpha=0.5) 

/opt/conda/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.   warnings.warn("The 'normed' kwarg is deprecated, and has been " 

for col in 'xy':#KDE可视化     sns.kdeplot(data[col],shade=True) 

sns.distplot(data['x'])#频次直方图与KDE的结合 sns.distplot(data['y']); 

/opt/conda/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.   warnings.warn("The 'normed' kwarg is deprecated, and has been " 

sns.kdeplot(data);#二维KDE图 

/opt/conda/lib/python3.5/site-packages/seaborn/distributions.py:645: UserWarning: Passing a 2D dataset for a bivariate plot is deprecated in favor of kdeplot(x, y), and it will cause an error in future versions. Please update your code.   warnings.warn(warn_msg, UserWarning) 

with sns.axes_style('white'):     sns.jointplot('x','y',data,kind='kde') 

with sns.axes_style('white'):     sns.jointplot('x','y',data,kind='hex') 

/opt/conda/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.   warnings.warn("The 'normed' kwarg is deprecated, and has been " 

iris=sns.load_dataset('iris') 

iris.head() 

Out[21]:

	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

sns.pairplot(iris,hue='species',size=2.5)#矩阵图 

Out[24]:

<seaborn.axisgrid.PairGrid at 0x7f380c3ac0b8>

tips=sns.load_dataset('tips') tips.head() 

Out[26]:

	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

tips['tip_pct']=100*tips['tip']/tips['total_bill']#分面频次直方图 grid=sns.FacetGrid(tips,row='sex',col='time',margin_titles=True) grid.map(plt.hist,'tip_pct',bins=np.linspace(0,40,15)); 

with sns.axes_style(style='ticks'):  # 因子图中不同离散因子分布对比     g = sns.factorplot('day', 'total_bill', 'sex', data=tips, kind='box')     g.set_axis_labels('Day', 'Total Bill') 

with sns.axes_style('white'):#联合分布图     sns.jointplot('total_bill','tip',data=tips,kind='hex') 

/opt/conda/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.   warnings.warn("The 'normed' kwarg is deprecated, and has been " 

sns.jointplot('total_bill','tip',data=tips,kind='reg')#带回归拟合的联合分布 

/opt/conda/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.   warnings.warn("The 'normed' kwarg is deprecated, and has been " 

Out[38]:

<seaborn.axisgrid.JointGrid at 0x7f37faf14dd8>

planets=sns.load_dataset('planets')#用行星数据 planets.head() 

Out[40]:

	method	number	orbital_period	mass	distance	year
0	Radial Velocity	1	269.300	7.10	77.40	2006
1	Radial Velocity	1	874.774	2.21	56.95	2008
2	Radial Velocity	1	763.000	2.60	19.84	2011
3	Radial Velocity	1	326.030	19.40	110.62	2007
4	Radial Velocity	1	516.220	10.50	119.47	2009

with sns.axes_style('white'):     g=sns.factorplot('year',data=planets,aspect=2,kind='count',color='steelblue')     g.set_xticklabels(step=5) 

with sns.axes_style('white'):#不同年份、方法发现的行星数量     g=sns.factorplot('year',data=planets,aspect=4.0,kind='count',hue='method',order=range(2001,2015))     g.set_ylabels('number of planets discovered') 

文章来源: seaborn可视化