Seaborn学习笔记总结大全

import seaborn as sns
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt

import random

def sinplot(filp=1):
    x = np.linspace(0,14,100) # 0-14 生成100个点
    for i in range(1,7):
        plt.plot(x,np.sin(x + i*0.5)*(7-i)*filp)
sinplot()

组合曲线图

sns.set() # 设置风格或者主题
sinplot()

风格主题一般有

• darkgrid
• whitegrid
• dark
• white
• ticks

箱线图

np.random.seed(0) # 设置全局随机种子
sns.set_style('ticks')
#　产生一个正态分布的20*6的数组，点对点
data = np.random.normal(size = (20,6))+np.arange(6)/2

sns.boxplot(data=data)

<matplotlib.axes._subplots.AxesSubplot at 0x2598873b888>

# 去掉上和右框线
sns.boxenplot(data=data)
sns.despine(offset=10)

sns.violinplot(data)
sns.despine(offset=10) # offset调节轴线距离

sns.set_style('whitegrid')
sns.boxplot(data=data,palette='deep')
# sns.despine(left=True)

<matplotlib.axes._subplots.AxesSubplot at 0x25988609048>

sns.set_style('whitegrid')
sns.boxplot(data=data,palette='deep')
sns.despine(left=True) # 指定隐藏

## 指定多个子图
with sns.axes_style('ticks'):
    plt.subplot(211)
    sinplot()
plt.subplot(212)
sinplot(-1)

sns.set()

调节线条和坐标轴大小

sns.set_context('paper') # 类似的参数还有poster\notebook
plt.figure(figsize=(8,6))
sinplot()

sns.set_context('poster') # 类似的参数还有poster(要大一点)\notebook
plt.figure(figsize=(8,6))
sinplot()

sns.set_context('notebook',font_scale=5.5,rc={'lines.linewidth':10.5}) # font_size 坐标数字大小，rc是线条粗细
plt.figure(figsize=(8,6))
sinplot()

调色

调色板

• color_palette()传入颜色
• set_palette()设置图的颜色

分类调色板

current_palette = sns.color_palette()
sns.palplot(current_palette)

一共10个颜色，通过color_palette()调节个数

sns.palplot(sns.color_palette('hls',20)) # hls是颜色空间，传出20种颜色

sns.set(rc={'figure.figsize':(20,8)}) # 指定画布大小
data = np.random.normal(size=(20,20))+np.arange(20)/2
sns.boxenplot(data=data,palette=sns.color_palette('hls',20))

<matplotlib.axes._subplots.AxesSubplot at 0x2598a3da108>

控制颜色亮度和饱和度

• hls_palette()
• l = light亮度
• s = saturation饱和度

sns.palplot(sns.hls_palette(20,l=0.09,s=0.01))

# 用于一对儿的数据
sns.palplot(sns.color_palette('Paired',20)) # 一对数据颜色相近

使用XKCD颜色来命名颜色

# 在指定固定颜色的时候可以用这种方法
plt.plot([0,1],[2,3],sns.xkcd_rgb['red'],lw=4)

plt.plot([0,1],[2,4],sns.xkcd_rgb['green'],lw=3)

plt.plot([0,1],[2,5],sns.xkcd_rgb['blue'],lw=2)

[<matplotlib.lines.Line2D at 0x2598a7b7a88>]

# 或者使用这种方法指定
colors= ['windows blue','amber','purple']
sns.palplot(sns.xkcd_palette(colors))

连续调色

一般热力图使用

sns.palplot(sns.color_palette('Reds')) # 注意这里要首字母大写。是复数形式

sns.palplot(sns.color_palette('Reds_r')) # 注意这里要首字母大写。是复数形式
# _r = reverse 颠倒

色调线性变换

• cubehelix_palette()

sns.palplot(sns.color_palette('cubehelix',10)) # 这个颜色还蛮好看的

sns.palplot(sns.cubehelix_palette(10,start =-0.1,rot = - 0.75,reverse = True))

sns.palplot(sns.cubehelix_palette(10,start =-0.1,rot = - 0.75))

sns.palplot(sns.light_palette('red',reverse=True))

sns.palplot(sns.dark_palette('red'))

轮廓图或者叫等高线图

# 参数长度为300个多元正态分布，并做转置
np.random.seed(2)
x,y = np.random.multivariate_normal([0,0],[[1,-0.5],[-0.5,1]],size=300).T 
pal = sns.light_palette('green',as_cmap=True)
sns.kdeplot(x,y,camp=pal)

C:\Users\kingS\anaconda3\lib\site-packages\seaborn\distributions.py:437: UserWarning: The following kwargs were not used by contour: 'camp'
  cset = contour_func(xx, yy, z, n_levels, **kwargs)





<matplotlib.axes._subplots.AxesSubplot at 0x2598ad709c8>

from scipy import stats,integrate # 导入科学计算库

# 设置主题参数
sns.set(color_codes=True)
np.random.seed(sum(map(ord,'distributions')))

x = np.random.normal(size=100)
sns.distplot(x,kde=False) # kde是是否需要核密度估计的参数

<matplotlib.axes._subplots.AxesSubplot at 0x259906898c8>

sns.distplot(x,bins = 5,kde=True) # kde是是否需要核密度估计的参数 
# bins 调节多少个区间

<matplotlib.axes._subplots.AxesSubplot at 0x2599066b448>

sns.distplot(x,kde=False,fit=stats.gamma) # fit拟合分布函数gamma

<matplotlib.axes._subplots.AxesSubplot at 0x25990ed1408>

np.random.normal(size=100)

array([-7.93670539e-02,  2.35623791e+00,  1.69823731e-01, -1.65983154e+00,
        1.38854404e+00, -1.56926211e+00, -7.30554288e-01, -6.02577362e-01,
        8.98263749e-01,  7.82067606e-01, -1.41254369e-01, -4.47245943e-01,
        2.91969802e-01,  4.27114940e-01,  5.94314228e-01,  1.53917596e-01,
       -1.53200567e+00, -5.69558781e-01,  7.88319084e-01,  2.82753716e-01,
       -5.86497918e-01, -1.16397748e+00,  2.88947587e-01, -2.63436097e-01,
       -1.50246105e+00, -1.75745611e+00, -1.36483802e+00, -7.33840531e-01,
       -5.64724904e-02,  1.33945114e+00,  2.06119424e+00,  5.25737590e-01,
       -1.97816956e-03, -3.53299540e-01, -3.12083544e-01, -7.51424413e-01,
        5.79962214e-01, -1.76068456e-01, -9.22589067e-01,  4.57838865e-01,
        4.67008945e-01, -8.33531122e-01,  2.33001609e-01, -1.61272298e+00,
        1.48554200e-01, -6.34437667e-01, -2.68405188e-01, -2.83733400e-01,
       -1.46665528e+00, -8.31031975e-01,  2.20334408e-01, -7.42256917e-01,
       -1.03642212e+00,  1.46894035e-01,  1.83128376e+00, -7.97836688e-01,
       -2.51106251e-02, -7.51063377e-01,  2.59559153e-01,  3.74713802e-01,
       -1.62470969e+00,  1.25857468e+00,  1.11413325e-01, -9.66904388e-01,
        5.24940304e-01, -1.04693257e+00,  1.19548873e+00,  8.69765920e-01,
       -5.38073347e-01,  2.78726165e-01,  2.47195055e-01,  3.69496598e-01,
       -2.80957399e-01, -1.70529391e+00,  9.04984230e-01,  1.60629597e+00,
       -2.67589907e-01,  5.65918694e-01, -3.29983562e-01, -1.48961748e-02,
       -1.49366521e+00,  5.76244481e-01,  1.41480402e+00, -3.64581041e-01,
        4.19481870e-01,  6.01141850e-01,  9.62268465e-01, -2.15160561e-01,
        8.14040853e-01, -1.20475982e+00,  5.40559848e-01,  7.75185845e-01,
        1.73212150e+00, -2.17369452e-02, -1.71062699e+00, -1.28783899e+00,
        9.02107169e-01, -1.00361959e+00, -8.49754217e-01, -2.09257982e+00])

np.random.normal(100) # 不加size=1000和加了之后的区别

99.1868940499386

import pandas as pd

# 参数多元分布数据
mean,cov = [0,1],[(1,0.5),(0.5,1)]
data = np.random.multivariate_normal(mean,cov,200)
df = pd.DataFrame(data,columns = ['x','y'])
df

	x	y
0	-0.579463	0.414803
1	0.880828	2.285103
2	-0.307332	0.653860
3	1.029192	1.250403
4	-0.892471	1.026103
...	...	...
195	0.249314	1.051238
196	-1.222601	0.894471
197	2.329006	2.152045
198	-0.192728	1.552358
199	-0.325603	1.476723

200 rows × 2 columns

散点图

sns.jointplot(x = 'x',y = 'y',data=df,color = 'k')

<seaborn.axisgrid.JointGrid at 0x2599217f888>

蜂巢散点图

x,y = np.random.multivariate_normal(mean,cov,1000).T
with sns.axes_style('ticks'):
    sns.jointplot(x = x,y = y,kind = 'hex',color = 'k')

两两关系图-散点图组合

iris = sns.load_dataset('iris')
sns.pairplot(iris)

<seaborn.axisgrid.PairGrid at 0x259940ad288>

sns回归分析

np.random.seed(sum(map(ord,'regression')))

tips = sns.load_dataset('tips') # 导入tips数据
tips.head(5) # 查看前五行

	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

regplot()和lmplot()都可以画回归关系的图

plt.figure(figsize=(8,6))
sns.regplot(x = 'total_bill',y='tip',data=tips)

<matplotlib.axes._subplots.AxesSubplot at 0x25994d9abc8>

sns.set(rc={'figure.figsize':(8,8)})  # 设置画布大小
sns.regplot(data=tips,x='size',y='tip')

<matplotlib.axes._subplots.AxesSubplot at 0x25994b29188>

sns.regplot(x='size',y = 'tip',data=tips,x_jitter=0.05) # 给x加上随机波动为0.05

<matplotlib.axes._subplots.AxesSubplot at 0x2599539ad48>

## 类别值的可视化展示

sns.set(style='whitegrid',color_codes=True)

np.random.seed(sum(map(ord,'categorical')))
titanic = sns.load_dataset('titanic')
tips = sns.load_dataset('tips')
iris = sns.load_dataset('iris')

sns.stripplot(x='day',y='total_bill',data=tips,jitter=.1)

<matplotlib.axes._subplots.AxesSubplot at 0x2599553ea08>

圣诞树图

像圣诞树一样的，和jitter的功能相同

sns.swarmplot(x='day',y='total_bill',data=tips)

<matplotlib.axes._subplots.AxesSubplot at 0x2599558ca08>

sns.swarmplot(x='day',y='total_bill',hue='sex',data=tips) # 加一个指标

<matplotlib.axes._subplots.AxesSubplot at 0x259955e5188>

盒图

• IQR统计学概念四分位距
• N = 1.5IQR，若果一个值>Q3+N或者 < Q1-N则为离群点

sns.boxplot(x='day',y='total_bill',hue='time',data=tips)
#,rc={'lines.linewidth':10.5}

<matplotlib.axes._subplots.AxesSubplot at 0x25996ad2e48>

sns.violinplot(x='total_bill',y='day',hue='time',data=tips)

<matplotlib.axes._subplots.AxesSubplot at 0x25996a13f48>

sns.violinplot(x='day',y='total_bill',hue='sex',data=tips,split=True)

<matplotlib.axes._subplots.AxesSubplot at 0x25996b65288>

sns.violinplot(x='day',y='total_bill',data=tips)
sns.swarmplot(x='day',y='total_bill',data=tips,color='w',alpha=0.5)

<matplotlib.axes._subplots.AxesSubplot at 0x25996e4eec8>

条形图

表示集中趋势

sns.barplot(x='sex',y='survived',hue='class',data=titanic)

<matplotlib.axes._subplots.AxesSubplot at 0x25996d325c8>

点图

点图可以更好地描述差异性

sns.pointplot(x='sex',y='survived',hue='class',data=titanic)

<matplotlib.axes._subplots.AxesSubplot at 0x25996db6c48>

点图的优化

• palette = {}颜色设置
• markers = []数据点样式
• linestyles=[]线条样式

sns.pointplot(x='class',y='survived',hue='sex',data=titanic,
             palette={'male':"g",'female':'m'},
              markers=['.','o'],
              linestyles=['-','--'])

<matplotlib.axes._subplots.AxesSubplot at 0x2599725b048>

sns.boxplot(data=iris,orient='v')# orient调整横或竖,'h'=横向,'v'=竖

<matplotlib.axes._subplots.AxesSubplot at 0x2599833a848>

多层面板分类

sns.factorplot(x='day',y='total_bill',hue='smoker',data=tips,kind='bar')

C:\Users\kingS\anaconda3\lib\site-packages\seaborn\categorical.py:3669: UserWarning: The `factorplot` function has been renamed to `catplot`. The original name will be removed in a future release. Please update your code. Note that the default `kind` in `factorplot` (`'point'`) has changed `'strip'` in `catplot`.
  warnings.warn(msg)





<seaborn.axisgrid.FacetGrid at 0x25998352788>

sns.factorplot(x='day',y='total_bill',hue='smoker',col='time',data=tips,kind='swarm')

<seaborn.axisgrid.FacetGrid at 0x259985107c8>

sns.factorplot(x='day',y='total_bill',hue='smoker',col='day',data=tips,kind='box',size=4,aspect=0.5)

C:\Users\kingS\anaconda3\lib\site-packages\seaborn\categorical.py:3675: UserWarning: The `size` parameter has been renamed to `height`; please update your code.
  warnings.warn(msg, UserWarning)





<seaborn.axisgrid.FacetGrid at 0x25998548488>

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

g = sns.FacetGrid(tips,col='time')
g.map(plt.hist,'tip')

<seaborn.axisgrid.FacetGrid at 0x25998628b08>

g = sns.FacetGrid(tips,col='sex',hue='smoker')
g.map(plt.scatter,'total_bill','tip',alpha=0.5)
g.add_legend() # smoker的标签

<seaborn.axisgrid.FacetGrid at 0x259998e9948>

g = sns.FacetGrid(tips,row='smoker',col='time',margin_titles=True)
g.map(sns.regplot,'size','total_bill',color='0.1',fit_reg=True,x_jitter=0.1)

<seaborn.axisgrid.FacetGrid at 0x25999ddd188>

g = sns.FacetGrid(tips,col='day',size=4,aspect=0.5)
g.map(sns.barplot,'sex','total_bill')

C:\Users\kingS\anaconda3\lib\site-packages\seaborn\axisgrid.py:243: UserWarning: The `size` parameter has been renamed to `height`; please update your code.
  warnings.warn(msg, UserWarning)
C:\Users\kingS\anaconda3\lib\site-packages\seaborn\axisgrid.py:728: UserWarning: Using the barplot function without specifying `order` is likely to produce an incorrect plot.
  warnings.warn(warning)





<seaborn.axisgrid.FacetGrid at 0x25999f2dcc8>

# 导入pandas的类别方法
from pandas import Categorical
ordered_days = tips.day.value_counts().index
print(ordered_days)
ordered_days = Categorical(['Thur','Fri','Sat','Sun'])

g = sns.FacetGrid(tips,row='day',row_order=ordered_days,size = 2,aspect = 4)
g.map(sns.boxplot,'total_bill')

CategoricalIndex(['Sat', 'Sun', 'Thur', 'Fri'], categories=['Thur', 'Fri', 'Sat', 'Sun'], ordered=False, dtype='category')


C:\Users\kingS\anaconda3\lib\site-packages\seaborn\axisgrid.py:243: UserWarning: The `size` parameter has been renamed to `height`; please update your code.
  warnings.warn(msg, UserWarning)
C:\Users\kingS\anaconda3\lib\site-packages\seaborn\axisgrid.py:728: UserWarning: Using the boxplot function without specifying `order` is likely to produce an incorrect plot.
  warnings.warn(warning)





<seaborn.axisgrid.FacetGrid at 0x259a45378c8>

pal = dict(Lunch = 'seagreen',Dinner='gray')
g = sns.FacetGrid(tips,hue='time',palette=pal,size=5,hue_kws={'marker':['*','v']})
g.map(plt.scatter,'total_bill','tip',s=50,alpha=0.7,linewidth=0.5,edgecolor='w') # s表示圆圈的大小
g.add_legend()

<seaborn.axisgrid.FacetGrid at 0x259a4d40308>

with sns.axes_style('white'):
    g = sns.FacetGrid(tips,row='sex',col='smoker',margin_titles=True,size=2.5)
g.map(plt.scatter,'total_bill','tip',color='#ff3384',edgecolor='w',lw=0.5)
g.set_axis_labels('Total bill ($)','Tip')
g.set(xticks=[10,30,50],yticks=[2,6,10]) # 调节轴的长度
g.fig.subplots_adjust(wspace=0.02,hspace=0.02) # 调节子图间隔

iris = sns.load_dataset('iris')
g = sns.PairGrid(iris)
g.map(plt.scatter)

<seaborn.axisgrid.PairGrid at 0x259a5290e08>

g = sns.PairGrid(iris)
g.map_diag(plt.hist)
g.map_offdiag(plt.scatter)

<seaborn.axisgrid.PairGrid at 0x259a26099c8>

g = sns.PairGrid(iris,hue = 'species') # 添加区分的类别
g.map_diag(plt.hist)
g.map_offdiag(plt.scatter)
g.add_legend()

<seaborn.axisgrid.PairGrid at 0x259a6e5b688>

g = sns.PairGrid(iris,vars=['sepal_length','sepal_width'],hue='species')
g.map(plt.scatter) # 指定变量画图

<seaborn.axisgrid.PairGrid at 0x259a73e8608>

g = sns.PairGrid(tips,hue='size',palette='GnBu_d')
g.map(plt.scatter,s=50,edgecolor='w')
g.add_legend()

<seaborn.axisgrid.PairGrid at 0x259a7ff8bc8>

热力图

sns.set()

np.random.seed(20)
uniform_data = np.random.normal(size=(3,3))
print(uniform_data)
heatmap = sns.heatmap(uniform_data)

[[ 0.88389311  0.19586502  0.35753652]
 [-2.34326191 -1.08483259  0.55969629]
 [ 0.93946935 -0.97848104  0.50309684]]

np.random.seed(20)
uniform_data = np.random.normal(size=(3,3))
print(uniform_data)
heatmap = sns.heatmap(uniform_data,vmin=0.2,vmax=0.5,center=0) 
# 调整调色板的区间 vmin and vmax
# 调整调色板的中心 center 

[[ 0.88389311  0.19586502  0.35753652]
 [-2.34326191 -1.08483259  0.55969629]
 [ 0.93946935 -0.97848104  0.50309684]]

flights = sns.load_dataset('flights')
flights

	year	month	passengers
0	1949	January	112
1	1949	February	118
2	1949	March	132
3	1949	April	129
4	1949	May	121
...	...	...	...
139	1960	August	606
140	1960	September	508
141	1960	October	461
142	1960	November	390
143	1960	December	432

144 rows × 3 columns

flights = sns.load_dataset('flights')
flights = flights.pivot('month', 'year', 'passengers')
print(flights)
# 读到表格中
#flight.to_csv("res.csv",sep=',',encoding='gbk')
sns.set(rc={'figure.figsize':(8,8)}) 
ax = sns.heatmap(flights)

year       1949  1950  1951  1952  1953  1954  1955  1956  1957  1958  1959  \
month                                                                         
January     112   115   145   171   196   204   242   284   315   340   360   
February    118   126   150   180   196   188   233   277   301   318   342   
March       132   141   178   193   236   235   267   317   356   362   406   
April       129   135   163   181   235   227   269   313   348   348   396   
May         121   125   172   183   229   234   270   318   355   363   420   
June        135   149   178   218   243   264   315   374   422   435   472   
July        148   170   199   230   264   302   364   413   465   491   548   
August      148   170   199   242   272   293   347   405   467   505   559   
September   136   158   184   209   237   259   312   355   404   404   463   
October     119   133   162   191   211   229   274   306   347   359   407   
November    104   114   146   172   180   203   237   271   305   310   362   
December    118   140   166   194   201   229   278   306   336   337   405   

year       1960  
month            
January     417  
February    391  
March       419  
April       461  
May         472  
June        535  
July        622  
August      606  
September   508  
October     461  
November    390  
December    432  

flights = sns.load_dataset('flights')
# 取出这三个属性画热力图，坐标点的位置是passengers
flights = flights.pivot('month', 'year', 'passengers')
ax = sns.heatmap(flights, annot=False, fmt='d',linewidths = 0.05,cmap='PuRd')  #实际的数值注解在图上
# annot 打开数据标签。fmt是调节格式整型，默认是科学计数法的格式
# linewidths 调节间隔
# cmap 调色板

cmap调色板参数请参照！
https://blog.csdn.net/qq_38048756/article/details/118724555