数据分析补充----Seaborn

红太狼 2022-03-14 10:42 244阅读 0赞

#  #

# seaborn的参考文档：[http://seaborn.pydata.org/api.html][http_seaborn.pydata.org_api.html] #

## 设置背景 ##

import matplotlib.pyplot as plt
    import numpy as np
    import seaborn as sns
    %matplotlib inline  # 在matplotlib中显示图片
    
    # seaborn中有五种主题风格
    # darkgrid  whitegrid  dark  white  ticks
    # 可以通过sns.set_style('dark')设置风格
    with sns.axes_style('darkgrid'):
        plt.subplot(221)
        sinplot()
    plt.subplot(212)
    sinplot()
    
    # sinplot()是之前定义的一个画sin图像的函数

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70][]

sns.set()  # 设定回默认的背景参数
    sns.set_context('notebook',font_scale=3.5,rc={'line.linewidth':2.5})  # 指定图中标注的大小，还有线的粗细
    sinplot()

## ![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 1][] ##

## 调色板 ##

# 调色板
    # color_palette()能传入任何Matplotlib所支持的颜色，不写参数则使用默认颜色
    # set_palette()设置所有图的颜色
    current_platte = sns.color_palette()
    sns.palplot(current_platte)
    # 有六个默认的颜色循环主题

![20190304120226960.png][]

# 圆形画板：当你有六个以上的类要进行区分的时候，最简单的方法就是在一个圆形的颜色空间中画出均匀间隔的颜色（这样的色调会保持亮度和饱和度不变）这是大多数的当他们需要使用比当前默认颜色多的时的默认方案
    # 最常用的就是使用hls的空间，这是RGB值的一个简单的转换
    sns.palplot(sns.color_palette('hls',8))

![20190304120348615.png][]

# np.arange和range的区别就是np.arange返回的是一个ndarray，并且步长支持float，返回的数值也是float
    data = np.random.normal(size=(20,8)) + np.arange(8)/2
    sns.boxplot(data=data,palette=sns.color_palette('hls',8))
    #sns.boxplot(data=data,palette=sns.hls_palette(8,l=.5,s=.3))  # 通过hls_palette可以调节整个图像的亮度和饱和度

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 2][]

# xkcd包含了一套众包努力的针对随机RGB色的命名，产生了954个可以随机通过xkcd_rgb字典中调用的命名颜色
    sns.set()
    plt.plot([0,1],[0,1],sns.xkcd_rgb['pale red'],lw=3)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 3][]

# 连续色板
    sns.palplot(sns.color_palette('Blues'))
    # 如果想要翻转渐变，可以在面板名称中添加一个_r后缀
    sns.palplot(sns.color_palette('Blues_r'))

![20190304120749381.png][]

![2019030412075851.png][]

# light_palette()和dark_palette()调用定制连续调色板
    sns.palplot(sns.light_palette('green'))
    sns.palplot(sns.dark_palette('purple'))
    sns.palplot(sns.light_palette('green',reverse=True))

![20190304120847735.png][]

![2019030412090112.png][]

![20190304120915890.png][]

## 单变量绘图（distplot） ##

# 单变量绘图，画直方图
    x = np.random.normal(size=100)
    sns.distplot(x,bins=20,kde=False)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 4][]

## jointplot ##

import pandas as pd
    mean,cov = [0,1],[(1,.5),(.5,1)]
    data = np.random.multivariate_normal(mean,cov,200)
    df = pd.DataFrame(data,columns=['x','y'])
    
    sns.jointplot(x='x',y='y',data=df)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 5][]

# 当数据量很大的时候，不容易看出来变量之间的关系，可以通过hex图来看一下相互之间的关系
    with sns.axes_style('white'):
        sns.jointplot(x='x',y='y',kind='hex',color='k',data=df)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 6][]

## pairplot ##

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

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 7][]

## regplot ##

# 回归分析绘图
    tips = sns.load_dataset('tips')
    tips.head()
    sns.regplot(x='total_bill',y='tip',data=tips)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 8][]

sns.regplot(x='size',y='tip',data=tips,x_jitter=.05)  # 在原始数据上加上抖动，这样的话可以使离散型数据画出的回归图更加精确

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 9][]

## stripplot ##

# 多变量分析绘图
    sns.stripplot(x='day',y='total_bill',data=tips,jitter=True)  # jitter的作用就是使数据分散一些，否则重叠会很厉害

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 10][]

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

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 11][]

sns.swarmplot(x='day',y='total_bill',hue='sex',data=tips)  # 先将数据画出来，然后根据不同性别进行标注

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 12][]

## boxplot ##

# 盒图
    sns.boxplot(x='day',y='total_bill',hue='time',data=tips)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 13][]

## violinplot ##

# 小提琴图
    # sns.violinplot(x='day',y='total_bill',hue='time',data=tips)
    sns.violinplot(x='day',y='total_bill',hue='time',data=tips,split=True)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 14][]

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

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 15][]

[http_seaborn.pydata.org_api.html]: http://seaborn.pydata.org/api.html
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70]: /images/20220313/6036630b28c245ee982819c8bd52cb63.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 1]: /images/20220313/400a31534fd9415185f24b881cc3bf6b.png
[20190304120226960.png]: /images/20220313/f5f3e963eb8f452dac1a45c4340a46ea.png
[20190304120348615.png]: /images/20220313/ec71ab7e5f9b439598abb337f696f8a2.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 2]: /images/20220313/70b876bd75bf48d483f08a79af8a1209.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 3]: /images/20220313/7ce24222124c4b6981d1dd0719c471f9.png
[20190304120749381.png]: /images/20220313/7925c668cbc64073a7b18db1925cdc18.png
[2019030412075851.png]: /images/20220313/f4f9bcfd4bbb43caaef3289dfbbf66b8.png
[20190304120847735.png]: /images/20220313/b01207ad496a4156b977e1c5c7cf31fe.png
[2019030412090112.png]: /images/20220313/aabc8ef83ebf4dfb8f6f0049f1f76351.png
[20190304120915890.png]: /images/20220313/4aa2bed935e4467788a9f8d6beb7f124.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 4]: /images/20220313/41984da8bb784e5583436dd2fcbdb367.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 5]: /images/20220313/c1a77024fcfb4b8091b328c33083b225.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 6]: /images/20220313/1ff5682234e1498ea2e446f12935ba56.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 7]: /images/20220313/79e5360c96be4cac87ad47c928393f94.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 8]: /images/20220313/ea526be368ae4366af5320878fd982a6.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 9]: /images/20220313/9990ec71fc144c64ae9e53f2d2eb111d.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 10]: /images/20220313/091c7bd187894094a6cb5fe9d436979c.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 11]: /images/20220313/cdd43571ee1541c4a994c19f9a96e37d.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 12]: /images/20220313/018415bf0db746c492d445ff35eb51c3.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 13]: /images/20220313/537f14c7feca4205b9a119e0a3fcdf05.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 14]: /images/20220313/47bfdff5dafa4dc78d0c0341dd5cd2ee.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTkzMTU0MA_size_16_color_FFFFFF_t_70 15]: /images/20220313/81143822bc8f45a692ce634c0fac3004.png