seaborn绘制barplot、scatterplot、boxplot、boxplot、distplot

A histogram barplot

The official argument:

seaborn.barplot(x=None, y=None, hue=None, data=None, order=None, hue_order=None, estimator=<function mean>,ci=95, n_boot=1000, units=None, orient=None,   color=None, palette=None, saturation=0.75,            errcolor='.26', errwidth=None, capsize=None, dodge=True, ax=None, **kwargs)

Of parameters:
X, Y: coordinate value of
hue: classification variable
data: Data
color: Color
palette: palette
orient: a columnar direction

import os
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt

os.chdir(r'C:\Users\MAR\Desktop\新建文件夹')

#解决中文乱码问题
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False

data=pd.read_csv(r'my_csv_date.csv',encoding='gbk')
print(data[['分','属1','分类']])
plt.xticks(rotation=45)

sns.barplot(x='分',y='属1',data=data,hue='分类',palette='husl')
plt.legend(bbox_to_anchor=(1.01,0.8))
plt.show()

Draw a scatter plot scatterplot ()

Of parameters:
X, Y: coordinate value of
hue: classification variable
data: Data
color: Color
palette: palette
style: categorical variables plotted to produce different shapes
s: Shape Size
markers: Shape

import os
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt

os.chdir(r'C:\Users\MAR\Desktop\新建文件夹')

#解决中文乱码问题
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False

data=pd.read_csv(r'iris.csv',encoding='gbk')
plt.xticks(rotation=45)

labels=['setosa','versicolor','virginica']
sns.scatterplot(x='Length',y='Width',hue=data.Species,data=data,palette='husl',marker='x',s=20,\
                )
plt.legend(bbox_to_anchor=(1.01,0.8))
plt.show()

Boxplot boxplot ()

Of parameters:
X, Y: coordinate value of
hue: classification variable
data: Data
color: Color
palette: palette
flierzise: size outlier
width: line width box
linewidth: Specifies the width of the border of the box

#解决中文乱码问题
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False

data=pd.read_csv(r'titanic.csv',encoding='gbk')
data.dropna(subset=['Age'],inplace=True)

sns.boxplot(y='Age',data=data,showmeans=True,color='c',\
            flierprops={'marker':'x','markerfacecolor':'red'},\
           meanprops={'marker':'o','markersize':4},
           medianprops={'linestyle':'-','color':'orange'})

plt.show()

With a plurality of coordinates plotted boxplot

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

os.chdir(r'C:\Users\MAR\Desktop\test')
#解决中文乱码问题
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False

my_data=pd.read_csv('my_csv_date.csv',encoding='gbk')
print(my_data)

my_data.dropna(inplace=True)#删除缺失值的行
my_data.reset_index(drop=True,inplace=True)#数据索引重置
print(my_data)

my_group=my_data.groupby('分类') # 数据表分类索引设置

#功能:将数据分组后并按指定的列降序排列，与下两行功能一样，但下面需要多一个变量,
att1_avg=my_group.agg({'属1':np.mean}).sort_values('属1',ascending=False)
# att1_avg=my_group.agg({'属1':np.mean})#按照上边的索引对表聚合
# data_sort=att1_avg.sort_values('属1',)

print(att1_avg)
#多个箱线图的绘制要有顺序，可自己定义，而数据使用原来的数据
sns.boxplot(x='分类',y='属1',data=my_data,order=att1_avg.index,showmeans=True,\
            color='lightblue',width=0.3,\
            flierprops={'marker':'x','markerfacecolor':'red','markersize':8},#范围外的数据
            meanprops={'marker':'D','markersize':4,'markerfacecolor':'red'},
           medianprops={'linestyle':'--','color':'orange'})
plt.ylabel('数值')
plt.title('不同分类的属性1的值')
plt.show()

Wants to establish a corresponding plurality of box plots, the most important is that you want to sort the data items processed, to obtain a value corresponding to the order (the content box on FIG orange). If only every packet a display housing (disordered), you only need to be displayed in the index column incoming X , you will require data incoming y columns indexed to the, order polymerization

Histogram

import os
import seaborn as sns
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import norm

os.chdir(r'C:\Users\MAR\Desktop\test\web_data')
#解决中文乱码问题
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False

titan=pd.read_csv('titanic.csv',encoding='gbk')

Age_male=titan[titan.Sex=='male'].Age
Age_female=titan[titan.Sex=='female'].Age

titan.dropna(subset=['Age'],inplace=True)#删除缺失值的行
titan.reset_index(drop=True,inplace=True)#数据索引重置

#kde:是否显示高斯核密度图，hist_kws:直方图参，norm_hist:出现的数据是按频率（<1）显示，
sns.distplot(Age_male,bins=30,kde=False,hist_kws={'color':'red'},norm_hist=True,label='男性')
#不显示直方图和核密度图，fit：和数据匹配的正态分布图（norm），fit拟合曲线，这里是scipy中的正态函数，此时，hist=False
sns.distplot(Age_female,hist=False,kde=False,fit=norm,fit_kws={'color':'blue'},\
             norm_hist=True,label='男性正态分布图',)

sns.distplot(Age_female,bins=30,kde=False,hist_kws={'color':'black'},\
            norm_hist=True,label='女性')
sns.distplot(Age_male,hist=False,kde=False,fit=norm,fit_kws={'color':'green'},\
             norm_hist=True,label='女性正态分布图',)
plt.legend(loc='best')
plt.show()