python astype category_python类别比较型图表条形图系列条形图汇总

条形图系列

在条形图的柱形变为横向，条形图更加强调项目之间的大小对比；尤其在项目名称较长以及数量较多时，采用条形图可视化数据会更加美观、清晰；

plotnine包绘制条形图

使用plotnine包绘制条形图，Y轴变量和图例变量默认按字母顺序绘制；在plotnine绘制柱形图时，添加coord_flip()，就可以将X-Y轴旋转，将柱形图转换成条形图；

plotnine绘制单数据系列条形图

import pandas as pd

import numpy as np

from plotnine import *

import matplotlib.pyplot as plt

df=pd.read_csv('d:\python\out\StackedbarD.csv')

df=df.sort_values(by='Pensions', ascending=True)

df['Country']=df['Country'].astype("category", df['Country'])

base_plot=(ggplot(df,aes('Country','Pensions'))+

geom_bar(stat="identity", color="black", width=0.6,fill="#FC4E07",size=0.25) +#"#00AFBB"

coord_flip()+

theme(

axis_title=element_text(size=15,face="plain",color="black"),

axis_text = element_text(size=12,face="plain",color="black"),

legend_title=element_text(size=13,face="plain",color="black"),

legend_position = "right",

aspect_ratio =1.15,

figure_size = (6.5, 6.5),

dpi = 50

))

print(base_plot)

plotnine绘制多数据系列条形图

import pandas as pd

import numpy as np

from plotnine import *

import matplotlib.pyplot as plt

df=pd.read_csv('d:\python\out\StackedbarD.csv')

df=df.iloc[:,[0,2,1]]

df=df.sort_values(by='Pensions', ascending=True)

mydata=pd.melt(df,id_vars='Country')

mydata['Country']=mydata['Country'].astype("category",df['Country'])

base_plot=(ggplot(mydata,aes('Country','value',fill='variable'))+

geom_bar(stat="identity", color="black", position=position_dodge(),width=0.7,size=0.25)+

scale_fill_manual(values=("#00AFBB", "#FC4E07", "#E7B800"))+

coord_flip()+

theme(

axis_title=element_text(size=15,face="plain",color="black"),

axis_text = element_text(size=12,face="plain",color="black"),

legend_title=element_text(size=14,face="plain",color="black"),

legend_background =element_blank(),

legend_position = (0.8,0.2),

aspect_ratio =1.15,

figure_size = (6.5, 6.5),

dpi = 50

))

print(base_plot)

plotnine绘制堆积条形图

import pandas as pd

import numpy as np

from plotnine import *

import matplotlib.pyplot as plt

df=pd.read_csv('d:\python\out\StackedbarD.csv')

Sum_df=df.iloc[:,1:].apply(lambda x: x.sum(), axis=0).sort_values(ascending=True)

meanRow_df=df.iloc[:,1:].apply(lambda x: x.mean(), axis=1)

Sing_df=df['Country'][meanRow_df.sort_values(ascending=True).index]

mydata=pd.melt(df,id_vars='Country')

mydata['variable']=mydata['variable'].astype("category",Sum_df.index)

mydata['Country']=mydata['Country'].astype("category",Sing_df)

base_plot=(ggplot(mydata,aes('Country','value',fill='variable'))+

geom_bar(stat="identity", color="black", position='stack',width=0.65,size=0.25)+

scale_fill_brewer(palette="YlOrRd")+

coord_flip()+

theme(

axis_title=element_text(size=18,face="plain",color="black"),

axis_text = element_text(size=16,face="plain",color="black"),

legend_title=element_text(size=18,face="plain",color="black"),

legend_text = element_text(size=16,face="plain",color="black"),

legend_background =element_blank(),

legend_position = 'right',

aspect_ratio =1.15,

figure_size = (6.5, 6.5),

dpi = 50

))

print(base_plot)

base_plot.save('d:\python\out\堆积条形图.pdf')

plotnine绘制百分比堆积条形图

import pandas as pd

import numpy as np

from plotnine import *

import matplotlib.pyplot as plt

df=pd.read_csv('d:\python\out\StackedbarD.csv')

SumCol_df=df.iloc[:,1:].apply(lambda x: x.sum(), axis=1)

df.iloc[:,1:]=df.iloc[:,1:].apply(lambda x: x/SumCol_df, axis=0)

meanRow_df=df.iloc[:,1:].apply(lambda x: x.mean(), axis=0).sort_values(ascending=True)

Per_df=df.loc[:,meanRow_df.idxmax()].sort_values(ascending=True)

Sing_df=df['Country'][Per_df.index]

mydata=pd.melt(df,id_vars='Country')

mydata['Country']=mydata['Country'].astype("category",Sing_df)

mydata['variable']=mydata['variable'].astype("category",meanRow_df.index)

base_plot=(ggplot(mydata,aes(x='Country',y='value',fill='variable'))

+geom_bar(stat="identity", color="black", position='fill',width=0.7,size=0.25)

+scale_fill_brewer(palette="GnBu")

+coord_flip()

+theme(

axis_title=element_text(size=18,face="plain",color="black"),

axis_text = element_text(size=16,face="plain",color="black"),

legend_title=element_text(size=18,face="plain",color="black"),

legend_text = element_text(size=16,face="plain",color="black"),

aspect_ratio =1.15,

figure_size = (6.5, 6.5),

dpi = 50

)

)

print(base_plot)

base_plot.save('d:\python\out\百分比堆积柱形图.pdf')

matplotlib包绘制条形图

使用matplotlib包绘制条形图，用plt.barh()函数替代plt.bar()就可以实现柱形图转换成条形图；X轴变成数值型坐标，Y轴变成类别型坐标；

matplotlib绘制堆积条形图

from matplotlib import cm,colors

from matplotlib import pyplot as plt

from matplotlib.pyplot import figure, show, rc

import numpy as np

import pandas as pd

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

plt.rcParams['axes.unicode_minus']=False #解决负号无法显示的问题

plt.rc('axes',axisbelow=True)

df=pd.read_csv('d:\python\out\StackedCD.csv')

df=df.set_index("Clarity")

Sum_df=df.apply(lambda y: y.sum(), axis=0).sort_values(ascending=False)

df=df.loc[:,Sum_df.index]

meanRow_df=df.apply(lambda y: y.mean(), axis=1)

Sing_df=meanRow_df.sort_values(ascending=False).index

n_row,n_col=df.shape

y_value=np.arange(n_col)

cmap=cm.get_cmap('YlOrRd_r',n_row)

color=[colors.rgb2hex(cmap(i)[:3]) for i in range(cmap.N) ]

bottom_x=np.zeros(n_col)

fig=plt.figure(figsize=(5,5))

for i in range(n_row):

label=Sing_df[i]

plt.barh(y_value,df.loc[label,:],color=color[i],label=label,edgecolor='k', linewidth=0.25)

bottom_x=bottom_x+df.loc[label,:].values

plt.xticks(y_value,df.columns,size=10) #设置y轴刻度

plt.legend(loc=(1,0.3),ncol=1,frameon=False)

plt.grid(axis="x",c=(166/256,166/256,166/256))

ax = plt.gca() #获取整个表格边框

ax.spines['top'].set_color('none') # 设置上‘脊梁’为无色

ax.spines['right'].set_color('none') # 设置右‘脊梁’为无色

ax.spines['left'].set_color('none') # 设置左‘脊梁’为无色

matplotlib绘制百分比堆积条形图

from matplotlib import cm,colors

from matplotlib import pyplot as plt

from matplotlib.pyplot import figure, show, rc

import numpy as np

import pandas as pd

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

plt.rcParams['axes.unicode_minus']=False #解决负号无法显示的问题

plt.rc('axes',axisbelow=True)

df=pd.read_csv('d:\python\out\StackedCD.csv')

df=df.set_index("Clarity")

SumCol_df=df.apply(lambda y: y.sum(), axis=0)

df=df.apply(lambda y: y/SumCol_df, axis=1)

meanRow_df=df.apply(lambda y: y.mean(), axis=1)

Per_df=df.loc[meanRow_df.idxmax(),:].sort_values(ascending=False)

Sing_df=meanRow_df.sort_values(ascending=False).index

df=df.loc[:,Per_df.index]

n_row,n_col=df.shape

y_value=np.arange(n_col)

cmap=cm.get_cmap('YlOrRd_r',n_row)

color=[colors.rgb2hex(cmap(i)[:3]) for i in range(cmap.N) ]

bottom_x=np.zeros(n_col)

fig=plt.figure(figsize=(5,5))

for i in range(n_row):

label=Sing_df[i]

plt.barh(y_value,df.loc[label,:],color=color[i],label=label,edgecolor='k', linewidth=0.25)

bottom_x=bottom_x+df.loc[label,:].values

plt.yticks(y_value,df.columns,size=10) #设置y轴刻度

plt.gca().set_xticklabels(['{:.0f}%'.format(y*100) for y in plt.gca().get_xticks()])

plt.legend(loc=(1,0.3),ncol=1,frameon=False)

plt.grid(axis="x",c=(166/256,166/256,166/256))

ax = plt.gca() #获取整个表格边框

ax.spines['top'].set_color('none') # 设置上‘脊梁’为无色

ax.spines['right'].set_color('none') # 设置右‘脊梁’为无色

ax.spines['left'].set_color('none') # 设置左‘脊梁’为无色