分组统计绘图处理matplotlib

可以参考代码

import matplotlib.pyplot as plt
import numpy as np
#显示中文
plt.rcParams['font.sans-serif']=['SimHei']
 
data1=[3,2,4,2]
data2=[5,4,6,3]
 
#显示多个柱形图所必须
x=np.arange(4)
 
myNames=["姓名1","姓名2","姓名3","姓名4"]
plt.xlabel("name")
plt.ylabel("value")
 
plt.bar(x-0.1,data1,color="red",width=0.2,label="年龄")
plt.bar(x+0.1,data2,color="blue",width=0.2,label="收入")
 
#显示柱状图值
for x1, y1 in zip(x,data1):
    plt.text(x1-0.1, y1, str(y1), ha='center', va='bottom', fontsize=10,color="red")
 
for x1, y1 in zip(x,data2):
    plt.text(x1+0.1, y1, str(y1), ha='center', va='bottom', fontsize=10,color="blue")
 
#设置x轴刻度值
plt.xticks(x,myNames)
#显示图例
plt.legend()
 
plt.show()

效果

 

-------------------------------------------------------------------------------------------------------------------

pandas分组处理，结果清晰。

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
df=pd.read_excel("数据可视化-1.xls",sheet_name="成绩")
mymax=df["收入"].max()
df1=df[df["收入"]>=mymax]
print(df1["姓名"].tolist()[0],df1["收入"].tolist()[0])
#分组操作------饼图--------------------------------------------
df2=df.groupby(["性别"])
#male
dfMale=df2.get_group("male")
#female
dfFemale=df2.get_group("female")
 
mydata=[dfMale["收入"].count(),dfFemale["收入"].count()]
 
mylab=["male","femal"]
explode=[0,0.05]
plt.pie(mydata, labels =mylab,autopct='%1.2f%%',colors=["red","blue"],explode=explode)
plt.title("男女百分比",fontsize=20)
plt.show()
#-----柱状图--------------------------------------------------------
#查询条件
dfAge=["less 30","[30,50]","above 50"]
dfless30=df[df["年龄"]<30]
df3050=df[(df["年龄"]>=30)&(df["年龄"]<=50)]
dfabove50=df[df["年龄"]>50]
 
#x坐标轴分区
listX=np.arange(3)
dfMoney=[dfless30["收入"].mean(),df3050["收入"].mean(),dfabove50["收入"].mean()]
dfScore=[dfless30["积分"].sum(),df3050["积分"].sum(),dfabove50["积分"].sum()]
 
plt.xlim([-0.5,3])
plt.bar(listX,    dfMoney,color="red",width=0.2,label="收入均值")
plt.bar(listX+0.2,dfScore,color="blue",width=0.2,label="积分和")
 
for x1, y1 in zip(listX, dfMoney):
    plt.text(x1, y1, str(y1), ha='center', va='bottom', fontsize=10)
 
for x1, y1 in zip(listX, dfScore):
    plt.text(x1+0.2, y1, str(y1), ha='center', va='bottom', fontsize=10)
 
plt.legend(loc="upper right")
plt.show()
#--------折线图---------------------------------------------------------------
plt.plot(dfAge,dfScore,"ro--",color="r",linewidth=0.5,alpha=0.8,label="消费积分")
plt.plot(dfAge,dfMoney,"ro--",color="b",linewidth=0.5,alpha=0.8,label="平均收入")
 
plt.legend(loc="upper left")
plt.title("标题信息",fontsize=20)
plt.xlabel("年龄阶段",fontsize=10)
plt.ylabel("数据数量",fontsize=10)
 
for x1, y1 in zip(listX, dfMoney):
    plt.text(x1, y1-500, str(y1), ha='center', va='bottom', fontsize=10)
 
for x1, y1 in zip(listX, dfScore):
    plt.text(x1, y1+100, str(y1), ha='center', va='bottom', fontsize=10)
plt.show()
exit()
"""  
x=np.arange(-10,10.5,0.5)
y=x**2
plt.plot(x,y)    #坐标绘图
#plt.step(x,y)   #梯度图
#plt.bar(x,y)    #柱状图
#plt.scatter(x,y) #散列图
#plt.pie(x,y)
plt.grid(True,color='b')  #网格线，默认是关闭的
plt.xlabel("angle")       #x轴标签
plt.ylabel("sin(x)")      #y轴标签
plt.title("sin")          #图形标题
plt.xlim(-15,15)          #x轴显示范围
plt.ylim(-2,120)          #y轴显示范围
#plt.xticks(x)            #x轴刻度列表
plt.show()
langs = ['C', 'C++', 'Java', 'Python', 'PHP']
students = [23,17,35,29,12]
#绘制饼状图
plt.pie(students, labels = langs,autopct='%1.2f%%')
plt.show()
#准备数据
data = [[30, 25, 50, 20],
[40, 23, 51, 17],
[35, 22, 45, 19]]
X = np.arange(4)
#绘制柱状图
plt.bar(X + 0.00, data[0], color = 'b', width = 0.25)
plt.bar(X + 0.25, data[1], color = 'g', width = 0.25)
plt.bar(X + 0.50, data[2], color = 'r', width = 0.25)
plt.show()
"""
import numpy as np
import matplotlib.pyplot as plt
 
countries = ['USA', 'India', 'China', 'Russia', 'Germany'] 
bronzes = np.array([38, 17, 26, 19, 15]) 
silvers = np.array([37, 23, 18, 18, 10]) 
golds = np.array([46, 27, 26, 19, 17]) 
# 此处的 _ 下划线表示将循环取到的值放弃，只得到[0,1,2,3,4]
#ind = [x for x, _ in enumerate(countries)] 
ind = countries
#绘制堆叠图
plt.bar(ind, golds, width=0.5, label='golds', color='gold', bottom=silvers+bronzes) 
plt.bar(ind, silvers, width=0.5, label='silvers', color='silver', bottom=bronzes) 
plt.bar(ind, bronzes, width=0.5, label='bronzes', color='#CD853F') 
#设置坐标轴
plt.xticks(ind, countries) 
plt.ylabel("Medals") 
plt.xlabel("Countries") 
plt.legend(loc="upper right") 
plt.title("2019 Olympics Top Scorers")
plt.show()

结果：