可视化整理3---matplotlib绘制统计图形

大佬，救命！！！

于 2023-09-18 14:21:52 发布

阅读量104

点赞数 1

分类专栏： jupyter 学习笔记 Python 文章标签： matplotlib python 信息可视化

本文链接：https://blog.csdn.net/qq_42217078/article/details/132971166

版权

Python 同时被 3 个专栏收录

9 篇文章 0 订阅

订阅专栏

学习笔记

7 篇文章 0 订阅

订阅专栏

jupyter

6 篇文章 0 订阅

订阅专栏

1. 柱状图

函数 bar(x,y,align = "center",color = "b",tick_label = ["A","B","C","D","E"],alpha = 0.6)

参数含义：
x:柱状图中的柱体标签值;
y:柱状图中的柱体高度;
align:柱体对齐方式;
color:柱体颜色;
tick_label:刻度标签值;
alpha:柱体透明度



import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams["font.sans-serif"] = ["SimHei"]#字体选 SimHei
mpl.rcParams["axes.unicode_minus"] = False

x = [1,2,3,4,5]
y = [6,10,4,5,1]

plt.bar(x,#柱状图中的柱体标签值
        y,#柱状图中的柱体高度
        align = "center",#柱体对齐方式
        color = "b",#柱体颜色
        tick_label = ["A","B","C","D","E"],#刻度标签值
        alpha = 0.6)#柱体透明度

plt.xlabel = ("测试难度")
plt.ylabel = ("试卷份数")

plt.grid(True,axis = "y",ls = ":",color = "r",alpha = 0.3)
plt.show()

2. 条形图

函数 barh(x,y,align = "ceter",color = "k",tick_label = ["A","B","C","D","E"])

参数含义：
x:y轴上的柱体标签值;
y:柱体的宽度在x轴显示;
align:柱体对齐方式;
color:柱体颜色;
tick_label:刻度标签值;


import matplotlib as mpl
import matplotlib.pyplot as plt
mpl.rcParams["font.sans-serif"] = ["SimHei"]
mpl.rcParams["axes.unicode_minus"] = False

x = [1,2,3,4,5]
y = [6,10,4,5,1]
plt.barh(x,#y轴上的柱体标签值
         y,#柱体的宽度在x轴显示
         align = "center",#柱体对齐方式
         color = "c",#柱体颜色
         tick_label = ["A","B","C","D","E"])#刻度标签值


plt.ylabel = ("测试难度")
plt.xlabel = ("试卷份数")

plt.grid(True,
         axis = "x",
         ls = ":",
         color = "r",
         alpha = 0.3
        )

plt.show()

3. 堆积图将若干统计图形堆叠起来

函数 bar()/barh()

3.1 堆积柱状图

函数 bar(x,y,bottom = y,color = "r")

参数含义：
x:y轴上的柱体标签值;
y:柱体的宽度在x轴显示;
bottom:取值设定为列表y

import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False

x = [1,2,3,4,5]
y = [6,10,4,5,1]
y1 = [2,6,3,8,5]


plt.bar(x,y,
        align = "center",
        color = "#66c2a5",
        tick_label = ["A","B","C","D","E"],
        label = "班级A"
       )

plt.bar(x,y,
        align = "center",
        bottom = y,
        color = "#8da0cb",
        label ="班级B"
       )

plt.xlabel = ("测试难度")
plt.ylabel = ("试卷份数")


plt.legend()#两个变量加图例更加直观
plt.show()

3.2 堆积条形图

函数 barh(x,y1,left = y,color = "r")

参数含义:
y1:另一套试卷的份数;
left:取值设定为列表y

import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False

import matplotlib as mpl
import matplotlib.pyplot as  plt

mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False

x = [1,2,3,4,5]
y = [6,10,4,5,1]
y1 = [2,6,3,8,5]

plt.barh(x,y,
         align = "center",
         color = "#66c2a5",
         tick_label = ["A","B","C","D","E"],
         label = "班级A")        

plt.barh(x,y1,
        align = "center",
        left = y,
        color = "#8da0cd",
        label = "班级B")

plt.ylabel = ("测试难度")
plt.xlabel = ("试卷份数")
         
plt.legend()
plt.show()

4. 分块图对比多数据分布差异

4.1 多数据并列柱状图

函数 bar()

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


mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False

x = np.arange(5)
y = [6,10,4,5,1]
y1 = [2,6,3,8,5]
bar_width = 0.35
tick_label = ["A","B","C","D","E"]

plt.bar(x,y,
        bar_width,color = "c",
        align = "center",
        label = "班级A",
        alpha = 0.5)

plt.bar(x+bar_width,y1,
        bar_width,
        color = "b",
        align = "center",
        label = "班级B",
        alpha = 0.5
       )


#坐标轴标签名字
plt.xlabel = "测试难度"
plt.ylabel = "试卷份数"


plt.xticks(x+bar_width/2,tick_label)

plt.legend()
plt.show()

4.2 多数据平行条形图

函数 barh()

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

mpl.rcParams["font.sans-serif"] = ["simhei"]#中文显示
mpl.rcParams["axes.unicode_minus"] = False#负值显示

x = np.arange(5)
y = [6,10,4,5,1]
y1 = [2,6,3,8,5]

bar_width= 0.35
tick_label = ["A","B","C","D","E"]


plt.barh(x,y,
          bar_width,
          color = "c",
          align = "center",
          label = "班级A",
          alpha = 0.5
        )

plt.barh(x + bar_width,
         y1,bar_width,
         color = "b",
         align = "center",
         label = "班级B",
         alpha = 0.5)

plt.xlabel = "试卷份数"
plt.ylabel = "测试难度"

plt.yticks(x+bar_width/2 , tick_label)

plt.legend()
plt.show()

5. 参数探索柱体上设置装饰线和装饰图

函数 bar(hatch = "@")

import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False


x = [1,2,3,4,5]
y = [6,10,4,5,1]

plt.bar(x,y,
        align = "center",
        color = "c",
        label = "试卷份数",
        tick_label = ["A","B","C","D","E"],
        hatch = "///"
       )

plt.gca().set_facecolor('yellowgreen')
plt.xlabel = "测试难度"
plt.ylabel = "试卷份数"
plt.legend()
plt.show()

6. 衍生图(折线图,柱状图,条形图基础上衍生出来的图形)

6.1 堆积折线图

函数 stackplot()

'''
堆积折线图 通过绘制不同数据集的折线图生成，
堆积折线图 是按照垂直方向上彼此堆叠且又不相互覆盖的排列顺序，绘制若干条折线图而组成的

'''
import matplotlib.pyplot as plt
import numpy as np

x = np.arange(1,6,1)
y = [0,4,3,5,6]
y1 = [1,3,4,2,7]
y2 = [3,4,1,6,5]

labels = ["BluePlanet","BrownPlanet","GreenPlanet"]
colors = ["#8da0cb","#fc8d62","#66c2a5"]

plt.stackplot(x,y,y1,y2,labels = labels,colors = colors)

plt.legend(loc = "upper left")
plt.show()

6.2 间断条形图

函数 broken_barh()

'''
间断条形图是在条形图的基础上绘制而成的，

主要用来可视化 定性数据 的相同标准在时间维度上的指标值的变化情况，

实现定性数据的相同指标的变化情况的有效直观比较


'''

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

mpl.rcParams["font.sans-serif"] = ["lisu"]#隶书
mpl.rcParams["axes.unicode_minus"] = False

#间断条形图
plt.broken_barh([(30,100),(180,50),(260,70)],
                (20,8),
                facecolors = "#1f78b4")

plt.broken_barh([(60,90),(190,20),(230,30),(280,60)],#从起点x轴60的位置，x轴正方向移动90单位 为柱体的距离和水平起始位置
                (10,8),#起点y轴的数值 为10的位置起，沿y轴正方向移动8个单位  为每一个柱体的高度和垂直起始位置
                facecolors = ("#7fc97f","#beaed4","#fdc086","#ffff99"))#柱体填充颜色

plt.xlim(0,360)
plt.ylim(5,35)
                 
plt.xlabel("演出时间")

plt.xticks(np.arange(0,361,60))
plt.yticks([15,25],["歌剧院A","歌剧院B"])

plt.grid(ls = "-",lw = 1,color = "gray")
plt.title("不同地区的歌剧院的演出时间比较")

plt.show()

6.3 阶梯图

函数 step()


'''
阶梯图 反映数据的趋势变化或者 周期 规律的，
在时间序列数据的可视化任务中，凸显 时序数据的波动周期和规律

'''

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

x = np.linspace(1,10,10)
y = np.sin(x)

#阶梯图
plt.step(x,y,
         color = "#8dd3c7",
         where = "pre",
         lw = 2)

plt.xlim(0,11)
plt.xticks(np.arange(1,11,1))
plt.ylim(-1.2,1.2)
plt.show()

7. 直方图

用来展示连续型数据分布特征的统计图形,直观地分析出数据的集中趋势和波动情况

7.1 应用场景

定量数据的分布展示中

7.2 绘制原理

函数 hist()

参数含义:
x:连续型数据输入值;
bins:用于确定柱体的个数或是柱体边缘范围;
color:柱体的颜色;
histtype:柱体类型;
label:图例内容;
rwidth:柱体的相对宽度,取值范围是[0.0,1.0]

'''
参数含义：
hist(x,bins = bins,color = "b",histtype = "bar",label = "score",rwidth = 10)

x:连续型数据输入值;
bins:用于确定柱体的个数或者柱体边缘范围;
color：柱体的颜色;
histtype:柱体的类型;
label:图例内容;
rwidth:柱体的相对宽度[0-1]

'''
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as  np

mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False

scoresT = np.random.randint(0,100,100)

x = scoresT
bins = range(0,101,10)

plt.hist(x,
         bins = bins,
         color = "#377eb8",
         histtype = "bar",
         rwidth = 1.0)

plt.xlabel("测试成绩")
plt.ylabel("学生人数")


plt.show()

7.3 直方图和柱状图的关系

一方面:直方图描述的是连续型数据的分布,柱状图描述的是离散型数据的分布;
另一方面:直方图柱体间没有空隙,柱状图柱体间有空隙;

7.4 堆积直方图

函数 hist(stacked = True) 堆积直方图
函数 hist(stacked = False) 并排直方图

# 函数 hist(stacked = True) 堆积直方图
# 函数 hist(stacked = False) 并排直方图


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


mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False

scoresT1 = np.random.randint(0,100,100)
scoresT2 = np.random.randint(0,100,100)


plt.hist(x = [scoresT1,scoresT2],
         bins = range(0,101,10),
         color = ["#8dd3c7","#bebada"],
         histtype = "bar",
         rwidth = 1.0,
         stacked = True,#堆积直方图
#          stacked = False,#并排直方图
         label = ["班级A","班级B"])

plt.xlabel("测试成绩(分)")
plt.ylabel("学生人数")
plt.title("不同班级的测试成绩的直方图")
plt.legend(loc = "upper left")
plt.show()

7.5 直方图的不同形状

函数 hist(histtype = "stepfilled") 阶梯型直方图
函数 hist(histtype = "stepfilled",stacked = True)堆积阶梯型直方图

# 函数 hist(histtype = "stepfilled") 阶梯型直方图
# 函数 hist(histtype = "stepfilled",stacked = True)堆积阶梯型直方图


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

mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False


scoreT1 = np.random.randint(0,100,100)
scoreT2 = np.random.randint(0,100,100)


plt.hist(x = [scoreT1,scoreT2],
         color = ["#8dd3c7","#bebada"],
         label = ["班级A","班级B"],
         rwidth = 1.0,
         histtype = "stepfilled",
         stacked = True
        )


plt.xlabel("测试成绩(分)")
plt.ylabel("学生人数")

plt.title("不同班级的测试成绩的直方图")
plt.legend()

plt.show()

8. 饼图用来展示定性数据(离散型数据)比例分布特征的统计图形

函数 pie()

'''
函数 pie()
参数含义：
pie(students,explode = explode,labels = labels,autopct = "%3.1f%%",shartangle = 45,shadow = True,colors = colors ,rwidth = 10)

students:饼片代表的百分比;
explode:饼片边缘偏离半径的百分比;
labels:标记饼片的文本标签内容;
autopct:饼片文本标签内容对应的数值百分比样式;
starangle:从x轴作为起始位置,第一个饼片逆时针旋转的角度;
shadow:是否绘制饼片的阴影;
colors:饼片的颜色;
pctdistance 控制百分比数值显示位置
labeldistance 控制标签值显示位置

'''

import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False



students = [0.35,0.15,0.20,0.30]#饼片代表的百分比
labels = "A难度水平","B难度水平","C难度水平","D难度水平"#标记饼片文本标签内容

plt.pie(students,#饼片代表的百分比
        labels = labels,#标签内容
        explode = (0.1,0.1,0.1,0.1),#偏离半径
        autopct = "%3.1f%%",#文本标签对应的数值百分比样式
        startangle = 45,#第一个饼片逆时针旋转角度
        shadow = True,#是否绘制饼片的阴影
        colors = colors)#饼片的颜色

plt.title("选择不同难度测试试卷的学生占比")
plt.show()

#测试练习

import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False

students = [2.97,2.87,2.49,2.22,2.14,1.95,1.8,1.49,1.44,1.41]#饼片代表的百分比
labels = ["纽康恩-现结","金妈家","深圳比芙肉食有限公司","物以稀为贵（杭州）供应链管理有限公司","北京我爱小城科技有限公司",
          "毕","河南牛匠食品有限公司","荣成福泽交洋贸易有限公司","范总杭州牛茂","徐小军"]#标签内容
explode = (0.2,0.18,0.16,0.14,0.12,0.10,0.08,0.06,0.04,0.02)#偏离半径
colors = ["#377eb8","#4daf4a","#984ea3","#ff7f00","#377eb8","#4daf4a","#984ea3","#ff7f00"]#饼片的颜色


plt.pie(students,#饼片代表的百分比
        labels = labels,#标签内容
        explode = explode,#偏离半径
        autopct = "%3.2f%%",#文本标签对应的数值百分比样式
        startangle = 0,#第一个饼片逆时针旋转角度
        shadow = True,#是否绘制饼片阴影
        colors = colors)#饼片的颜色

plt.title("客户综合加权得分")
plt.show()

8.1 非分裂式饼图

不绘制分裂式饼图只需要去除参数explode
此外以下参数以半径长度比例值作为显示位置依据的
pctdistance 控制百分比数值
labeldistance 控制标签值显示位置

# 不绘制 分裂式饼图  只需要去除参数explode 
# 此外 以下参数 以半径长度比例值作为显示位置依据的 
# pctdistance 控制百分比数值显示位置
# labeldistance 控制标签值显示位置


import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams["font.sans-serif"] = ["simhei"]
mpl.rcParams["axes.unicode_minus"] = False



students = [0.35,0.15,0.20,0.30]#饼片代表的百分比
labels = "A难度水平","B难度水平","C难度水平","D难度水平"#标记饼片文本标签内容

plt.pie(students,#饼片代表的百分比
        labels = labels,#标签内容
#         explode = (0.1,0.1,0.1,0.1),#偏离半径
        autopct = "%3.1f%%",#文本标签对应的数值百分比样式
        startangle = 45,#第一个饼片逆时针旋转角度
        pctdistance = 0.7,# pctdistance 控制百分比数值显示位置
        labeldistance = 1.2,# labeldistance 控制标签值显示位置

        shadow = True,#是否绘制饼片的阴影
        colors = colors)#饼片的颜色

plt.title("选择不同难度测试试卷的学生占比")
plt.show()

8.2 内嵌环形饼图多个饼图嵌套

从单一数据集比例分布情况转换为展示多数据集的比例分布情况

# 从单一数据集比例分布情况转换为展示多数据集的比例分布情况 

import matplotlib as mpl
import matplotlib.pyplot as plt

plt.rcParams["font.sans-serif"] = ["simhei"]
plt.rcParams["axes.unicode_minus"] = False


elements = ["面粉","砂糖","奶油","草莓酱","坚果"]

weight1 = [40,15,20,10,15]
weight2 = [30,25,15,20,10]

colormapList = ["#e41a1c","#377eb8","#4daf4a","#984ea3","#ff7f00"]

outer_colors = colormapList
inner_colors = colormapList



wedges1,texts1,autotexts1 = plt.pie(weight1,
                                    autopct = "%3.1f%%",
                                    radius = 1,
                                    pctdistance = 0.85,
                                    colors = outer_colors,
                                    textprops = dict(color = "w"),
                                    wedgeprops = dict(width = 0.3,edgecolor = "w"))

wedges2,texts2,autotexts2 = plt.pie(weight2,
                                    autopct = "%3.1f%%",
                                    radius = 0.7,
                                    pctdistance = 0.75,
                                    colors = inner_colors,
                                    textprops = dict(color = "w"),
                                    wedgeprops = dict(width = 0.3,edgecolor = "w"))
plt.legend(wedges1,elements,
           fontsize = 12,
           title = "配料表",
           loc = "center left",
           bbox_to_anchor = (0.91,0,0.3,1))
plt.setp(autotexts1,size = 15,weight = "bold")
plt.setp(autotexts2,size = 15,weight = "bold")

plt.setp(texts1,size = 12)
plt.title("不同果酱面包配料比例表")
           
plt.show()

#测试 圆环图
import matplotlib as mpl
import matplotlib.pyplot as plt

plt.rcParams["font.sans-serif"] = ["simhei"]
plt.rcParams["axes.unicode_minus"] = False


elements = ["面粉","砂糖","奶油","草莓酱","坚果"]

weight1 = [40,15,20,10,15]


wedges1,texts1,autotexts1 = plt.pie(weight1,autopct = "%3.1f%%",
                                    radius = 1,
                                    pctdistance = 0.85,
                                    textprops = dict(color = "w"),
                                    wedgeprops = dict(width = 0.3,edgecolor = "w"))

plt.legend(wedges1,elements,
           fontsize = 12,
           title = "配料表",
           loc = "center left",
           bbox_to_anchor = (0.91,0,0.3,1))

plt.setp(autotexts1,size = 10,weight = "bold")

plt.setp(texts1,size = 15)
plt.title("不同果酱面包配料比例表")
           
plt.show()

9. 箱线图箱体(四分位数)和箱须组成 (多组定量数据的分布比较)

9.1 应用场景

一系列测量或观测数据的比较场景中
箱须的末端以外的数值可以理解成离群值 ,箱须是对一组数据范围的大致直观描述

9.2 绘制原理

函数 boxplot()

参数含义:
testList:绘制箱线图的输入数据;
whis:四分位间距的倍数,用来确定箱须包含数据的范围的大小;
widths:设置箱体的宽度;
sym:离散值的标记样式;
labels:绘制每一个数据集的刻度标签;
patch_artist:是否给箱体添加颜色;

'''
函数 boxplot()

参数含义:
testList:绘制箱线图的输入数据;
whis:四分位间距的倍数,用来确定箱须包含数据的范围的大小;
widths:设置箱体的宽度;
sym:离散值的标记样式;
labels:绘制每一个数据集的刻度标签;
patch_artist:是否给箱体添加颜色;
vert #箱线图是否纵向显示
showfliers #箱线图的离群值是否显示

'''

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

plt.rcParams["font.sans-serif"] =  ["fangsong"]
plt.rcParams["axes.unicode_minus"] = False

testA = np.random.randn(5000)
testB = np.random.randn(5000)

testList = [testA,testB]
labels = ["随机数生成器AlphaRM","随机数生成器BetaRM"]#绘制每一个数据集的刻度标签


whis = 1.6 #四分位间距的倍数
width = 0.35 #设置箱体的宽度

bplot = plt.boxplot(testList,#绘制箱线图的输入数据
                   whis = whis,#四分位间距的倍数,用来确定箱须包含数据的范围的大小
                   widths = width,#设置箱体的宽度
                   sym = "o",#离散值的标记样式
                   labels = labels,#绘制每一个数据集的刻度标签
                   patch_artist = True)#是否给箱体添加颜色

for patch,color in zip(bplot["boxes"],colors):
    patch.set_facecolor(color)
    
plt.ylabel("随机数值")
plt.title("生成器抗干扰能力的稳定性比较")

plt.grid(axis = "y",ls = ":",lw = 1,color = "gray",alpha = 0.4)

plt.show()

#测试 notch = True,#变成V型凹痕箱体
'''
vert #箱线图是否纵向显示
showfliers #箱线图的离群值是否显示

'''



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

plt.rcParams["font.sans-serif"] =  ["fangsong"]
plt.rcParams["axes.unicode_minus"] = False

testA = np.random.randn(5000)
testB = np.random.randn(5000)

testList = [testA,testB]
labels = ["随机数生成器AlphaRM","随机数生成器BetaRM"]#绘制每一个数据集的刻度标签


whis = 1.6 #四分位间距的倍数
width = 0.35 #设置箱体的宽度

bplot = plt.boxplot(testList,#绘制箱线图的输入数据
                    whis = whis,#四分位间距的倍数,用来确定箱须包含数据的范围的大小
                    widths = width,#设置箱体的宽度
                    sym = "o",#离散值的标记样式
                    labels = labels,#绘制每一个数据集的刻度标签
                    notch = True,#变成V型凹痕箱体
                    vert = False,#箱线图是否纵向显示
                    showfliers = False,#箱线图的离群值是否显示
                    patch_artist = True)#是否给箱体添加颜色

#用键'boxes' 来调出值"bplot["boxes"]"   ,再用拉链函数 zip() 生成元组列表，使用 for循环 填充颜色
for patch,color in zip(bplot["boxes"],colors):
    patch.set_facecolor(color)
    
plt.ylabel("随机数值")
plt.title("生成器抗干扰能力的稳定性比较")

plt.grid(axis = "y",ls = ":",lw = 1,color = "gray",alpha = 0.4)

plt.show()

9.3 箱体,箱须,离群值的含义和计算方法

#计算四分位数

import numpy as np
data = [10,1,25,11,24,13,54,4,42,-3]
pc = np.array(data)

np.percentile(pc,np.arange(0,100,25))

运行结果:
array([-3.  ,  5.5 , 12.  , 24.75])

#确定四分位数的范围[Q1-whis*IQR,Q3-whis*IQR]  其中 IQR = Q3 - Q1

#q1-whis*(q3-q1) < value < q3+whis*(q3-q1)

Q1 = 5.5#第一四分位数
Q3 = 24.75#第三四分位数
whis = 1.5
madian = 12#中位数
IQR = Q3-Q1

MIN = Q1 - whis * IQR
MAX = Q3 + whis * IQR
print("IQR =",IQR)

print("MIN =",round(MIN))
print("MAX =",round(MAX))

运行结果:
IQR = 19.25
MIN = -23
MAX = 54

9.4 案例1---水平方向的箱线图

boxplot(vert = False)

# boxplot(vert = False)

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

mpl.rcParams["font.sans-serif"] = ["fangsong"]
mpl.rcParams["axes.unicode_minus"] = False

x = np.random.randn(1000)

plt.boxplot(x,vert = False)

plt.xlabel("随机数值")
plt.yticks([1],["随机数生成器AlphaRM"],rotation = 90)
plt.title("随机数生成器抗干扰能力的稳定性")

# plt.grid(True),用于显示点状网格线，它有助于辅助构图
plt.grid(axis = "x",
         ls = ":",
         lw = 1,
         color = "gray",
         alpha = 0.4)

plt.show()

9.5 案例2---不绘制离群值的水平方向的箱线图

boxplot(vert = False,showfliers = False)

# boxplot(vert = False,showfliers = False)


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

mpl.rcParams["font.sans-serif"] = ["fangsong"]
mpl.rcParams["axes.unicode_minus"] = False

x = np.random.randn(100)
plt.boxplot(x,vert = False,showfliers = False)
plt.xlabel("随机数值")
plt.yticks([1],["随机数生成器AlphaRM"],rotation = 90)
plt.title("随机数生成器抗干扰能力的稳定性")

plt.grid(axis = "x",
         ls = ":",
         lw = 1,
         color = "gray",
         alpha = 0.4)

plt.show()

10. 误差棒图可以给实验结果增加观测结果的误差以表示客观存在的测量偏差

函数 errorbar()

参数含义:
x,y:数据点的位置;
yerr:单一数值的标记样式和数据点标记的连接线样式;
fmt:数据点的标记样式和数据点标记的连接线样式;
ecolor:误差棒的线条颜色;
elinewidth:误差棒的线条粗细;
ms:数据点的大小;
mfc:数据点的标记颜色;
mec:数据点的标记边缘颜色;
capthick:误差棒边界横杠的厚度;
capsize:误差棒边界横杠的大小;

'''
误差棒图样式:1.水平误差棒图 2.垂直误差棒图 3.对称误差棒图 4.非对称误差棒图
函数 errorbar()

参数含义:
x,y:数据点的位置;
yerr:单一数值的标记样式和数据点标记的连接线样式;
fmt:数据点的标记样式和数据点标记的连接线样式;
ecolor:误差棒的线条颜色;
elinewidth:误差棒的线条粗细;
ms:数据点的大小;
mfc:数据点的标记颜色;
mec:数据点的标记边缘颜色;
capthick:误差棒边界横杠的厚度;
capsize:误差棒边界横杠的大小;

'''


#P68 例3.10.2 绘制原理
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np

mpl.rcParams["font.sans-serif"] = ["fangsong"]
mpl.rcParams["axes.unicode_minus"] = False

x = np.linspace(0.1,0.6,10)
y = np.exp(x)

error = 0.05 + 0.15 * x
lower_error = error
upper_error = 0.3 * error

error_limit = [lower_error,upper_error]

plt.errorbar(x,y,#数据点的位置
             yerr = error_limit,#单一数值的标记样式和数据点标记的连接线样式
             fmt =  ":o",#数据点的标记样式和数据点标记的连接线样式
             ecolor = "y",#误差棒的线条颜色
             elinewidth = 4,#误差棒的线条粗细
             ms = 5,#数据点的大小
             mfc = "c",#数据点的标记颜色
             mec = "r",#数据点的标记边缘颜色
             capthick = 1,#误差棒边界横杠的厚度
             capsize = 2#误差棒边界横杠的大小
            )

plt.xlim = (0,0.7)

plt.show()

#测试 误差棒图

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

mpl.rcParams["font.sans-serif"] = ["fangsong"]
mpl.rcParams["axes.unicode_minus"] = False

x = np.linspace(0.1,0.6,10)
y = np.exp(x)

error = 0.05 + 0.15 * x
lower_error = error
upper_error = 0.3 * error

error_limit = [lower_error,upper_error]

plt.errorbar(x,y,#数据点的位置
             yerr = error_limit,#单一数值的标记样式和数据点标记的连接线样式
             fmt =  ":o",#数据点的标记样式和数据点标记的连接线样式
             ecolor = "y",#误差棒的线条颜色
             elinewidth = 4,#误差棒的线条粗细
             ms = 5,#数据点的大小
             mfc = "c",#数据点的标记颜色
             mec = "r",#数据点的标记边缘颜色
             capthick = 1,#误差棒边界横杠的厚度
             capsize = 2#误差棒边界横杠的大小
            )

plt.xlim = (0,0.7)

plt.show()

10.1 案例1---带误差棒的柱状图

#案例1---带误差棒的柱状图

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

mpl.rcParams["font.sans-serif"] = ["lisu"]
mpl.rcParams["axes.unicode_minus"] = False

x = np.arange(5)
y = [100,68,79,91,82]
std_err = [7,2,6,10,5]
error_attri = dict(elinewidth = 2,ecolor = "black",capsize = 3)

plt.bar(x,y,
        color = "c",
        width = 0.6,
        align = "center",
        yerr  = std_err,
        error_kw = error_attri,
        tick_label = ["园区1","园区2","园区3","园区4","园区5"]
       )

plt.xlabel("芒果种植区")
plt.ylabel("收割量")

plt.title("不同芒果种植区的单次收割量")

plt.show()

10.2 案例2---带误差棒的条形图

#案例2---带误差棒的条形图

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

mpl.rcParams["font.sans-serif"] = ["lisu"]
mpl.rcParams["axes.unicode_minus"] = False

x = np.arange(5)
y = [1200,2400,1800,2200,1600]
str_err = [150,100,180,130,80]

bar_width = 0.6
colors = ["#e41a1c","#377eb8","#4daf4a","#984ea3","#ff7f00"]

plt.barh(x,y,
          bar_width,
          color = colors,
          align =  "center",
          xerr =  str_err,
          tick_label = ["家庭","小说","心理","科技","儿童"]
)       

plt.xlabel("订购数量")
plt.ylabel("图书种类")

plt.title("大型图书展销会的不同图书种类的采购情况")
plt.grid(True,axis = "x",ls = ":",color = "gray",alpha = 0.2)
# plt.xlim(0,2600) #元组对象不可调用
plt.show()

10.3 案例3---带误差棒的多数据并列柱状图

#案例3---带误差棒的多数据并列柱状图

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

mpl.rcParams["font.sans-serif"] = ["lisu"]
mpl.rcParams["axes.unicode_minus"] = False

x = np.arange(5)
y1 = [100,68,79,91,82]
y2 = [120,75,70,78,85]

std_err1 = [7,2,6,10,5]
std_err2 = [5,1,4,8,9]

error_attri = dict(elinewidth = 2,ecolor = "black",capsize = 3)

bar_width = 0.4
tick_label = ["园区1","园区2","园区3","园区4","园区5"]

plt.bar(x,y1,
        bar_width,
        color = "#87ceeb",
        align = "center",
        yerr = std_err1,
        error_kw = error_attri,
        label = "2010"
       )

plt.bar(x+bar_width,y2,
        bar_width,
        color = "#cd5c5c",
        align = "center",
        yerr = std_err2,
        error_kw = error_attri,
        label = "2013"
       )

plt.xlabel("芒果种植区")
plt.ylabel("收割量")

plt.xticks(x + bar_width/2,tick_label)
plt.title("不同年份的芒果种植区的单次收割量")
plt.grid(True,axis = "y",ls = ":",color = "gray",alpha = 0.2)
plt.legend()
plt.show()

10.4 案例4---带误差棒的堆积柱状图

#P74 例3.10.6 案例4---带误差棒的堆积柱状图

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

mpl.rcParams["font.sans-serif"] = ["lisu"]
mpl.rcParams["axes.unicode_minus"] = False

x = np.arange(5)
y1 = [1200,2400,1800,2200,1600]
y2 = [1050,2100,1300,1600,1340]

std_err1 = [150,100,180,130,80]
std_err2 = [120,110,170,150,120]

bar_width = 0.6
tick_label = ["家庭","小说","心理","科技","儿童"]

plt.bar(x,y1,
        bar_width,
        color = "#6495ed",
        align = "center",
        yerr = std_err1,
        label = "地区1",
        error_kw = error_attri
       )

plt.bar(x,y2,
        bar_width,
        bottom = y1,#bottom的值应该是［第0个类别～（当前类别－1）］的数据总和
        color = "#ffa500",
        align = "center",
        label = "地区2",
        error_kw = error_attri
       )
plt.xlabel("图书种类")
plt.ylabel("订购数量")

plt.title("不同地区大型图书展销会的图书采购情况")

plt.grid(True,axis = "y",ls = ":",color = "gray",alpha = 0.2)
plt.xticks(x,tick_label)
plt.legend()
plt.show()