相关性分析你了解多少？可视化展示一下吧~~

test_data = pd.read_excel('scatter_plot_data.xlsx')


import pandas as pd
import numpy as np
from scipy import optimize
import matplotlib.pyplot as plt
from sklearn.metrics import mean_squared_error,r2_score
from matplotlib.pyplot import MultipleLocator
from scipy.stats import linregress  
#统一修改字体
plt.rcParams['font.family'] = ['Times New Roman']

test_data = pd.read_excel('scatter_plot_data.xlsx')

N = len(test_data['true_data'])
x = test_data['true_data'].values.ravel() #真实值
y = test_data['model01_estimated'].values.ravel()#预测值
C=round(r2_score(x,y),4)
rmse = round(np.sqrt(mean_squared_error(x,y)),3)
#绘制拟合线
x2 = np.linspace(-10,10)
y2=x2
def f_1(x, A, B):  
    return A*x + B  
A1, B1 = optimize.curve_fit(f_1, x, y)[0]  
y3 = A1*x + B1

#绘制误差线数据点
up_y2 = 1.15*x2 + 0.05
down_y2 = 0.85*x2 - 0.05

#绘制误差线数据点
up_y2 = 1.15*x2 + 0.05
down_y2 = 0.85*x2 - 0.05

line_01 = linregress(x2,y2)
line_top = linregress(x2,up_y2)
line_bopptom = linregress(x2,down_y2)

# 统计计算所得
all_data = 4348
top_counts = 1681
bottom_counts = 404
bottom_top_counts = 2263

#开始绘图
fig, ax = plt.subplots(figsize=(7,5),dpi=200)
ax.scatter(x, y,edgecolor=None, c='k', s=12,marker='s')
ax.plot(x2,y2,color='k',linewidth=1.5,linestyle='-',zorder=2)
ax.plot(x,y3,color='r',linewidth=2,linestyle='-',zorder=2)

#添加上线和下线
ax.plot(x2,up_y2,color='k',lw=1.,ls='--',zorder=2,alpha=.8)
ax.plot(x2,down_y2,color='k',lw=1.,ls='--',zorder=2,alpha=.8)
fontdict1 = {"size":17,"color":"k",}
ax.set_xlabel("True Values", fontdict=fontdict1)
ax.set_ylabel("Estimated Values ", fontdict=fontdict1)
ax.grid(which='major',axis='y',ls='--',c='k',alpha=.7)
ax.set_axisbelow(True)
ax.set_xlim((0, 2.0))
ax.set_ylim((0, 2.0))
ax.set_xticks(np.arange(0, 2.2, step=0.2))
ax.set_yticks(np.arange(0, 2.2, step=0.2))



for spine in ['top','left','right']:
    ax.spines[spine].set_visible(None)
ax.spines['bottom'].set_color('k')
ax.tick_params(bottom=True,direction='out',labelsize=14,width=1.5,length=4,
              left=False)
#ax.tick_params()
#添加题目
titlefontdict = {"size":20,"color":"k",}
ax.set_title('Scatter plot of Correlation Analysis',titlefontdict,pad=20)
#ax.set_title()
fontdict = {"size":16,"color":"k"}
ax.text(0.1,1.8,r'$R^2=$'+str(round(C,3)),fontdict=fontdict)
ax.text(0.1,1.6,"RMSE="+str(rmse),fontdict=fontdict)
ax.text(0.1,1.4,r'$y=$'+str(round(A1,3))+'$x$'+" + "+str(round(B1,3)),fontdict=fontdict)
ax.text(0.1,1.2,r'$N=$'+ str(N),fontdict=fontdict)

#添加上下线的统计个数
text_font = {'size':'16','weight':'medium','color':'black'}
label_font = {'size':'24','weight':'medium','color':'black'}
ax.text(.9,.9,"(a)",transform = ax.transAxes,fontdict=text_font,zorder=4)

ax.text(.7,.25,s='Within EE = ' + '{:.0%}'.format(bottom_top_counts/all_data),transform = ax.transAxes,
        ha='left', va='center',fontdict=text_font)
ax.text(.7,.18,s='Above EE = ' + '{:.0%}'.format(top_counts/all_data),transform = ax.transAxes,
        ha='left', va='center',fontdict=text_font)
ax.text(.7,.11,s='Below EE = ' + '{:.0%}'.format(bottom_counts/all_data),transform = ax.transAxes,
        ha='left', va='center',fontdict=text_font)

ax.text(.8,.056,'\nVisualization by DataCharm',transform = ax.transAxes,
        ha='center', va='center',fontsize = 10,color='black')
plt.show()

library(tidyverse)
scatter_data <- read.csv('scatter_ggplot2.csv')

#可视化绘制
ggplot(scatter_data,aes(x = true_data,y = model01_estimated)) +
  geom_point(shape=15) + 
  geom_smooth(method = 'lm',se = F,color='red',size=1) +
  #绘制对角线:最佳拟合线
  geom_abline(slope = 1,intercept = 0,color='black',size=1) +
  #绘制上误差线
  geom_abline(slope = 1.15,intercept = .05,linetype = "dashed",size=1) +
  #绘制下误差线
  geom_abline(slope = .85,intercept = -.05,linetype = "dashed",size=1) +
  #使用 ggpubr 包添加R2等元素
  stat_regline_equation(label.x = .1,label.y = 1.8,size=6,family='Times_New_Roman',fontface='bold')+
  stat_cor(aes(label = paste(..rr.label.., ..p.label.., sep = "~`,`~")),
      label.x = .1, label.y = 1.6,size=6,family='Times_New_Roman',fontface='bold') +
  geom_text(x=.1,y=1.4,label="N = 4348",size=6,family='Times_New_Roman',hjust = 0)+
  #修改坐标轴刻度
  scale_x_continuous(limits = c(0,2),breaks = seq(0,2,0.2),expand = c(0,0)) +
  scale_y_continuous(limits = c(0,2),breaks = seq(0,2,0.2),expand = c(0,0)) +
  labs(x ='True Values',y="Model Estimated",
       title = "The scatter chart of Train data and Tset data",
       subtitle = "scatter R-ggplot2 Exercise(no color)",
       caption = 'Visualization by DataCharm')+
  #添加图序号（a）
  geom_text(x=1.85,y=1.85,label='(a)',size=9,family='Times_New_Roman',fontface='bold')+
  #添加误差个数
  geom_text(x=1.4,y=.4,label='Within EE = 52%',size=5,family='Times_New_Roman',hjust = 0)+
  geom_text(x=1.4,y=.3,label='Above EE = 39%',size=5,family='Times_New_Roman',hjust = 0)+
  geom_text(x=1.4,y=.2,label='Below EE = 9%',size=5,family='Times_New_Roman',hjust = 0)+
  #theme_base() +
  theme(text = element_text(family = "Times_New_Roman",face='bold'),
           axis.text = element_text(family = 'Times_New_Roman',size = 12,face = 'bold'),
           #修改刻度线内
           axis.ticks.length=unit(0.22, "cm"), 
           #绘制虚线网格
           panel.grid.major.y = element_line(linetype = 'dotted',color = 'black'),
           #去除y刻度
           axis.ticks.y = element_blank(),
           axis.line.y = element_blank(),
           #去除panel 背景颜色
           panel.background = element_rect(fill = NA),
           panel.ontop = F,
           #加宽图边框
           #panel.border = element_rect(size=1),
           plot.background = element_rect(fill = NULL),
           axis.line = element_line(size = .8),
           axis.ticks = element_line(size = .8),
           #设置刻度label的边距
           axis.text.x = element_text(margin=unit(c(0.5,0.5,0.5,0.5), "cm")), 
           axis.text.y = element_text(margin=unit(c(0.3,0.3,0.3,0.3), "cm")))