2 个级别上的数据子集的散点图和趋势线

Question

我有一个数据集（问题末尾的数据集），由 2 组（组 1、组 2）组成，每组有 4 个散点测量值（R1、R2、R3、R4）。 我想绘制：

• 每个测量值的散点图（R1、R2、R3、R4）
• 每个测量值的趋势线（R1、R2、R3、R4）
• 每个组的平均线（组 1、组 2）
• 每个平均值的填充彩色误差区域线（平均线 +- stddev）

这是情节应如下所示

正如您从上面的图中可以看到的，我已经成功绘制了它（下面的数据集和工作示例）；但是代码很长，也许有一个更简单的方法来做到这一点？我认为“误差区域，两组趋势线”是很多人都会做的事情。

代码

import pandas as pd
 #model fitting 
from scipy import stats
import numpy as np
 #plotting 
import plotly.express as px
import plotly.graph_objs as go
from plotly.subplots import make_subplots

 #import the data 
df = pd.read_csv("/content/dfs.csv", sep=None)


 #1 Fun: fit the data
def model(df_):
  y = df_["y"].values
  X = df_["x"].values
  mask = ~np.isnan(X) & ~np.isnan(y)
   #eliminate values with nan #! this shouldn't exist in my case ? 
  reg = stats.linregress(X[mask], y[mask])
  return (reg)

 #2 Fun: make average fit and upper lower bounds
def get_average_line (df_, results_ ):
    
  name_ = df_["Group"].iloc[0] 
  r=results_.query("Group == @name_").describe() #This works but is a patch 
  x = df_["x"].unique()
  y=r["m"]["mean"]*x + r["x"]["mean"]
  y_upper = (r["m"]["mean"]+r["m"]["std"]) *x + (r["x"]["mean"]+r["x"]["std"])
  y_lower = (r["m"]["mean"]-r["m"]["std"]) *x + (r["x"]["mean"]-r["x"]["std"])
  average_line = pd.DataFrame({"x": x, "y":y, "y_upper":y_upper, "y_lower":y_lower})
  return average_line

 #5 plot the upper and lower bound 
def plot_avearge_lines (df_, name_line ="Group", row=1, col=1):
  #Assume a figure is already started
   #name to use in addition for plotting 
  name = " " + df_["Group"].iloc[0]

  fig.add_trace(go.Scatter(
        name='Average' + name, 
        x=df_["x"],
        y=df_["y"],
        mode='lines',
        line=dict(color='rgb(31, 119, 180)'),
        legendgroup=name
    ),
              row=row, col=col)
  
   #uppet bound
  fig.add_trace(go.Scatter(
        name='Upper Bound'+ name ,
        x=df_["x"],
        y=df_['y_upper'],
        mode='lines',
        marker=dict(color="#444"),
        line=dict(width=0),
        showlegend=False,
        legendgroup=name
    ),
              row=row, col=col)
  
   #lower bound - fill = tonexty will make it fill until line before it
  fig.add_trace(go.Scatter(
        name='Lower Bound' + name ,
        x=df_["x"],
        y=df_['y_lower'],
        marker=dict(color="#444"),
        line=dict(width=0),
        mode='lines',
        fillcolor='rgba(68, 68, 68, 0.3)',
        fill='tonexty',
        showlegend=False, 
        legendgroup=name
    ),
              row=row, col=row)
 
 #scatter of each line (R1, R2, R3, R4)
def plot_scatter_and_fit (df_ , color ="name", row=1, col=1):
  for t in px.scatter(df_, x="x", y="y", color=color, title='',  trendline="ols" ).data:
      fig.add_trace(t, row=1, col=1)


##### MAIN ##########
 #1fit the data  
df_grouped_Group_mes = df.groupby(["Group", "Mes"])
results = df_grouped_Group_mes.apply(model).reset_index().rename(columns={0:'fit_results'})
results = pd.concat([results, pd.DataFrame([(reg.intercept, reg.slope, reg.rvalue, reg.pvalue, reg.stderr)  for reg in results["fit_results"]], columns=["x", "m", "r-value", "p-value", "y-std"])], axis=1)
 #2 make average fit and upper lower bounds
df_grouped_Group = df.groupby(["Group"])
avearge_lines = df_grouped_Group.apply(get_average_line, results_=results).reset_index()

 #3 plot a figure with..
fig = make_subplots(
    rows=1,
    cols=1,
    shared_xaxes=False,
    vertical_spacing=0.03,
    specs=[[{"type": "scatter"}]], #, {"type": "table"}
)



 #4 scatter of each line (R1, R2, R3, R4)
df_grouped_Group.apply(plot_scatter_and_fit,  color ="name", row=1, col=1)
 
 #5 plot the upper and lower bound
averge_line_grouped_name = avearge_lines.groupby(["Group"])
averge_line_grouped_name.apply(plot_avearge_lines, name_line ="name", row=1, col=1)

 #layout 
fig.update_layout(
    yaxis_title='y',
    xaxis_title ="x",
    title='error area and trendlines for 2 groups of scatters series',
    width=800,
    height=800,
    hovermode="x",
    xaxis = dict(
        tickmode = 'array',
        tickvals = df["x"]        
    ),
)

fig.show()

数据集

 Group Mes      name     x     y
group1  R1 group1-R1  2.00   3.0
group1  R1 group1-R1 13.00  50.0
group1  R1 group1-R1 25.00  78.0
group1  R1 group1-R1 37.00 130.0
group2  R1 group2-R1  2.00  35.0
group2  R1 group2-R1  6.00  63.0
group2  R1 group2-R1 10.00  93.0
group2  R1 group2-R1 22.00 323.0
group2  R1 group2-R1 34.00 455.0
group1  R2 group1-R2  5.00  16.0
group1  R2 group1-R2 16.00  76.0
group1  R2 group1-R2 28.00 110.0
group1  R2 group1-R2 40.00 153.0
group2  R2 group2-R2  3.00  47.0
group2  R2 group2-R2  7.13  68.0
group2  R2 group2-R2 13.00 111.0
group2  R2 group2-R2 25.00 353.0
group2  R2 group2-R2 37.00 493.0
group1  R3 group1-R3  8.00  45.0
group1  R3 group1-R3 19.00  82.0
group1  R3 group1-R3 31.00 128.0
group2  R3 group2-R3  0.00  12.0
group2  R3 group2-R3  4.00  53.0
group2  R3 group2-R3  8.00  80.0
group2  R3 group2-R3 16.00 121.0
group2  R3 group2-R3 28.00 394.0
group2  R3 group2-R3 40.00 521.0
group1  R4 group1-R4 11.00  45.0
group1  R4 group1-R4 22.00  90.0
group1  R4 group1-R4 34.00 128.0
group2  R4 group2-R4  1.00  13.0
group2  R4 group2-R4  5.00  71.0
group2  R4 group2-R4  9.00   NaN
group2  R4 group2-R4 19.00 139.0
group2  R4 group2-R4 31.00 400.0

Answer 1

我唯一能想到的是，您正在使用 .add_trace 方法来绘制平均值、上限和下限，并调用此方法三次。您可以通过使用 zip 函数同时迭代每个跟踪的不同参数来压缩此内容，因此您只需写出 .add_trace 一次。

就我个人而言，我认为这比您已有的更难阅读，并且它与您的代码没有任何不同或节省时间，但它更简洁（20 行与 40 行）

注意：我无法重现您的确切内容因为我相信您包含的数据样本不是完整的数据集。但是，我检查了您的原始 plot_average_lines 函数和我的 plot_average_lines 函数是否生成相同的绘图。

def plot_average_lines (df_, name_line ="Group", row=1, col=1):
    name = " " + df_["Group"].iloc[0]
    for bound_type, y_col, marker, line, showlegend, fillcolor, fill in zip(
        ['Average','Upper Bound','Lower Bound'],
        ["y","y_upper","y_lower"],
        [None, dict(color="#444"), dict(color="#444")],
        [dict(color='rgb(31, 119, 180)'), dict(width=0), dict(width=0)],
        [True, False, False],
        [None, None, 'rgba(68, 68, 68, 0.3)'],
        [None, None, 'tonexty']
    ):
        fig.add_trace(go.Scatter(
            name=bound_type + name ,
            x=df_["x"],
            y=df_[y_col],
            marker=marker,
            line=line,
            mode='lines',
            fillcolor=fillcolor,
            fill=fill,
            showlegend=showlegend, 
            legendgroup=name
        ),
              row=row, col=row)

结果不变：