Scipy Curve_fit 给出了一个相当奇怪的拟合

Question

亲爱的 Python 程序员，

我目前正在使用 scipy 中的 curve_fit 来找出 x 和 y 数据与 echoouter 的相关性。然而，即使我拟合一个简单的线性公式，曲线拟合也变得非常奇怪。我尝试将数组更改为 numpy 数组： def func(x, a, b, c): "Fit functie" return a * np.asarray(x) + b 部分，但是它仍然给我一个看起来像一个 3 岁的孩子用红铅笔刮画的图表。

我记得的一件事是将质量流量和 rms_smote 的值从低到高排序。您可以在 def func(x, a, b, c) 位上方查看。因为 curve_fit 让我适应了。然而，当值未排序时，也有点像你在画草图一样。我不知道 curve_fit 是否会以不同的方式考虑数据（如果数据已排序）。

如果您需要更多信息，请告诉我:) 欢迎任何建议！

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
from scipy.stats import linregress
from scipy.optimize import curve_fit

data_15 = pd.read_csv(r"C:\Users\Thomas\Documents\Pythondata\2022-01-15_SMOTERapport.csv", header= 0, sep=';', decimal=',')
data_06 = pd.read_csv(r"C:\Users\Thomas\Documents\Pythondata\2022-02-06_SMOTERapport.csv", header= 0, sep=';', decimal=',')
data_10 = pd.read_csv(r"C:\Users\Thomas\Documents\Pythondata\2022-02-10_SMOTERapport.csv", header= 0, sep=';', decimal=',')

speed_15 = data_15['SPEED_ACT']
speed_06 = data_06['SPEED_ACT']
speed_10 = data_10['SPEED_ACT']

"Data filter 01_15"

filter = [i for i, e in enumerate(speed_15) if e >= 80]
s_15 = pd.DataFrame(data_15)
speed15 = s_15.filter(items = filter, axis=0)
speed15.reset_index(drop=True, inplace=True)

temp15 = speed15['TP_SMOTE']

foutmetingen2 = [i for i, e in enumerate(temp15) if e < 180]
speed15 = speed15.drop(foutmetingen2)

tp_strip15 = speed15['TP_AMBIENT']
tp_target15 = speed15['TP_TARGET']
tp_smote15 = speed15['TP_SMOTE']
v_15 = speed15['SPEED_ACT']
width15 = speed15['STRIP_WIDTH']
thickness15 = speed15['STRIP_THICKNESS']
power15 = speed15['POWER_INVERTER_PRE']
voltage15 = speed15['VOLTAGE_INVERTER_PRE']

"Data filter 02_06"

filter = [i for i, e in enumerate(speed_06) if e >= 80]
s_06 = pd.DataFrame(data_06)
speed06 = s_06.filter(items = filter, axis=0)
speed06.reset_index(drop=True, inplace=True)

temp06 = speed06['TP_SMOTE']

foutmetingen2 = [i for i, e in enumerate(temp06) if e < 180]
speed06 = speed06.drop(foutmetingen2)

tp_strip06 = speed06['TP_AMBIENT']
tp_target06 = speed06['TP_TARGET']
tp_smote06 = speed06['TP_SMOTE']
v_06 = speed06['SPEED_ACT']
width06 = speed06['STRIP_WIDTH']
thickness06 = speed06['STRIP_THICKNESS']
power06 = speed06['POWER_INVERTER_PRE']
voltage06 = speed06['VOLTAGE_INVERTER_PRE']

"Data filter 02_10"

filter = [i for i, e in enumerate(speed_10) if e >= 80]
s_10 = pd.DataFrame(data_10)
speed10 = s_10.filter(items = filter, axis=0)
speed10.reset_index(drop=True, inplace=True)

temp_01 = speed10['TP_SMOTE']

foutmetingen2 = [i for i, e in enumerate(temp_01) if e < 180]
speed10 = speed10.drop(foutmetingen2)

tp_strip10 = speed10['TP_AMBIENT']
tp_target10 = speed10['TP_TARGET']
tp_smote10 = speed10['TP_SMOTE']
v_10 = speed10['SPEED_ACT']
width10 = speed10['STRIP_WIDTH']
thickness10 = speed10['STRIP_THICKNESS']
power10 = speed10['POWER_INVERTER_PRE']
voltage10 = speed10['VOLTAGE_INVERTER_PRE']

"Constanten"
widthmax = 1253
Kra = 0.002033636
Kosc = 0.073086272
Pnominal = 2200
meting_15 = np.arange(0, len(speed15), 1)
meting_06 = np.arange(0, len(speed06), 1)
meting_10 = np.arange(0, len(speed10), 1)
cp = 480
rho = 7850
"---------------------------------------------------------------------"
def temp(power, speed, width, thickness, tp_strip, tp_target, tp_smote,
         voltage):
    "Berekende temperatuur vergelijken met target temperatuur"
    
    massflow = (speed/60)*width*10**-3*thickness*10**-3*rho
    LossesRA = Kra*Pnominal*(width/widthmax)
    LossesOSC = Kosc*Pnominal*(voltage/100)**2
    Plosses = (LossesRA + LossesOSC)
    power_nl = (power/100)*Pnominal - Plosses
    
    temp_c = ((power_nl*1000)/(massflow*cp)) + tp_strip
    verschil_t = (temp_c/tp_target)*100-100
    verschil_smote = (temp_c/tp_smote)*100-100
    
    return temp_c, verschil_t, verschil_smote, massflow

temp_15 = temp(power15, v_15, width15, thickness15, tp_strip15, tp_target15,
               tp_smote15, voltage15)
temp_06 = temp(power06, v_06, width06, thickness06, tp_strip06, tp_target06,
               tp_smote06, voltage06)
temp_10 = temp(power10, v_10, width10, thickness10, tp_strip10, tp_target10,
               tp_smote10, voltage10)
"---------------------------------------------------------------------"
def rms(Temperatuurberekend, TemperatuurGemeten):
    "De Root Mean Square berekenen tussen berekend en gemeten data"

    rootmeansquare = (TemperatuurGemeten - Temperatuurberekend)
    rootmeansquare_totaal = np.sum(rootmeansquare)
    rootmeansquare_gem = rootmeansquare_totaal/len(rootmeansquare)
    
    return rootmeansquare, rootmeansquare_totaal, rootmeansquare_gem

rms_tp_smote15 = (rms(temp_15[0], tp_smote15))
rms_tp_smote06 = (rms(temp_06[0], tp_smote06))
rms_tp_smote10 = (rms(temp_10[0], tp_smote10))
"----------------------------------------------------------------------"
massflows = [np.sum(temp_06[3])/len(temp_06[3]), np.sum(temp_15[3])/
             len(temp_15[3]), np.sum(temp_10[3])/len(temp_10[3])]
rms_smote = [rms_tp_smote06[2], rms_tp_smote10[2], rms_tp_smote15[2]]

rms_tp_smote_pre = np.append(rms_tp_smote15[0].tolist(),
                             rms_tp_smote06[0].tolist())
rms_tp_smote = np.append(rms_tp_smote_pre, rms_tp_smote10[0].tolist())

massflow_pre = np.append(temp_15[3].tolist(), temp_06[3].tolist())
massflow = np.append(massflow_pre, temp_10[3].tolist())

massflow_sort = np.sort(massflow)
rms_tp_smote_sort = [x for _, x in sorted(zip(massflow, rms_tp_smote))]

a,b,r,p, s_a= linregress (massflows,rms_smote)
print('RC: ' ,a ,'\n','std: ', s_a , '\n', 'Offset: ', b)

def func(x, a, b, c):
    "Fit functie"
    return a * np.asarray(x) + b

popt, pcov = curve_fit(func, massflow_sort, rms_tp_smote_sort)
popt

functie = func(massflow_sort, *popt)

sns.set_theme(style='whitegrid')
fig, axs = plt.subplots(2, figsize=(10, 10))
axs[0].plot(massflows, rms_smote, label='Temp afwijking als f(massflow)')
axs[0].plot ([massflows[0] ,massflows[len (massflows) -1]] ,
             [a*massflows [0]+b,a*massflows[len (massflows) -1]+b] ,
             label ='trendlijn')
axs[0].set(xlabel='Mass flow ($kg/s$)',
           ylabel='Temperatuur afwijking gem ($\u00b0C$)', title='Met Verliezen')
axs[0].legend(loc='upper right')

axs[1].plot(massflow_sort, rms_tp_smote_sort, 'o', label='Temp/Massflow 01-15')
#axs[1].plot(temp_06[3], rms_tp_smote06[0], 'o', label='Temp/Massflow 02-06')
#axs[1].plot(temp_10[3], rms_tp_smote10[0], 'o', label='Temp/Massflow 02-10')
axs[1].plot(massflow, func(massflow_sort, *popt), 'r-',
            label='fit: a=%5.3f, b=%5.3f, c=%5.3f' % tuple(popt))
axs[1].set(xlabel='Mass flow ($kg/s$)',
           ylabel='Temperatuur afwijking gem ($\u00b0C$)')
axs[1].legend(loc='upper right')
print("Gemiddelde verschil temperatuur smote: ", rms_tp_smote15[1])
print("Gemiddelde uitwijking temperatuur smote: ", rms_tp_smote15[2])