python - 如何正确优化热剖面上的拟合数据？

Question

我试图拟合热剖面的高温和低温状态的数据，但我无法正确拟合。根据实验报告，每个级别应该有 3 到 4 个测量点，但我无法管理它，因为总是有一些点可能超出热曲线曲线并破坏一切。我检查了这篇关于 的帖子optimize.curve_fit()，我不确定它是否可以帮助我优化它。如上图所示，每个高或低状态的测量点应该适合每个停留时间，彼此相邻：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import itertools
import copy
from sklearn import preprocessing

# load dataset
data_train = pd.read_csv("data.csv", header=None)
Temp = data_train.iloc[:, 2::3] 
print(Temp)


"""
stack(): transform your (sliced) dataframe to a series with index (row, col)
reset_index(): reset the double-level index above to level_0 (row), level_1 (col).
"""

def preprocess(data):
    for i in range(data.shape[0] // 480):       
        if 150 in data.iloc[i*480:(i+1)*480].to_numpy() and -40 in data.iloc[i*480:(i+1)*480].to_numpy():
            if 150 in data.iloc[(i-1)*480:i*480].to_numpy():
                data.iloc[i*480:(i+1)*480] = -40
            else:
                data.iloc[i*480:(i+1)*480] = 150

    return data

Temp = data_train.iloc[:, 2::3][100:200].stack().reset_index().reset_index()
Temp.columns = ['idx', 'level_0', 'level_1', 'Temperature']
Temp.Temperature = preprocess(Temp.Temperature)
temperature_data = copy.deepcopy(Temp)

fig, ax = plt.subplots(1,1, figsize=(16,10))
Temp.plot('level_0', 'Temperature', ax=ax, kind='scatter', c='level_0', colormap='prism', colorbar=False, legend=True)
ax.set_title('Temperature data distribution over cycles ', fontweight='bold', fontsize=18)
ax.set_xlabel('Cycles', fontsize=16)
ax.set_ylabel('Temperature', fontsize=16)
ax.tick_params(axis='both', which='major', labelsize=14)
#ax.tick_params(axis='both', which='minor', labelsize=10)
plt.show()

import matplotlib.pyplot as plt
import numpy as np
from scipy.optimize import curve_fit

### A continuous function that somewhat fits the data
### but definitively gets the period and levels. 
### The ramp is less well defined
def fit_func( t, low, high, period, s,  delta):
    return  ( high + low ) / 2. + ( high - low )/2. * np.tanh( s * np.sin( 2 * np.pi * ( t - delta ) / period ) )

time1List = np.arange( data_train.shape[0] )
time2List = np.linspace( 0, data_train.shape[0], 7213*20 )
tempList = np.fromiter( ( np.mean(temperature_data.Temperature[temperature_data.level_0 == t]) for t in time1List ), np.float )

sol, err = curve_fit( fit_func, time1List, tempList, [ -40, 150, 1, 10, 0 ] )
print(sol)

fittedLow, fittedHigh, fittedPeriod, fittedS, fittedOff = sol
# sol = -40, fittedHigh, fittedPeriod, fittedS, fittedOff
realHigh = fit_func( 1/4 * fittedPeriod, *sol)
realLow = fit_func( 3/4 * fittedPeriod, *sol)
print("high, low : ", [ realHigh, realLow ])
print("apprx ramp: ", fittedPeriod/( 2 * np.pi * fittedS ) * 2) 

realAmp = realHigh - realLow
topX, topY = zip( *[ [ t, d ] for t, d in zip( time1List, tempList ) if ( ( d > realHigh - 0.05 * realAmp ) ) ] )
botX, botY = zip( *[ [ t, d ] for t, d in zip( time1List, tempList ) if ( ( d < realLow + 0.05 * realAmp ) ) ] )

fig = plt.figure(figsize=(20, 15))
ax = fig.add_subplot( 2, 1, 1 )
bx = fig.add_subplot( 2, 1, 2 )

ax.plot( time1List, tempList, marker='x', linestyle='', zorder=100 )
ax.plot( time2List, fit_func( time2List, *sol ), zorder=0 )
ax.set_title('Fitting whole MPs on standrad thermal profile ', fontweight='bold', fontsize=25)
ax.set_xlabel('cycles', fontsize=20)
ax.set_ylabel('Thermal regime', fontsize=20)

bx.plot( time1List, tempList, marker='x', linestyle='' )
bx.plot( time2List, fit_func( time2List, *sol ) )
bx.plot( topX, topY, linestyle='', marker='o', markersize=10, fillstyle='none', color='#00FFAA')
bx.plot( botX, botY, linestyle='', marker='o', markersize=10, fillstyle='none', color='#80DD00')
bx.set_title('Fitting part of MPs on standrad thermal profile ', fontweight='bold', fontsize=25)
bx.set_xlabel('cycles', fontsize=20)
bx.set_ylabel('Thermal regime', fontsize=20)
bx.set_xlim( [ 110, 120 ] )
plt.show()

有什么建议可以在热剖面的停留时间上正确安装测量点吗？

标签： pythonmatplotlibscipycurve-fittingscipy-optimize