Issue with Curve Fitting tooland code

Question

Marcello 2015-4-23

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/213168-issue-with-curve-fitting-tooland-code

dear all I have generated a code from CFT and have personalised so to be able to import data from excel and add starting points for a customised equation. The code looks as follows

% CREATEFIT(RR ,QT ) % Create a 3P exponential fit. % % Data for 'untitled fit 1' fit: % X Input : RR % Y Output: QT % Output: % fitresult : a fit object representing the fit. % gof : structure with goodness-of fit info.

[filename file_path]= uigetfile ({'*.xls';'*.xlsx'},'Select an Excel File'); x = xlsread(strcat(file_path, filename), 'C31:C1048576'); y = xlsread(strcat(file_path, filename), 'D31:D1048576');

x(isnan(x)) = []; y(isnan(y))=[];

%% Fit: 'untitled fit 1'. [xData, yData] = prepareCurveData( x, y );

% Set up fittype and options. ft = fittype( 'a*exp(-b*x)+c', 'independent', 'x', 'dependent', 'y' ); opts = fitoptions( 'Method', 'NonlinearLeastSquares' ); opts.Display = 'Off'; opts.StartPoint = [-min(y) 0.01 max(y)];

% Fit model to data. [fitresult, gof] = fit( xData, yData, ft, opts );

a = fitresult.a; b = fitresult.b; c = fitresult.c;

a = num2str(a); b = num2str(b); c = num2str(c);

eq = ['y = ' a ' *exp( ' b '*RR )+' c]; dNo = filename(1:15);

% Plot fit with data. figure( 'Name', dNo); h = plot( fitresult, xData, yData ); legend( h,dNo, eq, 'Location', 'SouthEast' ); % Label axes xlabel RR ylabel QT grid on

% create a tiff file of the figure # % using the dNo as file name

outName = strcat(dNo, '.tiff'); saveas(gcf, outName);

Proble is that when I use the tool with the same data and same initial points, the results I am obtaining are different compared to those I get if I am using the code. I can't find the problem and not sure which of the two results I get is the correct one. Any suggestion/advice? I am using Matlab 2015a. Thank you Marcello