How to find out the model from given data

Question

I have a file containing data. From the plotting I can deduce that the model is a periodic and trigonometric function.

My goal is to find the model and possible the frequencies.

I used NonlinearModelFit and FindFormula to find out the model without any success.

The data in the file:

{{-0.1, -0.0622821}, {-0.099, 1.87434}, {-0.098, 2.13679}, {-0.097, 
1.34418}, {-0.096, 1.04328}, {-0.095, 1.8515}, {-0.094, 
2.52654}, {-0.093, 2.06614}, {-0.092, 0.789174}, {-0.091, 
0.0474938}, {-0.09, 0.23035}, {-0.089, 
0.260663}, {-0.088, -0.741624}, {-0.087, -2.59957}, {-0.086, \
-3.23313}, {-0.085, -2.25539}, {-0.084, -0.841191}, {-0.083, \
-0.890904}, {-0.082, -1.38617}, {-0.081, -1.56477}, {-0.08, \
-0.400696}, {-0.079, 1.27557}, {-0.078, 1.56815}, {-0.077, 
1.08095}, {-0.076, 1.3197}, {-0.075, 2.38857}, {-0.074, 
3.23696}, {-0.073, 2.28299}, {-0.072, 
0.31218}, {-0.071, -0.805857}, {-0.07, -0.0573411}, {-0.069, 
0.416767}, {-0.068, -0.41286}, {-0.067, -1.86552}, {-0.066, \
-2.69618}, {-0.065, -2.31118}, {-0.064, -1.425}, {-0.063, -1.42586}, \
{-0.062, -1.95482}, {-0.061, -1.525}, {-0.06, 0.18301}, {-0.059, 
1.79601}, {-0.058, 2.10051}, {-0.057, 1.10133}, {-0.056, 
0.667925}, {-0.055, 1.88153}, {-0.054, 2.82576}, {-0.053, 
2.54252}, {-0.052, 0.998126}, {-0.051, -0.049864}, {-0.05, 
0.108199}, {-0.049, 
0.116833}, {-0.048, -1.10017}, {-0.047, -2.38839}, {-0.046, \
-2.98824}, {-0.045, -1.89365}, {-0.044, -0.700723}, {-0.043, \
-0.630803}, {-0.042, -2.03987}, {-0.041, -1.83158}, {-0.04, \
-0.350693}, {-0.039, 1.45547}, {-0.038, 1.89983}, {-0.037, 
1.57732}, {-0.036, 1.43025}, {-0.035, 2.19391}, {-0.034, 
2.76342}, {-0.033, 1.87159}, {-0.032, 
0.401489}, {-0.031, -0.219963}, {-0.03, 0.118037}, {-0.029, 
0.544355}, {-0.028, -0.337913}, {-0.027, -2.38913}, {-0.026, \
-3.15683}, {-0.025, -2.40203}, {-0.024, -1.1465}, {-0.023, -1.19873}, \
{-0.022, -1.71968}, {-0.021, -1.16559}, {-0.02, 0.0766209}, {-0.019, 
1.66594}, {-0.018, 1.63393}, {-0.017, 0.70867}, {-0.016, 
1.07513}, {-0.015, 2.16549}, {-0.014, 3.30807}, {-0.013, 
2.6966}, {-0.012, 
0.728343}, {-0.011, -0.277433}, {-0.01, -0.273288}, {-0.009, \
-0.206787}, {-0.008, -0.680366}, {-0.007, -2.03802}, {-0.006, \
-2.67713}, {-0.005, -1.96914}, {-0.004, -1.05758}, {-0.003, \
-1.30517}, {-0.002, -2.31628}, {-0.001, -1.85295}, {0., 
0.173436}, {0.001, 1.76388}, {0.002, 2.22286}, {0.003, 
1.38202}, {0.004, 1.12941}, {0.005, 1.94544}, {0.006, 
2.61935}, {0.007, 2.18036}, {0.008, 
0.649334}, {0.009, -0.0867474}, {0.01, 0.254235}, {0.011, 
0.348242}, {0.012, -0.629415}, {0.013, -2.51307}, {0.014, -3.2367}, \
{0.015, -2.45705}, {0.016, -0.831338}, {0.017, -0.810549}, {0.018, \
-1.51079}, {0.019, -1.49582}, {0.02, -0.152844}, {0.021, 
1.22463}, {0.022, 1.46817}, {0.023, 1.10753}, {0.024, 
1.27707}, {0.025, 2.36378}, {0.026, 3.22339}, {0.027, 
2.1831}, {0.028, 
0.49384}, {0.029, -0.600537}, {0.03, -0.243927}, {0.031, 
0.289749}, {0.032, -0.415532}, {0.033, -2.02509}, {0.034, \
-2.62382}, {0.035, -2.40972}, {0.036, -1.26999}, {0.037, -1.17311}, \
{0.038, -1.95739}, {0.039, -1.50133}, {0.04, 0.231449}, {0.041, 
1.85946}, {0.042, 1.95253}, {0.043, 0.967388}, {0.044, 
0.671136}, {0.045, 1.82168}, {0.046, 2.94848}, {0.047, 
2.4914}, {0.048, 0.933417}, {0.049, 
0.0160948}, {0.05, -0.0412908}, {0.051, 
0.0481004}, {0.052, -0.822245}, {0.053, -2.49393}, {0.054, \
-3.09013}, {0.055, -1.96377}, {0.056, -0.806867}, {0.057, -1.0216}, \
{0.058, -2.14312}, {0.059, -1.91439}, {0.06, -0.307443}, {0.061, 
1.49778}, {0.062, 1.96111}, {0.063, 1.42132}, {0.064, 
1.28766}, {0.065, 2.30393}, {0.066, 2.9453}, {0.067, 
2.0613}, {0.068, 0.342548}, {0.069, -0.504865}, {0.07, 
0.0779691}, {0.071, 
0.728221}, {0.072, -0.377568}, {0.073, -2.37961}, {0.074, \
-3.11988}, {0.075, -2.37731}, {0.076, -1.15611}, {0.077, -1.16658}, \
{0.078, -1.51178}, {0.079, -1.3618}, {0.08, 0.283396}, {0.081, 
1.62506}, {0.082, 1.58162}, {0.083, 0.941375}, {0.084, 
0.989153}, {0.085, 2.27732}, {0.086, 3.34886}, {0.087, 
2.56467}, {0.088, 
0.784093}, {0.089, -0.271929}, {0.09, -0.482589}, {0.091, \
-0.00980706}, {0.092, -0.682073}, {0.093, -2.18204}, {0.094, \
-2.52101}, {0.095, -1.96053}, {0.096, -0.929182}, {0.097, -1.2858}, \
{0.098, -2.20629}, {0.099, -1.89749}, {0.1, 0.0722412}}

The plotting:

SetDirectory[FileNameJoin[{NotebookDirectory[],"Data"}]];
data = Import["fg1.dat"]
plot = ListPlot[data]

Answer 1

Try to tweak your initial guesses in the NonlinearModelFit to help the fit:

mod = NonlinearModelFit[data, c*Sin[a*x + b], {{a, 300}, b, {c, 3}}, x]

Show[ListLinePlot[data], Plot[mod[x], {x, -.1, .1}, PlotStyle -> Red]]

I'm not very familiar with FindFormula, but you can use that as well:

ff[x_] = FindFormula[data, x, TargetFunctions -> {Sin, Times}]

the outputs varies every time you run it, this is one of the simplest I got:

0.00134705 + 2.12462 Sin[314.153 x] + 0.324263 Sin[816.616 x] + 0.999382 Sin[1256.8 x]

It's also interesting to see that using an incomplete set of data, you can still kind of "fit" the noise pattern of the whole dataset:

ff[x_] = FindFormula[data[[;; 120]], x, TargetFunctions -> {Sin, Times}]

2.11911 Sin[314. x] + Sin[1257. x]