I have a small model that I use to estimate the growth of a population of fungi given the environmental condition. The model, practically, is a MATLAB function in the following form:
growth=myfunction(envdata,params)
where growth is how much my fungi grow (duh!), envdata is a matrix of enviromental variables (one row per timestep, each column is a different variable such as temperature, humidity, etc. etc. etc.) and params are the parameters of my model. The latter are the ones that I would like to optimize and they include such things as the (unknown) initial fungal population, maximum fungi that can exist as a certain time, etcetera etcetera.
At the same time I have a vector of growth measured in the lab (my observations) and my objective is now to fit my model to the observations by varying the input parameters.
My natural answer would have been to use something such as fminsearch, but it has no option of using an observation vector as a minimum. Or am I wrong?
You want to fit the difference between your observations and the model's fitted growth rate as closely as possible but, as you pointed out, fminsearch doesn't allow you to use a target vector.
The solution is to define a wrapper function that defines the thing you are trying to minimize (often called the loss). One popular loss is the mean-square error,
MSE(x, y) = Σ (x - y)2
so you could define, for example,
function loss = objectiveFun(observations, envdata, params)
growth = myfunction(envdata, params);
loss = sum((observation - growth).^2); // or your favorite loss function
end
and then run
paramsInit = 0; // whatever initial value you have for params
paramsOpt = fminsearch(#(x) objectiveFun(observations, envdata, x), paramsInit);
Related
I have a multivariable linear optimization problem that I could use some guidance with on finding an optimal function/code method (Matlab). My problem is as as follows:
I have a set of observed data, I'll call this d(i), which is a 5000x1 vector (# of rows may change).
I have 10 - 100 sets of simulated data, the number of sets is a number I decide on. Each of these sets is also a 5000x1 vector (again, # of rows may change). I'll call these c1(i), c2(i), etc.
I would like to fit the simulated data sets to the observed data set with this equation:
sf1*c1(i) + sf2*c2(i) + sf3*c3(i) sf4*c4(i) + ... = d(i) + error
In this equation, I would like to solve for all of the scale factors (sf) (non-negative constants) and the error. I am assuming I need to set initial values for all the scale factors for this problem to work. I have looked into things like lssqnonneg, but I am unclear on whether that function can solve or optimize for this many variables per equation.
See above - I have also manually input the values of some scale factors and I can get a pretty good fit to the data by hand, but this is impractical for large quantities of simulated data sets.
did you try looking at https://www.mathworks.com/help/stats/linear-regression.html?s_tid=CRUX_lftnav ?
Instead of using c1,c2,...c100 as different vectors better concatenate them into an array 100x5000, say A=[c1;c2;...;c100] this will be needed to make life easier.
Then look for example at ridge regression
Ans= ridge(d,A,k)
where k is the regularization parameter that can be found by cross-validation:
[U,s,V]=svd( A,"econ");
k=gcv(U,diag(s),d,'tsvd');
see the function gcv here https://www.mathworks.com/matlabcentral/fileexchange/52-regtools
I am taking an Econometrics course, and have been trying to use Python rather than the propreitry STATA and EVIEWS they set the assignments in.
In one of the questions, I have consumption data over time. I am asked to compute it in two ways.
The first way is calculating a model of the form consumption = Aexp(Bt), and the second way is to log both sides and do ordinary OLS on log(consumption) = alpha + Bt
I know how to do the second way. Howver, when I try to do the first way it goes wrong. Using statsmodels, I can exponentiate the time data (after normalising), but this calculates a regression in the form consumption = Aexp(t) + B, which is not what I want. (I want to specify where the parameters go). In sklearn I could find a polynomial regression, but not exponential.
Then I found scipy.curve_fit
However this seems to have two problems:
(1) It seems to rely on initial guesses for parameters, which means my output will end up being different from proprietry software (whereas output for things like OLS are the same) [as I assume initial guesses means some iterative solution is done which is helpful for very weird and wonderful functions, but I assume fairly standard results hold for exponential regression]
(2) every time I try to implement it, it just returns the guess parameters.
Here is my code
`consumption_data = pd.read_csv(......\consumption.csv")
def func(x,a,b):
return a * np.exp(b*x)
xdata = consumption_data.YEAR
ydata = consumption_data.CONSUMPTION
ydata = (ydata - 1948)/100
popt, pcov = curve_fit(func, xdata, ydata, (1,1))
print(popt)
plt.plot(xdata, func(xdata, *popt), 'g--',)
`
The scipy.optimize code is basically just copy-pasted from their tutorial
https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.curve_fit.html
short answer: use statsmodels GLM
statsmodels does not have nonlinear least squares. The best python library for that is lmfit https://pypi.org/project/lmfit/
curve_fit, lmfit and nonlinear least squares algorithm in general find an iterative solution to the optimization problem. Even when we have to provide starting values, the solution is in many cases the same across packages up to convergence tolerance, e.g. 1e-5 or 1e-6.
Many standard models in statistics and econometrics have a single global maximum with well behaved data. However, in other cases like mixture models, there might be many local optima and the estimation might converge to one of them.
To the specific case:
consumption = A exp(B t)
can be rewritten as
consumption = exp(a + B t)
So this is just a single index model or a generalized linear model with an exponential mean function.
The general version has the expectation of the dependent variable as a nonlinear function of a linear combination of the explanatory variables:
E(y | x) = g(x b)
This can be estimated with statsmodels with GLM with family Gaussian and the log-link.
Aside: In econometrics, there is a literature to use Poisson quasi-likelihood as an estimator for exp models instead of taking the log of the dependent variable.
Poisson usually uses the log-link function as in the above.
However, using GLM allows us to use log-link, i.e. exponential mean function, with any of the supported distribution families. The main difference is in the underlying variance assumption. Gaussian assumes constant variance, Poisson assumes that the variance is proportional to the mean and Gamma assumes that the variance is quadratic in the mean.
If we use a robust sandwich covariance estimator for parameter inference, then standard errors and inference are correct even if the variance function is misspecified.
I have a time series of N data points of sunspots and would like to predict based on a subset of these points the remaining points in the series and then compare the correctness.
I'm just getting introduced to linear prediction using Matlab and so have decided that I would go the route of using the following code segment within a loop so that every point outside of the training set until the end of the given data has a prediction:
%x is the data, training set is some subset of x starting from beginning
%'unknown' is the number of points to extend the prediction over starting from the
%end of the training set (i.e. difference in length of training set and data vectors)
%x_pred is set to x initially
p = length(training_set);
coeffs = lpc(training_set, p);
for i=1:unknown
nextValue = -coeffs(2:end) * x_pred(end-unknown-1+i:-1:end-unknown-1+i-p+1)';
x_pred(end-unknown+i) = nextValue;
end
error = norm(x - x_pred)
I have three questions regarding this:
1) Does this appropriately do what I have described? I ask because my error seems rather large (>100) when predicting over only the last 20 points of a dataset that has hundreds of points.
2) Am I interpreting the second argument of lpc correctly? Namely, that it means the 'order' or rather number of points that you want to use in predicting the next point?
3) If this is there a more efficient, single line function in Matlab that I can call to replace the looping and just compute all necessary predictions for me given some subset of my overall data as a training set?
I tried looking through the lpc Matlab tutorial but it didn't seem to do the prediction as I have described my needs require. I have also been using How to use aryule() in Matlab to extend a number series? as a reference.
So after much deliberation and experimentation I have found the above approach to be correct and there does not appear to be any single Matlab function to do the above work. The large errors experienced are reasonable since I am using a linear prediction algorithm for a problem (i.e. sunspot prediction) that has inherent nonlinear behavior.
Hope this helps anyone else out there working on something similar.
I am processing a set of data using ridge regression. I found a very interesting phenomenon when apply the learned function to data. Namely, when the ridge parameter increases from zero, the test error keeps increasing. But if we penalize small coefficients(set the parameter <0), the test error can even be smaller.
This is my matlab code:
for i = 1:100
beta = ridgePolyRegression(ty_train,tX_train,lambda(i));
sqridge_train_cost(i) = computePolyCostMSE(ty_train,tX_train,beta);
sqridge_test_cost(i) = computePolyCostMSE(ty_valid,tX_valid,beta);
end
plot(lambda,sqridge_test_cost,'color','b');
lambda is the ridge parameter. ty_train is the output of the training data, tX_train is the input of training data. Also, we use a quadratic function regression here.
function [ beta ] = ridgePolyRegression( y,tX,lambda )
X = tX(:,2:size(tX,2));
tX2 = [tX,X.^2];
beta = (tX2'*tX2 + lambda * eye(size(tX2,2))) \ (tX2'*y);
end
The plotted picture is:
Why the error is minimal when lambda is negative? Is it a sign of under-fitting?
You should not use negative lambdas.
From (probabilistic) theoretic point of view, lambda relates to the inverse of variance of parameter prior distribution, and variance can't be negative.
From computational point of view, it can (given it's less that the smallest eigenvalue of the covariance matrix) turn your positive-definite form into an indefinite form, which means you'll have not a maximum, but a saddle point. It also means there are points where your target function is as small (or as big) as you want, so you can reduce loss indefinitely and no minimum / maximum exists at all.
Your optimization algorithm gives you just a stationary point, which will be a global maximum if and only if the form is positive definite.
Short Answer: When lambda is negative, you're actually overfitting your data. Hence, it's reasonable to get much less error.
Long Answer:
The regularization term (or the penalty term as described by many statisticians) aims to penalize the weights (or the betas as written in the coming Eq.) for going too high (overfitting) and going too low (underfitting). Giving you the power to control how your model behaves, and you usually aim the "right fitting" model.
For mathematical intuition, you can check the following Eq. (P. S. Equation is screenshotted from Elements of Statistical Learning by Trevor Hastie et. al)
When you decide to make your lambda negative, the penalty term is indeed turned into a utility term that helps to increase the weights (i.e., overfitting).
Overfitting is, simply, understanding your data along with the features more than you should, because you do not have the whole population yet; therefore, what you understood so far is possibly wrong on a different dataset.
So, you should never be using negative values of lambdas.
I'm working on doing a logistic regression using MATLAB for a simple classification problem. My covariate is one continuous variable ranging between 0 and 1, while my categorical response is a binary variable of 0 (incorrect) or 1 (correct).
I'm looking to run a logistic regression to establish a predictor that would output the probability of some input observation (e.g. the continuous variable as described above) being correct or incorrect. Although this is a fairly simple scenario, I'm having some trouble running this in MATLAB.
My approach is as follows: I have one column vector X that contains the values of the continuous variable, and another equally-sized column vector Y that contains the known classification of each value of X (e.g. 0 or 1). I'm using the following code:
[b,dev,stats] = glmfit(X,Y,'binomial','link','logit');
However, this gives me nonsensical results with a p = 1.000, coefficients (b) that are extremely high (-650.5, 1320.1), and associated standard error values on the order of 1e6.
I then tried using an additional parameter to specify the size of my binomial sample:
glm = GeneralizedLinearModel.fit(X,Y,'distr','binomial','BinomialSize',size(Y,1));
This gave me results that were more in line with what I expected. I extracted the coefficients, used glmval to create estimates (Y_fit = glmval(b,[0:0.01:1],'logit');), and created an array for the fitting (X_fit = linspace(0,1)). When I overlaid the plots of the original data and the model using figure, plot(X,Y,'o',X_fit,Y_fit'-'), the resulting plot of the model essentially looked like the lower 1/4th of the 'S' shaped plot that is typical with logistic regression plots.
My questions are as follows:
1) Why did my use of glmfit give strange results?
2) How should I go about addressing my initial question: given some input value, what's the probability that its classification is correct?
3) How do I get confidence intervals for my model parameters? glmval should be able to input the stats output from glmfit, but my use of glmfit is not giving correct results.
Any comments and input would be very useful, thanks!
UPDATE (3/18/14)
I found that mnrval seems to give reasonable results. I can use [b_fit,dev,stats] = mnrfit(X,Y+1); where Y+1 simply makes my binary classifier into a nominal one.
I can loop through [pihat,lower,upper] = mnrval(b_fit,loopVal(ii),stats); to get various pihat probability values, where loopVal = linspace(0,1) or some appropriate input range and `ii = 1:length(loopVal)'.
The stats parameter has a great correlation coefficient (0.9973), but the p values for b_fit are 0.0847 and 0.0845, which I'm not quite sure how to interpret. Any thoughts? Also, why would mrnfit work over glmfit in my example? I should note that the p-values for the coefficients when using GeneralizedLinearModel.fit were both p<<0.001, and the coefficient estimates were quite different as well.
Finally, how does one interpret the dev output from the mnrfit function? The MATLAB document states that it is "the deviance of the fit at the solution vector. The deviance is a generalization of the residual sum of squares." Is this useful as a stand-alone value, or is this only compared to dev values from other models?
It sounds like your data may be linearly separable. In short, that means since your input data is one dimensional, that there is some value of x such that all values of x < xDiv belong to one class (say y = 0) and all values of x > xDiv belong to the other class (y = 1).
If your data were two-dimensional this means you could draw a line through your two-dimensional space X such that all instances of a particular class are on one side of the line.
This is bad news for logistic regression (LR) as LR isn't really meant to deal with problems where the data are linearly separable.
Logistic regression is trying to fit a function of the following form:
This will only return values of y = 0 or y = 1 when the expression within the exponential in the denominator is at negative infinity or infinity.
Now, because your data is linearly separable, and Matlab's LR function attempts to find a maximum likelihood fit for the data, you will get extreme weight values.
This isn't necessarily a solution, but try flipping the labels on just one of your data points (so for some index t where y(t) == 0 set y(t) = 1). This will cause your data to no longer be linearly separable and the learned weight values will be dragged dramatically closer to zero.