-
Notifications
You must be signed in to change notification settings - Fork 0
/
mpfit.py
executable file
·2374 lines (2062 loc) · 92.7 KB
/
mpfit.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""
Perform Levenberg-Marquardt least-squares minimization, based on MINPACK-1.
AUTHORS
The original version of this software, called LMFIT, was written in FORTRAN
as part of the MINPACK-1 package by XXX.
Craig Markwardt converted the FORTRAN code to IDL. The information for the
IDL version is:
Craig B. Markwardt, NASA/GSFC Code 662, Greenbelt, MD 20770
craigm@lheamail.gsfc.nasa.gov
UPDATED VERSIONs can be found on my WEB PAGE:
http://cow.physics.wisc.edu/~craigm/idl/idl.html
Mark Rivers created this Python version from Craig's IDL version.
Mark Rivers, University of Chicago
Building 434A, Argonne National Laboratory
9700 South Cass Avenue, Argonne, IL 60439
rivers@cars.uchicago.edu
Updated versions can be found at http://cars.uchicago.edu/software
Sergey Koposov converted the Mark's Python version from Numeric to numpy
Sergey Koposov, University of Cambridge, Institute of Astronomy,
Madingley road, CB3 0HA, Cambridge, UK
koposov@ast.cam.ac.uk
Updated versions can be found at http://code.google.com/p/astrolibpy/source/browse/trunk/
DESCRIPTION
MPFIT uses the Levenberg-Marquardt technique to solve the
least-squares problem. In its typical use, MPFIT will be used to
fit a user-supplied function (the "model") to user-supplied data
points (the "data") by adjusting a set of parameters. MPFIT is
based upon MINPACK-1 (LMDIF.F) by More' and collaborators.
For example, a researcher may think that a set of observed data
points is best modelled with a Gaussian curve. A Gaussian curve is
parameterized by its mean, standard deviation and normalization.
MPFIT will, within certain constraints, find the set of parameters
which best fits the data. The fit is "best" in the least-squares
sense; that is, the sum of the weighted squared differences between
the model and data is minimized.
The Levenberg-Marquardt technique is a particular strategy for
iteratively searching for the best fit. This particular
implementation is drawn from MINPACK-1 (see NETLIB), and is much faster
and more accurate than the version provided in the Scientific Python package
in Scientific.Functions.LeastSquares.
This version allows upper and lower bounding constraints to be placed on each
parameter, or the parameter can be held fixed.
The user-supplied Python function should return an array of weighted
deviations between model and data. In a typical scientific problem
the residuals should be weighted so that each deviate has a
gaussian sigma of 1.0. If X represents values of the independent
variable, Y represents a measurement for each value of X, and ERR
represents the error in the measurements, then the deviates could
be calculated as follows:
DEVIATES = (Y - F(X)) / ERR
where F is the analytical function representing the model. You are
recommended to use the convenience functions MPFITFUN and
MPFITEXPR, which are driver functions that calculate the deviates
for you. If ERR are the 1-sigma uncertainties in Y, then
TOTAL( DEVIATES^2 )
will be the total chi-squared value. MPFIT will minimize the
chi-square value. The values of X, Y and ERR are passed through
MPFIT to the user-supplied function via the FUNCTKW keyword.
Simple constraints can be placed on parameter values by using the
PARINFO keyword to MPFIT. See below for a description of this
keyword.
MPFIT does not perform more general optimization tasks. See TNMIN
instead. MPFIT is customized, based on MINPACK-1, to the
least-squares minimization problem.
USER FUNCTION
The user must define a function which returns the appropriate
values as specified above. The function should return the weighted
deviations between the model and the data. It should also return a status
flag and an optional partial derivative array. For applications which
use finite-difference derivatives -- the default -- the user
function should be declared in the following way:
def myfunct(p, fjac=None, x=None, y=None, err=None)
# Parameter values are passed in "p"
# If fjac==None then partial derivatives should not be
# computed. It will always be None if MPFIT is called with default
# flag.
model = F(x, p)
# Non-negative status value means MPFIT should continue, negative means
# stop the calculation.
status = 0
return([status, (y-model)/err]
See below for applications with analytical derivatives.
The keyword parameters X, Y, and ERR in the example above are
suggestive but not required. Any parameters can be passed to
MYFUNCT by using the functkw keyword to MPFIT. Use MPFITFUN and
MPFITEXPR if you need ideas on how to do that. The function *must*
accept a parameter list, P.
In general there are no restrictions on the number of dimensions in
X, Y or ERR. However the deviates *must* be returned in a
one-dimensional Numeric array of type Float.
User functions may also indicate a fatal error condition using the
status return described above. If status is set to a number between
-15 and -1 then MPFIT will stop the calculation and return to the caller.
ANALYTIC DERIVATIVES
In the search for the best-fit solution, MPFIT by default
calculates derivatives numerically via a finite difference
approximation. The user-supplied function need not calculate the
derivatives explicitly. However, if you desire to compute them
analytically, then the AUTODERIVATIVE=0 keyword must be passed to MPFIT.
As a practical matter, it is often sufficient and even faster to allow
MPFIT to calculate the derivatives numerically, and so
AUTODERIVATIVE=0 is not necessary.
If AUTODERIVATIVE=0 is used then the user function must check the parameter
FJAC, and if FJAC!=None then return the partial derivative array in the
return list.
def myfunct(p, fjac=None, x=None, y=None, err=None)
# Parameter values are passed in "p"
# If FJAC!=None then partial derivatives must be comptuer.
# FJAC contains an array of len(p), where each entry
# is 1 if that parameter is free and 0 if it is fixed.
model = F(x, p)
Non-negative status value means MPFIT should continue, negative means
# stop the calculation.
status = 0
if (dojac):
pderiv = zeros([len(x), len(p)], Float)
for j in range(len(p)):
pderiv[:,j] = FGRAD(x, p, j)
else:
pderiv = None
return([status, (y-model)/err, pderiv]
where FGRAD(x, p, i) is a user function which must compute the
derivative of the model with respect to parameter P[i] at X. When
finite differencing is used for computing derivatives (ie, when
AUTODERIVATIVE=1), or when MPFIT needs only the errors but not the
derivatives the parameter FJAC=None.
Derivatives should be returned in the PDERIV array. PDERIV should be an m x
n array, where m is the number of data points and n is the number
of parameters. dp[i,j] is the derivative at the ith point with
respect to the jth parameter.
The derivatives with respect to fixed parameters are ignored; zero
is an appropriate value to insert for those derivatives. Upon
input to the user function, FJAC is set to a vector with the same
length as P, with a value of 1 for a parameter which is free, and a
value of zero for a parameter which is fixed (and hence no
derivative needs to be calculated).
If the data is higher than one dimensional, then the *last*
dimension should be the parameter dimension. Example: fitting a
50x50 image, "dp" should be 50x50xNPAR.
CONSTRAINING PARAMETER VALUES WITH THE PARINFO KEYWORD
The behavior of MPFIT can be modified with respect to each
parameter to be fitted. A parameter value can be fixed; simple
boundary constraints can be imposed; limitations on the parameter
changes can be imposed; properties of the automatic derivative can
be modified; and parameters can be tied to one another.
These properties are governed by the PARINFO structure, which is
passed as a keyword parameter to MPFIT.
PARINFO should be a list of dictionaries, one list entry for each parameter.
Each parameter is associated with one element of the array, in
numerical order. The dictionary can have the following keys
(none are required, keys are case insensitive):
'value' - the starting parameter value (but see the START_PARAMS
parameter for more information).
'fixed' - a boolean value, whether the parameter is to be held
fixed or not. Fixed parameters are not varied by
MPFIT, but are passed on to MYFUNCT for evaluation.
'limited' - a two-element boolean array. If the first/second
element is set, then the parameter is bounded on the
lower/upper side. A parameter can be bounded on both
sides. Both LIMITED and LIMITS must be given
together.
'limits' - a two-element float array. Gives the
parameter limits on the lower and upper sides,
respectively. Zero, one or two of these values can be
set, depending on the values of LIMITED. Both LIMITED
and LIMITS must be given together.
'parname' - a string, giving the name of the parameter. The
fitting code of MPFIT does not use this tag in any
way. However, the default iterfunct will print the
parameter name if available.
'step' - the step size to be used in calculating the numerical
derivatives. If set to zero, then the step size is
computed automatically. Ignored when AUTODERIVATIVE=0.
'mpside' - the sidedness of the finite difference when computing
numerical derivatives. This field can take four
values:
0 - one-sided derivative computed automatically
1 - one-sided derivative (f(x+h) - f(x) )/h
-1 - one-sided derivative (f(x) - f(x-h))/h
2 - two-sided derivative (f(x+h) - f(x-h))/(2*h)
Where H is the STEP parameter described above. The
"automatic" one-sided derivative method will chose a
direction for the finite difference which does not
violate any constraints. The other methods do not
perform this check. The two-sided method is in
principle more precise, but requires twice as many
function evaluations. Default: 0.
'mpmaxstep' - the maximum change to be made in the parameter
value. During the fitting process, the parameter
will never be changed by more than this value in
one iteration.
A value of 0 indicates no maximum. Default: 0.
'tied' - a string expression which "ties" the parameter to other
free or fixed parameters. Any expression involving
constants and the parameter array P are permitted.
Example: if parameter 2 is always to be twice parameter
1 then use the following: parinfo(2).tied = '2 * p(1)'.
Since they are totally constrained, tied parameters are
considered to be fixed; no errors are computed for them.
[ NOTE: the PARNAME can't be used in expressions. ]
'mpprint' - if set to 1, then the default iterfunct will print the
parameter value. If set to 0, the parameter value
will not be printed. This tag can be used to
selectively print only a few parameter values out of
many. Default: 1 (all parameters printed)
Future modifications to the PARINFO structure, if any, will involve
adding dictionary tags beginning with the two letters "MP".
Therefore programmers are urged to avoid using tags starting with
the same letters; otherwise they are free to include their own
fields within the PARINFO structure, and they will be ignored.
PARINFO Example:
parinfo = [{'value':0., 'fixed':0, 'limited':[0,0], 'limits':[0.,0.]}
for i in range(5)]
parinfo[0]['fixed'] = 1
parinfo[4]['limited'][0] = 1
parinfo[4]['limits'][0] = 50.
values = [5.7, 2.2, 500., 1.5, 2000.]
for i in range(5): parinfo[i]['value']=values[i]
A total of 5 parameters, with starting values of 5.7,
2.2, 500, 1.5, and 2000 are given. The first parameter
is fixed at a value of 5.7, and the last parameter is
constrained to be above 50.
EXAMPLE
import mpfit
import numpy.oldnumeric as Numeric
x = arange(100, float)
p0 = [5.7, 2.2, 500., 1.5, 2000.]
y = ( p[0] + p[1]*[x] + p[2]*[x**2] + p[3]*sqrt(x) +
p[4]*log(x))
fa = {'x':x, 'y':y, 'err':err}
m = mpfit('myfunct', p0, functkw=fa)
print 'status = ', m.status
if (m.status <= 0): print 'error message = ', m.errmsg
print 'parameters = ', m.params
Minimizes sum of squares of MYFUNCT. MYFUNCT is called with the X,
Y, and ERR keyword parameters that are given by FUNCTKW. The
results can be obtained from the returned object m.
THEORY OF OPERATION
There are many specific strategies for function minimization. One
very popular technique is to use function gradient information to
realize the local structure of the function. Near a local minimum
the function value can be taylor expanded about x0 as follows:
f(x) = f(x0) + f'(x0) . (x-x0) + (1/2) (x-x0) . f''(x0) . (x-x0)
----- --------------- ------------------------------- (1)
Order 0th 1st 2nd
Here f'(x) is the gradient vector of f at x, and f''(x) is the
Hessian matrix of second derivatives of f at x. The vector x is
the set of function parameters, not the measured data vector. One
can find the minimum of f, f(xm) using Newton's method, and
arrives at the following linear equation:
f''(x0) . (xm-x0) = - f'(x0) (2)
If an inverse can be found for f''(x0) then one can solve for
(xm-x0), the step vector from the current position x0 to the new
projected minimum. Here the problem has been linearized (ie, the
gradient information is known to first order). f''(x0) is
symmetric n x n matrix, and should be positive definite.
The Levenberg - Marquardt technique is a variation on this theme.
It adds an additional diagonal term to the equation which may aid the
convergence properties:
(f''(x0) + nu I) . (xm-x0) = -f'(x0) (2a)
where I is the identity matrix. When nu is large, the overall
matrix is diagonally dominant, and the iterations follow steepest
descent. When nu is small, the iterations are quadratically
convergent.
In principle, if f''(x0) and f'(x0) are known then xm-x0 can be
determined. However the Hessian matrix is often difficult or
impossible to compute. The gradient f'(x0) may be easier to
compute, if even by finite difference techniques. So-called
quasi-Newton techniques attempt to successively estimate f''(x0)
by building up gradient information as the iterations proceed.
In the least squares problem there are further simplifications
which assist in solving eqn (2). The function to be minimized is
a sum of squares:
f = Sum(hi^2) (3)
where hi is the ith residual out of m residuals as described
above. This can be substituted back into eqn (2) after computing
the derivatives:
f' = 2 Sum(hi hi')
f'' = 2 Sum(hi' hj') + 2 Sum(hi hi'') (4)
If one assumes that the parameters are already close enough to a
minimum, then one typically finds that the second term in f'' is
negligible [or, in any case, is too difficult to compute]. Thus,
equation (2) can be solved, at least approximately, using only
gradient information.
In matrix notation, the combination of eqns (2) and (4) becomes:
hT' . h' . dx = - hT' . h (5)
Where h is the residual vector (length m), hT is its transpose, h'
is the Jacobian matrix (dimensions n x m), and dx is (xm-x0). The
user function supplies the residual vector h, and in some cases h'
when it is not found by finite differences (see MPFIT_FDJAC2,
which finds h and hT'). Even if dx is not the best absolute step
to take, it does provide a good estimate of the best *direction*,
so often a line minimization will occur along the dx vector
direction.
The method of solution employed by MINPACK is to form the Q . R
factorization of h', where Q is an orthogonal matrix such that QT .
Q = I, and R is upper right triangular. Using h' = Q . R and the
ortogonality of Q, eqn (5) becomes
(RT . QT) . (Q . R) . dx = - (RT . QT) . h
RT . R . dx = - RT . QT . h (6)
R . dx = - QT . h
where the last statement follows because R is upper triangular.
Here, R, QT and h are known so this is a matter of solving for dx.
The routine MPFIT_QRFAC provides the QR factorization of h, with
pivoting, and MPFIT_QRSOLV provides the solution for dx.
REFERENCES
MINPACK-1, Jorge More', available from netlib (www.netlib.org).
"Optimization Software Guide," Jorge More' and Stephen Wright,
SIAM, *Frontiers in Applied Mathematics*, Number 14.
More', Jorge J., "The Levenberg-Marquardt Algorithm:
Implementation and Theory," in *Numerical Analysis*, ed. Watson,
G. A., Lecture Notes in Mathematics 630, Springer-Verlag, 1977.
MODIFICATION HISTORY
Translated from MINPACK-1 in FORTRAN, Apr-Jul 1998, CM
Copyright (C) 1997-2002, Craig Markwardt
This software is provided as is without any warranty whatsoever.
Permission to use, copy, modify, and distribute modified or
unmodified copies is granted, provided this copyright and disclaimer
are included unchanged.
Translated from MPFIT (Craig Markwardt's IDL package) to Python,
August, 2002. Mark Rivers
Converted from Numeric to numpy (Sergey Koposov, July 2008)
"""
import time
import numpy
import scipy.linalg
from multiprocessing import Pool as mpPool
from multiprocessing.pool import ApplyResult
# Original FORTRAN documentation
# **********
#
# subroutine lmdif
#
# the purpose of lmdif is to minimize the sum of the squares of
# m nonlinear functions in n variables by a modification of
# the levenberg-marquardt algorithm. the user must provide a
# subroutine which calculates the functions. the jacobian is
# then calculated by a forward-difference approximation.
#
# the subroutine statement is
#
# subroutine lmdif(fcn,m,n,x,fvec,ftol,xtol,gtol,maxfev,epsfcn,
# diag,mode,factor,nprint,info,nfev,fjac,
# ldfjac,ipvt,qtf,wa1,wa2,wa3,wa4)
#
# where
#
# fcn is the name of the user-supplied subroutine which
# calculates the functions. fcn must be declared
# in an external statement in the user calling
# program, and should be written as follows.
#
# subroutine fcn(m,n,x,fvec,iflag)
# integer m,n,iflag
# double precision x(n),fvec(m)
# ----------
# calculate the functions at x and
# return this vector in fvec.
# ----------
# return
# end
#
# the value of iflag should not be changed by fcn unless
# the user wants to terminate execution of lmdif.
# in this case set iflag to a negative integer.
#
# m is a positive integer input variable set to the number
# of functions.
#
# n is a positive integer input variable set to the number
# of variables. n must not exceed m.
#
# x is an array of length n. on input x must contain
# an initial estimate of the solution vector. on output x
# contains the final estimate of the solution vector.
#
# fvec is an output array of length m which contains
# the functions evaluated at the output x.
#
# ftol is a nonnegative input variable. termination
# occurs when both the actual and predicted relative
# reductions in the sum of squares are at most ftol.
# therefore, ftol measures the relative error desired
# in the sum of squares.
#
# xtol is a nonnegative input variable. termination
# occurs when the relative error between two consecutive
# iterates is at most xtol. therefore, xtol measures the
# relative error desired in the approximate solution.
#
# gtol is a nonnegative input variable. termination
# occurs when the cosine of the angle between fvec and
# any column of the jacobian is at most gtol in absolute
# value. therefore, gtol measures the orthogonality
# desired between the function vector and the columns
# of the jacobian.
#
# maxfev is a positive integer input variable. termination
# occurs when the number of calls to fcn is at least
# maxfev by the end of an iteration.
#
# epsfcn is an input variable used in determining a suitable
# step length for the forward-difference approximation. this
# approximation assumes that the relative errors in the
# functions are of the order of epsfcn. if epsfcn is less
# than the machine precision, it is assumed that the relative
# errors in the functions are of the order of the machine
# precision.
#
# diag is an array of length n. if mode = 1 (see
# below), diag is internally set. if mode = 2, diag
# must contain positive entries that serve as
# multiplicative scale factors for the variables.
#
# mode is an integer input variable. if mode = 1, the
# variables will be scaled internally. if mode = 2,
# the scaling is specified by the input diag. other
# values of mode are equivalent to mode = 1.
#
# factor is a positive input variable used in determining the
# initial step bound. this bound is set to the product of
# factor and the euclidean norm of diag*x if nonzero, or else
# to factor itself. in most cases factor should lie in the
# interval (.1,100.). 100. is a generally recommended value.
#
# nprint is an integer input variable that enables controlled
# printing of iterates if it is positive. in this case,
# fcn is called with iflag = 0 at the beginning of the first
# iteration and every nprint iterations thereafter and
# immediately prior to return, with x and fvec available
# for printing. if nprint is not positive, no special calls
# of fcn with iflag = 0 are made.
#
# info is an integer output variable. if the user has
# terminated execution, info is set to the (negative)
# value of iflag. see description of fcn. otherwise,
# info is set as follows.
#
# info = 0 improper input parameters.
#
# info = 1 both actual and predicted relative reductions
# in the sum of squares are at most ftol.
#
# info = 2 relative error between two consecutive iterates
# is at most xtol.
#
# info = 3 conditions for info = 1 and info = 2 both hold.
#
# info = 4 the cosine of the angle between fvec and any
# column of the jacobian is at most gtol in
# absolute value.
#
# info = 5 number of calls to fcn has reached or
# exceeded maxfev.
#
# info = 6 ftol is too small. no further reduction in
# the sum of squares is possible.
#
# info = 7 xtol is too small. no further improvement in
# the approximate solution x is possible.
#
# info = 8 gtol is too small. fvec is orthogonal to the
# columns of the jacobian to machine precision.
#
# nfev is an integer output variable set to the number of
# calls to fcn.
#
# fjac is an output m by n array. the upper n by n submatrix
# of fjac contains an upper triangular matrix r with
# diagonal elements of nonincreasing magnitude such that
#
# t t t
# p *(jac *jac)*p = r *r,
#
# where p is a permutation matrix and jac is the final
# calculated jacobian. column j of p is column ipvt(j)
# (see below) of the identity matrix. the lower trapezoidal
# part of fjac contains information generated during
# the computation of r.
#
# ldfjac is a positive integer input variable not less than m
# which specifies the leading dimension of the array fjac.
#
# ipvt is an integer output array of length n. ipvt
# defines a permutation matrix p such that jac*p = q*r,
# where jac is the final calculated jacobian, q is
# orthogonal (not stored), and r is upper triangular
# with diagonal elements of nonincreasing magnitude.
# column j of p is column ipvt(j) of the identity matrix.
#
# qtf is an output array of length n which contains
# the first n elements of the vector (q transpose)*fvec.
#
# wa1, wa2, and wa3 are work arrays of length n.
#
# wa4 is a work array of length m.
#
# subprograms called
#
# user-supplied ...... fcn
#
# minpack-supplied ... dpmpar,enorm,fdjac2,,qrfac
#
# fortran-supplied ... dabs,dmax1,dmin1,dsqrt,mod
#
# argonne national laboratory. minpack project. march 1980.
# burton s. garbow, kenneth e. hillstrom, jorge j. more
#
# **********
class mpfit:
# blas_enorm32, = scipy.linalg.get_blas_funcs(['nrm2'],numpy.array([0],dtype=numpy.float32))
# blas_enorm64, = scipy.linalg.get_blas_funcs(['nrm2'],numpy.array([0],dtype=numpy.float64))
def __init__(self, fcn, xall=None, functkw={}, parinfo=None,
ftol=1.e-10, xtol=1.e-10, gtol=1.e-10,
damp=0., maxiter=200, factor=100., nprint=1,
iterfunct='default', iterkw={}, nocovar=0,
rescale=0, autoderivative=1, quiet=0, ncpus=1,
diag=None, epsfcn=None, debug=0, fstep=1.0, showtime=False):
"""
Inputs:
fcn:
The function to be minimized. The function should return the weighted
deviations between the model and the data, as described above.
xall:
An array of starting values for each of the parameters of the model.
The number of parameters should be fewer than the number of measurements.
This parameter is optional if the parinfo keyword is used (but see
parinfo). The parinfo keyword provides a mechanism to fix or constrain
individual parameters.
Keywords:
autoderivative:
If this is set, derivatives of the function will be computed
automatically via a finite differencing procedure. If not set, then
fcn must provide the (analytical) derivatives.
Default: set (=1)
NOTE: to supply your own analytical derivatives,
explicitly pass autoderivative=0
ftol:
A nonnegative input variable. Termination occurs when both the actual
and predicted relative reductions in the sum of squares are at most
ftol (and status is accordingly set to 1 or 3). Therefore, ftol
measures the relative error desired in the sum of squares.
Default: 1E-10
functkw:
A dictionary which contains the parameters to be passed to the
user-supplied function specified by fcn via the standard Python
keyword dictionary mechanism. This is the way you can pass additional
data to your user-supplied function without using global variables.
Consider the following example:
if functkw = {'xval':[1.,2.,3.], 'yval':[1.,4.,9.],
'errval':[1.,1.,1.] }
then the user supplied function should be declared like this:
def myfunct(p, fjac=None, xval=None, yval=None, errval=None):
Default: {} No extra parameters are passed to the user-supplied
function.
gtol:
A nonnegative input variable. Termination occurs when the cosine of
the angle between fvec and any column of the jacobian is at most gtol
in absolute value (and status is accordingly set to 4). Therefore,
gtol measures the orthogonality desired between the function vector
and the columns of the jacobian.
Default: 1e-10
iterkw:
The keyword arguments to be passed to iterfunct via the dictionary
keyword mechanism. This should be a dictionary and is similar in
operation to FUNCTKW.
Default: {} No arguments are passed.
iterfunct:
The name of a function to be called upon each NPRINT iteration of the
MPFIT routine. It should be declared in the following way:
def iterfunct(myfunct, p, iter, fnorm, functkw=None,
parinfo=None, quiet=0, dof=None, [iterkw keywords here])
# perform custom iteration update
iterfunct must accept all three keyword parameters (FUNCTKW, PARINFO
and QUIET).
myfunct: The user-supplied function to be minimized,
p: The current set of model parameters
iter: The iteration number
functkw: The arguments to be passed to myfunct.
fnorm: The chi-squared value.
quiet: Set when no textual output should be printed.
dof: The number of degrees of freedom, normally the number of points
less the number of free parameters.
See below for documentation of parinfo.
In implementation, iterfunct can perform updates to the terminal or
graphical user interface, to provide feedback while the fit proceeds.
If the fit is to be stopped for any reason, then iterfunct should return a
a status value between -15 and -1. Otherwise it should return None
(e.g. no return statement) or 0.
In principle, iterfunct should probably not modify the parameter values,
because it may interfere with the algorithm's stability. In practice it
is allowed.
Default: an internal routine is used to print the parameter values.
Set iterfunct=None if there is no user-defined routine and you don't
want the internal default routine be called.
maxiter:
The maximum number of iterations to perform. If the number is exceeded,
then the status value is set to 5 and MPFIT returns.
Default: 200 iterations
nocovar:
Set this keyword to prevent the calculation of the covariance matrix
before returning (see COVAR)
Default: clear (=0) The covariance matrix is returned
ncpus:
Number of cpus to use when multiprocessing
Default value: 1
nprint:
The frequency with which iterfunct is called. A value of 1 indicates
that iterfunct is called with every iteration, while 2 indicates every
other iteration, etc. Note that several Levenberg-Marquardt attempts
can be made in a single iteration.
Default value: 1
parinfo
Provides a mechanism for more sophisticated constraints to be placed on
parameter values. When parinfo is not passed, then it is assumed that
all parameters are free and unconstrained. Values in parinfo are never
modified during a call to MPFIT.
See description above for the structure of PARINFO.
Default value: None All parameters are free and unconstrained.
quiet:
Set this keyword when no textual output should be printed by MPFIT
damp:
A scalar number, indicating the cut-off value of residuals where
"damping" will occur. Residuals with magnitudes greater than this
number will be replaced by their hyperbolic tangent. This partially
mitigates the so-called large residual problem inherent in
least-squares solvers (as for the test problem CURVI,
http://www.maxthis.com/curviex.htm).
A value of 0 indicates no damping.
Default: 0
Note: DAMP doesn't work with autoderivative=0
xtol:
A nonnegative input variable. Termination occurs when the relative error
between two consecutive iterates is at most xtol (and status is
accordingly set to 2 or 3). Therefore, xtol measures the relative error
desired in the approximate solution.
Default: 1E-10
Outputs:
Returns an object of type mpfit. The results are attributes of this class,
e.g. mpfit.status, mpfit.errmsg, mpfit.params, npfit.niter, mpfit.covar.
.status
An integer status code is returned. All values greater than zero can
represent success (however .status == 5 may indicate failure to
converge). It can have one of the following values:
-16
A parameter or function value has become infinite or an undefined
number. This is usually a consequence of numerical overflow in the
user's model function, which must be avoided.
-15 to -1
These are error codes that either MYFUNCT or iterfunct may return to
terminate the fitting process. Values from -15 to -1 are reserved
for the user functions and will not clash with MPFIT.
0 Improper input parameters.
1 Both actual and predicted relative reductions in the sum of squares
are at most ftol.
2 Relative error between two consecutive iterates is at most xtol
3 Conditions for status = 1 and status = 2 both hold.
4 The cosine of the angle between fvec and any column of the jacobian
is at most gtol in absolute value.
5 The maximum number of iterations has been reached.
6 ftol is too small. No further reduction in the sum of squares is
possible.
7 xtol is too small. No further improvement in the approximate solution
x is possible.
8 gtol is too small. fvec is orthogonal to the columns of the jacobian
to machine precision.
.fnorm
The value of the summed squared residuals for the returned parameter
values.
.covar
The covariance matrix for the set of parameters returned by MPFIT.
The matrix is NxN where N is the number of parameters. The square root
of the diagonal elements gives the formal 1-sigma statistical errors on
the parameters if errors were treated "properly" in fcn.
Parameter errors are also returned in .perror.
To compute the correlation matrix, pcor, use this example:
cov = mpfit.covar
pcor = cov * 0.
for i in range(n):
for j in range(n):
pcor[i,j] = cov[i,j]/sqrt(cov[i,i]*cov[j,j])
If nocovar is set or MPFIT terminated abnormally, then .covar is set to
a scalar with value None.
.errmsg
A string error or warning message is returned.
.nfev
The number of calls to MYFUNCT performed.
.niter
The number of iterations completed.
.perror
The formal 1-sigma errors in each parameter, computed from the
covariance matrix. If a parameter is held fixed, or if it touches a
boundary, then the error is reported as zero.
If the fit is unweighted (i.e. no errors were given, or the weights
were uniformly set to unity), then .perror will probably not represent
the true parameter uncertainties.
*If* you can assume that the true reduced chi-squared value is unity --
meaning that the fit is implicitly assumed to be of good quality --
then the estimated parameter uncertainties can be computed by scaling
.perror by the measured chi-squared value.
dof = len(x) - len(mpfit.params) # deg of freedom
# scaled uncertainties
pcerror = mpfit.perror * sqrt(mpfit.fnorm / dof)
"""
self.niter = 0
self.ncpus = ncpus
self.params = None
self.covar = None
self.perror = None
self.status = 0 # Invalid input flag set while we check inputs
self.debug = debug
self.errmsg = ''
self.nfev = 0
self.damp = damp
self.dof=0
self.fstep = fstep
self.showtime = showtime
self.starttime = time.time()
if fcn==None:
self.errmsg = "Usage: parms = mpfit('myfunt', ... )"
return
if iterfunct == 'default':
iterfunct = self.defiter
# Parameter damping doesn't work when user is providing their own
# gradients.
if (self.damp != 0) and (autoderivative == 0):
self.errmsg = 'ERROR: keywords DAMP and AUTODERIVATIVE are mutually exclusive'
return
# Parameters can either be stored in parinfo, or x. x takes precedence if it exists
if (xall is None) and (parinfo is None):
self.errmsg = 'ERROR: must pass parameters in P or PARINFO'
return
# Be sure that PARINFO is of the right type
if parinfo is not None:
if type(parinfo) is not list:
self.errmsg = 'ERROR: PARINFO must be a list of dictionaries.'
return
else:
if type(parinfo[0]) is not dict:
self.errmsg = 'ERROR: PARINFO must be a list of dictionaries.'
return
if ((xall is not None) and (len(xall) != len(parinfo))):
self.errmsg = 'ERROR: number of elements in PARINFO and P must agree'
return
# If the parameters were not specified at the command line, then
# extract them from PARINFO
if xall is None:
xall = self.parinfo(parinfo, 'value')
if xall is None:
self.errmsg = 'ERROR: either P or PARINFO(*)["value"] must be supplied.'
return
# Make sure parameters are numpy arrays
xall = numpy.asarray(xall)
# In the case if the xall is not float or if is float but has less
# than 64 bits we do convert it into double
if xall.dtype.kind != 'f' or xall.dtype.itemsize<=4:
xall = xall.astype(numpy.float)
npar = len(xall)
self.fnorm = -1.
fnorm1 = -1.
# TIED parameters?
ptied = self.parinfo(parinfo, 'tied', default='', n=npar)
self.qanytied = 0
for i in range(npar):
ptied[i] = ptied[i].strip()
if ptied[i] != '':
self.qanytied = 1
self.ptied = ptied
# FIXED parameters ?
pfixed = self.parinfo(parinfo, 'fixed', default=0, n=npar)
pfixed = (pfixed == 1)
for i in range(npar):
pfixed[i] = pfixed[i] or (ptied[i] != '') # Tied parameters are also effectively fixed
# Finite differencing step, absolute and relative, and sidedness of deriv.
step = self.parinfo(parinfo, 'step', default=0., n=npar)
dstep = self.parinfo(parinfo, 'relstep', default=0., n=npar)
dside = self.parinfo(parinfo, 'mpside', default=0, n=npar)
# Maximum and minimum steps allowed to be taken in one iteration
maxstep = self.parinfo(parinfo, 'mpmaxstep', default=0., n=npar)
minstep = self.parinfo(parinfo, 'mpminstep', default=0., n=npar)
qmin = minstep != 0
qmin[:] = False # Remove minstep for now!!
qmax = maxstep != 0
if numpy.any(qmin & qmax & (maxstep<minstep)):
self.errmsg = 'ERROR: MPMINSTEP is greater than MPMAXSTEP'
return
wh = (numpy.nonzero((qmin!=0.) | (qmax!=0.)))[0]
qminmax = len(wh > 0)
# Finish up the free parameters
ifree = (numpy.nonzero(pfixed != 1))[0]
nfree = len(ifree)
if nfree == 0:
self.errmsg = 'ERROR: no free parameters'
return
# Compose only VARYING parameters
self.params = xall.copy() # self.params is the set of parameters to be returned
x = self.params[ifree] # x is the set of free parameters
# LIMITED parameters ?
limited = self.parinfo(parinfo, 'limited', default=[0,0], n=npar)
limits = self.parinfo(parinfo, 'limits', default=[0.,0.], n=npar)
if (limited is not None) and (limits is not None):
# Error checking on limits in parinfo
if numpy.any((limited[:,0] & (xall < limits[:,0])) |
(limited[:,1] & (xall > limits[:,1]))):
self.errmsg = 'ERROR: parameters are not within PARINFO limits'
return
if numpy.any((limited[:,0] & limited[:,1]) &
(limits[:,0] >= limits[:,1]) &
(pfixed == 0)):
self.errmsg = 'ERROR: PARINFO parameter limits are not consistent'
return
# Transfer structure values to local variables
qulim = (limited[:,1])[ifree]
ulim = (limits [:,1])[ifree]
qllim = (limited[:,0])[ifree]
llim = (limits [:,0])[ifree]
if numpy.any((qulim!=0.) | (qllim!=0.)):
qanylim = 1
else:
qanylim = 0
else:
# Fill in local variables with dummy values
qulim = numpy.zeros(nfree)
ulim = x * 0.
qllim = qulim
llim = x * 0.
qanylim = 0
n = len(x)
# Check input parameters for errors
if (n < 0) or (ftol < 0) or (xtol < 0) or (gtol < 0) \
or (maxiter < 0) or (factor <= 0):
self.errmsg = 'ERROR: input keywords are inconsistent'
return
if rescale != 0:
self.errmsg = 'ERROR: DIAG parameter scales are inconsistent'
if len(diag) < n: