Related
In this example, the guide step is defined as follows
def guide(params):
# returns the Bernoulli probablility
alpha = pyro.param(
"alpha", torch.tensor(params[0]), constraint=constraints.positive
)
beta = pyro.param(
"beta", torch.tensor(params[1]), constraint=constraints.positive
)
return pyro.sample("beta_dist", dist.Beta(alpha, beta))
svi = pyro.infer.SVI(
model=conditioned_data_model,
guide=guide,
optim=pyro.optim.SGD({"lr": 0.001, "momentum": 0.8}),
loss=pyro.infer.Trace_ELBO(),
)
params_prior = [prior.concentration1, prior.concentration0]
# Iterate over all the data and store results
losses, alpha, beta = [], [], []
pyro.clear_param_store()
num_steps = 3000
for t in range(num_steps):
losses.append(svi.step(params_prior))
alpha.append(pyro.param("alpha").item())
beta.append(pyro.param("beta").item())
posterior_vi = dist.Beta(alpha[-1], beta[-1])
However, running the above step gives the following error, what does those hints of fix mean and how to fix it accordingly?
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Input In [9], in <cell line: 15>()
14 num_steps = 3000
15 for t in range(num_steps):
---> 16 losses.append(svi.step(params_prior))
17 alpha.append(pyro.param("alpha").item())
18 beta.append(pyro.param("beta").item())
ValueError: at site "data_dist", invalid log_prob shape
Expected [], actual [100, 1]
Try one of the following fixes:
- enclose the batched tensor in a with pyro.plate(...): context
- .to_event(...) the distribution being sampled
- .permute() data dimensions
I am having a weird "ValueError: mean must be 1 dimensional" when I am trying to build a Hierarchical GL-LVM model. Basically I'm trying to reproduce this paper: Hierarchical Gaussian Process Latent Variable Models using GPflow.
Therefore I implemented my own new model as follow:
class myGPLVM(gpflow.models.BayesianModel):
def __init__(self, data, latent_data, x_data_mean, kernel):
super().__init__()
print("GPLVM")
self.kernel0 = kernel[0]
self.kernel1 = kernel[1]
self.mean_function = Zero()
self.likelihood0 = gpflow.likelihoods.Gaussian(1.0)
self.likelihood1 = gpflow.likelihoods.Gaussian(1.0)
# make some parameters
self.data = (gpflow.Parameter(x_data_mean), gpflow.Parameter(latent_data), data)
def hierarchy_ll(self):
x, h, y = self.data
K = self.kernel0(x)
num_data = x.shape[0]
k_diag = tf.linalg.diag_part(K)
s_diag = tf.fill([num_data], self.likelihood0.variance)
ks = tf.linalg.set_diag(K, k_diag + s_diag)
L = tf.linalg.cholesky(ks)
m = self.mean_function(x)
return multivariate_normal(h, m, L)
def log_likelihood(self):
"""
Computes the log likelihood.
.. math::
\log p(Y | \theta).
"""
x, h, y = self.data
K = self.kernel1(h)
num_data = h.shape[0]
k_diag = tf.linalg.diag_part(K)
s_diag = tf.fill([num_data], self.likelihood1.variance)
ks = tf.linalg.set_diag(K, k_diag + s_diag)
L = tf.linalg.cholesky(ks)
m = self.mean_function(h)
# [R,] log-likelihoods for each independent dimension of Y
log_prob = multivariate_normal(y, m, L). # <- trows the error!
log_prob_h = self.hierarchy_ll()
log_likelihood = tf.reduce_sum(log_prob) + tf.reduce_sum(log_prob_h)
return log_likelihood
The model seems to work with a toy example:
from sklearn.datasets.samples_generator import make_blobs
X, y = make_blobs(n_samples=40, centers=3, n_features=12, random_state=2)
Y = tf.convert_to_tensor(X, dtype=default_float())
but fails and trough me the error when I am trying with a bvh file (the one from the paper actually). I also used Lawrence's code to read my bvh from mocap which I modified to fit python3
Anyway, it's been few a days and I am out of ideas. I tried multiple way to force my mean array "m" to be of one dimensional but nothing worked. I also tried with the "three_phase_oil_flow" dataset from the first GPLVM paper which works as well.
Therefore, I would assume that my model is correct, or at least I got some optimisation going on, and would think that perhaps the bvh reader could be the cause. But the data seems all fine to me... Especially I don't understand why when forcing multivariate function like:
m = np.zeros((np.shape(m)[0], 1))
log_prob = multivariate_normal(y, m, L)
or even with the gpflow Zero function
m = Zero(h)
log_prob = multivariate_normal(y, m, L)
it still trows me the error. Any help will be highly appreciated.
edited thanks to: Artem Artemev
The rest of the code if anyone wants to try to reproduce:
https://github.com/michaelStettler/h-GPLVM
error flow:
(venv) MacBookMichael2:stackOverflow michaelstettler$ python3 HGPLVM.py
(199, 96)
shape Y (199, 3, 38)
2020-01-26 17:00:48.104029: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-01-26 17:00:48.113609: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f8dd5ff5410 executing computations on platform Host. Devices:
2020-01-26 17:00:48.113627: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): Host, Default Version
shape Y (199, 38)
Number of points: 199 and Number of dimensions: 38
shape x_mean_latent (199, 8)
shape x_mean_init (199, 2)
HGPLVM
gpr_data (199, 2) (199, 8) (199, 38)
2020-01-26 17:00:48.139003: W tensorflow/python/util/util.cc:299] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
shape m (199, 1)
Traceback (most recent call last):
File "HGPLVM.py", line 131, in <module>
_ = opt.minimize(closure, method="bfgs", variables=model.trainable_variables, options=dict(maxiter=maxiter))
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/gpflow/optimizers/scipy.py", line 60, in minimize
**scipy_kwargs)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/_minimize.py", line 594, in minimize
return _minimize_bfgs(fun, x0, args, jac, callback, **options)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 998, in _minimize_bfgs
gfk = myfprime(x0)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 327, in function_wrapper
return function(*(wrapper_args + args))
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 73, in derivative
self(x, *args)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 65, in __call__
fg = self.fun(x, *args)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/gpflow/optimizers/scipy.py", line 72, in _eval
loss, grads = _compute_loss_and_gradients(closure, variables)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/gpflow/optimizers/scipy.py", line 116, in _compute_loss_and_gradients
loss = loss_cb()
File "HGPLVM.py", line 127, in closure
return - model.log_marginal_likelihood()
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/gpflow/models/model.py", line 45, in log_marginal_likelihood
return self.log_likelihood(*args, **kwargs) + self.log_prior()
File "HGPLVM.py", line 62, in log_likelihood
log_prob = multivariate_normal(y, m, L)
File "mtrand.pyx", line 3729, in numpy.random.mtrand.RandomState.multivariate_normal
ValueError: mean must be 1 dimensional
I would recommend posting a working MWE code. I have tried to use your code snippets, but it gives me errors.
I don't have issues with multivariate_normal function. If you have localised the issue correctly you can debug TF2.0 more thoroughly and find the place that causes that exception. Here is the code which I'm running:
In [2]: from sklearn.datasets.samples_generator import make_blobs
...: X, y = make_blobs(n_samples=40, centers=3, n_features=12, random_state=2)
In [10]: m = np.zeros((np.shape(y)[0], 1))
In [11]: m.shape
Out[11]: (40, 1)
In [12]: y.shape
Out[12]: (40,)
In [13]: L = np.eye(m.shape[0])
In [15]: gpflow.logdensities.multivariate_normal(y, m, L)
Out[15]:
<tf.Tensor: shape=(40,), dtype=float64, numpy=
array([ -56.75754133, ...])>
I have question about the data type of the result returned by Sympy Poly.all_coeffs(). I have started to use Sympy just recently.
My Sympy transfer function is following:
Then I run this code:
n,d = fraction(Gs)
num = Poly(n,s)
den = Poly(d,s)
num_c = num.all_coeffs()
den_c = den.all_coeffs()
I get:
Then I run this code:
from scipy import signal
#nu = [5000000.0]
#de = [4.99, 509000.0]
nu = num_c
de = den_c
sys = signal.lti(nu, de)
w,mag,phase = signal.bode(sys)
plt.plot(w/(2*np.pi), mag)
and the result is:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-131-fb960684259c> in <module>
4 nu = num_c
5 de = den_c
----> 6 sys = signal.lti(nu, de)
But if I use those commented line 'nu' and 'de' straight python lists instead, the program works. So what is wrong here?
Why did you just show a bit the error? Why not the full message, maybe even the full traceback!
In [60]: sys = signal.lti(num_c, den_c)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-60-21f71ecd8884> in <module>
----> 1 sys = signal.lti(num_c, den_c)
/usr/local/lib/python3.6/dist-packages/scipy/signal/ltisys.py in __init__(self, *system, **kwargs)
590 self._den = None
591
--> 592 self.num, self.den = normalize(*system)
593
594 def __repr__(self):
/usr/local/lib/python3.6/dist-packages/scipy/signal/filter_design.py in normalize(b, a)
1609 leading_zeros = 0
1610 for col in num.T:
-> 1611 if np.allclose(col, 0, atol=1e-14):
1612 leading_zeros += 1
1613 else:
<__array_function__ internals> in allclose(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/numpy/core/numeric.py in allclose(a, b, rtol, atol, equal_nan)
2169
2170 """
-> 2171 res = all(isclose(a, b, rtol=rtol, atol=atol, equal_nan=equal_nan))
2172 return bool(res)
2173
<__array_function__ internals> in isclose(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/numpy/core/numeric.py in isclose(a, b, rtol, atol, equal_nan)
2267 y = array(y, dtype=dt, copy=False, subok=True)
2268
-> 2269 xfin = isfinite(x)
2270 yfin = isfinite(y)
2271 if all(xfin) and all(yfin):
TypeError: ufunc 'isfinite' not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule ''safe''
Now look at the elements of the num_c list (same for den_c):
In [55]: num_c[0]
Out[55]: 500000.000000000
In [56]: type(_)
Out[56]: sympy.core.numbers.Float
The scipy code is doing numpy testing on the inputs. So it's first turned the lists into arrays:
In [61]: np.array(num_c)
Out[61]: array([500000.000000000], dtype=object)
This array contains sympy object(s). It can't cast that to numpy float with 'safe'. But an explicit astype uses unsafe as the default:
In [63]: np.array(num_c).astype(float)
Out[63]: array([500000.])
So lets convert both lists into valid numpy float arrays:
In [64]: sys = signal.lti(np.array(num_c).astype(float), np.array(den_c).astype(float))
In [65]: sys
Out[65]:
TransferFunctionContinuous(
array([100200.4008016]),
array([1.00000000e+00, 1.02004008e+05]),
dt: None
)
Conversion in a list comprehension also works:
sys = signal.lti([float(i) for i in num_c],[float(i) for i in den_c])
You likely need to conver sympy objects to floats / lists of floats.
In the IPython and Jupyter documentation it says that get_ipython().magic() is deprecated. But when I changed my code to use run_line_magic it is failing to push to R (see below). Might be related to this problem
https://bitbucket.org/rpy2/rpy2/issues/184/valueerror-call-stack-is-not-deep-enough
I'm on Mac Yosemite, using Anaconda with Python 2.7. I just updated both Anaconda and rpy2 yesterday. The code below is from a Jupyter notebook.
%load_ext rpy2.ipython
import pandas as pd
'''Two test functions with rpy2.
The only difference between them is that
rpy2fun_magic uses 'magic' to push variable to R and
rpy2fun_linemagic uses 'run_line_magic' to push variable.
'magic' works fine. 'run_line_magic' returns an error.'''
def rpy2fun_magic(df):
get_ipython().magic('R -i df')
get_ipython().run_line_magic('R','df_cor <- cor(df)')
get_ipython().run_line_magic('R','-o df_cor')
return (df_cor)
def rpy2fun_linemagic(df):
get_ipython().run_line_magic('R','-i df')
get_ipython().run_line_magic('R','df_cor <- cor(df)')
get_ipython().run_line_magic('R','-o df_cor')
return (df_cor)
dataframetest = pd.DataFrame([[1,2,3,4],[6,3,4,5],[9,1,7,3]])
df_cor_magic = rpy2fun_magic(dataframetest)
print 'Using magic to push variable works fine\n'
print df_cor_magic
print '\nBut using run_line_magic returns an error\n'
df_cor_linemagic = rpy2fun_linemagic(dataframetest)
Using magic to push variable works fine
[[ 1. -0.37115374 0.91129318 -0.37115374]
[-0.37115374 1. -0.72057669 1. ]
[ 0.91129318 -0.72057669 1. -0.72057669]
[-0.37115374 1. -0.72057669 1. ]]
But using run_line_magic returns an error
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-1-e418b72a8621> in <module>()
28 print '\nBut using run_line_magic returns an error\n'
29
---> 30 df_cor_linemagic = rpy2fun_linemagic(dataframetest)
<ipython-input-1-e418b72a8621> in rpy2fun_linemagic(df)
15
16 def rpy2fun_linemagic(df):
---> 17 get_ipython().run_line_magic('R','-i df')
18 get_ipython().run_line_magic('R','df_cor <- cor(df)')
19 get_ipython().run_line_magic('R','-o df_cor')
/Users/alexmillner/anaconda/lib/python2.7/site-packages/IPython/core/interactiveshell.pyc in run_line_magic(self, magic_name, line)
2255 kwargs['local_ns'] = sys._getframe(stack_depth).f_locals
2256 with self.builtin_trap:
-> 2257 result = fn(*args,**kwargs)
2258 return result
2259
/Users/alexmillner/anaconda/lib/python2.7/site-packages/rpy2/ipython/rmagic.pyc in R(self, line, cell, local_ns)
/Users/alexmillner/anaconda/lib/python2.7/site-packages/IPython/core/magic.pyc in <lambda>(f, *a, **k)
191 # but it's overkill for just that one bit of state.
192 def magic_deco(arg):
--> 193 call = lambda f, *a, **k: f(*a, **k)
194
195 if callable(arg):
/Users/alexmillner/anaconda/lib/python2.7/site-packages/rpy2/ipython/rmagic.pyc in R(self, line, cell, local_ns)
657 val = self.shell.user_ns[input]
658 except KeyError:
--> 659 raise NameError("name '%s' is not defined" % input)
660 if args.converter is None:
661 ro.r.assign(input, self.pyconverter(val))
NameError: name 'df' is not defined
Some discussion of the same issue with %timeit first, followed by workaround answers at the bottom. I'm using IPython 3.1.0 with Anaconda 2.7.10, so my observations below could be different based on version differences alone.
This is not unique to the R extension, you can reproduce this with something simpler like %timeit:
In [47]: dfrm
Out[47]:
A B C
0 0.690466 0.370793 0.963782
1 0.478427 0.358897 0.689173
2 0.189277 0.268237 0.570624
3 0.735665 0.342549 0.509810
4 0.929736 0.090079 0.384444
5 0.210941 0.347164 0.852408
6 0.241940 0.187266 0.961489
7 0.768143 0.548450 0.604004
8 0.055765 0.842224 0.668782
9 0.717827 0.047011 0.948673
In [48]: def run_timeit(df):
get_ipython().run_line_magic('timeit', 'df.sum()')
....:
In [49]: run_timeit(dfrm)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-49-1e62302232b6> in <module>()
----> 1 run_timeit(dfrm)
<ipython-input-48-0a3e09ec1e0c> in run_timeit(df)
1 def run_timeit(df):
----> 2 get_ipython().run_line_magic('timeit', 'df.sum()')
3
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/interactiveshell.pyc in run_line_magic(self, magic_name, line)
2226 kwargs['local_ns'] = sys._getframe(stack_depth).f_locals
2227 with self.builtin_trap:
-> 2228 result = fn(*args,**kwargs)
2229 return result
2230
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in timeit(self, line, cell)
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/magic.pyc in <lambda>(f, *a, **k)
191 # but it's overkill for just that one bit of state.
192 def magic_deco(arg):
--> 193 call = lambda f, *a, **k: f(*a, **k)
194
195 if callable(arg):
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in timeit(self, line, cell)
1034 number = 1
1035 for _ in range(1, 10):
-> 1036 time_number = timer.timeit(number)
1037 worst_tuning = max(worst_tuning, time_number / number)
1038 if time_number >= 0.2:
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in timeit(self, number)
130 gc.disable()
131 try:
--> 132 timing = self.inner(it, self.timer)
133 finally:
134 if gcold:
<magic-timeit> in inner(_it, _timer)
NameError: global name 'df' is not defined
The issue is that the line magics are set to look for variable names at global scope, not at function scope. If the argument to your function rpy2fun_linemagic happened to coincide with a global variable name, the interior code would pick that up, for example:
In [52]: def run_timeit(dfrm):
get_ipython().run_line_magic('timeit', 'dfrm.sum()')
....:
In [53]: run_timeit(dfrm)
The slowest run took 5.67 times longer than the fastest. This could mean that an intermediate result is being cached
10000 loops, best of 3: 99.1 µs per loop
But this only works by accident, because the interior string passed to run_line_magic contains a name that is found globally.
However, I do get the same error even if using the plain magic function:
In [58]: def run_timeit(df):
get_ipython().magic('timeit df.sum()')
....:
In [59]: run_timeit(dfrm)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-59-1e62302232b6> in <module>()
----> 1 run_timeit(dfrm)
<ipython-input-58-e98c720ea7e8> in run_timeit(df)
1 def run_timeit(df):
----> 2 get_ipython().magic('timeit df.sum()')
3
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/interactiveshell.pyc in magic(self, arg_s)
2305 magic_name, _, magic_arg_s = arg_s.partition(' ')
2306 magic_name = magic_name.lstrip(prefilter.ESC_MAGIC)
-> 2307 return self.run_line_magic(magic_name, magic_arg_s)
2308
2309 #-------------------------------------------------------------------------
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/interactiveshell.pyc in run_line_magic(self, magic_name, line)
2226 kwargs['local_ns'] = sys._getframe(stack_depth).f_locals
2227 with self.builtin_trap:
-> 2228 result = fn(*args,**kwargs)
2229 return result
2230
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in timeit(self, line, cell)
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/magic.pyc in <lambda>(f, *a, **k)
191 # but it's overkill for just that one bit of state.
192 def magic_deco(arg):
--> 193 call = lambda f, *a, **k: f(*a, **k)
194
195 if callable(arg):
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in timeit(self, line, cell)
1034 number = 1
1035 for _ in range(1, 10):
-> 1036 time_number = timer.timeit(number)
1037 worst_tuning = max(worst_tuning, time_number / number)
1038 if time_number >= 0.2:
/home/ely/anaconda/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in timeit(self, number)
130 gc.disable()
131 try:
--> 132 timing = self.inner(it, self.timer)
133 finally:
134 if gcold:
<magic-timeit> in inner(_it, _timer)
NameError: global name 'df' is not defined
One (super bad) way to get around this is to use globals to locate the item that is the same as the argument that was passed to your function, and then you'll have a global name for it.
For example:
In [68]: def run_timeit(df):
for var_name, var_val in globals().iteritems():
if df is var_val:
get_ipython().run_line_magic('timeit', '%s.sum()'%(var_name))
break
....:
In [69]: run_timeit(dfrm)
The slowest run took 5.72 times longer than the fastest. This could mean that an intermediate result is being cached
10000 loops, best of 3: 99.2 µs per loop
But this is very unstable, since it relies on pass-by-name in Python. If I passed an object like an integer or string, I would have to check whether it was interned or something, but otherwise couldn't find it "by name" in the global namespace.
Another way to do it that might be slightly better is to use the user_ns namespace dict that IPython stores. Then at least you're not looking at globals, and there is more stability over specific variables that have been named when assigned by the user in IPython:
In [71]: def run_timeit(df):
....: g = get_ipython()
....: for var_name, var_val in g.user_ns.iteritems():
....: if df is var_val:
....: g.run_line_magic('timeit', '%s.sum()'%(var_name))
....: break
....:
In [72]: run_timeit(dfrm)
The slowest run took 5.58 times longer than the fastest. This could mean that an intermediate result is being cached
10000 loops, best of 3: 99 µs per loop
In the case of your specific R function call, I would try:
def rpy2fun_linemagic(df):
g = get_ipython()
for var_name, var_val in g.user_ns.iteritems():
if df is var_val:
g.run_line_magic('R', '-i %s'%(var_name))
g.run_line_magic('R', 'df_cor <- cor(%s)'%(var_name))
g.run_line_magic('R', '-o df_cor')
return df_cor
You might also have to be careful on the return statement. You might need to use return g.user_ns['df_cor'] or something if the result of the output conversion back to Python is to create the variable at global scope as well, rather than function scope. Or, if that variable gets created as a side effect, you may not want to return anything at all. I'm not a big fan of relying on implicit mutation like that, but it could work for you.
I suspect that the code example you are providing is there only to demonstrate the issue with run_line_magic(), but for reference I am adding a way to do the same without ipython being involved.
from rpy2.robjects import globalenv
def rpy2cor(df):
fun = globalenv.get('cor', wantfun=True)
df_cor = fun(df)
return df_cor
I have an [x,y] dataset and I would like to fit a function to it.
This are x and y
parang = np.array([ 61.1725 , 62.140625, 62.93275 , 63.701625, 65.89225 ,
66.476875, 68.33525 , 68.902375, 72.03975 , 72.590375,
73.144125, 73.670625, 80.36525 , 80.80275 , 87.505375,
87.90375 , 100.557875, 100.8915 ])
q = np.array([-0.03699417, -0.03451252, -0.03851238, -0.0393034 , -0.04059193,
-0.03941371, -0.04206476, -0.04153004, -0.04721763, -0.04667099,
-0.03996427, -0.03872865, -0.05054322, -0.0466561 , -0.05476921,
-0.05274144, -0.0474299 , -0.04974607])
and then I want to fit a function to the data that goes as follows:
def fq(x,bq,cuq):
qval = bq*stndqu[0]*np.cos(np.radians(2*x))+cuq*stndqu[1]*np.sin(np.radians(2*x))
print qval
print qval.dtype
return qval
where 'bq,cuq' are the parameter I need to fit and stndqu are global parameters I obtain as:
stnd = input(r'P ($\%$) and $\theta$ of pol. standard? (as tuple)')
p = stnd[0]/100.
ang = np.radians(stnd[1])
x,y = sympy.symbols('x y')
stndqu = sympy.solve([sympy.sqrt(x**2+y**2)-p,(0.5*sympy.atan(y/x))-ang],[x,y])[1]
and P and theta are 2.73 and 95. The stndqu[0] and stndqu[1] I get out from that block are
0.0272334985720932 and 0.00190435173321445
To find the parameters 'bq' and 'cuq' of the function that fit my data I do:
qpopt,pconv = scio.curve_fit(fq, parang, q)
and here's the result:
[-0.0129614827538107 -0.0137658898997091 -0.0144124082012406
-0.0150294169782742 -0.0167265263727253 -0.0171633151430064
-0.0185034265676582 -0.0188971421096823 -0.0209373417940197
-0.0212701779430718 -0.0215969783128203 -0.0219002154908251
-0.0250793309165333 -0.0252411052388773 -0.0269646924974054
-0.0270214005655701 -0.0260909416985902 -0.0259956074319825]
object
[-0.0129614827538107 -0.0137658898997091 -0.0144124082012406
-0.0150294169782742 -0.0167265263727253 -0.0171633151430064
-0.0185034265676582 -0.0188971421096823 -0.0209373417940197
-0.0212701779430718 -0.0215969783128203 -0.0219002154908251
-0.0250793309165333 -0.0252411052388773 -0.0269646924974054
-0.0270214005655701 -0.0260909416985902 -0.0259956074319825]
object
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
TypeError: array cannot be safely cast to required type
---------------------------------------------------------------------------
error Traceback (most recent call last)
/Users/mj/Documents/NACO/VLT/DataReduction/<ipython-input-57-cac353117232> in <module>()
----> 1 qpopt,pconv = scio.curve_fit(fq, parang, q)
/Library/Frameworks/Python.framework/Versions/2.6/lib/python2.6/site-packages/scipy/optimize/minpack.pyc in curve_fit(f, xdata, ydata, p0, sigma, **kw)
408 # Remove full_output from kw, otherwise we're passing it in twice.
409 return_full = kw.pop('full_output', False)
--> 410 res = leastsq(func, p0, args=args, full_output=1, **kw)
411 (popt, pcov, infodict, errmsg, ier) = res
412
/Library/Frameworks/Python.framework/Versions/2.6/lib/python2.6/site-packages/scipy/optimize/minpack.pyc in leastsq(func, x0, args, Dfun, full_output, col_deriv, ftol, xtol, gtol, maxfev, epsfcn, factor, diag, warning)
268 if (maxfev == 0):
269 maxfev = 200*(n+1)
--> 270 retval = _minpack._lmdif(func,x0,args,full_output,ftol,xtol,gtol,maxfev,epsfcn,factor,diag)
271 else:
272 if col_deriv:
error: Result from function call is not a proper array of floats.
I tried specifying the type of the qval element making it
def fq(x,bq,cuq):
qval = np.array(
bq*stndqu[0]*np.cos(np.radians(2*x))+cuq*stndqu[1]*np.sin(np.radians(2*x)),
dtype=float)
and then the result changes to:
qpopt = scio.curve_fit(fq, parang, q)
[-0.01296148 -0.01376589 -0.01441241 -0.01502942 -0.01672653 -0.01716332
-0.01850343 -0.01889714 -0.02093734 -0.02127018 -0.02159698 -0.02190022
-0.02507933 -0.02524111 -0.02696469 -0.0270214 -0.02609094 -0.02599561]
float64
[-0.01296148 -0.01376589 -0.01441241 -0.01502942 -0.01672653 -0.01716332
-0.01850343 -0.01889714 -0.02093734 -0.02127018 -0.02159698 -0.02190022
-0.02507933 -0.02524111 -0.02696469 -0.0270214 -0.02609094 -0.02599561]
float64
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
TypeError: array cannot be safely cast to required type
---------------------------------------------------------------------------
error Traceback (most recent call last)
/Users/mj/Documents/NACO/VLT/DataReduction/<ipython-input-50-1f4d3764f7ae> in <module>()
----> 1 qpopt = scio.curve_fit(fq, parang, q)
/Library/Frameworks/Python.framework/Versions/2.6/lib/python2.6/site-packages/scipy/optimize/minpack.pyc in curve_fit(f, xdata, ydata, p0, sigma, **kw)
408 # Remove full_output from kw, otherwise we're passing it in twice.
409 return_full = kw.pop('full_output', False)
--> 410 res = leastsq(func, p0, args=args, full_output=1, **kw)
411 (popt, pcov, infodict, errmsg, ier) = res
412
/Library/Frameworks/Python.framework/Versions/2.6/lib/python2.6/site-packages/scipy/optimize/minpack.pyc in leastsq(func, x0, args, Dfun, full_output, col_deriv, ftol, xtol, gtol, maxfev, epsfcn, factor, diag, warning)
268 if (maxfev == 0):
269 maxfev = 200*(n+1)
--> 270 retval = _minpack._lmdif(func,x0,args,full_output,ftol,xtol,gtol,maxfev,epsfcn,factor,diag)
271 else:
272 if col_deriv:
error: Result from function call is not a proper array of floats.
So no progress...
Can someone tell me where is this going wrong?
Thank you very much in advance!
M.
Since stndqu is the result of a call to sympy.solve, it is a symbolic object still. The numbers that you see when printing qval from within your function are probably sympy floats (and thus generic objects to numpy). You should convert stndqu into a numpy array before using it with scipy.curve_fit:
stndqun = numpy.array([sympy.N(i) for i in stndqu])