I have used the example described here (http://openmdao.readthedocs.org/en/1.5.0/usr-guide/tutorials/doe-drivers.html?highlight=driver) to show my problem. I want to use the same approach for one component were "params" are array and no longer float . See example below
from openmdao.api import IndepVarComp, Group, Problem, ScipyOptimizer, ExecComp, DumpRecorder, Component
from openmdao.drivers.latinhypercube_driver import LatinHypercubeDriver, OptimizedLatinHypercubeDriver
import numpy as np
class Paraboloid(Component):
""" Evaluates the equation f(x,y) = (x-3)^2 + xy + (y+4)^2 - 3 """
def __init__(self):
super(Paraboloid, self).__init__()
self.add_param('x', val=0.0)
self.add_param('y', val=0.0)
self.add_output('f_xy', val=0.0)
def solve_nonlinear(self, params, unknowns, resids):
"""f(x,y) = (x-3)^2 + xy + (y+4)^2 - 3
"""
x = params['x']
y = params['y']
unknowns['f_xy'] = (x-3.0)**2 + x*y + (y+4.0)**2 - 3.0
def linearize(self, params, unknowns, resids):
#""" Jacobian for our paraboloid."""
x = params['x']
y = params['y']
J = {}
J['f_xy', 'x'] = 2.0*x - 6.0 + y
J['f_xy', 'y'] = 2.0*y + 8.0 + x
return J
class ParaboloidArray(Component):
""" Evaluates the equation f(x,y) = (x-3)^2 + xy + (y+4)^2 - 3 """
def __init__(self):
super(ParaboloidArray, self).__init__()
self.add_param('X', val=np.array([0., 0.]))
self.add_output('f_xy', val=0.0)
def solve_nonlinear(self, params, unknowns, resids):
"""f(x,y) = (x-3)^2 + xy + (y+4)^2 - 3
"""
x = params['X'][0]
y = params['y'][1]
unknowns['f_xy'] = (x-3.0)**2 + x*y + (y+4.0)**2 - 3.0
top = Problem()
root = top.root = Group()
root.add('p1', IndepVarComp('x', 50.0), promotes=['*'])
root.add('p2', IndepVarComp('y', 50.0), promotes=['*'])
root.add('comp', Paraboloid(), promotes=['*'])
top.driver = OptimizedLatinHypercubeDriver(num_samples=4, seed=0, population=20, generations=4, norm_method=2)
top.driver.add_desvar('x', lower=-50.0, upper=50.0)
top.driver.add_desvar('y', lower=-50.0, upper=50.0)
top.driver.add_objective('f_xy')
top.setup()
top.run()
top.cleanup()
###########################
print("case float ok")
top = Problem()
root = top.root = Group()
root.add('p1', IndepVarComp('X', np.array([50., 50.])), promotes=['*'])
root.add('comp', ParaboloidArray(), promotes=['*'])
top.driver = OptimizedLatinHypercubeDriver(num_samples=4, seed=0, population=20, generations=4, norm_method=2)
top.driver.add_desvar('X', lower=np.array([-50., -50.]), upper=np.array([50., 50.]))
top.driver.add_objective('f_xy')
top.setup()
top.run()
top.cleanup()
I obtain the following error :
Traceback (most recent call last):
File "C:\Program Files (x86)\Wing IDE 101 5.0\src\debug\tserver\_sandbox.py", line 102, in <module>
File "D:\tlefeb\Anaconda2\Lib\site-packages\openmdao\core\problem.py", line 1038, in run
self.driver.run(self)
File "D:\tlefeb\Anaconda2\Lib\site-packages\openmdao\drivers\predeterminedruns_driver.py", line 108, in run
for run in runlist:
File "D:\tlefeb\Anaconda2\Lib\site-packages\openmdao\drivers\latinhypercube_driver.py", line 57, in _build_runlist
design_var_buckets = self._get_buckets(bounds['lower'], bounds['upper'])
File "D:\tlefeb\Anaconda2\Lib\site-packages\openmdao\drivers\latinhypercube_driver.py", line 101, in _get_buckets
bucket_walls = np.linspace(low, high, self.num_samples + 1)
File "D:\tlefeb\Anaconda2\Lib\site-packages\numpy\core\function_base.py", line 102, in linspace
if step == 0:
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
Did I misunderstood something in my way of coding ?
I get a different error than you, using the the latest OpenMDAO master, but I get an error non-the-less. There isn't anything wrong with the mode, but rather there are some bugs with using array variables for DOEs. I've added a bug-fix story to the OpenMDAO backlog, which we'll hopefully be able to deal with in the next couple weeks. We'd gladly accept a pull request if you develop a fix before we get to it though.
Related
Tensorflow: convert PrefetchDataset to BatchDataset
With latest Tensorflow version 2.3.1I am trying to follow basic text classification example at: https://www.tensorflow.org/tutorials/keras/text_classification. Instead of creating dataset from directory as example does, I am using a csv file:
SELECT_COLUMNS = ['SentimentText','Sentiment']
LABEL_COLUMN = 'Sentiment'
LABELS = [0, 1]
def get_dataset(file_path, **kwargs):
dataset = tf.data.experimental.make_csv_dataset(
file_path,
batch_size=3, # Artificially small to make examples easier to show.
label_name=LABEL_COLUMN,
na_value="?",
num_epochs=1,
ignore_errors=True,
**kwargs)
return dataset
all_data = get_dataset(data_path, select_columns=SELECT_COLUMNS)
As a result I get:
type(all_data)
tensorflow.python.data.ops.dataset_ops.PrefetchDataset
Example loads data from directory with:
batch_size = 32
seed = 42
raw_train_ds = tf.keras.preprocessing.text_dataset_from_directory(
'aclImdb/train',
batch_size=batch_size,
validation_split=0.2,
subset='training',
seed=seed)
And gets dataset of another type:
type(raw_train_ds)
tensorflow.python.data.ops.dataset_ops.BatchDataset
Now when I try to standardise and vectorise data with functions from example:
def custom_standardization(input_data):
lowercase = tf.strings.lower(input_data)
stripped_html = tf.strings.regex_replace(lowercase, '<br />', ' ')
return tf.strings.regex_replace(stripped_html,
'[%s]' % re.escape(string.punctuation),
'')
max_features = 10000
sequence_length = 250
vectorize_layer = TextVectorization(
standardize=custom_standardization,
max_tokens=max_features,
output_mode='int',
output_sequence_length=sequence_length)
And apply them to my dataset I get error:
# Make a text-only dataset (without labels), then call adapt
train_text = all_data.map(lambda x, y: x)
vectorize_layer.adapt(train_text)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-20-1f1fc445912d> in <module>
1 # Make a text-only dataset (without labels), then call adapt
2 train_text = all_data.map(lambda x, y: x)
----> 3 vectorize_layer.adapt(train_text)
/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/layers/preprocessing/text_vectorization.py in adapt(self, data, reset_state)
378 shape = dataset_ops.get_legacy_output_shapes(data)
379 if not isinstance(shape, tensor_shape.TensorShape):
--> 380 raise ValueError("The dataset passed to 'adapt' must contain a single "
381 "tensor value.")
382 if shape.rank == 0:
ValueError: The dataset passed to 'adapt' must contain a single tensor value.
How to convert PrefetchDataset to BatchDataset ?
You could use tf.stack method to pack the features into a single array. The below function is from Custom training: walkthrough in Tensorflow.
def pack_features_vector(features, labels):
features = tf.stack(list(features.values()), axis=1)
return features, labels
all_data = get_dataset(data_path, select_columns=SELECT_COLUMNS)
train_dataset = all_data.map(pack_features_vector)
train_text = train_dataset.map(lambda x, y: x)
vectorize_layer.adapt(train_text)
I am currently learning about how to code neural networks in numpy/python. I used the code from this tutorial and tried to adapt it to make an importable module. However, when i tried using my own dataset. It threw a numpy error ValueError: shapes (1,3) and (1,1) not aligned: 3 (dim 1) != 1 (dim 0).
I have already tried reshaping all of the matrices from (x,) to (x,1) but with no success. After a bit of reading around, transposing the arrays was also meant to fix the issue, but i tried that as well and no success there either.
Here is the module (called hidden_net):
import numpy as np
class network:
def __init__(self,layer_num,learning_rate=0.7,seed=None,logistic_coefficent=0.9):
self.logistic_coefficent=logistic_coefficent
self.learning_rate=learning_rate
self.w0 = np.random.random((layer_num[0],layer_num[1]))
self.w1 = np.random.random((layer_num[1],layer_num[2]))
np.random.seed(seed)
def sigmoid(self,x,reverse=False):
if(reverse==True):
return x*(1-x)
return 1/(1+np.exp(-x*self.logistic_coefficent))
def train(self,inps,outs):
inps=np.array(inps)
layer0 = inps
layer1 = self.sigmoid(np.dot(layer0,self.w0))
layer2 = self.sigmoid(np.dot(layer1,self.w1))
layer2_error = outs - layer2
layer2_delta = layer2_error*self.sigmoid(layer2,reverse=True)#*self.learning_rate
layer1_error = layer2_delta.dot(self.w1.T)
layer1_delta = layer1_error * self.sigmoid(layer1,reverse=True)#*self.learning_rate
layer1= np.reshape(layer1, (layer1.shape[0], 1))
layer2= np.reshape(layer2, (layer2.shape[0], 1))
layer1_delta= np.reshape(layer1_delta, (layer1_delta.shape[0], 1)) #Other attempts to reshape to avoid this error
layer2_delta= np.reshape(layer2_delta, (layer2_delta.shape[0], 1))
self.w1 += layer1.T.dot(layer2_delta)
self.w0 += layer0.T.dot(layer1_delta)
Here is the program importing that module:
import hidden_net
op=open('Mall_Customers_Mod.txt','r')
full=op.read()
op.close()
full_lines=full.split('\n')
training_lines=[]
for i in range(174):
training_lines.append(full_lines[0])
del full_lines[0]
training_inputs=[]
training_outputs=[]
for j in training_lines:
training_inputs.append([float(j.split(',')[0]),float(j.split(',')[1])])
training_outputs.append(float(j.split(',')[2]))
testing_lines=full_lines
testing_inputs=[]
testing_outputs=[]
for l in testing_lines:
testing_inputs.append([float(l.split(',')[0]),float(l.split(',')[1])])
testing_outputs.append(float(l.split(',')[2]))
nn=hidden_net.network([2,3,1],seed=10)
for i in range(1000):
for cur in range(len(training_inputs)):
nn.train(training_inputs[cur],training_outputs[cur])
and here is part of my data set (Mall_Customers_Mod.txt)
-1,19,15
-1,21,15
1,20,16
1,23,16
1,31,17
1,22,17
1,35,18
1,23,18
-1,64,19
1,30,19
-1,67,19
1,35,19
1,58,20
1,24,20
-1,37,20
-1,22,20
1,35,21
-1,20,21
-1,52,23
The error is on line 30:
self.w1 += layer1.T.dot(layer2_delta)
ValueError: shapes (1,3) and (1,1) not aligned: 3 (dim 1) != 1 (dim 0)
Also sorry, i know i am meant to avoid pasting entire files, but it seems pretty unavoidable here
The lines below are wrong, layer0 is the input layer and does not contain any neurons.
self.w1 += layer1.T.dot(layer2_delta)
self.w0 += layer0.T.dot(layer1_delta)
They should be:
self.w1 += layer2.T.dot(layer2_delta)
self.w0 += layer1.T.dot(layer1_delta)
All the reshape operations should be removed too. The updated train function
def train(self,inps,outs):
inps=np.array(inps)
layer0 = inps
layer1 = self.sigmoid(np.dot(layer0,self.w0))
layer2 = self.sigmoid(np.dot(layer1,self.w1))
layer2_error = outs - layer2
layer2_delta = layer2_error*self.sigmoid(layer2,reverse=True)#*self.learning_rate
layer1_error = layer2_delta.dot(self.w1.T)
layer1_delta = layer1_error * self.sigmoid(layer1,reverse=True)#*self.learning_rate
self.w1 += layer2.T.dot(layer2_delta)
self.w0 += layer1.T.dot(layer1_delta)
I want to constrain (not bound) the z design variable so that each entry is constrained to be less that or equal to 5 and greater than or equal to -5: -5<=Z<=5. I attempt to do this by defining the constraint to just return the values of z (self.add('con_cmp1', ExecComp('con1 = z'), promotes=['z', 'con1'])) then defining the constraint to have an upper limit of 5.0 and a lower limit of -5.0 (top.driver.add_constraint('con1', lower=np.array([-5., -5.]), upper=np.array([5.,5.]))).
When I do this, I get the error Type <type 'numpy.ndarray'> of source 'pz.z' (z) must be the same as type <type 'float'> of target 'con_cmp1.z' (z). What does this error mean? How can I properly set this constraint?
from __future__ import print_function
from openmdao.api import ExecComp, IndepVarComp, Group, NLGaussSeidel, \
ScipyGMRES, Problem, ScipyOptimizer
import numpy as np
from openmdao.api import Component
class SellarDis1(Component):
"""Component containing Discipline 1."""
def __init__(self):
super(SellarDis1, self).__init__()
# Global Design Variable
self.add_param('z', val=np.zeros(2))
# Local Design Variable
self.add_param('x', val=0.)
# Coupling parameter
self.add_param('y2', val=1.0)
# Coupling output
self.add_output('y1', val=1.0)
def solve_nonlinear(self, params, unknowns, resids):
"""Evaluates the equation
y1 = z1**2 + z2 + x1 - 0.2*y2"""
z1 = params['z'][0]
z2 = params['z'][1]
x1 = params['x']
y2 = params['y2']
unknowns['y1'] = z1**2 + z2 + x1 - 0.2*y2
def linearize(self, params, unknowns, resids):
""" Jacobian for Sellar discipline 1."""
J = {}
J['y1','y2'] = -0.2
J['y1','z'] = np.array([[2*params['z'][0], 1.0]])
J['y1','x'] = 1.0
return J
class SellarDis2(Component):
"""Component containing Discipline 2."""
def __init__(self):
super(SellarDis2, self).__init__()
# Global Design Variable
self.add_param('z', val=np.zeros(2))
# Coupling parameter
self.add_param('y1', val=1.0)
# Coupling output
self.add_output('y2', val=1.0)
def solve_nonlinear(self, params, unknowns, resids):
"""Evaluates the equation
y2 = y1**(.5) + z1 + z2"""
z1 = params['z'][0]
z2 = params['z'][1]
y1 = params['y1']
# Note: this may cause some issues. However, y1 is constrained to be
# above 3.16, so lets just let it converge, and the optimizer will
# throw it out
y1 = abs(y1)
unknowns['y2'] = y1**.5 + z1 + z2
def linearize(self, params, unknowns, resids):
""" Jacobian for Sellar discipline 2."""
J = {}
J['y2', 'y1'] = .5*params['y1']**-.5
#Extra set of brackets below ensure we have a 2D array instead of a 1D array
# for the Jacobian; Note that Jacobian is 2D (num outputs x num inputs).
J['y2', 'z'] = np.array([[1.0, 1.0]])
return J
class SellarDerivatives(Group):
""" Group containing the Sellar MDA. This version uses the disciplines
with derivatives."""
def __init__(self):
super(SellarDerivatives, self).__init__()
self.add('px', IndepVarComp('x', 1.0), promotes=['x'])
self.add('pz', IndepVarComp('z', np.array([5.0, 2.0])), promotes=['z'])
self.add('d1', SellarDis1(), promotes=['z', 'x', 'y1', 'y2'])
self.add('d2', SellarDis2(), promotes=['z', 'y1', 'y2'])
self.add('obj_cmp', ExecComp('obj = x**2 + z[1] + y1 + exp(-y2)',
z=np.array([0.0, 0.0]), x=0.0, y1=0.0, y2=0.0),
promotes=['obj', 'z', 'x', 'y1', 'y2'])
self.add('con_cmp1', ExecComp('con1 = z'), promotes=['z', 'con1'])
self.nl_solver = NLGaussSeidel()
self.nl_solver.options['atol'] = 1.0e-12
self.ln_solver = ScipyGMRES()
top = Problem()
top.root = SellarDerivatives()
top.driver = ScipyOptimizer()
top.driver.options['optimizer'] = 'SLSQP'
top.driver.options['tol'] = 1.0e-8
top.driver.add_desvar('z', lower=np.array([-10.0, 0.0]),
upper=np.array([10.0, 10.0]))
top.driver.add_desvar('x', lower=0.0, upper=10.0)
top.driver.add_objective('obj')
top.driver.add_constraint('con1', lower=np.array([-5., -5.]), upper=np.array([5.,5.]))
top.setup()
# Setting initial values for design variables
top['x'] = 1.0
top['z'] = np.array([5.0, 2.0])
top.run()
print("\n")
print( "Minimum found at (%f, %f, %f)" % (top['z'][0], \
top['z'][1], \
top['x']))
print("Coupling vars: %f, %f" % (top['y1'], top['y2']))
print("Minimum objective: ", top['obj'])
The fundamental problem is that ExecComp assumes everything is scalar unless you tell it otherwise. So you can make the code you have work, if you give it some size information.
self.add('con_cmp1', ExecComp('con1 = z', inits={'z':np.zeros(2), 'con1': np.zeros(2)}), promotes=['z', 'con1'])
However, you don't actually needed the ExecComp at all. You can directly constraint the design variable like this:
top.driver.add_constraint('z', lower=np.array([-5., -5.]), upper=np.array([5.,5.]))
I am setting up an optimization in OpenMDAO v0.13 using several components that are used many times. My assembly seems to be working just fine with the default driver, but when I run with an optimizer it does not solve. The optimizer simply runs with the inputs given and returns the answer using those inputs. I am not sure what the issue is, but I would appreciate any insights. I have included a simple code mimicking my structure that reproduces the error. I think the problem is in the connections, summer.fs does not update after initialization.
from openmdao.main.api import Assembly, Component
from openmdao.lib.datatypes.api import Float, Array, List
from openmdao.lib.drivers.api import DOEdriver, SLSQPdriver, COBYLAdriver, CaseIteratorDriver
from pyopt_driver.pyopt_driver import pyOptDriver
import numpy as np
class component1(Component):
x = Float(iotype='in')
y = Float(iotype='in')
term1 = Float(iotype='out')
a = Float(iotype='in', default_value=1)
def execute(self):
x = self.x
a = self.a
term1 = a*x**2
self.term1 = term1
print "In comp1", self.name, self.a, self.x, self.term1
def list_deriv_vars(self):
return ('x',), ('term1',)
def provideJ(self):
x = self.x
a = self.a
dterm1_dx = 2.*a*x
J = np.array([[dterm1_dx]])
print 'In comp1, J = %s' % J
return J
class component2(Component):
x = Float(iotype='in')
y = Float(iotype='in')
term1 = Float(iotype='in')
f = Float(iotype='out')
def execute(self):
y = self.y
x = self.x
term1 = self.term1
f = term1 + x + y**2
self.f = f
print "In comp2", self.name, self.x, self.y, self.term1, self.f
class summer(Component):
total = Float(iotype='out', desc='sum of all f values')
def __init__(self, size):
super(summer, self).__init__()
self.size = size
self.add('fs', Array(np.ones(size), iotype='in', desc='f values from all cases'))
def execute(self):
self.total = sum(self.fs)
print 'In summer, fs = %s and total = %s' % (self.fs, self.total)
class assembly(Assembly):
x = Float(iotype='in')
y = Float(iotype='in')
total = Float(iotype='out')
def __init__(self, size):
super(assembly, self).__init__()
self.size = size
self.add('a_vals', Array(np.zeros(size), iotype='in', dtype='float'))
self.add('fs', Array(np.zeros(size), iotype='out', dtype='float'))
print 'in init a_vals = %s' % self.a_vals
def configure(self):
# self.add('driver', SLSQPdriver())
self.add('driver', pyOptDriver())
self.driver.optimizer = 'SNOPT'
# self.driver.pyopt_diff = True
#create this first, so we can connect to it
self.add('summer', summer(size=len(self.a_vals)))
self.connect('summer.total', 'total')
print 'in configure a_vals = %s' % self.a_vals
# create instances of components
for i in range(0, self.size):
c1 = self.add('comp1_%d'%i, component1())
c1.missing_deriv_policy = 'assume_zero'
c2 = self.add('comp2_%d'%i, component2())
self.connect('a_vals[%d]' % i, 'comp1_%d.a' % i)
self.connect('x', ['comp1_%d.x'%i, 'comp2_%d.x'%i])
self.connect('y', ['comp1_%d.y'%i, 'comp2_%d.y'%i])
self.connect('comp1_%d.term1'%i, 'comp2_%d.term1'%i)
self.connect('comp2_%d.f'%i, 'summer.fs[%d]'%i)
self.driver.workflow.add(['comp1_%d'%i, 'comp2_%d'%i])
self.connect('summer.fs[:]', 'fs[:]')
self.driver.workflow.add(['summer'])
# set up main driver (optimizer)
self.driver.iprint = 1
self.driver.maxiter = 100
self.driver.accuracy = 1.0e-6
self.driver.add_parameter('x', low=-5., high=5.)
self.driver.add_parameter('y', low=-5., high=5.)
self.driver.add_objective('summer.total')
if __name__ == "__main__":
""" the result should be -1 at (x, y) = (-0.5, 0) """
import time
from openmdao.main.api import set_as_top
a_vals = np.array([1., 1., 1., 1.])
test = set_as_top(assembly(size=len(a_vals)))
test.a_vals = a_vals
print test.a_vals
test.x = 2.
test.y = 2.
tt = time.time()
test.run()
print "Elapsed time: ", time.time()-tt, "seconds"
print 'result = ', test.summer.total
print '(x, y) = (%s, %s)' % (test.x, test.y)
print test.fs
I played around with your model, and found that the following line caused problems:
#self.connect('summer.fs[:]', 'fs[:]')
When I commented it out, I got the optimization to move.
I am not sure what is happening there, but the graph transformations sometimes have some issues with component input nodes that are promoted as outputs on the assembly boundary. If you still want those values to be available on the assembly, you could try promoting the outputs from the comp2_n components instead.
Here's my code. I keep getting that error, no matter if I use inside_sig_r or inside_sig_r2. If I take out the last line I don't get this error. Thanks for any help.
import numpy as np
from scipy import integrate, interpolate
from math import sqrt,pi,cos,sin,exp
rho = 2.78e11 * .3
delta = 1.68
def M(r):
return ((4*pi)/3)*(r**3)*rho
def R(M):
return (( 3 * M) / (4 * pi * rho)) ** (.3333)
def W(x):
return 3.*(sin(x) - x*cos(x))/(x**3.)
data = np.loadtxt("//Users//Slemons//Downloads//pk2.dat", float)
k_data = (10**data[:,0])
Pk_data = (10**data[:,1])
Pk = interpolate.interp1d(k_data,Pk_data,kind='cubic')
Masses = np.arange(1e10,1e16,1e10)
r_from_M = np.array(map(R,Masses),float)
print r_from_M[0]
def inside_sig_r(k,r):
return ((W(k*r)**2.) * Pk(k) * (k**2.)) / (2. * (pi ** 2.))
def inside_sig_r2(z,r):
k = (1.+z)/(1.-z)
return inside_sig_r(k,r) *2./(1.-z)**2.
sigma_r = lambda k : sqrt(integrate.quad(inside_sig_r,.4,np.inf,args=(k)))
sigr = np.array(map(sigma_r,Masses),float)
It is not really a standalone code, since I can't see your data in '//Users//Slemons//Downloads//pk2.dat'. However, the error is quite specific - the data produced by inside_sig_r(2) are above or below the range you supplied (0.4, np.inf). You should either change the range or make sure that the functions return values inside this range.