bioFAM / MOFA

Multi-Omics Factor Analysis
GNU Lesser General Public License v3.0
235 stars 60 forks source link

Error in py_call_impl(callable, dots$args, dots$keywords) : AttributeError: 'NoneType' object has no attribute 'getExpectations' #56

Open FfKB opened 4 years ago

FfKB commented 4 years ago

Hello Guys I am having that error, please could someone help me with this

[1] "No output file provided, using a temporary file..."

###########################################################
###                 __  __  ___  _____ _                ### 
###                |  \/  |/ _ \|  ___/ \               ### 
###                | |\/| | | | | |_ / _ \              ### 
###                | |  | | |_| |  _/ ___ \             ### 
###                |_|  |_|\___/|_|/_/   \_\            ### 
###                                                     ###
########################################################### 

Loaded view 0 with 55 samples and 31 features... Loaded view 1 with 55 samples and 591 features... Loaded view 2 with 55 samples and 838 features...

##############################################

Doing sanity checks and parsing the data

##############################################

Centering features for view Chemokine... Centering features for view Metabolite... Centering features for view miRNA...

After parsing the data: view Chemokine has 55 samples and 31 features... view Metabolite has 55 samples and 591 features... view miRNA has 55 samples and 838 features... Removing incomplete samples... Removing incomplete samples... Likelihoods are defined as: Chemokine: gaussian Metabolite: gaussian miRNA: gaussian ########################

Building the model

######################## Setting random seed 2000... ##################################

Running MOFA with seed 2000

################################## Error in py_call_impl(callable, dots$args, dots$keywords) : AttributeError: 'NoneType' object has no attribute 'getExpectations'

Detailed traceback: File "/home/XXX/.local/lib/python2.7/site-packages/mofapy/core/entry_point.py", line 413, in train_model self.model = runMOFA(self.parsed_data, self.data_opts, self.model_opts, self.train_opts, self.train_opts['seed']) File "/home/XXX/.local/lib/python2.7/site-packages/mofapy/core/build_model.py", line 143, in runMOFA net.iterate() File "/home/XXX/.local/lib/python2.7/site-packages/mofapy/core/BayesNet.py", line 148, in iterate self.nodes[node].update() File "/home/XXX/.local/lib/python2.7/site-packages/mofapy/core/multiview_nodes.py", line 114, in update self.nodes[m].updateParameters() File "/home/XXX/.local/lib/python2.7/site-packages/mofapy/core/updates.py", line 229, in updateParameters thetatmp = self.markov_blanket["Theta"].getExpectations()

rargelaguet commented 4 years ago

I have absolutely no clue what's going on. Could you join the Slack group and send me the MOFA object before training the model?

Also, I would suggest to move to MOFA v2, as MOFA v1 is now depreciated.