- python version (spyder 3.7).
- No GPUs available.
I am trying to apply the PC algorithm to my data( 7 patients, 9 columns). I runn a boostraping with replacement.
Then, when i change from gaussian to CItest='hsic_perm' I am getting an error.
line 224, in launcg_R_script
raise RuntimeError("RProcessError ") from None
RuntimeError: RProcessError
bootstrapping = []
sim = 2
for i in range(sim):
x_boot = resample(x,replace =True,random_state = i) #bootstrapping with replacement
x_boot = pd.DataFrame(x_boot, columns= x.columns)
boots.append(x_boot)
obj = PC(CItest='hsic_perm', method_indep='corr', alpha=0.01, njobs=None, verbose=None)
The predict() method works without a graph, or with a
#directed or undirected graph provided as an input
output = obj.predict(x_boot) #No graph provided as an argument
nx.draw_networkx(output, font_size=8)
plt.show()
I am trying to apply the PC algorithm to my data( 7 patients, 9 columns). I runn a boostraping with replacement. Then, when i change from gaussian to CItest='hsic_perm' I am getting an error. line 224, in launcg_R_script raise RuntimeError("RProcessError ") from None RuntimeError: RProcessError bootstrapping = []
sim = 2 for i in range(sim): x_boot = resample(x,replace =True,random_state = i) #bootstrapping with replacement x_boot = pd.DataFrame(x_boot, columns= x.columns) boots.append(x_boot) obj = PC(CItest='hsic_perm', method_indep='corr', alpha=0.01, njobs=None, verbose=None)
The predict() method works without a graph, or with a
Thank you, Angela