def init_causal_graph_dot_src(self, df, forbidden_edges, required_edges):
p = pc()
p.start_vm()
tetrad = s.tetradrunner()
prior = pr.knowledge(forbiddirect = forbidden_edges, requiredirect = required_edges)
tetrad.run(algoId = 'fges', dfs = df, priorKnowledge = prior, scoreId = 'sem-bic', dataType = 'continuous', penaltyDiscount = 2, maxDegree = -1, faithfulnessAssumed = True, verbose = True)
dot_src = p.tetradGraphToDot(tetrad.getTetradGraph())
#p.stop_vm()
self.edges = tetrad.getEdges()
self.nodes = tetrad.getNodes()
dot_src = self.trim_init_src_string(dot_src)
self.dot_src_lines = self.dot_src_to_lines(dot_src)
self.dot_src = self.lines_to_dot_src(self.dot_src_lines)
self.init_dot_src = self.dot_src
self.uncolored_dot_src = self.init_dot_src
def learn_fci(self, df, tabu_edges):
"""This function is used to learn model using FCI"""
from pycausal.pycausal import pycausal as pc
from pycausal import search as s
from pycausal import prior as p
pc = pc()
pc.start_vm()
forbid = [list(i) for i in tabu_edges]
prior = p.knowledge(forbiddirect=forbid)
tetrad = s.tetradrunner()
tetrad.getAlgorithmParameters(algoId='fci', testId='fisher-z-test')
tetrad.run(algoId='fci',
dfs=df,
testId='fisher-z-test',
depth=-1,
maxPathLength=-1,
completeRuleSetUsed=False,
verbose=False)
edges = tetrad.getEdges()
dot_str = pc.tetradGraphToDot(tetrad.getTetradGraph())
graph = pydot.graph_from_dot_data(dot_str)
# graph[0].write_pdf(fname)
pc.stop_vm()
return edges
# Make prediction
y_pred = model.predict(X)
#Generate causal assured dataset D'
causal_targets = pd.DataFrame(y_pred, columns = [args.target_var])
causal_targets.reset_index(drop=True, inplace = True)
causal_df = input_df.copy().join(causal_targets)
# Calculate Score
mse = mean_squared_error(y_pred, y)
#print("MSE = ", mse)
edges = list(map(tuple, args.e))
#print("Required edges = ", edges)
prior = p.knowledge(requiredirect= edges)
if args.discrete:
ll = get_ll_mixed(causal_df, prior)
else:
ll = get_ll_continuous(causal_df, prior)
#print("LL(G|D) = ", ll)
CAM = ll * args.l + mse
#print("Overall CAM score = ", CAM)
MSE.append(mse)
LL.append(ll)
filenames.append(file)
# Save score
combined = normalize(LL) * args.l + normalize(MSE)
s = sorted(zip(combined, filenames))
print(s)
def fges_stem(file_path, sys_iter, SGA_l, A_D):
BIC_l = [float(0)]
SGA = pd.DataFrame(SGA_l)
SGA.columns = ['cause gene name']
A_D_i = A_D
for i in range(sys_iter):
print(i)
file_l = os.listdir(file_path + '/Output/run%i' % i)
while 'completeMatrixn.csv' not in file_l:
df_name = file_path + '/Output/run%i/completeMatrix.csv' % i
df = pd.read_csv(df_name, header=0, index_col=None)
from pycausal.pycausal import pycausal as pc
pc = pc()
pc.start_vm(java_max_heap_size='6400M')
from pycausal import prior as p
# get knowledge from knowledge file
#prior = p.knowledgeFromFile(file_path + '/Input/Knowledge')
# get knowledge from DEG and SGA list
DEG_l = [x for x in df.columns if x not in SGA_l]
A_D_i = A_D_i[DEG_l]
forbid = create_knowledge(SGA, SGA_l, A_D_i)
temporal = [SGA_l, p.ForbiddenWithin(DEG_l)]
prior = p.knowledge(forbiddirect=forbid, addtemporal=temporal)
from pycausal import search as s
tetrad = s.tetradrunner()
tetrad.getAlgorithmParameters(algoId='fges', scoreId='bdeu-score')
tetrad.run(
algoId='fges',
dfs=df,
scoreId='bdeu-score',
priorKnowledge=prior,
dataType='discrete',
structurePrior=1.0,
samplePrior=1.0,
maxDegree=100,
faithfulnessAssumed=True,
verbose=True,
symmetricFirstStep=True
) # , numberResampling=10, resamplingEnsemble=1, addOriginalDataset=True)
# save edges.csv
node_l = tetrad.getNodes()
edge_l = tetrad.getEdges()
#edge_split_l = []
#for edge in edge_l:
#if '---' in edge:
#edge_n = edge.split(' ')
#if np.sum(df[edge.split(' ')[0]]) > np.sum(df[edge.split(' ')[2]]):
# edge_n.reverse()
#else:
# edge_n = edge_n
#edge_split_l.append(edge_n)
#else:
#edge_split_l.append(edge.split(' '))
#edge_split_l = [edge.split(' ') for edge in edge_l if '---' not in edge]
edge_split_l = [edge.split(' ') for edge in edge_l]
edge_df = pd.DataFrame(edge_split_l).iloc[:, [0, 2]]
edge_df.to_csv(file_path + '/Output/run%i/Edge.csv' % i,
index=False,
header=False)
# save completeMatrixn.csv
new_df = df.loc[:, node_l]
new_df.to_csv(file_path + '/Output/run%i/completeMatrixn.csv' % i,
index=False,
header=True)
# save BIC.txt
print(tetrad.getTetradGraph(),
file=open(file_path + '/Output/run%i/BIC.txt' % i, 'a'))
file_l = os.listdir(file_path + '/Output/run%i' % i)
else:
# save BIC which used to verify convergency
with open(file_path + '/Output/run%i/BIC.txt' % i, 'r') as BIC_txt:
for line in BIC_txt:
if 'BIC: -' in line:
BIC_l.append(float(line[5:-1]))
j = i + 1
mk_dir(file_path + '/Output/run%d' % j)
next_file_l = os.listdir(file_path + '/Output/run%i' % j)
while 'completeMatrix.csv' not in next_file_l:
exe_path = './MCMC/inferSGAInNetwork_TDI.exe'
m_path = ' -m ' + file_path + '/Output/run%i/completeMatrixn.csv' % i
i_path = ' -i ' + file_path + '/Input/S_A0.csv'
e_path = ' -e ' + file_path + '/Output/run%i/Edge.csv' % i
o_path = ' -o ' + file_path + '/Output/run%d/ -x 50' % j
combine = exe_path + m_path + i_path + e_path + o_path
os.system(combine)
time.sleep(20)
next_file_l = os.listdir(file_path + '/Output/run%i' % j)
else:
pd.DataFrame(BIC_l).to_csv(file_path + '/Output/BIC.csv',
index=False,
header=False)