def MPCorrelation(self):
call('progs/ViennaRNA-2.1.8/Progs/RNALfold -d2 --noLP -L 100 < data/hsa_chr11_sample_2.fasta > data/hsa_chr11_sample_2.folds', shell=True)
MPpairs = []
with open('data/hsa_chr11_sample_2.folds', 'r') as fileIn:
with open('results/mp_pairs_neg.tsv', 'w') as fileOut:
writeSeq = False
for line in fileIn:
if line[0] in '.()':
writeFold = True
fold = line.split()[0]
try:
float(line.split('(')[-1].split(')')[0])
except ValueError:
print "Invalid float:", line.split('(')[-1].split(')')[0]
continue
if '..' in line.split('(')[-1].split(')')[0]:
print line
# Restrictive Must-be-a-perfect-hairpin
for s in fold.split(')')[1:]:
if '(' in s:
writeFold = False
if writeFold:
MPpairs.append( (float(line.split('(')[-1].split(')')[0]), line.count('(') - 1) )
fileOut.write( str(float(line.split('(')[-1].split(')')[0])) +'\t'+ str(line.count('(')-1)+'\n')
# Less restrictive can-have-anything-inside-hairpin
# elif float(line.split('(')[-1].split(')')[0]) <= -15.00 and fold.split(')')[0].count('(') >= 18 and fold.split('(')[-1].count(')') >= 18:
# out.write(line)
# writeSeq = True
p = Plotter()
p.plot_scatter(MPpairs, "mp_scatter_neg.png")
def make_metrics_plot(df, output):
"""
Plot metrics table
:param df: pandas df
:param output: output path
:return: None
"""
pl = Plotter(df, "metrics", output)
pl.plot_metrics_table()
def make_score(df_list, output):
"""
Make global plot long short profit.
:param df_list: list of pd dfs
:param output: output path
:return: None
"""
logger.info("in score plots")
for item in df_list:
df = item[0]
df_name = item[1]
if pc['prediction'] in df_name:
score_ens_df = pd.DataFrame(columns=['model', 'r2', 'mse'])
score_single_df = pd.DataFrame(columns=['model', 'r2', 'mse'])
for i in df.columns.to_list():
if pc['prediction'] in i:
scr_r2 = r2_score(df[mc["label"]], df[i])
scr_mse = mean_squared_error(df[mc["label"]], df[i])
score_single_df = score_single_df.append(
{'model': i,
'r2': scr_r2,
'mse': scr_mse},
ignore_index=True
)
if 'ens' in i:
ens_scr_r2 = r2_score(df[mc["label"]], df[i])
ens_scr_mse = mean_squared_error(df[mc["label"]], df[i])
score_ens_df = score_ens_df.append(
{'model': i,
'r2': ens_scr_r2,
'mse': ens_scr_mse},
ignore_index=True
)
logger.info("df name: {}, single score df shape: {} ".format(df_name, score_single_df.shape))
logger.info("df name: {}, ens score df shape: {} ".format(df_name, score_ens_df.shape))
# single_name = str(df_name) + "_single"
# ens_name = str(df_name) + "_ens"
# score_ens_df = score_ens_df.sort_values(by=['r2'], ascending=False)
# score_single_df = score_single_df.sort_values(by=['r2'], ascending=False)
# plotter_sng = Plotter(score_single_df, single_name, output)
# plotter_sng.plot_score_table()
# plotter_ens = Plotter(score_ens_df, ens_name, output)
# plotter_ens.plot_ens_score_table()
plotter_sng = Plotter(score_single_df.sort_values(by=['r2'], ascending=False),
str(df_name) + "_single",
output)
plotter_sng.plot_score_table()
plotter_ens = Plotter(score_ens_df.sort_values(by=['r2'], ascending=False),
str(df_name) + "_ens",
output)
plotter_ens.plot_ens_score_table()
def single_model_profit(df, csv_str, output):
"""
Plot daily profit and ls_profit by checking
the columns
:param df: pandas df
:param csv_str: model name string
:param output: output path
:return: None
"""
if pc["profit_csv"] in csv_str:
if pc["rf_csv"] in csv_str:
output_loc = create_folder(output, csv_str)
pl = Plotter(df, csv_str, output_loc)
pl.plot_profit_template()
else:
output_loc = create_folder(output, csv_str)
pl = Plotter(df, csv_str, output_loc)
pl.plot_profit_template()
discriminatorIterationsRatio = 1
dataRoot = './Data'
#%%
if (lookup):
batchSize = 9
training_mode = False
dataRoot = './Lookup'
#%%
if (not training_mode):
epochs = 1
#%%
generator = G(lookup=lookup)
discriminator = D(lookup=lookup, batch_size=batchSize)
plotter = Plotter(batchSize)
noiseGenerator = NGen()
generator.cuda()
discriminator.cuda()
#%%
if (load_weights):
generator.load_state_dict(load('./generator.pth'))
discriminator.load_state_dict(load('./discriminator.pth'))
#%%
if (load_weights):
generator.eval()
discriminator.eval()
def crossValidate(self, posFile, negFile, numFolds):
allData = FeatureSet()
allData.load('data/'+posFile, patternClass='real')
allData.add_instances('data/'+negFile, patternClass='pseudo')
allData.libsvm_scale(paramOut = 'data/params')
subsets = allData.get_cv_subsets(numFolds)
resultList = []
# Go through all n folds...
for i in range(numFolds):
# Build training and test sets
testSet = subsets[i]
trainSet = FeatureSet()
for j in range(numFolds):
if j != i:
trainSet.add_instances_from_featureset(subsets[j])
# Create svm files for train and test fold data. Train and test on these files.
trainSet.weka_smote()
trainSet.export_svm('data/trainSet.libsvm')
testSet.export_svm('data/testSet.libsvm')
# SVM settings for HMP features
call('svm-train -c 1 -d 1 -h 1 -e 0.001 -g 0.06 -b 1 data/trainSet.libsvm models/'+str(i)+'.model', shell=True)
# SVM settings for MicroPred features
# call('svm-train -c 10000000 -d 1 -h 1 -e 0.001 -g 0.0019531 -b 1 data/trainSet.libsvm models/'+str(i)+'.model', shell=True)
call('svm-predict -b 1 data/testSet.libsvm models/'+str(i)+'.model data/'+str(i)+'.results', shell=True)
# Calculate sensitivity and specificity for fold model
with open('data/'+str(i)+'.results', 'r') as resultFile:
with open("data/"+str(i)+".sresults", 'w') as resultOut:
# resultLines = resultFile.readlines()
# posLines = resultLines[1:testSet.get_numpos())].sorted( key=lambda l: float(l.split()[1]) )
# negLines = resultLines[testSet.get_numpos():].sorted( key=lambda l: float(l.split()[1]) )
trueNeg = 0.0
truePos = 0.0
falseNeg = 0.0
falsePos = 0.0
resultSet = []
resultFile.readline()
for j in range(testSet.get_numpos()):
line = resultFile.readline()
if line[0] == '1':
resultSet.append(Result(t='1', p='1', conf=line.split()[1]))
truePos += 1.0
else:
resultSet.append(Result(t='1', p='0', conf=line.split()[1]))
falseNeg += 1.0
for j in range(testSet.get_numneg()):
line = resultFile.readline()
if line[0] == '1':
resultSet.append(Result(t='0', p='1', conf=line.split()[1]))
falsePos += 1.0
else:
resultSet.append(Result(t='0', p='0', conf=line.split()[1]))
trueNeg += 1.0
resultSet = sorted(resultSet, key=lambda l: float(l.conf), reverse=True)
for r in resultSet:
resultOut.write(r.t + '\t' + r.p + '\t' + r.conf + '\n')
resultList.append( (truePos/(truePos+falseNeg),trueNeg/(trueNeg+falsePos)) )
with open("roc_"+str(i)+".tsv", 'w') as rocOut:
with open("pr_"+str(i)+".tsv", 'w') as prOut:
ssList = []
prList = []
sens = 0.0
spec = 1.0
for r in resultSet:
if r.t == '1':
sens += 1.0 / testSet.get_numpos()
if r.t == '0':
spec -= 1.0 / testSet.get_numneg()
ssList.append((sens*self.hpSens, (1-spec)*self.hpSpec))
if (sens*self.hpSens+(1-spec)*self.ci*self.hpSpec) != 0:
prList.append((sens*self.hpSens/(sens*self.hpSens+(1-spec)*self.ci*self.hpSpec), sens*self.hpSens))
rocOut.write(str(sens)+'\t'+str(1-spec)+'\n')
prOut.write(str(sens/(sens+spec*self.ci))+'\t'+str(sens)+'\n')
p = Plotter()
p.plot_roc(ssList, "Test", "roc_"+str(i)+".png")
p.plot_pr(prList, "Test", self.ci, "pr_"+str(i)+".png")
###################
# Report Results
###################
for i in range(len(resultList)):
print "## SVM "+str(i)+" ##"
print 'Sensitivity: '+str(resultList[i][0])
print 'Specificity: '+str(resultList[i][1])
print 'average Sensitivity: '+str(sum([result[0] for result in resultList])/numFolds)
print 'average Specificity: '+str(sum([result[1] for result in resultList])/numFolds)
print 'Geometric mean: '+str(pow(sum([result[0] for result in resultList])/numFolds*sum([result[1] for result in resultList])/numFolds, 0.5))
