def make_listing_clusters():
#for now
#shape up features
import features
#make big and small features (stored in database)
features.main() #really only need to make fancy features
#cluster
import listing_cluster
listing_cluster.main()
def make_listing_clusters():
#for now
#shape up features
import features
#make big and small features (stored in database)
features.main() #really only need to make fancy features
#cluster
import listing_cluster
listing_cluster.main()
def stream_handler(message):
print(message["path"]) # /-K7yGTTEp7O549EzTYtI
print(message["data"]) # {'title': 'Pyrebase', "body": "etc..."}
entry_len = len(message["path"])
entry = message["path"]
if (message and message['data'] != None):
if (entry_len > 1 and (entry[entry_len - 1] + entry[entry_len - 2] +
entry[entry_len - 3] != 'mP/')):
newpath = r"C:\Users\HP\Desktop\%s" % message["path"]
if not os.path.exists(newpath):
os.makedirs(newpath)
time.sleep(2)
st.child("uploads/air/394.jpg").download(
r"C:\Users\HP\Desktop\%s\1.jpg" % message["path"])
features.main()
nearest_loc.main()
def main():
url = sys.argv[1]
features_test = features.main(url)
clf = joblib.load('random_forest.pkl')
pred = clf.predict(features_test)
if int(pred[0]) == 1:
print("Website ini aman")
elif int(pred[0]) == -1:
print("Website ini tidak aman!")
def main():
url=sys.argv[1]
features_test=features.main(url)
clf = joblib.load('random_forest.pkl')
pred=clf.predict(features_test)
prob=clf.predict_proba(features_test)
if int(pred[0])==1:
print ("This is a safe website.")
elif int(pred[0])==-1:
print ("This is a phishing website..!")
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import sys
###
import evaluation
import check_tests as ct
import features
###
from sklearn.ensemble import GradientBoostingClassifier, RandomForestClassifier
from sklearn.metrics import roc_curve, auc
train = pd.read_csv('../data/training.csv', index_col='id')
subset = [1,2,3,4,5]
variables = train.columns[subset]
trained_model = features.main('rf', variables)
ct.agreement(trained_model, variables)
ct.correlation(trained_model, variables)
ct.weightedAuc(trained_model, variables, train)
def extractFeatures_given_gff(config, gff_infile, outdir, has_mirna,
is_consider_corr):
cparser = SafeConfigParser()
cparser.read(config)
tc_config = cparser.get('configs', 'tcconfig')
m_mirna = cparser.get('correlation', 'srnaseqmatrix')
f_fasta = cparser.get('genome', 'fasta')
f_chromsizes = cparser.get('genome', 'chromsizes')
d_phastcons = cparser.get('cons', 'phastcons')
TRAP = cparser.get('tata', 'trap')
f_psemmatrix = cparser.get('tata', 'psem')
mirbase_gff2 = cparser.get('mirbase', 'gff2')
corrmethod = cparser.get('correlation', 'corrmethod')
## PART1: tc normalization
## 1a. setup infile
outdir_tc = os.path.join(outdir, 'tc-norm')
f1_pos = os.path.join(outdir, 'f1_pos.txt')
ensure_dir(outdir_tc)
## 1b. reformat infile so that can be read by tc-quantify
_reformat_infile_gff2tcnorm(gff_infile, f1_pos)
## 1c. run
fo_bed = tc_normalization.main(tc_config, f1_pos, outdir_tc)
ncount_dict = {}
with open(fo_bed) as f:
for line in f:
l = line.strip().split('\t')
try:
_, chrom, start, _, stop, strand = re.split('[r:.,]', l[3])
pos = '.'.join([chrom, start, stop, strand])
ncount_dict[pos] = l[6]
except ValueError:
print '#[tcBedSpltErr]: %s' % line,
## 1d. setup outfile
f_rle = re.sub('max_tpm.bed$', 'tpm_rle.matrix', fo_bed)
tcparser = SafeConfigParser()
tcparser.read(tc_config)
f_ids = tcparser.get('tc_normalization', 'ids')
## PART2: compute cpg, cons, tata ...
outdir_seqfeatures = os.path.join(outdir, 'seqfeatures/')
ensure_dir(outdir_seqfeatures)
gff1kb_infile = os.path.join(outdir_seqfeatures, 'infile_1kbseq.gff')
gff_1kbfeatures = os.path.join(outdir_seqfeatures, 'features_1kbseq.gff')
_reformat_tss_to_1kb(f1_pos, gff1kb_infile)
features.main(gff1kb_infile, outdir_seqfeatures, f_fasta, f_chromsizes,
d_phastcons, TRAP, f_psemmatrix, gff_1kbfeatures)
## PART3: compute mprox ...
outdir_tmp = os.path.join(outdir, 'intermediates')
ensure_dir(outdir_tmp, False)
gff_mproxfeatures = os.path.join(outdir_tmp, 'features_mprox.gff')
gff_ufeat1 = os.path.join(outdir_tmp, 'features.1kb.mprox.gff')
if has_mirna:
_interpret_mprox(gff_infile, mirbase_gff2, gff_mproxfeatures)
else:
mirna_proximity.main(gff1kb_infile, mirbase_gff2, gff_mproxfeatures)
gff_unify_features.main(gff_1kbfeatures, gff_mproxfeatures, 'mirna_prox',
'0', gff_ufeat1, True)
## PART4: compute corr
if is_consider_corr:
## correlation setup:
outdir_corr = os.path.join(outdir, 'corr')
ensure_dir(outdir_corr, False)
gff_mirna = os.path.join(outdir_corr, '4corr_mirna.gff')
gff_tss = os.path.join(outdir_corr, '4corr_tss.gff')
pair_pos = os.path.join(outdir_corr, '4corrPair_row_pos_tss-mirna.txt')
pair_sample = os.path.join(outdir_corr,
'4corrPair_col_sample_CAGE-sRNAseq.txt')
fo_corr = os.path.join(outdir_corr,
'features_correlation-%s.gff' % corrmethod)
gff_ufeat2 = os.path.join(outdir_tmp, 'features.1kb.mprox.corr.gff')
## position pair:
correlation._find_miRNA_pos(m_mirna, mirbase_gff2, gff_mirna)
correlation._get_tss_pos(f1_pos, gff_tss)
if has_mirna:
_interpret_tss_mirna_pairings(gff_infile, gff_tss, gff_mirna,
pair_pos)
else:
correlation._get_tss_mirna_pairings(gff_tss, gff_mirna, pair_pos)
## sample pair:
srnaseq_index = correlation._index_srnaseq(m_mirna)
cage_index = _index_tcnorm(f_ids)
correlation._get_sample_pairings(cage_index, srnaseq_index,
pair_sample)
## compute correlation:
correlation._compute_correlation(pair_pos, pair_sample, f_rle, m_mirna,
fo_corr, corrmethod, '.')
gff_unify_features.main(gff_ufeat1, fo_corr, 'corr', '0', gff_ufeat2,
True)
gff_ufeat = gff_ufeat2
else:
gff_ufeat = gff_ufeat1
findex = _index_feat(gff_ufeat, has_mirna)
## PART4: start consolidating features ...
gff_allfeatures = os.path.join(outdir, 'features.gff')
with open(gff_allfeatures, 'w') as out:
with open(gff_infile) as f:
for l in f:
chrom, _, _, start, stop, _, strand, _, mirna = l.strip(
).split('\t')
mirna = mirna.lower()
## setting ids...
tssid = '.'.join([chrom, start, stop, strand])
## getting info...
try:
ncount = ncount_dict[tssid]
except KeyError:
ncount = '0'
if findex.has_key(tssid):
for n in findex[tssid]:
if has_mirna:
m, n = n.split(':')
if m != mirna: continue
newline = linecache.getline(gff_ufeat, int(n))
newline = newline.split('\t')
newline[2] = mirna
newline[5] = ncount
out.write('\t'.join(newline))
return gff_allfeatures
import features
import numpy as np
from collections import defaultdict
def gensif(temp, f):
infile2 = os.path.dirname(os.path.abspath(__file__)) + '/csvFiles/pred.csv'
fh1 = open(infile2, 'w')
for k in temp:
k = int(k)
print >> fh1, str(k)
fh1.close()
gengraph.main(f)
features.main()
tex = loadtxt('/home/aditya/Project/csvFiles/trainNLP.csv', delimiter=',')
tex_dev = loadtxt('/home/aditya/Project/csvFiles/devNLP.csv', delimiter=',')
tex_test = loadtxt('/home/aditya/Project/csvFiles/testNLP.csv', delimiter=',')
vals = tex.shape
vals_dev = tex_dev.shape
vals_test = tex_test.shape
ty = tex[:, vals[1] - 1]
tx = tex[:, 0:vals[1] - 2]
ty_dev = tex_dev[:, vals_dev[1] - 1]
tx_dev = tex_dev[:, 0:vals_dev[1] - 2]
tx_test = tex_test[:, 0:vals_test[1] - 1]
#clf=svm.SVC()
#clf.fit(tx,ty)/home/aditya/Project/dev
newtext_train = './GRN.py --a1-dir /home/aditya/Project/train --a2-dir /home/aditya/Project/train --pred-sif /home/aditya/Project/output_train.sif /home/aditya/Project/train/PMID-*.txt'
newtext_dev = './GRN.py --a1-dir /home/aditya/Project/dev --a2-dir /home/aditya/Project/dev --pred-sif /home/aditya/Project/output_dev.sif /home/aditya/Project/dev/PMID-*.txt'
def main(f_config, gff_cage, is_gff, outdir, make_plots):
cparser = SafeConfigParser()
cparser.read(f_config)
in_bname = os.path.basename(gff_cage)
if outdir == None:
outdir = 'promi2_outdir_' + in_bname + '_' + random_string(6)
ensure_dir(outdir, False)
f_param = cparser.get('promi2', 'params')
listoffeatures = cparser.get('promi2', 'features')
listoffeatures = listoffeatures.split(',')
if 'corr' in listoffeatures:
is_consider_corr = True
corrmethod = cparser.get('correlation', 'corrmethod')
else:
is_consider_corr = False
## PART1: Feature extraction
if not is_gff:
## feature extraction: cpg, cons, tata (features.py)
outdir_seqfeatures = os.path.join(outdir, 'seqfeatures')
ensure_dir(outdir_seqfeatures, False)
gff_1kbfeatures = os.path.join(outdir_seqfeatures,
'features_1kbseq.gff')
f_fasta = cparser.get('genome', 'fasta')
f_chromsizes = cparser.get('genome', 'chromsizes')
d_phastcons = cparser.get('cons', 'phastcons')
TRAP = cparser.get('tata', 'trap')
f_psemmatrix = cparser.get('tata', 'psem')
features.main(gff_cage, outdir_seqfeatures, f_fasta, f_chromsizes,
d_phastcons, TRAP, f_psemmatrix, gff_1kbfeatures)
## feature extraction: mirna_proximity (mirna_proximity.py)
outdir_mprox = os.path.join(outdir, 'mprox')
ensure_dir(outdir_mprox, False)
gff_mirnaprox = os.path.join(outdir_mprox, 'features_mirnaprox.gff')
gff_mirna = cparser.get('mirbase', 'gff2')
mirna_proximity.main(gff_cage, gff_mirna, gff_mirnaprox)
## merge extracted features (gff_unify_features.py)
gff_features = os.path.join(outdir, 'Features.1kb.mprox.' + in_bname)
gff_unify_features.main(gff_1kbfeatures, gff_mirnaprox, 'mirna_prox',
'0', gff_features)
if is_consider_corr:
## merge extracted features (gff_unify_features.py) after compute correlation
gff_features_corr = os.path.join(
outdir, 'Features.1kb.mprox.%s.%s' % (corrmethod, in_bname))
outdir_corr = os.path.join(outdir, 'corr')
m_mirna = cparser.get('correlation', 'srnaseqmatrix')
m_tss = cparser.get('correlation', 'cageseqmatrix')
gff_corr = correlation.main(gff_mirna, m_mirna, m_tss, corrmethod,
outdir_corr)
gff_unify_features.main(gff_features, gff_corr, 'corr', '0',
gff_features_corr)
gff_allfeatures = gff_features_corr
else:
gff_allfeatures = gff_features
else:
gff_allfeatures = gff_cage
with open(gff_allfeatures) as f:
l = f.readline().split('\t')
if not (':' in l[7]):
sys.exit('ERROR: this is not a features.gff formatted file')
## PART2: extract parameters & run promirna
f_prediction = os.path.join(outdir, 'Predictions.' + in_bname + '.txt')
print 'COMPUTING: "%s"...' % f_prediction
promi2(f_param, listoffeatures, gff_allfeatures, f_prediction)
## PART3: plots
if make_plots:
plotdir = os.path.join(outdir, 'plots')
ensure_dir(plotdir, False)
plots.main(f_prediction, plotdir, f_config)
import os
import gengraph
import features
import re
def gensif(temp):
infile2=os.path.dirname(os.path.abspath(__file__))+'/csvFiles/pred.csv'
fh1=open(infile2,'w')
for k in temp:
k=int(k)
print >>fh1,str(k)
fh1.close()
gengraph.main()
lb=preprocessing.L
features.main()
tex=loadtxt('/home/aditya/Project/csvFiles/trainNLP.csv',delimiter=',')
tex_dev=loadtxt('/home/aditya/Project/csvFiles/devNLP.csv',delimiter=',')
tex_test=loadtxt('/home/aditya/Project/csvFiles/testNLP.csv',delimiter=',')
vals= tex.shape
vals_dev= tex_dev.shape
vals_test= tex_test.shape
ty=tex[:,vals[1]-1]
tx=tex[:,0:vals[1]-2]
ty_dev=tex_dev[:,vals_dev[1]-1]
tx_dev=tex_dev[:,0:vals_dev[1]-2]
tx_test=tex_test[:,0:vals_test[1]-1]
#clf=svm.SVC()
#clf.fit(tx,ty)/home/aditya/Project/dev
newtext='./GRN.py --a1-dir /home/aditya/Project/dev --a2-dir /home/aditya/Project/dev --pred-sif /home/aditya/Project/output.sif /home/aditya/Project/dev/PMID-*.txt'
print '....'
def extractFeatures_given_gff(config, gff_infile, outdir, has_mirna, is_consider_corr):
cparser = SafeConfigParser()
cparser.read(config)
tc_config = cparser.get('configs', 'tcconfig')
m_mirna = cparser.get('correlation', 'srnaseqmatrix')
f_fasta = cparser.get('genome','fasta')
f_chromsizes = cparser.get('genome','chromsizes')
d_phastcons = cparser.get('cons','phastcons')
TRAP = cparser.get('tata','trap')
f_psemmatrix = cparser.get('tata','psem')
mirbase_gff2 = cparser.get('mirbase', 'gff2')
corrmethod = cparser.get('correlation', 'corrmethod')
## PART1: tc normalization
## 1a. setup infile
outdir_tc = os.path.join(outdir, 'tc-norm')
f1_pos = os.path.join(outdir, 'f1_pos.txt')
ensure_dir(outdir_tc)
## 1b. reformat infile so that can be read by tc-quantify
_reformat_infile_gff2tcnorm(gff_infile, f1_pos)
## 1c. run
fo_bed = tc_normalization.main(tc_config, f1_pos, outdir_tc)
ncount_dict = {}
with open(fo_bed) as f:
for line in f:
l = line.strip().split('\t')
try:
_, chrom, start, _, stop, strand = re.split('[r:.,]', l[3])
pos = '.'.join([chrom, start, stop, strand])
ncount_dict[pos] = l[6]
except ValueError:
print '#[tcBedSpltErr]: %s' % line,
## 1d. setup outfile
f_rle = re.sub('max_tpm.bed$', 'tpm_rle.matrix', fo_bed)
tcparser = SafeConfigParser()
tcparser.read(tc_config)
f_ids = tcparser.get('tc_normalization', 'ids')
## PART2: compute cpg, cons, tata ...
outdir_seqfeatures = os.path.join(outdir, 'seqfeatures/')
ensure_dir(outdir_seqfeatures)
gff1kb_infile = os.path.join(outdir_seqfeatures, 'infile_1kbseq.gff')
gff_1kbfeatures = os.path.join(outdir_seqfeatures, 'features_1kbseq.gff')
_reformat_tss_to_1kb(f1_pos, gff1kb_infile)
features.main(gff1kb_infile, outdir_seqfeatures,
f_fasta, f_chromsizes, d_phastcons, TRAP, f_psemmatrix,
gff_1kbfeatures)
## PART3: compute mprox ...
outdir_tmp = os.path.join(outdir, 'intermediates')
ensure_dir(outdir_tmp, False)
gff_mproxfeatures = os.path.join(outdir_tmp, 'features_mprox.gff')
gff_ufeat1 = os.path.join(outdir_tmp, 'features.1kb.mprox.gff')
if has_mirna:
_interpret_mprox(gff_infile, mirbase_gff2, gff_mproxfeatures)
else:
mirna_proximity.main(gff1kb_infile, mirbase_gff2, gff_mproxfeatures)
gff_unify_features.main(gff_1kbfeatures, gff_mproxfeatures, 'mirna_prox', '0', gff_ufeat1, True)
## PART4: compute corr
if is_consider_corr:
## correlation setup:
outdir_corr = os.path.join(outdir, 'corr')
ensure_dir(outdir_corr, False)
gff_mirna = os.path.join(outdir_corr, '4corr_mirna.gff')
gff_tss = os.path.join(outdir_corr, '4corr_tss.gff')
pair_pos = os.path.join(outdir_corr, '4corrPair_row_pos_tss-mirna.txt')
pair_sample = os.path.join(outdir_corr, '4corrPair_col_sample_CAGE-sRNAseq.txt')
fo_corr = os.path.join(outdir_corr, 'features_correlation-%s.gff' % corrmethod)
gff_ufeat2 = os.path.join(outdir_tmp, 'features.1kb.mprox.corr.gff')
## position pair:
correlation._find_miRNA_pos(m_mirna, mirbase_gff2, gff_mirna)
correlation._get_tss_pos(f1_pos, gff_tss)
if has_mirna:
_interpret_tss_mirna_pairings(gff_infile, gff_tss, gff_mirna, pair_pos)
else:
correlation._get_tss_mirna_pairings(gff_tss, gff_mirna, pair_pos)
## sample pair:
srnaseq_index = correlation._index_srnaseq(m_mirna)
cage_index = _index_tcnorm(f_ids)
correlation._get_sample_pairings(cage_index, srnaseq_index, pair_sample)
## compute correlation:
correlation._compute_correlation(pair_pos, pair_sample,
f_rle, m_mirna,
fo_corr, corrmethod, '.')
gff_unify_features.main(gff_ufeat1, fo_corr, 'corr', '0', gff_ufeat2, True)
gff_ufeat = gff_ufeat2
else:
gff_ufeat = gff_ufeat1
findex = _index_feat(gff_ufeat, has_mirna)
## PART4: start consolidating features ...
gff_allfeatures = os.path.join(outdir, 'features.gff')
with open(gff_allfeatures, 'w') as out:
with open(gff_infile) as f:
for l in f:
chrom, _, _, start, stop, _, strand, _, mirna = l.strip().split('\t')
mirna = mirna.lower()
## setting ids...
tssid = '.'.join([chrom, start, stop, strand])
## getting info...
try:
ncount = ncount_dict[tssid]
except KeyError:
ncount = '0'
if findex.has_key(tssid):
for n in findex[tssid]:
if has_mirna:
m, n = n.split(':')
if m != mirna: continue
newline = linecache.getline(gff_ufeat, int(n))
newline = newline.split('\t')
newline[2] = mirna
newline[5] = ncount
out.write('\t'.join(newline))
return gff_allfeatures
def main(files, outdir, N, percent_lib, is_get_id, f_config, verbose=False):
if os.path.isdir(outdir):
sys.exit('## ERROR: "%s" already exists' % outdir)
cparser = SafeConfigParser()
cparser.read(f_config)
verbose = True
f_mirbasegff = cparser.get('mirbase', 'gff2')
f_chromsizes = cparser.get('genome', 'chromsizes')
f_repeats = cparser.get('genome', 'repeats')
f_ensembl = cparser.get('genome', 'ensemblgtf')
f_fasta = cparser.get('genome', 'fasta')
d_phastcons = cparser.get('cons', 'phastcons')
TRAP = cparser.get('tata', 'trap')
f_psemmatrix = cparser.get('tata', 'psem')
f_traincfg = cparser.get('configs', 'tcconfig')
m_mirna = cparser.get('correlation', 'srnaseqmatrix')
m_tss = cparser.get('correlation', 'cageseqmatrix')
corrmethod = cparser.get('correlation', 'corrmethod')
f_trainingset = os.path.join(outdir, 'TrainingSet.gff')
outdir1 = f_trainingset + '_intermediates'
ensure_dir(outdir, False)
ensure_dir(outdir1, False)
_files = glob.glob(files)
## creating auxillary file for negative set
f_fiveprimegff = '../data/hsa.five_prime.gff'
if not os.path.exists(f_fiveprimegff):
if verbose:
print 'STATUS: creating "%s" auxillary file...' % f_fiveprimegff
extract_tss_from_ensembl(f_ensembl, f_fiveprimegff)
## create training set
gff_ts_pos = os.path.join(outdir1, 'trainingset_pos.gff')
gff_ts_neg = os.path.join(outdir1, 'trainingset_neg.gff')
if verbose: print 'STATUS: creating positive candidate set...'
create_positiveset(percent_lib, _files, f_mirbasegff, N, gff_ts_pos,
is_get_id)
if verbose: print 'STATUS: creating negative candidate set...'
create_negativeset(f_chromsizes, f_repeats, f_fiveprimegff, f_traincfg, N,
gff_ts_neg)
shutil.move(os.path.join(outdir1, 'tc-norm_negSet'),
os.path.join(outdir, 'tc-norm_negSet'))
## feature extraction: cpg, cons, tata (features.py)
if verbose: print 'STATUS: extracting features cpg/cons/tata...'
gff_1kbfeatures_pos = os.path.join(outdir1, 'features1kb_ts_pos.gff')
gff_1kbfeatures_neg = os.path.join(outdir1, 'features1kb_ts_neg.gff')
features.main(gff_ts_pos, outdir1, f_fasta, f_chromsizes, d_phastcons,
TRAP, f_psemmatrix, gff_1kbfeatures_pos)
features.main(gff_ts_neg, outdir1, f_fasta, f_chromsizes, d_phastcons,
TRAP, f_psemmatrix, gff_1kbfeatures_neg)
## feature extraction: mirna_proximity
if verbose: print 'STATUS: extracting features mirna_proximity...'
gff_mirnaprox_pos = os.path.join(outdir1, 'featureMprox_ts_pos.gff')
gff_mirnaprox_neg = os.path.join(outdir1, 'featureMprox_ts_neg.gff')
mirna_proximity.main(gff_ts_pos, f_mirbasegff, gff_mirnaprox_pos)
mirna_proximity.main(gff_ts_neg, f_mirbasegff, gff_mirnaprox_neg)
gff_features_pos = os.path.join(outdir1, 'Features_ts_pos.gff')
gff_features_neg = os.path.join(outdir1, 'Features_ts_neg.gff')
gff_unify_features.main(gff_1kbfeatures_pos, gff_mirnaprox_pos,
'mirna_prox', '0', gff_features_pos, True)
gff_unify_features.main(gff_1kbfeatures_neg, gff_mirnaprox_neg,
'mirna_prox', '0', gff_features_neg, True)
## create final training set ...
## where background must pass criteria: cpg <= 0.5 and cons <= 0.2 and tata <= 0.1 and mirna_prox == 0
if verbose: print 'STATUS: creating final training set...'
good_background = gff_features_neg + '_cpglt0.5-conslt0.2-tatalt0.1-mproxeq0.gff'
with open(good_background, 'w') as out:
with open(gff_features_neg) as f:
for line in f:
info = line.strip().split('\t')[7].split(';')
cpg = float(get_value_from_keycolonvalue_list('cpg', info))
cons = float(get_value_from_keycolonvalue_list('cons', info))
tata = float(get_value_from_keycolonvalue_list('tata', info))
mprx = float(
get_value_from_keycolonvalue_list('mirna_prox', info))
if cpg <= 0.5 and cons <= 0.2 and tata <= 0.1 and mprx == 0:
out.write(line)
wc = line_count(good_background)
selectedlines = random.sample(range(1, wc + 1), N)
with open(f_trainingset, 'w') as out:
## writing negative set
for l in selectedlines:
out.write(linecache.getline(good_background, l))
## writing positive set
with open(gff_features_pos) as f:
## when mirna_prox extraction feature was used,
## extracted all pairs within 50kb upstream mirna
## -> single tss could have many mirna
## take pair with min distance
## -> essential first entry
pos_list = []
for line in f:
l = line.split('\t')
pos = ','.join([l[0], l[3], l[4], l[6]])
if not (pos in pos_list):
pos_list.append(pos)
out.write(line)
if not (os.path.isfile(m_mirna) and os.path.isfile(m_tss)):
return f_trainingset
## create final training set with feature:correlation of closest tss->miRNA ...
if verbose:
print 'STATUS: creating final training set with correlation of closest tss->miRNA...'
f_trainingset2 = os.path.join(outdir, 'TrainingSet-corr.gff')
m_back = glob.glob('%s/tc-norm_negSet/*tpm_rle.matrix' % outdir)[0]
f_tcfilesinput = os.path.join(outdir, 'tc-norm_negSet', 'files.txt')
feature_closest_corr(f_trainingset, f_mirbasegff, m_mirna, m_tss, m_back,
f_tcfilesinput, corrmethod, f_trainingset2)
return f_trainingset2
import features
print("Hello")
url = input("Please Enter the URL and press enter to proceed : ")
# url = "http://ebay.co.uk"
response = features.main(url)
print(response)
