def main():
dh = Datahelper()
try:
chembl = pymysql.connect(host=os.environ["CHHOST"],
user=os.environ["CHUSER"],
passwd=os.environ["CHPWD"],
port=int(os.environ["CHPORT"]),
db=os.environ["CHDB"])
except:
#print "Unexpected error:", sys.exc_info()[0]
print "Unexpected error:", sys.exc_info()
exit()
count = 0
for line in sys.stdin:
data = line.strip().split(',')
atc_code = data[3]
rdata = data[:4]
query = "select level3_description from atc_classification where level3 = '%s' limit 1" % (
atc_code)
count = 0
with chembl.cursor() as cursor:
cursor.execute(query)
for row in cursor:
count += 1
descr = dh.get_normalised_phrase(row[0].lower())
rdata.append(descr)
rdata.append(data[4])
print ','.join(rdata)
chembl.close()
return count
def main(options):
count = 0
mcount = 0
umcount = 0
dh = Datahelper()
try:
fh = open(options.synfile, "r")
synonyms = load_synonyms(fh)
except IOError as e:
print "I/O error({0}): {1}".format(e.errno, e.strerror)
exit()
except TypeError as e:
print "Missing arguments ", e
exit()
except:
print "Unexpected error:", sys.exc_info()
exit()
for line in sys.stdin:
count += 1
data = line.strip().split(',')
phrase = data[1].lower()
matched = False
for key in dh.get_merge_key_list(phrase):
if key in synonyms:
print "%s,%s,%s" % (data[0], phrase, '|'.join(synonyms[key]))
matched = True
mcount += 1
break
if matched == False:
print "%s,%s" % (data[0], phrase)
return count, mcount
def main():
dh = Datahelper()
try:
except:
#print "Unexpected error:", sys.exc_info()[0]
print "Unexpected error:", sys.exc_info()
exit()
count = 0
for line in sys.stdin:
data = line.strip().split(',')
atc_code = data[0]
query = "select level1_description, level2_description, level3_description from atc_classification where level3 = '%s' limit 1" % (atc_code)
count = 0
with chembl.cursor() as cursor:
cursor.execute(query)
for row in cursor:
count += 1
descr = row[0].lower() + ": " + dh.get_normalised_phrase(row[1].lower() + " " + row[2].lower())
data.append(descr)
print ','.join(data)
chembl.close()
return count
def main(options):
"""
"""
dh = Datahelper()
try:
fh = open(options.bnfcodes, "r")
code_lookup = load_code_list(fh)
except:
print "Unexpected error:", sys.exc_info()
exit()
print "pheno,PHENOTYPE,Category,type"
count = 0
for line in sys.stdin:
data = line.strip().split(',')
count = 0
if data[0] in code_lookup:
count += 1
pheno_string = dh.get_normalised_phrase(code_lookup[data[0]])
pheno_string = dh.make_pheno_string(pheno_string)
#data.append(data[0] + "_" + pheno_string)
data.append(data[0])
data.append(pheno_string)
data.append("BINARY")
print ','.join(data)
return count
def main():
try:
dh = Datahelper()
except IOError as e:
print "I/O error({0}): {1}".format(e.errno, e.strerror)
print "I/O error:", sys.exc_info()
exit()
except TypeError as e:
print "Missing arguments ", e
exit()
except:
#print "Unexpected error:", sys.exc_info()[0]
print "Unexpected error:", sys.exc_info()
exit()
ewords = dh.get_excluded_words()
count = 0
outarray = []
for wd in ewords:
count += 1
outarray.append(wd)
if count % 4 == 0:
print ",".join(outarray)
outarray = []
if len(outarray) > 0:
print ",".join(outarray)
#print count
return
def main():
"""
Requires the input to be sorted on the first field (the numeric molregno).
One record per molregno is output.
Calls a datahelper function to normalise each word or phrase (convert to
lower case and remove special characters)
"""
count = 0
last_molno = ""
related_synonyms = []
dh = Datahelper()
for line in sys.stdin:
data = line.strip().split('\t')
if data[0] != last_molno and last_molno != "":
print '|'.join(related_synonyms) + "|MOLREGNO:" + last_molno
related_synonyms = []
last_molno = data[0]
text = dh.get_normalised_phrase(data[1])
stype = data[2]
syn = stype + ":" + text
if syn not in related_synonyms:
related_synonyms.append(syn)
# output the last synonym group
print '|'.join(related_synonyms) + "|MOLREGNO:" + last_molno
def main(options):
dh = Datahelper()
for line in sys.stdin:
data = line.strip().split(',')
data[0] = dh.format_atc_code(data[0], int(options.codelen))
data[1] = data[1].lower()
print ','.join(data)
def main(options):
count = 0
dh = Datahelper()
for line in sys.stdin:
count += 1
data = line.strip().split(',')
data[2] = dh.format_atc_code(data[2], int(options.codelen))
print ','.join(data)
return count
def main(options):
"""
The main match process - look up descriptions and
synonyms in the coding data dictionary (loaded
on initialisation
SEE ALSO: datahelper.py
"""
dcount = 0
count = 0
match_count = 0
miss_count = 0
# try to load the classification system codes file
try:
fh = open(options.clsfile, "r")
dh = Datahelper()
dcount = dh.load_cls_phrases(fh)
#print "Dictionary size = %d" % (dcount)
except IOError as e:
print "I/O error({0}): {1}".format(e.errno, e.strerror)
print "I/O error:", sys.exc_info()
exit()
except TypeError as e:
print "Missing arguments ", e
exit()
except:
#print "Unexpected error:", sys.exc_info()[0]
print "Unexpected error:", sys.exc_info()
exit()
# stdin used to read in medications coding data
hdr = sys.stdin.readline()
for line in sys.stdin:
count += 1
matched = False
data = line.strip().split(',')
all_phrases = [data[1]]
if len(data) == 3:
all_phrases += data[2].split('|')
match_string = ""
code_array, match_data, last_match, selected_code = dh.match_all_phrases(all_phrases)
if len(code_array) > 0:
# Current policy: output one line per code match (can be multiple per input record
for code_elem in code_array:
code_data = code_elem.split("~")
print "%s,%s,%s,%s,%s,%s,%d" % (data[0], data[1], last_match, '|'.join(match_data), code_data[1], code_data[0], len(code_array))
match_count += 1
else:
print "%s,%s,%s,%s,%s,%s,0" % (data[0], data[1], last_match, '|'.join(match_data), "NA", "NA")
miss_count += 1
return count, match_count, miss_count
def main():
count = 0
dh = Datahelper()
hdr = sys.stdin.readline().strip()
print hdr
for line in sys.stdin:
count += 1
data = line.strip().split(',')
data[0] = dh.format_digit_code(data[0], 3)
data[1] = data[1].lower()
print ','.join(data)
return count
def main():
count = 0
last_molno = ""
related_synonyms = []
dh = Datahelper()
for line in sys.stdin:
data = line.strip().split('\t')
print "%s\t%s" % (data[1], data[0])
def main(options):
"""
Access the CHEMBL db for each input line and use the description
from the appropriate level
"""
level = int(options.level)
dh = Datahelper()
try:
chembl = pymysql.connect(host=os.environ["CHHOST"],
user=os.environ["CHUSER"],
passwd=os.environ["CHPWD"],
port=int(os.environ["CHPORT"]),
db=os.environ["CHDB"])
except:
#print "Unexpected error:", sys.exc_info()[0]
print "Unexpected error:", sys.exc_info()
exit()
print "pheno,PHENOTYPE,Category,type"
count = 0
for line in sys.stdin:
data = line.strip().split(',')
atc_code = data[0]
query = "select level%d_description from atc_classification where level%d = '%s' limit 1" % (
level, level, atc_code)
count = 0
cursor = chembl.cursor()
cursor.execute(query)
for row in cursor:
count += 1
pheno_string = dh.get_normalised_phrase(row[0])
pheno_string = dh.make_pheno_string(pheno_string)
data.append(data[0] + "_" + pheno_string)
data.append(pheno_string)
data.append("BINARY")
print ','.join(data)
chembl.close()
return count
def main(options):
count = 0
match_count = 0
miss_count = 0
dh = Datahelper()
try:
fh = open(options.codefile, "r")
code_lookup = load_cs_codes(fh)
#print len(synonyms)
except IOError as e:
print "I/O error({0}): {1}".format(e.errno, e.strerror)
exit()
except TypeError as e:
print "Missing arguments ", e
exit()
except:
#print "Unexpected error:", sys.exc_info()[0]
print "Unexpected error:", sys.exc_info()
exit()
hdr = sys.stdin.readline().strip()
print "%s,%s" % (hdr, "cs_code")
for line in sys.stdin:
count += 1
data = line.strip().split(',')
data.append("NA")
if data[1] in code_lookup:
for code in code_lookup[data[1]]:
data[-1] = code
match_count += 1
print ",".join(data)
else:
miss_count += 1
print ",".join(data)
return count, match_count, miss_count