def keydb_get_note(note,dbName='keydb.data'):
'''
Args:
note: an actual pathology note from raw data.
dbName: The physical storage for the database
Returns:
Dictinoary of key frequencies
'''
from get_data_breast import checkAllcancer,get_section
record = checkAllcancer(note)
#specimens are not important any more.
#record['content'] = get_section(note)
return keydb_core(record)
def get_collection(data):
collection = {}
i=0
while i<len(data):
input_dict = checkAllcancer(data[i][1])
for item in input_dict.values():
for k in item.keys():
k_clean = keydb_clean_string(k)
if len(k_clean)==0:
break
k_clean = k_clean[0]
# k_clean = k
value = item[k][0]
if value!='' and value!="_":
if collection.get(k_clean)==None:
collection[k_clean]=[]
value = value.replace("_","")
collection[k_clean].append(value.lower())
i+=1
return collection
def get_collection(data):
# collect all data after extraction in order to be used as an input for calculating the value score
from get_data_breast import checkAllcancer
collection = {}
i = 0
while i < len(data):
input_dict = checkAllcancer(data[i][1])
for item in input_dict.values():
for k in item.keys():
k_clean = keydb_clean_string(k)
if len(k_clean) == 0:
break
k_clean = k_clean[0]
# k_clean = k
value = item[k][0]
if value != "" and value != "_":
if collection.get(k_clean) == None:
collection[k_clean] = []
value = value.replace("_", "")
collection[k_clean].append(value.lower())
i += 1
return collection
def Extract():
'''
depracted. Use jsontest instead.
this is a nice web interface for testing.
user only needs to input text and a univerid,
Returns:
json formated result from given text and universe_id
'''
args = parser.parse_args()
note = args['text']
cancerName = args['universe_id']
print 'args:',args
print 'form:',request.form
#should ahve just check form first then the args.
if note == None:
note = request.form.get('data')
cancerName = request.form.get('cancer')
if cancerName is None:
cancerName = ''
if note == None or note.strip()=='':
return 'No info'
else:
result = {}
try:
result = checkAllcancer(note)
result_confidence= result.copy()
for cancer in result.keys():
if cancerName.strip() != '':
marginaldbname = cancerName.lower()+'.data'
else:
marginaldbname=None
print 'marginaldbname: ',marginaldbname
if marginaldbname is not None:
marginaldb = keydb_marginal_load(marginaldbname)
else:
marginaldb = keydb_marginal_load()
########################################
# the below code is for getting confidence score.
#########################################
for k,v in result[cancer].items():
#note that v is a list contains value and original value.
value = v[0]
#now we can do value processing.
#put your code here
#now we can do key confidence processing.
#it needs a library indicating which unverse it belongs to.
#in here we will just try to use our pre-existing libraries.
#namely, if you have breast cancer as cancer, then
try:
result_confidence[cancer][k].append(keydb_marginal_newkey(k,value,marginaldb,marginaldbname,True))
except Exception, err:
print 'ERROR: key_confidence failed'
print err
try:
value_score = getScore(k,value,keydb_marginal_load('Valdb.data'))
result_confidence[cancer][k].append(' '.join([str(item) for item in value_score.values()]))
except Exception, err:
print 'ERROR: value_confidence failed'
print err
result['specimens']=get_section(note)
