def __readInfile__(self):
# Reads diagnosis data into class
first = True
with open(self.infile, "r") as f:
for line in f:
line = line.strip()
if not first:
self.__parseLine__(line.split(d))
else:
d = unixpath.getDelim(line)
self.__setHeader__(line.split(d))
first = False
def __setData__(self, infile):
# Reads file into data frame
d = None
rows = []
name = unixpath.getFileName(infile)
with open(infile, "r") as f:
for line in f:
line = line.strip()
if d:
rows.append(line.split(d))
else:
d = unixpath.getDelim(line)
head = line.split(d)
self.data[name] = pandas.DataFrame(rows, columns=head)
def __setTaxa__(self, infile):
# Stores references and species names
first = True
print("\n\tReading taxonomy...")
with open(infile, "r") as f:
for line in f:
line = line.strip()
if not first:
s = line.split(d)
self.taxa[s[-2]] = s[1:-2]
else:
d = unixpath.getDelim(line)
self.names = line.split(d)[1:-1]
first = False
def __setDiagnoses__(self):
# Reads in diagnoses as dict
first = True
print("\n\tReading diagnosis file...")
with open(self.diagfile, "r") as f:
for line in f:
line = line.strip()
if first == False:
row = line.split(d)
self.diagnoses[row[0]] = row[-1].strip()
else:
d = unixpath.getDelim(line)
self.__setHeader__(line.split(d))
first = False
print(("\tExtracted {:,} diagnosis records.").format(len(self.diagnoses)))
def setSpecies(self, indir):
# Calls stores species as dict of classes
print("\n\tReading species totals files...")
for i in glob(indir + "*"):
first = True
with open(i, "r") as f:
for line in f:
if first == True:
d = unixpath.getDelim(line)
first = False
s = self.__getRow__(d, line)
if len(s) >= 3:
if s[-1] in self.species.keys():
self.species[s[-1]].resolveSpecies(s)
else:
self.species[s[-1]] = Species(self.delim, s)
def __readFile__(self, infile):
# Reads file and returns dict
first = True
ret = {}
print(("\tReading {}...").format(os.path.split(infile)[1]))
with open(infile, "r") as f:
for line in f:
line = line.strip()
if not first:
s = line.split(d)
# Store with ID as key
ret[s[0]] = s[1:]
else:
d = unixpath.getDelim(line)
h = line.split(d)
first = False
return ret, h
def __readInfile__(self, infile, diagnosis, malignant): # Sorts and stores records from input file first = True with open(infile, "r") as f: for line in f: if first == False: s = line.strip().split(d) if len(s) == self.columns.length: if s[0] in self.records.keys(): self.records[s[0]].resolveRecord(self.columns, s) else: self.records[s[0]] = Record(malignant, self.delim, diagnosis) self.records[s[0]].setRecord(self.columns, s) else: d = unixpath.getDelim(line) if self.columns is None: self.columns = Columns(line.split(d)) first = False
def mergeDiagnoses(self):
# Merges full data with diagnoses
first = True
count = 0
print("\tMerging full data file with diagnoses...")
with open(self.outfile, "w") as out:
with open(self.infile, "r") as f:
for line in f:
line = line.strip()
if first == False:
row = line.split(d)
uid = row[self.head["UID"]].strip()
if len(row) > self.head["Diagnosis"]:
row[self.head["Diagnosis"]], c = self.__getDiagnosis__(uid, row[self.head["Diagnosis"]].strip())
count += c
row = self.__checkQuotes__(row)
out.write(",".join(row) + "\n")
else:
d = unixpath.getDelim(line)
self.__setHeader__(line.split(d))
out.write(line + "\n")
first = False
print(("\tMerged {:,} diagnosis records.").format(count))