def __setCounts__(self, infile, nec):
# Gets species counts
first = True
print("\tReading {}...".format(os.path.split(infile)[1]))
for i in unixpath.readFile(infile, header=True, d=","):
if not first:
total = int(i[header["RecordsWithDenominators"]])
if self.min < total:
tid = i[header["taxa_id"]]
if tid not in self.records.keys():
sp = i[header["Species"]]
if sp != "NA":
self.records[tid] = Species(tid, sp)
if tid in self.records.keys():
rec = self.records[tid]
n = int(i[header["NeoplasiaWithDenominators"]])
p = float(i[header["NeoplasiaPrevalence"]])
if nec:
rec.setNecropsy(total, n, p)
if rec.necropsy and rec.other:
# Calculate significance and store
rec.setSignificance()
else:
rec.setOther(total, n, p)
else:
header = i
first = False
def __readDeathBooks__(self):
# Records totals LZ deathbooks
first = True
print("\n\tReading species from deathbooks...")
for line in unixpath.readFile(self.infile):
if not first:
self.__addSpecies__(line[h["Scientific name"]])
else:
h = line
first = False
def format(self):
# Preformats London zoo data
with open(self.outfile, "w") as out:
print("\n\tFormatting London Zoo data...")
out.write(self.outheader)
for line in readFile(self.infile):
if not self.header:
self.header = line
else:
row = self.__formatLine__(line)
out.write(",".join(row) + "\n")
def __setConfig__(self):
# Stores input file values
first = True
for i in unixpath.readFile(self.config, True, "\t"):
if not first and len(i) > 0 and i[0] != "#":
self.commands.append(
Command(i[header["Command"]], i[header["Directory"]],
self.user, self.password, self.outdir))
elif first:
header = deepcopy(i)
first = False
def __setAccounts__(self, infile):
# Stores account names in dict
first = True
print("\n\tReading accounts file...")
for i in unixpath.readFile(infile, d=",", header=True):
if not first:
self.accounts[i[head["account_id"]]] = i[
head["submitter_name"]]
else:
head = i
first = False
def __setAccounts__(self):
# Reads account names into dict
print("\n\tReading accounts file...")
first = True
for i in unixpath.readFile(self.accountfile, header=True, d=","):
if not first:
if i[head["submitter_name"]] != "NA":
self.accounts[i[head["account_id"]]] = i[
head["submitter_name"]]
else:
head = i
first = False
def __setCounts__(self, infile):
# Gets species counts
first = True
print("\n\tReading {}...".format(infile))
for i in unixpath.readFile(infile, header=True, d=","):
if not first:
sp = i[header[SPECIES]]
self.records[sp] = Species(sp, i[header[NAME]],
i[header[CASES]], i[header[ZIMS]],
i[header[DEATHBOOKS]])
else:
header = i
first = False
def __countRecords__(self):
# Counts records for each account id
print("\tReading records file...")
first = True
for i in unixpath.readFile(self.infile, header=True, d=","):
if not first:
a = i[head["account_id"]]
if a != "-1":
if i[head["Zoo"]] == "1" or i[head["Institute"]] == "1":
if a not in self.counts.keys():
# account_id: #records, approved
self.counts[a] = [0, i[head["Approved"]]]
self.counts[a][0] += 1
else:
head = i
first = False
def __setCases__(self, infile):
# Stores cases by species in dict
first = True
print("\tReading {}...".format(infile))
for i in unixpath.readFile(infile, d = self.d):
if not first:
if i[h["MassPresent"]] == "1":
t = i[h["Species"]].strip()
if t not in self.cases.keys():
self.cases[t] = []
row = []
for c in self.columns:
row.append(i[h[c]])
self.cases[t].append(row)
else:
h = i
first = False
def __setTaxa__(self, infile):
# Stores species and genus by common name
first = True
print("\n\tReading preformatted file...")
for i in unixpath.readFile(infile, d = self.d):
if not first:
c = i[h["CommonName"]]
if c not in self.taxa.keys():
s = i[h["ScientificName"]]
if " " not in s:
# Store genus only
self.taxa[c] = [s]
else:
self.taxa[c] = [s.split()[0], s]
else:
h = i
first = False
def __setCounts__(self, infile):
# Gets species counts
l = []
first = True
print("\tReading {}...".format(os.path.split(infile)[1]))
for i in unixpath.readFile(infile, header = True, d = ","):
if not first:
n = int(i[header[self.col]])
if self.min < n:
for j in self.bins:
if n >= j:
# Append value for each cutoff less than value
l.append(j)
else:
header = i
first = False
# l.sort()
return l
def __appendAccounts__(self, infile, outfile):
# Appends account name to records
first = True
with open(outfile, "w") as out:
for i in unixpath.readFile(infile, d=",", header=True):
if not first:
aid = i[head["account_id"]]
if aid in self.accounts.keys():
i.append(self.accounts[aid])
out.write(",".join(i) + "\n")
else:
head = i
header = ["" for n in range(len(head))]
for k in head.keys():
header[head[k]] = k
header.append("Account")
out.write(",".join(header) + "\n")
first = False
def __setTable__(self, infile, columns):
# Returns list of table columns
first = True
print("\tReading {}...".format(os.path.split(infile)[1]))
for line in unixpath.readFile(infile, header = True, d = ","):
if not first:
pid = line[head[self.id]]
if pid not in self.records.keys():
self.records[pid] = self.__newRecord__()
for i in columns:
val = line[head[i]]
if val:
try:
self.records[pid][i] = int(val)
except:
pass
else:
head = line
first = False
def __insertSpecies__(self):
# Added species and genus to input file
first = True
print("\tReading input file...")
with open(self.outfile, "w") as out:
for i in unixpath.readFile(self.infile, d = self.d):
if not first:
c = i[h["Name"]]
if c in self.taxa.keys():
i[h["Genus"]] = self.taxa[c][0]
if len(self.taxa[c]) > 1:
i[h["Species"]] = self.taxa[c][1]
out.write(self.d.join(i) + "\n")
else:
h = i
head = [-1] * len(h)
for k in i.keys():
head[h[k]] = k
out.write(self.d.join(head) + "\n")
first = False
def __identifySuspect__(self, infile):
# Attempts to identify suspect cases
count = 0
first = True
print("\tIdentifying suspect cases...")
with open(self.outfile, "w") as out:
for i in unixpath.readFile(infile, d = self.d):
if not first:
t = i[h["Taxa"]].strip()
if t.count(" ") > 1:
# Remove subspecies name
t = " ".join(t.split()[:2])
if t in self.cases.keys():
name = i[h["Common_Name"]].strip()
sex = i[h["Sex"]].strip()
date = i[h["Death_Date"]].strip()
if sex != "male" and sex != "female":
sex = "NA"
#diag = i[h["Diagnosis"]].strip()
#loc = i[h["Neoplasia_location"]].strip()
for r in self.cases[t]:
if date == r[5].replace(".", "/"):
#if r[0] == sex or r[4] == name:
row = deepcopy(r)
row.extend(i)
out.write(self.d.join(row) + "\n")
count += 1
else:
h = i
first = False
head = deepcopy(self.columns)
tail = [""] * len(h)
for k in i.keys():
tail[h[k]] = k
head.extend(tail)
out.write(self.d.join(head) + "\n")
print("\tFound {} potential records.".format(count))
