def permutater(healthy, disease, tobs, pVal):
# Combing to universal dataset
dataSet = np.append(healthy, disease)
setCombination = range(len(dataSet))
# Coming up with every permutation of healthy and disease combinations
healthyCombination = [list(x) for x in list(combinations(setCombination, len(healthy)))]
diseaseCombination = []
for comb in healthyCombination:
diseaseCombination.append([i for i in setCombination if i not in comb])
nSuccess = 0
confidence = 0.01
numRep = 0
for i, healthyRange in enumerate(healthyCombination):
numRep += 1 # Count Number of repititions
diseaseRange = diseaseCombination[i]
randHealthy = dataSet[healthyRange]
randDisease = dataSet[diseaseRange]
# trand calculation
trand = ttest(randHealthy, randDisease)
if(fabs(tobs) <= fabs(trand)):
nSuccess += 1
pValue = nSuccess/float(numRep)
# 2 Boolean Expressions for breaking out of loop
#interval = (pValue <= 0.01)
interval = (pValue <= (pVal + 0.01) and (pVal - 0.01 <= pValue))
if (interval):
break
print("Estimated p-value: {}".format(pValue))
print("Number of Repetitions Required For Estimate: {}".format(numRep))
from ttest import ttest from permutation import permutater healthy = [1.0, 3.0, 1.6, 2.1, 2.5, 2.7, 2.3, 1.5] disease = [1.1, 0.5, 2.0, 2.0, 1.2, 1.2, 1.3, 0.5, 1.4, 2.4] tobs = ttest(healthy, disease) permutater(healthy, disease, tobs, 0.02291)
#!/usr/bin/python
import sys
from ttest import print_ttest as ttest
def read(f):
d = {}
for line in f:
line = line.split()
query, score = line[0], float(line[1])
if query != 'all':
d[query] = score
return [value for (key, value) in sorted(d.items())]
if __name__ == '__main__':
if len(sys.argv) < 3:
print('Supply two data files')
exit()
d1_file = sys.argv[1]
d2_file = sys.argv[2]
with open(d1_file) as f:
d1 = read(f)
with open(d2_file) as f:
d2 = read(f)
ttest(d1, d2, False)
