def main():
# read in cancer data from text file
with open('cancer_data.txt') as file:
cancer_data = file.readlines()
# modifies cancer data to put it into proper format
cancer_data = np.array([i.split() for i in cancer_data])
class_vector = cancer_data[:,1]
class_vector.shape = (cancer_data.shape[0],1)
cancer_data = np.delete(cancer_data.astype('float16'), (0, 1), 1)
cancer_data = np.hstack((cancer_data, class_vector))
# prints 5 fold n_validator with cancer data and synthetic data
print(nn.n_validator(cancer_data, 5, nn.NNclassifier))
print(nn.n_validator(nn.synthetic_data(), 5, nn.NNclassifier))
def run_trials_k(data, p, clasifier, k, metric, trials):
''' Runs n_validator with the specified parameters a given number of
trials for a specified k value and returns the average performance for
that k
'''
bpf_sum = 0
i = 0
# Add the performances for each trial
while(i < trials):
bpf = nn.n_validator(data,p,clasifier,k,metric)
bpf_sum += bpf
i += 1
# Return the average
return bpf_sum/trials
def best_k(data_set, trials, dist_type):
'''
Determines the best k value for labeling test data given a
specific distance type
'''
k = 1
val = .1
last_val = 0
# test all k values until success rate is optimized
while(val > last_val):
last_val = val
# run nn_validator for a number of trials for each k
x = 0
for i in range(trials):
x += nn.n_validator(data_set, 15, nn.KNNclassifier, k, dist_type)
val = x/trials
# only test odd values of k
k += 2
return (k-2), val
def main():
'''Main function that calculates the accuracy of the
classifier using the breast cancer data set and the
synthetic data set'''
#read in the file and separate by commas
inFile = np.genfromtxt('wdbc.data.txt', delimiter = " ")
#delete patient IDs
inFile = np.delete(inFile, 0 , 1)
syntheticData = nn.createMultivariate(300)
BCDict = {}
synDict = {}
for i in range(3):
if i == 0:
metric = 'euclidean'
elif i == 1:
metric = 'cityblock'
elif i == 2:
metric = 'cosine'
k = 1
bestBCAvg = 0
bestSynAvg = 0
while k <= 15:
bcDataOutput = []
syntheticOutput = []
for j in range(100):
bcDataTest = nn.n_validator(inFile, 5, nn.KNNclassifier, k,
metric)
#append accuracy values for the given k value
bcDataOutput.append(bcDataTest)
syntheticValidator = nn.n_validator(syntheticData, 5,
nn.KNNclassifier, k, metric)
syntheticOutput.append(syntheticValidator)
curBCAvg = sum(bcDataOutput) / len(bcDataOutput)
curSynAvg = sum(syntheticOutput) / len(syntheticOutput)
#replace the value for the best average and best k value
if curBCAvg > bestBCAvg:
bestBCAvg = curBCAvg
kBestBC = k
if curSynAvg > bestSynAvg:
bestSynAvg = curSynAvg
kBestSyn = k
k += 2
#store the accuracy value for each metric
BCDict[metric] = (kBestBC, bestBCAvg)
synDict[metric] = (kBestSyn, bestSynAvg)
newBC = {}
newSyn = {}
#get the best k and distance metric combo
for keys in BCDict:
newBC[keys] = BCDict[keys][1]
maxBCDist = max(newBC, key = newBC.get)
bestKValBC = BCDict[maxBCDist][0]
for keys in synDict:
newSyn[keys] = synDict[keys][1]
maxSynDist = max(newSyn, key = newSyn.get)
bestKValSyn = synDict[maxSynDist][0]
print("Best k values using euclidean distance metric \n"
" Breast Cancer Data Set: {} with an accuracy of {} \n"
" Synthetic Data Set: {} with an accuracy of {}".format(
BCDict['euclidean'][0], BCDict['euclidean'][1],
synDict['euclidean'][0], synDict['euclidean'][1]))
print("Best k values using cityblock distance metric \n"
" Breast Cancer Data Set: {} with an accuracy of {} \n"
" Synthetic Data Set: {} with an accuracy of {}".format(
BCDict['cityblock'][0], BCDict['cityblock'][1],
synDict['cityblock'][0], synDict['cityblock'][1]))
print("Best k values using cosine distance metric \n"
" Breast Cancer Data Set: {} with an accuracy of {} \n"
" Synthetic Data Set: {} with an accuracy of {}".format(
BCDict['cosine'][0], BCDict['cosine'][1],
synDict['cosine'][0], synDict['cosine'][1]))
print("Best metric for {} is {} with a k value of {} \n"
"and an accuracy of {}".format(
'Breast Cancer', maxBCDist, bestKValBC, BCDict[maxBCDist][1]))
print("Best metric for {} is {} with a k value of {} \n"
"and an accuracy of {}".format(
'Synthetic Data', maxSynDist, bestKValSyn, synDict[maxSynDist][1]))
