def split_classes(file_name):
training_data = data_preprocessing.load_csv_data(file_name)
training_data.pop(0) # remove top row
print len(training_data)
class_zero = []
class_one = []
for row in training_data:
if (row[8] == "class1"):
class_one.append(row)
else:
class_zero.append(row)
random.shuffle(class_one)
random.shuffle(class_zero)
return class_one, class_zero # randomise the two lists and return it
def split_classes (file_name): training_data = data_preprocessing.load_csv_data(file_name) training_data.pop(0) # remove top row print len(training_data) class_zero = [] class_one = [] for row in training_data: if (row[8] == "class1"): class_one.append(row) else: class_zero.append(row) random.shuffle(class_one) random.shuffle(class_zero) return class_one,class_zero # randomise the two lists and return it
def main():
#attr_names = ['plasma_glucose_concentration','bmi','diabetes_pedigree','age','class'] # For CFS
attr_names = None
training_data = data_preprocessing.load_csv_data("pima.csv")
training_data.pop(0) #pop the header off
test_sample = training_data.pop(random.randint(0, len(training_data) - 1 ))
#print "Test sample:", test_sample
(c,correctness) = classify(10, test_sample, training_data, attr_names)
print "Classifier predicted: ", c, " Correctness: ", correctness
def main():
attr_names = ['plasma_glucose_concentration','bmi','diabetes_pedigree','age','class'] # For CFS
(class_zero, class_one) = init_bayes("pima.csv")
#print print_mean_sd(class_zero,"Class Zero")
#print print_mean_sd(class_one, "Class One")
data = data_preprocessing.load_csv_data("pima.csv")
data.pop(0)
count_correct = 0
count_incorrect = 0
for item in data:
(a,out) = classify(item, class_zero, class_one)
if out == True:
count_correct = count_correct + 1
else:
count_incorrect = count_incorrect + 1
print "Correct: %d Incorrect: %d" %(count_correct,count_incorrect)
#print print_mean_sd(class_zero,"Class Zero")
#print print_mean_sd(class_one, "Class One")
#initBayes(training_data)
return 1;
def init_bayes(file_name,attr_names=False): training_data = data_preprocessing.load_csv_data(file_name,False) return calculate_mean_sd(training_data,attr_names)