def classify(k, sample, training_data, att_names = None):
if att_names == None:
att_names = data_preprocessing.get_header()
attribute_indexes = convert_att_names_to_indexes(att_names)
# class_index = att_names.index("class")
class_index = data_preprocessing.get_header().index("class")
distances = []
class0_count = 0
class1_count = 0
for training_sample in training_data:
dist = euclid_distance_squared(sample, training_sample, attribute_indexes)
heappush(distances, (dist, training_sample) )
for i in range(k):
(_, training_sample) = heappop(distances)
if training_sample[class_index] == "class0":
class0_count+=1
if training_sample[class_index] == "class1":
class1_count+=1
if class0_count > class1_count:
if sample[class_index] == 'class0':
return 0,True
return 0,False
else:
if sample[class_index] == 'class1':
return 1,True
return 1,False
def convert_att_names_to_indexes(attributes): attribute_indexes = [] for attribute_name in attributes: if attribute_name == "class": continue index = data_preprocessing.get_header().index(attribute_name) if index > -1: attribute_indexes.append(index) return attribute_indexes
def calculate_PDF(inputArray,class_zero,class_one,attr_names=False):
if attr_names == False:
headers = data_preprocessing.get_header()
else:
headers = attr_names
pdf_array = {'class_zero':{},'class_one':{}}
for header in headers[:-1]:
pdf_array['class_zero'][header] = PDF_math(inputArray[header],class_zero[header]['mean'],class_zero[header]['sd'])
pdf_array['class_one'][header] = PDF_math(inputArray[header],class_one[header]['mean'],class_one[header]['sd'])
return pdf_array
def convert_array_to_dict(inputArray,custom_headers=False):
headers = data_preprocessing.get_header()
outputArray = {}
for header in headers: # don't include class
outputArray[header] = inputArray[headers.index(header)]
if (custom_headers != False): # subset of headers given
temp_output = {}
for key in custom_headers:
if key in outputArray:
temp_output[key] = outputArray[key]
outputArray = temp_output
return outputArray
def calculate_mean_sd(inputData,attr_names=False):
if attr_names == False:
headers = data_preprocessing.get_header() # headers to data
else:
headers = attr_names
class_one = {} # People with Diabetes
class_zero = {} # People without Diabetes
# Prepare arrays with initial data
for header in headers[:-1]:
class_one[header] = {'mean':0,"sd":0}
class_zero[header] = {'mean':0,"sd":0}
else:
class_one['size'] = 0
class_zero['size'] = 0
# Calculate Mean #
for row in inputData:
dictRow = convert_array_to_dict(row,attr_names)
class_name = dictRow.pop("class")
if class_name == "class1": # for class_one
for key in dictRow.keys():
class_one[key]['mean'] += dictRow[key]
class_one['size'] += 1 # increment
else: # for class_zero
for key in dictRow.keys():
class_zero[key]['mean'] += dictRow[key]
class_zero['size'] += 1 # increment
for header in headers[:-1]:
class_zero[header]['mean'] = class_zero[header]['mean']/class_zero['size']
class_one[header]['mean'] = class_one[header]['mean']/class_one['size']
# Calculate SD
for row in inputData:
dictRow = convert_array_to_dict(row, attr_names)
class_name = dictRow.pop("class")
if class_name == "class1": # for class_one
for key in dictRow.keys():
class_one[key]['sd'] += math.pow((dictRow[key]-class_one[key]['mean']),2) # (xi - mean)^2
else: # for class_zero
for key in dictRow.keys():
class_zero[key]['sd'] += math.pow((dictRow[key]-class_zero[key]['mean']),2)
for header in headers[:-1]:
class_zero[header]['sd'] = math.sqrt(class_zero[header]['sd']/class_zero['size']) # (total_sum/N)^1/2
class_one[header]['sd'] = math.sqrt(class_one[header]['sd']/class_one['size'])
return class_zero,class_one;
def classify(inputArray,class_zero,class_one,attr_names=False): if attr_names == False: headers = data_preprocessing.get_header() else: headers = attr_names inputArray = convert_array_to_dict(inputArray, attr_names) pdf_array = calculate_PDF(inputArray,class_zero,class_one,attr_names) test_one_val = float(class_one['size'])/float(class_one['size']+class_zero['size']) # total percentage of classOne test_zero_val = float(class_zero['size'])/float(class_one['size']+class_zero['size']) # total percentage of classZero for header in headers[:-1]: # multiplying out the bayes value for 0 and 1 test_one_val = test_one_val * pdf_array['class_one'][header] test_zero_val = test_zero_val * pdf_array['class_zero'][header] #print "one: %f zero: %f "%(test_one_val,test_zero_val) if ((test_one_val - test_zero_val) >= 0): if inputArray['class'] == 'class1': # return True if actual == calculated return 1,True # for Diabetic return 1,False else: if inputArray['class'] == 'class0': # return True if actual == calculated return 0,True return 0,False # for Non-Diabetic
