def main(argv):
setpath()
try:
opts, args = getopt.getopt(argv,"ht:e:",["train=","test="])
if(len(sys.argv) < 5):
raise getopt.GetoptError(None)
except getopt.GetoptError:
print '\nusage: run.py -t <trainfile> -e <testfile> \n'
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print 'run.py -t <trainfile> -e <testfile>'
sys.exit()
elif opt in ("-t", "--train"):
trainfile = arg
elif opt in ("-e", "--test"):
testfile = arg
from file_reader import FileReader
fr = FileReader(trainfile)
training_Set= fr.getRows()
#Readin the test file and creating the matrix
from file_reader import FileReader
test_File_Reader = FileReader(testfile)
testing_Set= test_File_Reader.getRows()
test_Result(logistic_Regression(training_Set),testing_Set)
def main(argv):
setpath()
try:
opts, args = getopt.getopt(argv, "ht:e:", ["train=", "test="])
if (len(sys.argv) < 5):
raise getopt.GetoptError(None)
except getopt.GetoptError:
print '\nusage: run.py -t <trainfile> -e <testfile> \n'
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print 'run.py -t <trainfile> -e <testfile>'
sys.exit()
elif opt in ("-t", "--train"):
trainfile = arg
elif opt in ("-e", "--test"):
testfile = arg
from file_reader import FileReader
fr = FileReader(trainfile)
training_Set = fr.getRows()
#Readin the test file and creating the matrix
from file_reader import FileReader
test_File_Reader = FileReader(testfile)
testing_Set = test_File_Reader.getRows()
test_Result(logistic_Regression(training_Set), testing_Set)
def main(argv):
setpath()
try:
opts, args = getopt.getopt(argv, "ht:e:", ["train=", "test="])
if (len(sys.argv) < 5):
raise getopt.GetoptError(None)
except getopt.GetoptError:
print('\nusage: run.py -t <trainfile> -e <testfile>\n')
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print('run.py -t <trainfile> -e <testfile>')
sys.exit()
elif opt in ("-t", "--train"):
trainfile = arg
elif opt in ("-e", "--test"):
testfile = arg
from file_reader import FileReader
fr = FileReader(testfile)
from naive_bayes import NaiveBayes
nb = NaiveBayes(trainfile)
test_file_reader = FileReader(testfile)
testData = test_file_reader.getRows()
num_errors = 0
true_positive = 0
false_positive = 0
true_negative = 0
false_negative = 0
#Testing phase
for idx, row in enumerate(testData):
prediction = nb.binary_classify(row)
if row[-1] != prediction:
num_errors += 1.0
print("Error on row: %s" % str(idx + 1))
if row[-1] == '1':
false_negative += 1
else:
false_positive += 1
elif row[-1] == '0':
true_negative += 1
else:
true_positive += 1
print('\n\n--------------Error Count----------------')
print(num_errors)
print('\n\n--------------Accuracy----------------')
print("\n\nThe Accuracy is " +
str((len(testData) - num_errors) * 100 / len(testData)) + "%")
print("\n===========The confusion matrix===========")
print("\t No \t Yes")
print("No \t", str(true_negative) + "\t", str(false_positive))
print("Yes \t", str(false_negative) + "\t", str(true_positive))
def main(argv):
setpath()
try:
opts, args = getopt.getopt(argv,"ht:e:",["train=","test="])
if(len(sys.argv) < 5):
raise getopt.GetoptError(None)
except getopt.GetoptError:
print('\nusage: run.py -t <trainfile> -e <testfile>\n')
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print('run.py -t <trainfile> -e <testfile>')
sys.exit()
elif opt in ("-t", "--train"):
trainfile = arg
elif opt in ("-e", "--test"):
testfile = arg
from file_reader import FileReader
fr = FileReader(testfile)
from naive_bayes import NaiveBayes
nb = NaiveBayes(trainfile)
test_file_reader = FileReader(testfile)
testData = test_file_reader.getRows()
num_errors = 0
true_positive = 0
false_positive = 0
true_negative = 0
false_negative = 0
#Testing phase
for idx, row in enumerate(testData):
prediction = nb.binary_classify(row)
if row[-1] != prediction:
num_errors += 1.0
print("Error on row: %s" % str(idx+1))
if row[-1] == '1':
false_negative += 1
else:
false_positive += 1
elif row[-1] == '0':
true_negative += 1
else:
true_positive += 1
print('\n\n--------------Error Count----------------')
print(num_errors)
print('\n\n--------------Accuracy----------------')
print("\n\nThe Accuracy is " +str((len(testData) - num_errors)*100/len(testData)) + "%")
print("\n===========The confusion matrix===========")
print("\t No \t Yes")
print("No \t", str(true_negative) + "\t", str(false_positive))
print("Yes \t", str(false_negative) +"\t", str(true_positive))
def calcCounts(self):
# Missing labels not yet added.
fr = FileReader(self._file)
rows = fr.getRows()
self._num_features = len(rows[0]) - 1
feature_count = {}
label_count = {}
label_count['total'] = 0
for row in rows:
label_count['total'] += 1
if label_count.get(row[-1]) is None:
label_count[row[-1]] = 1
else:
label_count[row[-1]] += 1
if feature_count.get(row[-1]) is None:
feature_count[row[-1]] = {}
for i in range(self._num_features):
feature_count[row[-1]][str(i)] = {}
feature_count[row[-1]][str(i)]['total'] = 0
for i in range(self._num_features):
feature_i = feature_count[row[-1]][str(i)]
value = feature_i.get(row[i])
feature_i[
row[i]] = 1 if value is None else feature_i[row[i]] + 1
feature_count[row[-1]][str(i)]['total'] += 1
for label in feature_count:
for feature in feature_count[label]:
feature_values = set()
for l in filter(lambda x: x != 'total', feature_count):
for value in feature_count[l][feature]:
feature_values.add(value)
for value in feature_values:
if feature_count[label][feature].get(value) is None:
feature_count[label][feature][value] = 0
return (label_count, feature_count)
def calcCounts(self):
# Missing labels not yet added.
fr = FileReader(self._file)
rows = fr.getRows()
self._num_features = len(rows[0])-1
feature_count = {}
label_count = {}
label_count['total'] = 0
for row in rows:
label_count['total'] += 1
if label_count.get(row[-1]) is None:
label_count[row[-1]] = 1
else:
label_count[row[-1]] += 1
if feature_count.get(row[-1]) is None:
feature_count[row[-1]] = {}
for i in range(self._num_features):
feature_count[row[-1]][str(i)] = {}
feature_count[row[-1]][str(i)]['total'] = 0
for i in range(self._num_features):
feature_i = feature_count[row[-1]][str(i)]
value = feature_i.get(row[i])
feature_i[row[i]] = 1 if value is None else feature_i[row[i]]+1
feature_count[row[-1]][str(i)]['total'] += 1
for label in feature_count:
for feature in feature_count[label]:
feature_values = set()
for l in filter(lambda x: x != 'total', feature_count):
for value in feature_count[l][feature]:
feature_values.add(value)
for value in feature_values:
if feature_count[label][feature].get(value) is None:
feature_count[label][feature][value] = 0
return(label_count, feature_count)
def main(argv):
setpath()
try:
opts, args = getopt.getopt(argv,"ht:e:d:",["train=","test=","maxDepth="])
if(len(sys.argv) < 7):
raise getopt.GetoptError(None)
except getopt.GetoptError:
print '\nusage: run.py -t <trainfile> -e <testfile> -d <maxDepth>\n'
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print 'run.py -t <trainfile> -e <testfile> -d <maxDepth>'
sys.exit()
elif opt in ("-t", "--train"):
trainfile = arg
elif opt in ("-e", "--test"):
testfile = arg
elif opt in ("-d", "--maxDepth"):
maxDepth = int(arg)
from file_reader import FileReader
fr = FileReader(trainfile)
from decision_tree_builder import DecisionTreeBuilder
# getRows() returns a dataMatrix;
dtb = DecisionTreeBuilder(fr.getRows())
print ('Features: {}'.format(fr.featureNames))
root = dtb.build(maxDepth)
print('Tree Building Complete and Successful')
print('Height of the tree is {}'.format(dtb.decisionTree.height()))
#Testing section
#create a zero initialized confusion matrix
confusion_matrix=[[0 for j in range(len(fr.getClassLabels()))] for j in range(len(fr.getClassLabels()))]
#read the test file
testFile_Reader = FileReader(testfile)
dataMatrix_testFile = testFile_Reader.getRows()
Error_Count =0
No =0
Yes=0
No_Error= 0
Yes_error=0
Total_records = len(dataMatrix_testFile)+0.0
#Testing phase
for row in dataMatrix_testFile:
predicted_classLabel = dtb.predict(row)
print ('\tActual Label is {}, and Predicted Label is {}'.format(row[len(row)-1], predicted_classLabel))
#confusion_matrix[int(row[len(row)-1])-1][int(predicted_classLabel)-1]+= 1
if not row[len(row)-1]==predicted_classLabel:
Error_Count += 1.0
#To print confusion matrix for zoo data set uncomment line 66
print ('\n\n------------------Confusion Matrix----------')
for row in confusion_matrix:
print row
print('\n\n--------------Error Count----------------')
print Error_Count
print('\n\n--------------Accuracy----------------')
print (Total_records-Error_Count)/Total_records
